Authors: Xiaoling Zhou, Wei Ye, Yidong Wang, Chaoya Jiang, Zhemg Lee, Rui Xie, Shikun Zhang
Abstract: The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality, quantity, and permutation of demonstrations, commonly leading to suboptimal and unstable performance. In this paper, we tackle this challenge for the first time from the perspective of demonstration augmentation. Specifically, we start with enriching representations of demonstrations by leveraging their deep feature distribution. We then theoretically reveal that when the number of augmented copies approaches infinity, the augmentation is approximately equal to a novel logit calibration mechanism integrated with specific statistical properties. This insight results in a simple yet highly efficient method that significantly improves the average and worst-case accuracy across diverse PLMs and tasks. Moreover, our method effectively reduces performance variance among varying demonstrations, permutations, and templates, and displays the capability to address imbalanced class distributions.
Authors: Aakash Sudhirbhai Vora, Dhrumil Chetankumar Joshi, Aksh Kantibhai Patel
Abstract: Stochastic Gradient Descent is used for large datasets to train models to reduce the training time. On top of that data parallelism is widely used as a method to efficiently train neural networks using multiple worker nodes in parallel. Synchronous and asynchronous approach to data parallelism is used by most systems to train the model in parallel. However, both of them have their drawbacks. We propose a third approach to data parallelism which is a hybrid between synchronous and asynchronous approaches, using both approaches to train the neural network. When the threshold function is selected appropriately to gradually shift all parameter aggregation from asynchronous to synchronous, we show that in a given time period our hybrid approach outperforms both asynchronous and synchronous approaches.
Authors: Biao Wu, Fang Meng, Ling Chen
Abstract: The impressive multimodal capabilities demonstrated by OpenAI's GPT-4 have generated significant interest in the development of Multimodal Large Language Models (MLLMs). Visual instruction tuning of MLLMs with machine-generated instruction-following data has shown to enhance zero-shot capabilities across various tasks. However, there has been limited exploration into controlling the quality of the instruction data.Current methodologies for data selection in MLLMs often rely on single, unreliable scores or use downstream tasks for selection, which is time-consuming and can lead to potential overfitting on the chosen evaluation datasets. To mitigate these limitations, we propose a novel data selection methodology that utilizes image-text correlation and model perplexity to evaluate and select data of varying quality. This approach leverages the distinct distribution of these two attributes, mapping data quality into a two-dimensional space that allows for the selection of data based on their location within this distribution. By utilizing this space, we can analyze the impact of task type settings, used as prompts, on data quality. Additionally, this space can be used to construct multi-stage subsets of varying quality to facilitate curriculum learning. Our research includes comprehensive experiments conducted on various datasets. The results emphasize substantial enhancements in five commonly assessed capabilities compared to using the complete dataset. Our codes, data, and models are publicly available at: \url{https://anonymous.4open.science/r/EHIT-31B4}
Authors: Iv\'an Matas, Carmen Serrano, Francisca Silva, Amalia Serrano, Tom\'as Toledo-Pastrana, Bego\~na Acha
Abstract: An AI tool has been developed to provide interpretable support for the diagnosis of BCC via teledermatology, thus speeding up referrals and optimizing resource utilization. The interpretability is provided in two ways: on the one hand, the main BCC dermoscopic patterns are found in the image to justify the BCC/Non BCC classification. Secondly, based on the common visual XAI Grad-CAM, a clinically inspired visual explanation is developed where the relevant features for diagnosis are located. Since there is no established ground truth for BCC dermoscopic features, a standard reference is inferred from the diagnosis of four dermatologists using an Expectation Maximization (EM) based algorithm. The results demonstrate significant improvements in classification accuracy and interpretability, positioning this approach as a valuable tool for early BCC detection and referral to dermatologists. The BCC/non-BCC classification achieved an accuracy rate of 90%. For Clinically-inspired XAI results, the detection of BCC patterns useful to clinicians reaches 99% accuracy. As for the Clinically-inspired Visual XAI results, the mean of the Grad-CAM normalized value within the manually segmented clinical features is 0.57, while outside this region it is 0.16. This indicates that the model struggles to accurately identify the regions of the BCC patterns. These results prove the ability of the AI tool to provide a useful explanation.
Authors: Yuqing Qian, Ziyu Zheng, Prayag Tiwari, Yijie Ding, Quan Zou
Abstract: Drug-side effect prediction has become an essential area of research in the field of pharmacology. As the use of medications continues to rise, so does the importance of understanding and mitigating the potential risks associated with them. At present, researchers have turned to data-driven methods to predict drug-side effects. Drug-side effect prediction is a link prediction problem, and the related data can be described from various perspectives. To process these kinds of data, a multi-view method, called Multiple Kronecker RLS fusion-based link propagation (MKronRLSF-LP), is proposed. MKronRLSF-LP extends the Kron-RLS by finding the consensus partitions and multiple graph Laplacian constraints in the multi-view setting. Both of these multi-view settings contribute to a higher quality result. Extensive experiments have been conducted on drug-side effect datasets, and our empirical results provide evidence that our approach is effective and robust.
Authors: Ilia Shumailov, Jamie Hayes, Eleni Triantafillou, Guillermo Ortiz-Jimenez, Nicolas Papernot, Matthew Jagielski, Itay Yona, Heidi Howard, Eugene Bagdasaryan
Abstract: Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical costs associated with exact unlearning. More recently unlearning is often discussed as an approach for removal of impermissible knowledge i.e. knowledge that the model should not possess such as unlicensed copyrighted, inaccurate, or malicious information. The promise is that if the model does not have a certain malicious capability, then it cannot be used for the associated malicious purpose. In this paper we revisit the paradigm in which unlearning is used for in Large Language Models (LLMs) and highlight an underlying inconsistency arising from in-context learning. Unlearning can be an effective control mechanism for the training phase, yet it does not prevent the model from performing an impermissible act during inference. We introduce a concept of ununlearning, where unlearned knowledge gets reintroduced in-context, effectively rendering the model capable of behaving as if it knows the forgotten knowledge. As a result, we argue that content filtering for impermissible knowledge will be required and even exact unlearning schemes are not enough for effective content regulation. We discuss feasibility of ununlearning for modern LLMs and examine broader implications.
Authors: Zuzanna Gawrysiak, Agata \.Zywot, Agnieszka {\L}awrynowicz
Abstract: We present WineGraph, an extended version of FlavorGraph, a heterogeneous graph incorporating wine data into its structure. This integration enables food-wine pairing based on taste and sommelier-defined rules. Leveraging a food dataset comprising 500,000 reviews and a wine reviews dataset with over 130,000 entries, we computed taste descriptors for both food and wine. This information was then utilised to pair food items with wine and augment FlavorGraph with additional data. The results demonstrate the potential of heterogeneous graphs to acquire supplementary information, proving beneficial for wine pairing.
Authors: Sebastian Vincent, Charlotte Prescott, Chris Bayliss, Chris Oakley, Carolina Scarton
Abstract: Incorporating extra-textual context such as film metadata into the machine translation (MT) pipeline can enhance translation quality, as indicated by automatic evaluation in recent work. However, the positive impact of such systems in industry remains unproven. We report on an industrial case study carried out to investigate the benefit of MT in a professional scenario of translating TV subtitles with a focus on how leveraging extra-textual context impacts post-editing. We found that post-editors marked significantly fewer context-related errors when correcting the outputs of MTCue, the context-aware model, as opposed to non-contextual models. We also present the results of a survey of the employed post-editors, which highlights contextual inadequacy as a significant gap consistently observed in MT. Our findings strengthen the motivation for further work within fully contextual MT.
Authors: Ben Fauber
Abstract: We describe the accurate prediction of ligand-protein interaction (LPI) affinities, also known as drug-target interactions (DTI), with instruction fine-tuned pretrained generative small language models (SLMs). We achieved accurate predictions for a range of affinity values associated with ligand-protein interactions on out-of-sample data in a zero-shot setting. Only the SMILES string of the ligand and the amino acid sequence of the protein were used as the model inputs. Our results demonstrate a clear improvement over machine learning (ML) and free-energy perturbation (FEP+) based methods in accurately predicting a range of ligand-protein interaction affinities, which can be leveraged to further accelerate drug discovery campaigns against challenging therapeutic targets.
Authors: Hao Yu, Xin Yang, Xin Gao, Yan Kang, Hao Wang, Junbo Zhang, Tianrui Li
Abstract: Personalized Federated Continual Learning (PFCL) is a new practical scenario that poses greater challenges in sharing and personalizing knowledge. PFCL not only relies on knowledge fusion for server aggregation at the global spatial-temporal perspective but also needs model improvement for each client according to the local requirements. Existing methods, whether in Personalized Federated Learning (PFL) or Federated Continual Learning (FCL), have overlooked the multi-granularity representation of knowledge, which can be utilized to overcome Spatial-Temporal Catastrophic Forgetting (STCF) and adopt generalized knowledge to itself by coarse-to-fine human cognitive mechanisms. Moreover, it allows more effectively to personalized shared knowledge, thus serving its own purpose. To this end, we propose a novel concept called multi-granularity prompt, i.e., coarse-grained global prompt acquired through the common model learning process, and fine-grained local prompt used to personalize the generalized representation. The former focuses on efficiently transferring shared global knowledge without spatial forgetting, and the latter emphasizes specific learning of personalized local knowledge to overcome temporal forgetting. In addition, we design a selective prompt fusion mechanism for aggregating knowledge of global prompts distilled from different clients. By the exclusive fusion of coarse-grained knowledge, we achieve the transmission and refinement of common knowledge among clients, further enhancing the performance of personalization. Extensive experiments demonstrate the effectiveness of the proposed method in addressing STCF as well as improving personalized performance. Our code now is available at https://github.com/SkyOfBeginning/FedMGP.
Authors: Zihao Wang, Shaofei Cai, Zhancun Mu, Haowei Lin, Ceyao Zhang, Xuejie Liu, Qing Li, Anji Liu, Xiaojian Ma, Yitao Liang
Abstract: We present OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in open-world Minecraft. Compared to prior works that either emit textual goals to separate controllers or produce the control command directly, OmniJARVIS seeks a different path to ensure both strong reasoning and efficient decision-making capabilities via unified tokenization of multimodal interaction data. First, we introduce a self-supervised approach to learn a behavior encoder that produces discretized tokens for behavior trajectories $\tau$ = {$o_0$, $a_0$, $\dots$} and an imitation learning (IL) policy decoder conditioned on these tokens. These additional behavior tokens will be augmented to the vocabulary of pretrained Multimodal Language Models (MLMs). With this encoder, we then pack long-term multimodal interactions involving task instructions, memories, thoughts, observations, textual responses, behavior trajectories, etc. into unified token sequences and model them with autoregressive transformers. Thanks to the semantically meaningful behavior tokens, the resulting VLA model, OmniJARVIS, can reason (by producing chain-of-thoughts), plan, answer questions, and act (by producing behavior tokens for the IL policy decoder). OmniJARVIS demonstrates excellent performances on a comprehensive collection of atomic, programmatic, and open-ended tasks in open-world Minecraft. Our analysis further unveils the crucial design principles in interaction data formation, unified tokenization, and its scaling potentials.
Authors: Zhengbo Zhang, Yuxi Zhou, Jia Gong, Jun Liu, Zhigang Tu
Abstract: Knowledge distillation (KD) enhances the performance of a student network by allowing it to learn the knowledge transferred from a teacher network incrementally. Existing methods dynamically adjust the temperature to enable the student network to adapt to the varying learning difficulties at different learning stages of KD. KD is a continuous process, but when adjusting the temperature, these methods consider only the immediate benefits of the operation in the current learning phase and fail to take into account its future returns. To address this issue, we formulate the adjustment of temperature as a sequential decision-making task and propose a method based on reinforcement learning, termed RLKD. Importantly, we design a novel state representation to enable the agent to make more informed action (i.e. instance temperature adjustment). To handle the problem of delayed rewards in our method due to the KD setting, we explore an instance reward calibration approach. In addition,we devise an efficient exploration strategy that enables the agent to learn valuable instance temperature adjustment policy more efficiently. Our framework can serve as a plug-and-play technique to be inserted into various KD methods easily, and we validate its effectiveness on both image classification and object detection tasks. Our code is at https://github.com/Zhengbo-Zhang/ITKD
Authors: Mahmoud Ibrahim, Yasmina Al Khalil, Sina Amirrajab, Chang Suna, Marcel Breeuwer, Josien Pluim, Bart Elen, Gokhan Ertaylan, Michel Dumontiera
Abstract: This paper presents a comprehensive systematic review of generative models (GANs, VAEs, DMs, and LLMs) used to synthesize various medical data types, including imaging (dermoscopic, mammographic, ultrasound, CT, MRI, and X-ray), text, time-series, and tabular data (EHR). Unlike previous narrowly focused reviews, our study encompasses a broad array of medical data modalities and explores various generative models. Our search strategy queries databases such as Scopus, PubMed, and ArXiv, focusing on recent works from January 2021 to November 2023, excluding reviews and perspectives. This period emphasizes recent advancements beyond GANs, which have been extensively covered previously. The survey reveals insights from three key aspects: (1) Synthesis applications and purpose of synthesis, (2) generation techniques, and (3) evaluation methods. It highlights clinically valid synthesis applications, demonstrating the potential of synthetic data to tackle diverse clinical requirements. While conditional models incorporating class labels, segmentation masks and image translations are prevalent, there is a gap in utilizing prior clinical knowledge and patient-specific context, suggesting a need for more personalized synthesis approaches and emphasizing the importance of tailoring generative approaches to the unique characteristics of medical data. Additionally, there is a significant gap in using synthetic data beyond augmentation, such as for validation and evaluation of downstream medical AI models. The survey uncovers that the lack of standardized evaluation methodologies tailored to medical images is a barrier to clinical application, underscoring the need for in-depth evaluation approaches, benchmarking, and comparative studies to promote openness and collaboration.
Authors: Xinji Mai, Zeng Tao, Junxiong Lin, Haoran Wang, Yang Chang, Yanlan Kang, Yan Wang, Wenqiang Zhang
Abstract: Multimodal Large Models (MLMs) are becoming a significant research focus, combining powerful large language models with multimodal learning to perform complex tasks across different data modalities. This review explores the latest developments and challenges in MLMs, emphasizing their potential in achieving artificial general intelligence and as a pathway to world models. We provide an overview of key techniques such as Multimodal Chain of Thought (M-COT), Multimodal Instruction Tuning (M-IT), and Multimodal In-Context Learning (M-ICL). Additionally, we discuss both the fundamental and specific technologies of multimodal models, highlighting their applications, input/output modalities, and design characteristics. Despite significant advancements, the development of a unified multimodal model remains elusive. We discuss the integration of 3D generation and embodied intelligence to enhance world simulation capabilities and propose incorporating external rule systems for improved reasoning and decision-making. Finally, we outline future research directions to address these challenges and advance the field.
Authors: Yuntao Shou, Wei Ai, Jiayi Du, Tao Meng, Haiyan Liu
Abstract: The task of multi-modal emotion recognition in conversation (MERC) aims to analyze the genuine emotional state of each utterance based on the multi-modal information in the conversation, which is crucial for conversation understanding. Existing methods focus on using graph neural networks (GNN) to model conversational relationships and capture contextual latent semantic relationships. However, due to the complexity of GNN, existing methods cannot efficiently capture the potential dependencies between long-distance utterances, which limits the performance of MERC. In this paper, we propose an Efficient Long-distance Latent Relation-aware Graph Neural Network (ELR-GNN) for multi-modal emotion recognition in conversations. Specifically, we first use pre-extracted text, video and audio features as input to Bi-LSTM to capture contextual semantic information and obtain low-level utterance features. Then, we use low-level utterance features to construct a conversational emotion interaction graph. To efficiently capture the potential dependencies between long-distance utterances, we use the dilated generalized forward push algorithm to precompute the emotional propagation between global utterances and design an emotional relation-aware operator to capture the potential semantic associations between different utterances. Furthermore, we combine early fusion and adaptive late fusion mechanisms to fuse latent dependency information between speaker relationship information and context. Finally, we obtain high-level discourse features and feed them into MLP for emotion prediction. Extensive experimental results show that ELR-GNN achieves state-of-the-art performance on the benchmark datasets IEMOCAP and MELD, with running times reduced by 52\% and 35\%, respectively.
Authors: Ibrahim Abdelaziz, Kinjal Basu, Mayank Agarwal, Sadhana Kumaravel, Matthew Stallone, Rameswar Panda, Yara Rizk, GP Bhargav, Maxwell Crouse, Chulaka Gunasekara, Shajith Ikbal, Sachin Joshi, Hima Karanam, Vineet Kumar, Asim Munawar, Sumit Neelam, Dinesh Raghu, Udit Sharma, Adriana Meza Soria, Dheeraj Sreedhar, Praveen Venkateswaran, Merve Unuvar, David Cox, Salim Roukos, Luis Lastras, Pavan Kapanipathi
Abstract: Large language models (LLMs) have recently shown tremendous promise in serving as the backbone to agentic systems, as demonstrated by their performance in multi-faceted, challenging benchmarks like SWE-Bench and Agent-Bench. However, to realize the true potential of LLMs as autonomous agents, they must learn to identify, call, and interact with external tools and application program interfaces (APIs) to complete complex tasks. These tasks together are termed function calling. Endowing LLMs with function calling abilities leads to a myriad of advantages, such as access to current and domain-specific information in databases and knowledge sources, and the ability to outsource tasks that can be reliably performed by tools, e.g., a Python interpreter or calculator. While there has been significant progress in function calling with LLMs, there is still a dearth of open models that perform on par with proprietary LLMs like GPT, Claude, and Gemini. Therefore, in this work, we introduce the GRANITE-20B-FUNCTIONCALLING model under an Apache 2.0 license. The model is trained using a multi-task training approach on seven fundamental tasks encompassed in function calling, those being Nested Function Calling, Function Chaining, Parallel Functions, Function Name Detection, Parameter-Value Pair Detection, Next-Best Function, and Response Generation. We present a comprehensive evaluation on multiple out-of-domain datasets comparing GRANITE-20B-FUNCTIONCALLING to more than 15 other best proprietary and open models. GRANITE-20B-FUNCTIONCALLING provides the best performance among all open models on the Berkeley Function Calling Leaderboard and fourth overall. As a result of the diverse tasks and datasets used for training our model, we show that GRANITE-20B-FUNCTIONCALLING has better generalizability on multiple tasks in seven different evaluation datasets.
Authors: Xian Wu, Qingchuan Tao, Shuang Wang
Abstract: Addressing the imperative need for efficient artificial intelligence in IoT and edge computing, this study presents RepAct, a re-parameterizable adaptive activation function tailored for optimizing lightweight neural networks within the computational limitations of edge devices. By employing a multi-branch structure with learnable adaptive weights, RepAct enriches feature processing and enhances cross-layer interpretability. When evaluated on tasks such as image classification and object detection, RepAct notably surpassed conventional activation functions in lightweight networks, delivering up to a 7.92% accuracy boost on MobileNetV3-Small for the ImageNet100 dataset, while maintaining computational complexity on par with HardSwish. This innovative approach not only maximizes model parameter efficiency but also significantly improves the performance and understanding capabilities of lightweight neural networks, demonstrating its potential for real-time edge computing applications.
Authors: Mazen Elabd, Sardar Jaf
Abstract: Big data contain rich information for machine learning algorithms to utilize when learning important features during classification tasks. Human beings express their emotion using certain words, speech (tone, pitch, speed) or facial expression. Artificial Intelligence approach to emotion classification are largely based on learning from textual information. However, public datasets containing text and speech data provide sufficient resources to train machine learning algorithms for the tack of emotion classification. In this paper, we present novel bimodal deep learning-based architectures enhanced with attention mechanism trained and tested on text and speech data for emotion classification. We report details of different deep learning based architectures and show the performance of each architecture including rigorous error analyses. Our finding suggests that deep learning based architectures trained on different types of data (text and speech) outperform architectures trained only on text or speech. Our proposed attention-based bimodal architecture outperforms several state-of-the-art systems in emotion classification.
Authors: Melanie Schaller, Daniel Schl\"or, Andreas Hotho
Abstract: External influences such as traffic and environmental factors induce vibrations in structures, leading to material degradation over time. These vibrations result in cracks due to the material's lack of plasticity compromising structural integrity. Detecting such damage requires the installation of vibration sensors to capture the internal dynamics. However, distinguishing relevant eigenmodes from external noise necessitates the use of Deep Learning models. The detection of changes in eigenmodes can be used to anticipate these shifts in material properties and to discern between normal and anomalous structural behavior. Eigenmodes, representing characteristic vibration patterns, provide insights into structural dynamics and deviations from expected states. Thus, we propose ModeConv to automatically capture and analyze changes in eigenmodes, facilitating effective anomaly detection in structures and material properties. In the conducted experiments, ModeConv demonstrates computational efficiency improvements, resulting in reduced runtime for model calculations. The novel ModeConv neural network layer is tailored for temporal graph neural networks, in which every node represents one sensor. ModeConv employs a singular value decomposition based convolutional filter design for complex numbers and leverages modal transformation in lieu of Fourier or Laplace transformations in spectral graph convolutions. We include a mathematical complexity analysis illustrating the runtime reduction.
Authors: Youhua Xia, Tiehua Zhang, Jiong Jin, Ying He, Fei Yu
Abstract: Efficient data transmission scheduling within vehicular environments poses a significant challenge due to the high mobility of such networks. Contemporary research predominantly centers on crafting cooperative scheduling algorithms tailored for vehicular networks. Notwithstanding, the intricacies of orchestrating scheduling in vehicular social networks both effectively and efficiently remain formidable. This paper introduces an innovative learning-based algorithm for scheduling data transmission that prioritizes efficiency and security within vehicular social networks. The algorithm first uses a specifically constructed neural network to enhance data processing capabilities. After this, it incorporates a Q-learning paradigm during the data transmission phase to optimize the information exchange, the privacy of which is safeguarded by differential privacy through the communication process. Comparative experiments demonstrate the superior performance of the proposed Q-learning enhanced scheduling algorithm relative to existing state-of-the-art scheduling algorithms in the context of vehicular social networks.
Authors: Christopher Irwin, Flavio Mignone, Stefania Montani, Luigi Portinale
Abstract: The gut microbiome, crucial for human health, presents challenges in analyzing its complex metaomic data due to high dimensionality and sparsity. Traditional methods struggle to capture its intricate relationships. We investigate graph neural networks (GNNs) for this task, aiming to derive meaningful representations of individual gut microbiomes. Unlike methods relying solely on taxa abundance, we directly leverage phylogenetic relationships, in order to obtain a generalized encoder for taxa networks. The representation learnt from the encoder are then used to train a model for phenotype prediction such as Inflammatory Bowel Disease (IBD).
Authors: Evgenia Rusak, Patrik Reizinger, Attila Juhos, Oliver Bringmann, Roland S. Zimmermann, Wieland Brendel
Abstract: Previous theoretical work on contrastive learning (CL) with InfoNCE showed that, under certain assumptions, the learned representations uncover the ground-truth latent factors. We argue these theories overlook crucial aspects of how CL is deployed in practice. Specifically, they assume that within a positive pair, all latent factors either vary to a similar extent, or that some do not vary at all. However, in practice, positive pairs are often generated using augmentations such as strong cropping to just a few pixels. Hence, a more realistic assumption is that all latent factors change, with a continuum of variability across these factors. We introduce AnInfoNCE, a generalization of InfoNCE that can provably uncover the latent factors in this anisotropic setting, broadly generalizing previous identifiability results in CL. We validate our identifiability results in controlled experiments and show that AnInfoNCE increases the recovery of previously collapsed information in CIFAR10 and ImageNet, albeit at the cost of downstream accuracy. Additionally, we explore and discuss further mismatches between theoretical assumptions and practical implementations, including extensions to hard negative mining and loss ensembles.
Authors: Dat Hong, Philip M. Polgreen, Alberto Maria Segre
Abstract: Hospitalizations that follow closely on the heels of one or more emergency department visits are often symptoms of missed opportunities to form a proper diagnosis. These diagnostic errors imply a failure to recognize the need for hospitalization and deliver appropriate care, and thus also bear important connotations for patient safety. In this paper, we show how data mining techniques can be applied to a large existing hospitalization data set to learn useful models that predict these upcoming hospitalizations with high accuracy. Specifically, we use an ensemble of logistics regression, na\"ive Bayes and association rule classifiers to successfully predict hospitalization within 3, 7 and 14 days of an emergency department discharge. Aside from high accuracy, one of the advantages of the techniques proposed here is that the resulting classifier is easily inspected and interpreted by humans so that the learned rules can be readily operationalized. These rules can then be easily distributed and applied directly by physicians in emergency department settings to predict the risk of early admission prior to discharging their emergency department patients.
Authors: Victor Borza, Andrew Estornell, Chien-Ju Ho, Bradley Malin, Yevgeniy Vorobeychik
Abstract: Our society collects data on people for a wide range of applications, from building a census for policy evaluation to running meaningful clinical trials. To collect data, we typically sample individuals with the goal of accurately representing a population of interest. However, current sampling processes often collect data opportunistically from data sources, which can lead to datasets that are biased and not representative, i.e., the collected dataset does not accurately reflect the distribution of demographics of the true population. This is a concern because subgroups within the population can be under- or over-represented in a dataset, which may harm generalizability and lead to an unequal distribution of benefits and harms from downstream tasks that use such datasets (e.g., algorithmic bias in medical decision-making algorithms). In this paper, we assess the relationship between dataset representativeness and group-fairness of classifiers trained on that dataset. We demonstrate that there is a natural tension between dataset representativeness and classifier fairness; empirically we observe that training datasets with better representativeness can frequently result in classifiers with higher rates of unfairness. We provide some intuition as to why this occurs via a set of theoretical results in the case of univariate classifiers. We also find that over-sampling underrepresented groups can result in classifiers which exhibit greater bias to those groups. Lastly, we observe that fairness-aware sampling strategies (i.e., those which are specifically designed to select data with high downstream fairness) will often over-sample members of majority groups. These results demonstrate that the relationship between dataset representativeness and downstream classifier fairness is complex; balancing these two quantities requires special care from both model- and dataset-designers.
Authors: Eunhae Lee
Abstract: This study investigates the impact of model size on Online Continual Learning performance, with a focus on catastrophic forgetting. Employing ResNet architectures of varying sizes, the research examines how network depth and width affect model performance in class-incremental learning using the SplitCIFAR-10 dataset. Key findings reveal that larger models do not guarantee better Continual Learning performance; in fact, they often struggle more in adapting to new tasks, particularly in online settings. These results challenge the notion that larger models inherently mitigate catastrophic forgetting, highlighting the nuanced relationship between model size and Continual Learning efficacy. This study contributes to a deeper understanding of model scalability and its practical implications in Continual Learning scenarios.
Authors: Samuel Stanton, Robert Alberstein, Nathan Frey, Andrew Watkins, Kyunghyun Cho
Abstract: There is a growing body of work seeking to replicate the success of machine learning (ML) on domains like computer vision (CV) and natural language processing (NLP) to applications involving biophysical data. One of the key ingredients of prior successes in CV and NLP was the broad acceptance of difficult benchmarks that distilled key subproblems into approachable tasks that any junior researcher could investigate, but good benchmarks for biophysical domains are rare. This scarcity is partially due to a narrow focus on benchmarks which simulate biophysical data; we propose instead to carefully abstract biophysical problems into simpler ones with key geometric similarities. In particular we propose a new class of closed-form test functions for biophysical sequence optimization, which we call Ehrlich functions. We provide empirical results demonstrating these functions are interesting objects of study and can be non-trivial to solve with a standard genetic optimization baseline.
Authors: Hongjun Choi, Jayaraman J. Thiagarajan, Ruben Glatt, Shusen Liu
Abstract: In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks. We present a surprising finding that, when recovering the original model accuracy is the sole objective, it can be achieved effectively through the weight reconstruction objective alone. Additionally, we explore the underlying factors for improving weight reconstruction under parameter-efficiency constraints, and propose a novel training scheme that decouples the reconstruction objective from auxiliary objectives such as knowledge distillation that leads to significant improvements compared to state-of-the-art approaches. Finally, these results pave way for more practical scenarios, where one needs to achieve improvements on both model accuracy and predictor network parameter-efficiency simultaneously.
Authors: Linjiang Zhou, Xiaochuan Shi, Chao Ma, Zepeng Wang
Abstract: Gradients play a pivotal role in neural networks explanation. The inherent high dimensionality and structural complexity of neural networks result in the original gradients containing a significant amount of noise. While several approaches were proposed to reduce noise with smoothing, there is little discussion of the rationale behind smoothing gradients in neural networks. In this work, we proposed a gradient smooth theoretical framework for neural networks based on the function mollification and Monte Carlo integration. The framework intrinsically axiomatized gradient smoothing and reveals the rationale of existing methods. Furthermore, we provided an approach to design new smooth methods derived from the framework. By experimental measurement of several newly designed smooth methods, we demonstrated the research potential of our framework.
Authors: Rui Cao, Shijie Xue, Jindong Li, Qi Wang, Yi Chang
Abstract: Unsupervised graph-level anomaly detection (UGAD) has attracted increasing interest due to its widespread application. In recent studies, knowledge distillation-based methods have been widely used in unsupervised anomaly detection to improve model efficiency and generalization. However, the inherent symmetry between the source (teacher) and target (student) networks typically results in consistent outputs across both architectures, making it difficult to distinguish abnormal graphs from normal graphs. Also, existing methods mainly rely on graph features to distinguish anomalies, which may be unstable with complex and diverse data and fail to capture the essence that differentiates normal graphs from abnormal ones. In this work, we propose a Graph Normalizing Flows-driven Asymmetric Network For Unsupervised Graph-Level Anomaly Detection (FANFOLD in short). We introduce normalizing flows to unsupervised graph-level anomaly detection due to their successful application and superior quality in learning the underlying distribution of samples. Specifically, we adopt the knowledge distillation technique and apply normalizing flows on the source network, achieving the asymmetric network. In the training stage, FANFOLD transforms the original distribution of normal graphs to a standard normal distribution. During inference, FANFOLD computes the anomaly score using the source-target loss to discriminate between normal and anomalous graphs. We conduct extensive experiments on 15 datasets of different fields with 9 baseline methods to validate the superiority of FANFOLD.
Authors: Weihan Li, Yule Wang, Chengrui Li, Anqi Wu
Abstract: Gaussian Processes (GPs) and Linear Dynamical Systems (LDSs) are essential time series and dynamic system modeling tools. GPs can handle complex, nonlinear dynamics but are computationally demanding, while LDSs offer efficient computation but lack the expressive power of GPs. To combine their benefits, we introduce a universal method that allows an LDS to mirror stationary temporal GPs. This state-space representation, known as the Markovian Gaussian Process (Markovian GP), leverages the flexibility of kernel functions while maintaining efficient linear computation. Unlike existing GP-LDS conversion methods, which require separability for most multi-output kernels, our approach works universally for single- and multi-output stationary temporal kernels. We evaluate our method by computing covariance, performing regression tasks, and applying it to a neuroscience application, demonstrating that our method provides an accurate state-space representation for stationary temporal GPs.
Authors: Benjamin Estermann, Luca A. Lanzend\"orfer, Yannick Niedermayr, Roger Wattenhofer
Abstract: Algorithmic reasoning is a fundamental cognitive ability that plays a pivotal role in problem-solving and decision-making processes. Reinforcement Learning (RL) has demonstrated remarkable proficiency in tasks such as motor control, handling perceptual input, and managing stochastic environments. These advancements have been enabled in part by the availability of benchmarks. In this work we introduce PUZZLES, a benchmark based on Simon Tatham's Portable Puzzle Collection, aimed at fostering progress in algorithmic and logical reasoning in RL. PUZZLES contains 40 diverse logic puzzles of adjustable sizes and varying levels of complexity; many puzzles also feature a diverse set of additional configuration parameters. The 40 puzzles provide detailed information on the strengths and generalization capabilities of RL agents. Furthermore, we evaluate various RL algorithms on PUZZLES, providing baseline comparisons and demonstrating the potential for future research. All the software, including the environment, is available at https://github.com/ETH-DISCO/rlp.
Authors: Tuan L. Vo, Thu Nguyen, Hugo L. Hammer, Michael A. Riegler, Pal Halvorsen
Abstract: Missing data is a prevalent issue that can significantly impair model performance and interpretability. This paper briefly summarizes the development of the field of missing data with respect to Explainable Artificial Intelligence and experimentally investigates the effects of various imputation methods on the calculation of Shapley values, a popular technique for interpreting complex machine learning models. We compare different imputation strategies and assess their impact on feature importance and interaction as determined by Shapley values. Moreover, we also theoretically analyze the effects of missing values on Shapley values. Importantly, our findings reveal that the choice of imputation method can introduce biases that could lead to changes in the Shapley values, thereby affecting the interpretability of the model. Moreover, and that a lower test prediction mean square error (MSE) may not imply a lower MSE in Shapley values and vice versa. Also, while Xgboost is a method that could handle missing data directly, using Xgboost directly on missing data can seriously affect interpretability compared to imputing the data before training Xgboost. This study provides a comprehensive evaluation of imputation methods in the context of model interpretation, offering practical guidance for selecting appropriate techniques based on dataset characteristics and analysis objectives. The results underscore the importance of considering imputation effects to ensure robust and reliable insights from machine learning models.
Authors: Robert Loftin, Saptarashmi Bandyopadhyay, Mustafa Mert \c{C}elikok
Abstract: Artificially intelligent agents deployed in the real-world will require the ability to reliably \textit{cooperate} with humans (as well as other, heterogeneous AI agents). To provide formal guarantees of successful cooperation, we must make some assumptions about how partner agents could plausibly behave. Any realistic set of assumptions must account for the fact that other agents may be just as adaptable as our agent is. In this work, we consider the problem of cooperating with a \textit{population} of agents in a finitely-repeated, two player general-sum matrix game with private utilities. Two natural assumptions in such settings are that: 1) all agents in the population are individually rational learners, and 2) when any two members of the population are paired together, with high-probability they will achieve at least the same utility as they would under some Pareto efficient equilibrium strategy. Our results first show that these assumptions alone are insufficient to ensure \textit{zero-shot} cooperation with members of the target population. We therefore consider the problem of \textit{learning} a strategy for cooperating with such a population using prior observations its members interacting with one another. We provide upper and lower bounds on the number of samples needed to learn an effective cooperation strategy. Most importantly, we show that these bounds can be much stronger than those arising from a "naive'' reduction of the problem to one of imitation learning.
Authors: Ryoichi Ishizuka, Takashi Imai, Kaoru Kawamoto
Abstract: In this paper, we propose a novel method of model-based time series clustering with mixtures of general state space models (MSSMs). Each component of MSSMs is associated with each cluster. An advantage of the proposed method is that it enables the use of time series models appropriate to the specific time series. This not only improves clustering and prediction accuracy but also enhances the interpretability of the estimated parameters. The parameters of the MSSMs are estimated using stochastic variational inference, a subtype of variational inference. The proposed method estimates the latent variables of an arbitrary state space model by using neural networks with a normalizing flow as a variational estimator. The number of clusters can be estimated using the Bayesian information criterion. In addition, to prevent MSSMs from converging to the local optimum, we propose several optimization tricks, including an additional penalty term called entropy annealing. Experiments on simulated datasets show that the proposed method is effective for clustering, parameter estimation, and estimating the number of clusters.
Authors: Agnieszka Niemczynowicz, Rados{\l}aw Antoni Kycia
Abstract: Fully tensorial theory of hypercomplex neural networks is given. The key point is to observe that the algebra multiplication can be represented as a rank three tensor. This approach is attractive for neural network libraries that support effective tensorial operations.
Authors: Agnieszka Niemczynowicz, Rados{\l}aw Antoni Kycia
Abstract: Neural networks used in computations with more advanced algebras than real numbers perform better in some applications. However, there is no general framework for constructing hypercomplex neural networks. We propose a library integrated with Keras that can do computations within TensorFlow and PyTorch. It provides Dense and Convolutional 1D, 2D, and 3D layers architectures.
Authors: Mirco Ravanelli, Titouan Parcollet, Adel Moumen, Sylvain de Langen, Cem Subakan, Peter Plantinga, Yingzhi Wang, Pooneh Mousavi, Luca Della Libera, Artem Ploujnikov, Francesco Paissan, Davide Borra, Salah Zaiem, Zeyu Zhao, Shucong Zhang, Georgios Karakasidis, Sung-Lin Yeh, Aku Rouhe, Rudolf Braun, Florian Mai, Juan Zuluaga-Gomez, Seyed Mahed Mousavi, Andreas Nautsch, Xuechen Liu, Sangeet Sagar, Jarod Duret, Salima Mdhaffar, Gaelle Laperriere, Renato De Mori, Yannick Esteve
Abstract: SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech recognition, speech enhancement, speaker recognition, text-to-speech, and much more.It promotes transparency and replicability by releasing both the pre-trained models and the complete "recipes" of code and algorithms required for training them. This paper presents SpeechBrain 1.0, a significant milestone in the evolution of the toolkit, which now has over 200 recipes for speech, audio, and language processing tasks, and more than 100 models available on Hugging Face. SpeechBrain 1.0 introduces new technologies to support diverse learning modalities, Large Language Model (LLM) integration, and advanced decoding strategies, along with novel models, tasks, and modalities. It also includes a new benchmark repository, offering researchers a unified platform for evaluating models across diverse tasks.
Authors: Ceyu Xu, Yongji Wu, Xinyu Yang, Beidi Chen, Matthew Lentz, Danyang Zhuo, Lisa Wu Wills
Abstract: As the parameter size of large language models (LLMs) continues to expand, the need for a large memory footprint and high communication bandwidth have become significant bottlenecks for the training and inference of LLMs. To mitigate these bottlenecks, various tensor compression techniques have been proposed to reduce the data size, thereby alleviating memory requirements and communication pressure. Our research found that video codecs, despite being originally designed for compressing videos, show excellent efficiency when compressing various types of tensors. We demonstrate that video codecs can be versatile and general-purpose tensor codecs while achieving the state-of-the-art compression efficiency in various tasks. We further make use of the hardware video encoding and decoding module available on GPUs to create a framework capable of both inference and training with video codecs repurposed as tensor codecs. This greatly reduces the requirement for memory capacity and communication bandwidth, enabling training and inference of large models on consumer-grade GPUs.
Authors: Luyuan Xie, Manqing Lin, ChenMing Xu, Tianyu Luan, Zhipeng Zeng, Wenjun Qian, Cong Li, Yuejian Fang, Qingni Shen, Zhonghai Wu
Abstract: In the evolving application of medical artificial intelligence, federated learning is notable for its ability to protect training data privacy. Federated learning facilitates collaborative model development without the need to share local data from healthcare institutions. Yet, the statistical and system heterogeneity among these institutions poses substantial challenges, which affects the effectiveness of federated learning and hampers the exchange of information between clients. To address these issues, we introduce a novel approach, MH-pFLGB, which employs a global bypass strategy to mitigate the reliance on public datasets and navigate the complexities of non-IID data distributions. Our method enhances traditional federated learning by integrating a global bypass model, which would share the information among the clients, but also serves as part of the network to enhance the performance on each client. Additionally, MH-pFLGB provides a feature fusion module to better combine the local and global features. We validate \model{}'s effectiveness and adaptability through extensive testing on different medical tasks, demonstrating superior performance compared to existing state-of-the-art methods.
Authors: Quanming Yao, Yongqi Zhang, Yaqing Wang, Nan Yin, James Kwok, Qiang Yang
Abstract: The scaling law, a strategy that involves the brute-force scaling of the training dataset and learnable parameters, has become a prevalent approach for developing stronger learning models. In this paper, we examine its rationale in terms of learning from relational graphs. We demonstrate that directly adhering to such a scaling law does not necessarily yield stronger models due to architectural incompatibility and representation bottlenecks. To tackle this challenge, we propose a novel framework for learning from relational graphs via knowledge-aware parsimony learning. Our method draws inspiration from the duality between data and knowledge inherent in these graphs. Specifically, we first extract knowledge (like symbolic logic and physical laws) during the learning process, and then apply combinatorial generalization to the task at hand. This extracted knowledge serves as the ``building blocks'' for achieving parsimony learning. By applying this philosophy to architecture, parameters, and inference, we can effectively achieve versatile, sample-efficient, and interpretable learning. Experimental results show that our proposed framework surpasses methods that strictly follow the traditional scaling-up roadmap. This highlights the importance of incorporating knowledge in the development of next-generation learning technologies.
Authors: Barproda Halder, Faisal Hamman, Pasan Dissanayake, Qiuyi Zhang, Ilia Sucholutsky, Sanghamitra Dutta
Abstract: Spurious patterns refer to a mathematical association between two or more variables in a dataset that are not causally related. However, this notion of spuriousness, which is usually introduced due to sampling biases in the dataset, has classically lacked a formal definition. To address this gap, this work presents the first information-theoretic formalization of spuriousness in a dataset (given a split of spurious and core features) using a mathematical framework called Partial Information Decomposition (PID). Specifically, we disentangle the joint information content that the spurious and core features share about another target variable (e.g., the prediction label) into distinct components, namely unique, redundant, and synergistic information. We propose the use of unique information, with roots in Blackwell Sufficiency, as a novel metric to formally quantify dataset spuriousness and derive its desirable properties. We empirically demonstrate how higher unique information in the spurious features in a dataset could lead a model into choosing the spurious features over the core features for inference, often having low worst-group-accuracy. We also propose a novel autoencoder-based estimator for computing unique information that is able to handle high-dimensional image data. Finally, we also show how this unique information in the spurious feature is reduced across several dataset-based spurious-pattern-mitigation techniques such as data reweighting and varying levels of background mixing, demonstrating a novel tradeoff between unique information (spuriousness) and worst-group-accuracy.
Authors: Weihang Xu, Maryam Fazel, Simon S. Du
Abstract: We study the gradient Expectation-Maximization (EM) algorithm for Gaussian Mixture Models (GMM) in the over-parameterized setting, where a general GMM with $n>1$ components learns from data that are generated by a single ground truth Gaussian distribution. While results for the special case of 2-Gaussian mixtures are well-known, a general global convergence analysis for arbitrary $n$ remains unresolved and faces several new technical barriers since the convergence becomes sub-linear and non-monotonic. To address these challenges, we construct a novel likelihood-based convergence analysis framework and rigorously prove that gradient EM converges globally with a sublinear rate $O(1/\sqrt{t})$. This is the first global convergence result for Gaussian mixtures with more than $2$ components. The sublinear convergence rate is due to the algorithmic nature of learning over-parameterized GMM with gradient EM. We also identify a new emerging technical challenge for learning general over-parameterized GMM: the existence of bad local regions that can trap gradient EM for an exponential number of steps.
Authors: Xueying Long, Daniel F. Schmidt, Christoph Bergmeir, Slawek Smyl
Abstract: In Smyl et al. [Local and global trend Bayesian exponential smoothing models. International Journal of Forecasting, 2024.], a generalised exponential smoothing model was proposed that is able to capture strong trends and volatility in time series. This method achieved state-of-the-art performance in many forecasting tasks, but its fitting procedure, which is based on the NUTS sampler, is very computationally expensive. In this work, we propose several modifications to the original model, as well as a bespoke Gibbs sampler for posterior exploration; these changes improve sampling time by an order of magnitude, thus rendering the model much more practically relevant. The new model, and sampler, are evaluated on the M3 dataset and are shown to be competitive, or superior, in terms of accuracy to the original method, while being substantially faster to run.
Authors: Olga Solodova, Nick Richardson, Deniz Oktay, Ryan P. Adams
Abstract: Message passing graph neural networks (GNNs) would appear to be powerful tools to learn distributed algorithms via gradient descent, but generate catastrophically incorrect predictions when nodes update asynchronously during inference. This failure under asynchrony effectively excludes these architectures from many potential applications, such as learning local communication policies between resource-constrained agents in, e.g., robotic swarms or sensor networks. In this work we explore why this failure occurs in common GNN architectures, and identify "implicitly-defined" GNNs as a class of architectures which is provably robust to partially asynchronous "hogwild" inference, adapting convergence guarantees from work in asynchronous and distributed optimization, e.g., Bertsekas (1982); Niu et al. (2011). We then propose a novel implicitly-defined GNN architecture, which we call an energy GNN. We show that this architecture outperforms other GNNs from this class on a variety of synthetic tasks inspired by multi-agent systems, and achieves competitive performance on real-world datasets.
Authors: Risto Vuorio, Mattie Fellows, Cong Lu, Cl\'emence Grislain, Shimon Whiteson
Abstract: In many real-world settings, an agent must learn to act in environments where no reward signal can be specified, but a set of expert demonstrations is available. Imitation learning (IL) is a popular framework for learning policies from such demonstrations. However, in some cases, differences in observability between the expert and the agent can give rise to an imitation gap such that the expert's policy is not optimal for the agent and a naive application of IL can fail catastrophically. In particular, if the expert observes the Markov state and the agent does not, then the expert will not demonstrate the information-gathering behavior needed by the agent but not the expert. In this paper, we propose a Bayesian solution to the Imitation Gap (BIG), first using the expert demonstrations, together with a prior specifying the cost of exploratory behavior that is not demonstrated, to infer a posterior over rewards with Bayesian inverse reinforcement learning (IRL). BIG then uses the reward posterior to learn a Bayes-optimal policy. Our experiments show that BIG, unlike IL, allows the agent to explore at test time when presented with an imitation gap, whilst still learning to behave optimally using expert demonstrations when no such gap exists.
Authors: Aicheng Gong, Kai Yang, Jiafei Lyu, Xiu Li
Abstract: Task allocation is a key combinatorial optimization problem, crucial for modern applications such as multi-robot cooperation and resource scheduling. Decision makers must allocate entities to tasks reasonably across different scenarios. However, traditional methods assume static attributes and numbers of tasks and entities, often relying on dynamic programming and heuristic algorithms for solutions. In reality, task allocation resembles Markov decision processes, with dynamically changing task and entity attributes. Thus, algorithms must dynamically allocate tasks based on their states. To address this issue, we propose a two-stage task allocation algorithm based on similarity, utilizing reinforcement learning to learn allocation strategies. The proposed pre-assign strategy allows entities to preselect appropriate tasks, effectively avoiding local optima and thereby better finding the optimal allocation. We also introduce an attention mechanism and a hyperparameter network structure to adapt to the changing number and attributes of entities and tasks, enabling our network structure to generalize to new tasks. Experimental results across multiple environments demonstrate that our algorithm effectively addresses the challenges of dynamic task allocation in practical applications. Compared to heuristic algorithms like genetic algorithms, our reinforcement learning approach better solves dynamic allocation problems and achieves zero-shot generalization to new tasks with good performance. The code is available at https://github.com/yk7333/TaskAllocation.
Authors: Tong Mo, Shiran Dai, An Fu, Xiaomeng Zhu, Shuxiao Li
Abstract: Accurate and efficient prediction of aeroengine performance is of paramount importance for engine design, maintenance, and optimization endeavours. However, existing methodologies often struggle to strike an optimal balance among predictive accuracy, computational efficiency, modelling complexity, and data dependency. To address these challenges, we propose a strategy that synergistically combines domain knowledge from both the aeroengine and neural network realms to enable real-time prediction of engine performance parameters. Leveraging aeroengine domain knowledge, we judiciously design the network structure and regulate the internal information flow. Concurrently, drawing upon neural network domain expertise, we devise four distinct feature fusion methods and introduce an innovative loss function formulation. To rigorously evaluate the effectiveness and robustness of our proposed strategy, we conduct comprehensive validation across two distinct datasets. The empirical results demonstrate :(1) the evident advantages of our tailored loss function; (2) our model's ability to maintain equal or superior performance with a reduced parameter count; (3) our model's reduced data dependency compared to generalized neural network architectures; (4)Our model is more interpretable than traditional black box machine learning methods.
Authors: Wei Fan, Kun Yi, Hangting Ye, Zhiyuan Ning, Qi Zhang, Ning An
Abstract: While most time series are non-stationary, it is inevitable for models to face the distribution shift issue in time series forecasting. Existing solutions manipulate statistical measures (usually mean and std.) to adjust time series distribution. However, these operations can be theoretically seen as the transformation towards zero frequency component of the spectrum which cannot reveal full distribution information and would further lead to information utilization bottleneck in normalization, thus hindering forecasting performance. To address this problem, we propose to utilize the whole frequency spectrum to transform time series to make full use of data distribution from the frequency perspective. We present a deep frequency derivative learning framework, DERITS, for non-stationary time series forecasting. Specifically, DERITS is built upon a novel reversible transformation, namely Frequency Derivative Transformation (FDT) that makes signals derived in the frequency domain to acquire more stationary frequency representations. Then, we propose the Order-adaptive Fourier Convolution Network to conduct adaptive frequency filtering and learning. Furthermore, we organize DERITS as a parallel-stacked architecture for the multi-order derivation and fusion for forecasting. Finally, we conduct extensive experiments on several datasets which show the consistent superiority in both time series forecasting and shift alleviation.
Authors: Simon Schmiedel
Abstract: Poor bucking decisions made by forest harvesters can have a negative effect on the products that are generated from the logs. Making the right bucking decisions is not an easy task because harvesters must rely on predictions of the stem profile for the part of the stems that is not yet measured. The goal of this project is to improve the bucking decisions made by forest harvesters with a stochastic bucking method. We developed a Long Short-Term Memory (LSTM) neural network that predicted the parameters of a Gaussian distribution conditioned on the known part of the stem, enabling the creation of multiple samples of stem profile predictions for the unknown part of the stem. The bucking decisions could then be optimized using a novel stochastic bucking algorithm which used all the stem profiles generated to choose the logs to generate from the stem. The stochastic bucking algorithm was compared to two benchmark models: A polynomial model that could not condition its predictions on more than one diameter measurement, and a deterministic LSTM neural network. All models were evaluated on stem profiles of four coniferous species prevalent in eastern Canada. In general, the best bucking decisions were taken by the stochastic LSTM models, demonstrating the usefulness of the method. The second-best results were mostly obtained by the deterministic LSTM model and the worst results by the polynomial model, corroborating the usefulness of conditioning the stem curve predictions on multiple measurements.
Authors: Sao Mai Nguyen, Maxime Devanne, Olivier Remy-Neris, Mathieu Lempereur, Andr\'e Thepaut
Abstract: While automatic monitoring and coaching of exercises are showing encouraging results in non-medical applications, they still have limitations such as errors and limited use contexts. To allow the development and assessment of physical rehabilitation by an intelligent tutoring system, we identify in this article four challenges to address and propose a medical dataset of clinical patients carrying out low back-pain rehabilitation exercises. The dataset includes 3D Kinect skeleton positions and orientations, RGB videos, 2D skeleton data, and medical annotations to assess the correctness, and error classification and localisation of body part and timespan. Along this dataset, we perform a complete research path, from data collection to processing, and finally a small benchmark. We evaluated on the dataset two baseline movement recognition algorithms, pertaining to two different approaches: the probabilistic approach with a Gaussian Mixture Model (GMM), and the deep learning approach with a Long-Short Term Memory (LSTM). This dataset is valuable because it includes rehabilitation relevant motions in a clinical setting with patients in their rehabilitation program, using a cost-effective, portable, and convenient sensor, and because it shows the potential for improvement on these challenges.
Authors: Yujia Zheng, Zeyu Tang, Yiwen Qiu, Bernhard Sch\"olkopf, Kun Zhang
Abstract: We argue that the selective inclusion of data points based on latent objectives is common in practical situations, such as music sequences. Since this selection process often distorts statistical analysis, previous work primarily views it as a bias to be corrected and proposes various methods to mitigate its effect. However, while controlling this bias is crucial, selection also offers an opportunity to provide a deeper insight into the hidden generation process, as it is a fundamental mechanism underlying what we observe. In particular, overlooking selection in sequential data can lead to an incomplete or overcomplicated inductive bias in modeling, such as assuming a universal autoregressive structure for all dependencies. Therefore, rather than merely viewing it as a bias, we explore the causal structure of selection in sequential data to delve deeper into the complete causal process. Specifically, we show that selection structure is identifiable without any parametric assumptions or interventional experiments. Moreover, even in cases where selection variables coexist with latent confounders, we still establish the nonparametric identifiability under appropriate structural conditions. Meanwhile, we also propose a provably correct algorithm to detect and identify selection structures as well as other types of dependencies. The framework has been validated empirically on both synthetic data and real-world music.
Authors: Aamir Hasan, Neeloy Chakraborty, Haonan Chen, Jung-Hoon Cho, Cathy Wu, Katherine Driggs-Campbell
Abstract: Fleets of autonomous vehicles can mitigate traffic congestion through simple actions, thus improving many socioeconomic factors such as commute time and gas costs. However, these approaches are limited in practice as they assume precise control over autonomous vehicle fleets, incur extensive installation costs for a centralized sensor ecosystem, and also fail to account for uncertainty in driver behavior. To this end, we develop a class of learned residual policies that can be used in cooperative advisory systems and only require the use of a single vehicle with a human driver. Our policies advise drivers to behave in ways that mitigate traffic congestion while accounting for diverse driver behaviors, particularly drivers' reactions to instructions, to provide an improved user experience. To realize such policies, we introduce an improved reward function that explicitly addresses congestion mitigation and driver attitudes to advice. We show that our residual policies can be personalized by conditioning them on an inferred driver trait that is learned in an unsupervised manner with a variational autoencoder. Our policies are trained in simulation with our novel instruction adherence driver model, and evaluated in simulation and through a user study (N=16) to capture the sentiments of human drivers. Our results show that our approaches successfully mitigate congestion while adapting to different driver behaviors, with up to 20% and 40% improvement as measured by a combination metric of speed and deviations in speed across time over baselines in our simulation tests and user study, respectively. Our user study further shows that our policies are human-compatible and personalize to drivers.
Authors: Dibyajyoti Chakraborty, Seung Whan Chung, Romit Maulik
Abstract: Forecasting high-dimensional dynamical systems is a fundamental challenge in various fields, such as the geosciences and engineering. Neural Ordinary Differential Equations (NODEs), which combine the power of neural networks and numerical solvers, have emerged as a promising algorithm for forecasting complex nonlinear dynamical systems. However, classical techniques used for NODE training are ineffective for learning chaotic dynamical systems. In this work, we propose a novel NODE-training approach that allows for robust learning of chaotic dynamical systems. Our method addresses the challenges of non-convexity and exploding gradients associated with underlying chaotic dynamics. Training data trajectories from such systems are split into multiple, non-overlapping time windows. In addition to the deviation from the training data, the optimization loss term further penalizes the discontinuities of the predicted trajectory between the time windows. The window size is selected based on the fastest Lyapunov time scale of the system. Multi-step penalty(MP) method is first demonstrated on Lorenz equation, to illustrate how it improves the loss landscape and thereby accelerating the optimization convergence. MP method can optimize chaotic systems in a manner similar to least-squares shadowing with significantly lower computational costs. Our proposed algorithm, denoted the Multistep Penalty NODE(MP-NODE), is applied to chaotic systems such as the Kuramoto-Sivashinsky equation and the two-dimensional Kolmogorov flow. It is observed that MP-NODE provide viable performance for such chaotic systems, not only for short-term trajectory predictions but also for invariant statistics that are hallmarks of the chaotic nature of these dynamics.
Authors: Khashayar Gatmiry, Jon Schneider
Abstract: We study a variant of prediction with expert advice where the learner's action at round $t$ is only allowed to depend on losses on a specific subset of the rounds (where the structure of which rounds' losses are visible at time $t$ is provided by a directed "feedback graph" known to the learner). We present a novel learning algorithm for this setting based on a strategy of partitioning the losses across sub-cliques of this graph. We complement this with a lower bound that is tight in many practical settings, and which we conjecture to be within a constant factor of optimal. For the important class of transitive feedback graphs, we prove that this algorithm is efficiently implementable and obtains the optimal regret bound (up to a universal constant).
Authors: Oliver R. A. Dunbar, Nicholas H. Nelsen, Maya Mutic
Abstract: Randomized algorithms exploit stochasticity to reduce computational complexity. One important example is random feature regression (RFR) that accelerates Gaussian process regression (GPR). RFR approximates an unknown function with a random neural network whose hidden weights and biases are sampled from a probability distribution. Only the final output layer is fit to data. In randomized algorithms like RFR, the hyperparameters that characterize the sampling distribution greatly impact performance, yet are not directly accessible from samples. This makes optimization of hyperparameters via standard (gradient-based) optimization tools inapplicable. Inspired by Bayesian ideas from GPR, this paper introduces a random objective function that is tailored for hyperparameter tuning of vector-valued random features. The objective is minimized with ensemble Kalman inversion (EKI). EKI is a gradient-free particle-based optimizer that is scalable to high-dimensions and robust to randomness in objective functions. A numerical study showcases the new black-box methodology to learn hyperparameter distributions in several problems that are sensitive to the hyperparameter selection: two global sensitivity analyses, integrating a chaotic dynamical system, and solving a Bayesian inverse problem from atmospheric dynamics. The success of the proposed EKI-based algorithm for RFR suggests its potential for automated optimization of hyperparameters arising in other randomized algorithms.
Authors: Dongxia Wu, Nikki Lijing Kuang, Ruijia Niu, Yi-An Ma, Rose Yu
Abstract: Black-box optimization (BBO) aims to optimize an objective function by iteratively querying a black-box oracle. This process demands sample-efficient optimization due to the high computational cost of function evaluations. While prior studies focus on forward approaches to learn surrogates for the unknown objective function, they struggle with high-dimensional inputs where valid inputs form a small subspace (e.g., valid protein sequences), which is common in real-world tasks. Recently, diffusion models have demonstrated impressive capability in learning the high-dimensional data manifold. They have shown promising performance in black-box optimization tasks but only in offline settings. In this work, we propose diffusion-based inverse modeling for black-box optimization (Diff-BBO), the first inverse approach leveraging diffusion models for online BBO problem. Diff-BBO distinguishes itself from forward approaches through the design of acquisition function. Instead of proposing candidates in the design space, Diff-BBO employs a novel acquisition function Uncertainty-aware Exploration (UaE) to propose objective function values, which leverages the uncertainty of a conditional diffusion model to generate samples in the design space. Theoretically, we prove that using UaE leads to optimal optimization outcomes. Empirically, we redesign experiments on the Design-Bench benchmark for online settings and show that Diff-BBO achieves state-of-the-art performance.
Authors: Ankur Sinha, Paritosh Pankaj
Abstract: In this paper, we formulate the hyperparameter tuning problem in machine learning as a bilevel program. The bilevel program is solved using a micro genetic algorithm that is enhanced with a linear program. While the genetic algorithm searches over discrete hyperparameters, the linear program enhancement allows hyper local search over continuous hyperparameters. The major contribution in this paper is the formulation of a linear program that supports fast search over continuous hyperparameters, and can be integrated with any hyperparameter search technique. It can also be applied directly on any trained machine learning or deep learning model for the purpose of fine-tuning. We test the performance of the proposed approach on two datasets, MNIST and CIFAR-10. Our results clearly demonstrate that using the linear program enhancement offers significant promise when incorporated with any population-based approach for hyperparameter tuning.
Authors: Qingyun Sun, Ziying Chen, Beining Yang, Cheng Ji, Xingcheng Fu, Sheng Zhou, Hao Peng, Jianxin Li, Philip S. Yu
Abstract: Graph condensation (GC) has recently garnered considerable attention due to its ability to reduce large-scale graph datasets while preserving their essential properties. The core concept of GC is to create a smaller, more manageable graph that retains the characteristics of the original graph. Despite the proliferation of graph condensation methods developed in recent years, there is no comprehensive evaluation and in-depth analysis, which creates a great obstacle to understanding the progress in this field. To fill this gap, we develop a comprehensive Graph Condensation Benchmark (GC-Bench) to analyze the performance of graph condensation in different scenarios systematically. Specifically, GC-Bench systematically investigates the characteristics of graph condensation in terms of the following dimensions: effectiveness, transferability, and complexity. We comprehensively evaluate 12 state-of-the-art graph condensation algorithms in node-level and graph-level tasks and analyze their performance in 12 diverse graph datasets. Further, we have developed an easy-to-use library for training and evaluating different GC methods to facilitate reproducible research. The GC-Bench library is available at https://github.com/RingBDStack/GC-Bench.
Authors: Yuheng Zhang, Dian Yu, Baolin Peng, Linfeng Song, Ye Tian, Mingyue Huo, Nan Jiang, Haitao Mi, Dong Yu
Abstract: Reinforcement Learning with Human Feedback (RLHF) has achieved great success in aligning large language models (LLMs) with human preferences. Prevalent RLHF approaches are reward-based, following the Bradley-Terry (BT) model assumption, which may not fully capture the complexity of human preferences. In this paper, we explore RLHF under a general preference framework and approach it from a game-theoretic perspective. Specifically, we formulate the problem as a two-player game and propose a novel algorithm, iterative Nash policy optimization (INPO). The key idea is to let the policy play against itself via no-regret learning, thereby approximating the Nash policy. Unlike previous methods, INPO bypasses the need for estimating the expected win rate for individual responses, which typically incurs high computational or annotation costs. Instead, we introduce a new loss objective that is directly minimized over a preference dataset. We provide theoretical analysis for our approach and demonstrate its effectiveness through experiments on various representative benchmarks. With an LLaMA-3-8B-based SFT model, INPO achieves a 41.5% length-controlled win rate on AlpacaEval 2.0 and a 38.3% win rate on Arena-Hard, showing substantial improvement over the state-of-the-art iterative algorithm [Dong et al., 2024] under the BT model assumption. Additionally, our ablation study highlights the benefits of incorporating KL regularization for response length control.
Authors: Sangwoong Yoon, Himchan Hwang, Dohyun Kwon, Yung-Kyun Noh, Frank C. Park
Abstract: We present a maximum entropy inverse reinforcement learning (IRL) approach for improving the sample quality of diffusion generative models, especially when the number of generation time steps is small. Similar to how IRL trains a policy based on the reward function learned from expert demonstrations, we train (or fine-tune) a diffusion model using the log probability density estimated from training data. Since we employ an energy-based model (EBM) to represent the log density, our approach boils down to the joint training of a diffusion model and an EBM. Our IRL formulation, named Diffusion by Maximum Entropy IRL (DxMI), is a minimax problem that reaches equilibrium when both models converge to the data distribution. The entropy maximization plays a key role in DxMI, facilitating the exploration of the diffusion model and ensuring the convergence of the EBM. We also propose Diffusion by Dynamic Programming (DxDP), a novel reinforcement learning algorithm for diffusion models, as a subroutine in DxMI. DxDP makes the diffusion model update in DxMI efficient by transforming the original problem into an optimal control formulation where value functions replace back-propagation in time. Our empirical studies show that diffusion models fine-tuned using DxMI can generate high-quality samples in as few as 4 and 10 steps. Additionally, DxMI enables the training of an EBM without MCMC, stabilizing EBM training dynamics and enhancing anomaly detection performance.
Authors: Jintai Chen, Yaojun Hu, Yue Wang, Yingzhou Lu, Xu Cao, Miao Lin, Hongxia Xu, Jian Wu, Cao Xiao, Jimeng Sun, Lucas Glass, Kexin Huang, Marinka Zitnik, Tianfan Fu
Abstract: Clinical trials are pivotal for developing new medical treatments, yet they typically pose some risks such as patient mortality, adverse events, and enrollment failure that waste immense efforts spanning over a decade. Applying artificial intelligence (AI) to forecast or simulate key events in clinical trials holds great potential for providing insights to guide trial designs. However, complex data collection and question definition requiring medical expertise and a deep understanding of trial designs have hindered the involvement of AI thus far. This paper tackles these challenges by presenting a comprehensive suite of meticulously curated AIready datasets covering multi-modal data (e.g., drug molecule, disease code, text, categorical/numerical features) and 8 crucial prediction challenges in clinical trial design, encompassing prediction of trial duration, patient dropout rate, serious adverse event, mortality rate, trial approval outcome, trial failure reason, drug dose finding, design of eligibility criteria. Furthermore, we provide basic validation methods for each task to ensure the datasets' usability and reliability. We anticipate that the availability of such open-access datasets will catalyze the development of advanced AI approaches for clinical trial design, ultimately advancing clinical trial research and accelerating medical solution development. The curated dataset, metrics, and basic models are publicly available at https://github.com/ML2Health/ML2ClinicalTrials/tree/main/AI4Trial.
URLs: https://github.com/ML2Health/ML2ClinicalTrials/tree/main/AI4Trial.
Authors: Michael Moran, Vladimir V. Gusev, Michael W. Gaultois, Dmytro Antypov, Matthew J. Rosseinsky
Abstract: The scarcity of property labels remains a key challenge in materials informatics, whereas materials data without property labels are abundant in comparison. By pretraining supervised property prediction models on self-supervised tasks that depend only on the "intrinsic information" available in any Crystallographic Information File (CIF), there is potential to leverage the large amount of crystal data without property labels to improve property prediction results on small datasets. We apply Deep InfoMax as a self-supervised machine learning framework for materials informatics that explicitly maximises the mutual information between a point set (or graph) representation of a crystal and a vector representation suitable for downstream learning. This allows the pretraining of supervised models on large materials datasets without the need for property labels and without requiring the model to reconstruct the crystal from a representation vector. We investigate the benefits of Deep InfoMax pretraining implemented on the Site-Net architecture to improve the performance of downstream property prediction models with small amounts (<10^3) of data, a situation relevant to experimentally measured materials property databases. Using a property label masking methodology, where we perform self-supervised learning on larger supervised datasets and then train supervised models on a small subset of the labels, we isolate Deep InfoMax pretraining from the effects of distributional shift. We demonstrate performance improvements in the contexts of representation learning and transfer learning on the tasks of band gap and formation energy prediction. Having established the effectiveness of Deep InfoMax pretraining in a controlled environment, our findings provide a foundation for extending the approach to address practical challenges in materials informatics.
Authors: Shahar Shaul-Ariel, Daphna Weinshall
Abstract: Continual Learning is an unresolved challenge, whose relevance increases when considering modern applications. Unlike the human brain, trained deep neural networks suffer from a phenomenon called Catastrophic Forgetting, where they progressively lose previously acquired knowledge upon learning new tasks. To mitigate this problem, numerous methods have been developed, many relying on replaying past exemplars during new task training. However, as the memory allocated for replay decreases, the effectiveness of these approaches diminishes. On the other hand, maintaining a large memory for the purpose of replay is inefficient and often impractical. Here we introduce TEAL, a novel approach to populate the memory with exemplars, that can be integrated with various experience-replay methods and significantly enhance their performance on small memory buffers. We show that TEAL improves the average accuracy of the SOTA method XDER as well as ER and ER-ACE on several image recognition benchmarks, with a small memory buffer of 1-3 exemplars per class in the final task. This confirms the hypothesis that when memory is scarce, it is best to prioritize the most typical data.
Authors: Jiongshu Wang, Jing Yang, Jiankang Deng, Hatice Gunes, Siyang Song
Abstract: Existing Graph Neural Networks (GNNs) are limited to process graphs each of whose vertices is represented by a vector or a single value, limited their representing capability to describe complex objects. In this paper, we propose the first GNN (called Graph in Graph Neural (GIG) Network) which can process graph-style data (called GIG sample) whose vertices are further represented by graphs. Given a set of graphs or a data sample whose components can be represented by a set of graphs (called multi-graph data sample), our GIG network starts with a GIG sample generation (GSG) module which encodes the input as a \textbf{GIG sample}, where each GIG vertex includes a graph. Then, a set of GIG hidden layers are stacked, with each consisting of: (1) a GIG vertex-level updating (GVU) module that individually updates the graph in every GIG vertex based on its internal information; and (2) a global-level GIG sample updating (GGU) module that updates graphs in all GIG vertices based on their relationships, making the updated GIG vertices become global context-aware. This way, both internal cues within the graph contained in each GIG vertex and the relationships among GIG vertices could be utilized for down-stream tasks. Experimental results demonstrate that our GIG network generalizes well for not only various generic graph analysis tasks but also real-world multi-graph data analysis (e.g., human skeleton video-based action recognition), which achieved the new state-of-the-art results on 13 out of 14 evaluated datasets. Our code is publicly available at https://github.com/wangjs96/Graph-in-Graph-Neural-Network.
URLs: https://github.com/wangjs96/Graph-in-Graph-Neural-Network.
Authors: Sydney Balboni, Grace Ivey, Brett Storoe, John Cisler, Tyge Plater, Caitlyn Grant, Ella Bruce, Benjamin Paulson
Abstract: Price volatility in global food commodities is a critical signal indicating potential disruptions in the food market. Understanding forthcoming changes in these prices is essential for bolstering food security, particularly for nations at risk. The Food and Agriculture Organization of the United Nations (FAO) previously developed sophisticated statistical frameworks for the proactive prediction of food commodity prices, aiding in the creation of global early warning systems. These frameworks utilize food security indicators to produce accurate forecasts, thereby facilitating preparations against potential food shortages. Our research builds on these foundations by integrating robust price security indicators with cutting-edge deep learning (DL) methodologies to reveal complex interdependencies. DL techniques examine intricate dynamics among diverse factors affecting food prices. Through sophisticated time-series forecasting models coupled with a classification model, our approach enhances existing models to better support communities worldwide in advancing their food security initiatives.
Authors: Kwanyoung Park, Youngwoon Lee
Abstract: Model-based offline reinforcement learning (RL) is a compelling approach that addresses the challenge of learning from limited, static data by generating imaginary trajectories using learned models. However, it falls short in solving long-horizon tasks due to high bias in value estimation from model rollouts. In this paper, we introduce a novel model-based offline RL method, Lower Expectile Q-learning (LEQ), which enhances long-horizon task performance by mitigating the high bias in model-based value estimation via expectile regression of $\lambda$-returns. Our empirical results show that LEQ significantly outperforms previous model-based offline RL methods on long-horizon tasks, such as the D4RL AntMaze tasks, matching or surpassing the performance of model-free approaches. Our experiments demonstrate that expectile regression, $\lambda$-returns, and critic training on offline data are all crucial for addressing long-horizon tasks. Additionally, LEQ achieves performance comparable to the state-of-the-art model-based and model-free offline RL methods on the NeoRL benchmark and the D4RL MuJoCo Gym tasks.
Authors: Andersen Ang, Waqas Bin Hamed, Hans De Sterck
Abstract: When applying nonnegative matrix factorization (NMF), generally the rank parameter is unknown. Such rank in NMF, called the nonnegative rank, is usually estimated heuristically since computing the exact value of it is NP-hard. In this work, we propose an approximation method to estimate such rank while solving NMF on-the-fly. We use sum-of-norm (SON), a group-lasso structure that encourages pairwise similarity, to reduce the rank of a factor matrix where the rank is overestimated at the beginning. On various datasets, SON-NMF is able to reveal the correct nonnegative rank of the data without any prior knowledge nor tuning. SON-NMF is a nonconvx nonsmmoth non-separable non-proximable problem, solving it is nontrivial. First, as rank estimation in NMF is NP-hard, the proposed approach does not enjoy a lower computational complexity. Using a graph-theoretic argument, we prove that the complexity of the SON-NMF is almost irreducible. Second, the per-iteration cost of any algorithm solving SON-NMF is possibly high, which motivated us to propose a first-order BCD algorithm to approximately solve SON-NMF with a low per-iteration cost, in which we do so by the proximal average operator. Lastly, we propose a simple greedy method for post-processing. SON-NMF exhibits favourable features for applications. Beside the ability to automatically estimate the rank from data, SON-NMF can deal with rank-deficient data matrix, can detect weak component with small energy. Furthermore, on the application of hyperspectral imaging, SON-NMF handle the issue of spectral variability naturally.
Authors: Jing Zhang, Xiaoqian Jiang, Yingjie Xie, Cangqi Zhou
Abstract: Heterogeneous graphs can well describe the complex entity relationships in the real world. For example, online shopping networks contain multiple physical types of consumers and products, as well as multiple relationship types such as purchasing and favoriting. More and more scholars pay attention to this research because heterogeneous graph representation learning shows strong application potential in real-world scenarios. However, the existing heterogeneous graph models use data augmentation techniques to enhance the use of graph structure information, which only captures the graph structure information from the spatial topology, ignoring the information displayed in the spectrum dimension of the graph structure. To address the issue that heterogeneous graph representation learning methods fail to model spectral information, this paper introduces a spectral-enhanced graph contrastive learning model (SHCL) and proposes a spectral augmentation algorithm for the first time in heterogeneous graph neural networks. The proposed model learns an adaptive topology augmentation scheme through the heterogeneous graph itself, disrupting the structural information of the heterogeneous graph in the spectrum dimension, and ultimately improving the learning effect of the model. Experimental results on multiple real-world datasets demonstrate substantial advantages of the proposed model.
Authors: Tuan L. Vo, Uyen Dang, Thu Nguyen
Abstract: As Artificial Intelligence (AI) models are gradually being adopted in real-life applications, the explainability of the model used is critical, especially in high-stakes areas such as medicine, finance, etc. Among the commonly used models, Linear Discriminant Analysis (LDA) is a widely used classification tool that is also explainable thanks to its ability to model class distributions and maximize class separation through linear feature combinations. Nevertheless, real-world data is frequently incomplete, presenting significant challenges for classification tasks and model explanations. In this paper, we propose a novel approach to LDA under missing data, termed \textbf{\textit{Weighted missing Linear Discriminant Analysis (WLDA)}}, to directly classify observations in data that contains missing values without imputation effectively by estimating the parameters directly on missing data and use a weight matrix for missing values to penalize missing entries during classification. Furthermore, we also analyze the theoretical properties and examine the explainability of the proposed technique in a comprehensive manner. Experimental results demonstrate that WLDA outperforms conventional methods by a significant margin, particularly in scenarios where missing values are present in both training and test sets.
Authors: Xikun Zhang, Dongjin Song, Yushan Jiang, Yixin Chen, Dacheng Tao
Abstract: Predicting the trajectories of systems with unknown dynamics (\textit{i.e.} the governing rules) is crucial in various research fields, including physics and biology. This challenge has gathered significant attention from diverse communities. Most existing works focus on learning fixed system dynamics within one single system. However, real-world applications often involve multiple systems with different types of dynamics or evolving systems with non-stationary dynamics (dynamics shifts). When data from those systems are continuously collected and sequentially fed to machine learning models for training, these models tend to be biased toward the most recently learned dynamics, leading to catastrophic forgetting of previously observed/learned system dynamics. To this end, we aim to learn system dynamics via continual learning. Specifically, we present a novel framework of Mode-switching Graph ODE (MS-GODE), which can continually learn varying dynamics and encode the system-specific dynamics into binary masks over the model parameters. During the inference stage, the model can select the most confident mask based on the observational data to identify the system and predict future trajectories accordingly. Empirically, we systematically investigate the task configurations and compare the proposed MS-GODE with state-of-the-art techniques. More importantly, we construct a novel benchmark of biological dynamic systems, featuring diverse systems with disparate dynamics and significantly enriching the research field of machine learning for dynamic systems.
Authors: Joan Bruna, Jiequn Han
Abstract: Score-based diffusion models have significantly advanced high-dimensional data generation across various domains, by learning a denoising oracle (or score) from datasets. From a Bayesian perspective, they offer a realistic modeling of data priors and facilitate solving inverse problems through posterior sampling. Although many heuristic methods have been developed recently for this purpose, they lack the quantitative guarantees needed in many scientific applications. In this work, we introduce the \textit{tilted transport} technique, which leverages the quadratic structure of the log-likelihood in linear inverse problems in combination with the prior denoising oracle to transform the original posterior sampling problem into a new `boosted' posterior that is provably easier to sample from. We quantify the conditions under which this boosted posterior is strongly log-concave, highlighting the dependencies on the condition number of the measurement matrix and the signal-to-noise ratio. The resulting posterior sampling scheme is shown to reach the computational threshold predicted for sampling Ising models [Kunisky'23] with a direct analysis, and is further validated on high-dimensional Gaussian mixture models and scalar field $\varphi^4$ models.
Authors: Dazhou Yu, Xiaoyun Gong, Yun Li, Meikang Qiu, Liang Zhao
Abstract: Multi-source spatial point data prediction is crucial in fields like environmental monitoring and natural resource management, where integrating data from various sensors is the key to achieving a holistic environmental understanding. Existing models in this area often fall short due to their domain-specific nature and lack a strategy for integrating information from various sources in the absence of ground truth labels. Key challenges include evaluating the quality of different data sources and modeling spatial relationships among them effectively. Addressing these issues, we introduce an innovative multi-source spatial point data prediction framework that adeptly aligns information from varied sources without relying on ground truth labels. A unique aspect of our method is the 'fidelity score,' a quantitative measure for evaluating the reliability of each data source. Furthermore, we develop a geo-location-aware graph neural network tailored to accurately depict spatial relationships between data points. Our framework has been rigorously tested on two real-world datasets and one synthetic dataset. The results consistently demonstrate its superior performance over existing state-of-the-art methods.
Authors: Farid Bozorgnia
Abstract: In this work, we improve the accuracy of several known algorithms to address the classification of large datasets when few labels are available. Our framework lies in the realm of graph-based semi-supervised learning. With novel modifications on Gaussian Random Fields Learning and Poisson Learning algorithms, we increase the accuracy and create more robust algorithms. Experimental results demonstrate the efficiency and superiority of the proposed methods over conventional graph-based semi-supervised techniques, especially in the context of imbalanced datasets.
Authors: Govinda Anantha Padmanabha, Jan Niklas Fuhg, Cosmin Safta, Reese E. Jones, Nikolaos Bouklas
Abstract: Most scientific machine learning (SciML) applications of neural networks involve hundreds to thousands of parameters, and hence, uncertainty quantification for such models is plagued by the curse of dimensionality. Using physical applications, we show that $L_0$ sparsification prior to Stein variational gradient descent ($L_0$+SVGD) is a more robust and efficient means of uncertainty quantification, in terms of computational cost and performance than the direct application of SGVD or projected SGVD methods. Specifically, $L_0$+SVGD demonstrates superior resilience to noise, the ability to perform well in extrapolated regions, and a faster convergence rate to an optimal solution.
Authors: Shijun Zhang, Hongkai Zhao, Yimin Zhong, Haomin Zhou
Abstract: In this work, we propose a balanced multi-component and multi-layer neural network (MMNN) structure to approximate functions with complex features with both accuracy and efficiency in terms of degrees of freedom and computation cost. The main idea is motivated by a multi-component, each of which can be approximated effectively by a single-layer network, and multi-layer decomposition in a "divide-and-conquer" type of strategy to deal with a complex function. While an easy modification to fully connected neural networks (FCNNs) or multi-layer perceptrons (MLPs) through the introduction of balanced multi-component structures in the network, MMNNs achieve a significant reduction of training parameters, a much more efficient training process, and a much improved accuracy compared to FCNNs or MLPs. Extensive numerical experiments are presented to illustrate the effectiveness of MMNNs in approximating high oscillatory functions and its automatic adaptivity in capturing localized features.
Authors: Alessio Russo, Alexandre Proutiere
Abstract: We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be collected to identify a nearly-optimal policy. Deriving this lower bound along with the optimal exploration strategy entails solving an intricate optimization problem and requires a model of the system. In turn, most existing sample optimal exploration algorithms rely on estimating the model. We derive an approximation of the instance-specific lower bound that only involves quantities that can be inferred using model-free approaches. Leveraging this approximation, we devise an ensemble-based model-free exploration strategy applicable to both tabular and continuous Markov decision processes. Numerical results demonstrate that our strategy is able to identify efficient policies faster than state-of-the-art exploration approaches
Authors: Ori Linial, Guy Tennenholtz, Uri Shalit
Abstract: In many reinforcement learning (RL) applications one cannot easily let the agent act in the world; this is true for autonomous vehicles, healthcare applications, and even some recommender systems, to name a few examples. Offline RL provides a way to train agents without real-world exploration, but is often faced with biases due to data distribution shifts, limited coverage, and incomplete representation of the environment. To address these issues, practical applications have tried to combine simulators with grounded offline data, using so-called hybrid methods. However, constructing a reliable simulator is in itself often challenging due to intricate system complexities as well as missing or incomplete information. In this work, we outline four principal challenges for combining offline data with imperfect simulators in RL: simulator modeling error, partial observability, state and action discrepancies, and hidden confounding. To help drive the RL community to pursue these problems, we construct ``Benchmarks for Mechanistic Offline Reinforcement Learning'' (B4MRL), which provide dataset-simulator benchmarks for the aforementioned challenges. Our results suggest the key necessity of such benchmarks for future research.
Authors: Matthew Lowery, John Turnage, Zachary Morrow, John D. Jakeman, Akil Narayan, Shandian Zhe, Varun Shankar
Abstract: This paper introduces the Kernel Neural Operator (KNO), a novel operator learning technique that uses deep kernel-based integral operators in conjunction with quadrature for function-space approximation of operators (maps from functions to functions). KNOs use parameterized, closed-form, finitely-smooth, and compactly-supported kernels with trainable sparsity parameters within the integral operators to significantly reduce the number of parameters that must be learned relative to existing neural operators. Moreover, the use of quadrature for numerical integration endows the KNO with geometric flexibility that enables operator learning on irregular geometries. Numerical results demonstrate that on existing benchmarks the training and test accuracy of KNOs is higher than popular operator learning techniques while using at least an order of magnitude fewer trainable parameters. KNOs thus represent a new paradigm of low-memory, geometrically-flexible, deep operator learning, while retaining the implementation simplicity and transparency of traditional kernel methods from both scientific computing and machine learning.
Authors: Zekai Wang, Tieming Liu, Bing Yao
Abstract: The era of big data has made vast amounts of clinical data readily available, particularly in the form of electronic health records (EHRs), which provides unprecedented opportunities for developing data-driven diagnostic tools to enhance clinical decision making. However, the application of EHRs in data-driven modeling faces challenges such as irregularly spaced multi-variate time series, issues of incompleteness, and data imbalance. Realizing the full data potential of EHRs hinges on the development of advanced analytical models. In this paper, we propose a novel Missingness-aware mUlti-branching Self-attention Encoder (MUSE-Net) to cope with the challenges in modeling longitudinal EHRs for data-driven disease prediction. The MUSE-Net leverages a multi-task Gaussian process (MGP) with missing value masks for data imputation, a multi-branching architecture to address the data imbalance problem, and a time-aware self-attention encoder to account for the irregularly spaced time interval in longitudinal EHRs. We evaluate the proposed MUSE-Net using both synthetic and real-world datasets. Experimental results show that our MUSE-Net outperforms existing methods that are widely used to investigate longitudinal signals.
Authors: Jiajun Zhu, Siqi Miao, Rex Ying, Pan Li
Abstract: The interpretability of machine learning models has gained increasing attention, particularly in scientific domains where high precision and accountability are crucial. This research focuses on distinguishing between two critical data patterns -- sensitive patterns (model-related) and decisive patterns (task-related) -- which are commonly used as model interpretations but often lead to confusion. Specifically, this study compares the effectiveness of two main streams of interpretation methods: post-hoc methods and self-interpretable methods, in detecting these patterns. Recently, geometric deep learning (GDL) has shown superior predictive performance in various scientific applications, creating an urgent need for principled interpretation methods. Therefore, we conduct our study using several representative GDL applications as case studies. We evaluate thirteen interpretation methods applied to three major GDL backbone models, using four scientific datasets to assess how well these methods identify sensitive and decisive patterns. Our findings indicate that post-hoc methods tend to provide interpretations better aligned with sensitive patterns, whereas certain self-interpretable methods exhibit strong and stable performance in detecting decisive patterns. Additionally, our study offers valuable insights into improving the reliability of these interpretation methods. For example, ensembling post-hoc interpretations from multiple models trained on the same task can effectively uncover the task's decisive patterns.
Authors: Nexhi Sula, Abhinav Kumar, Jie Hou, Han Wang, Reza Tourani
Abstract: With the continued advancement and widespread adoption of machine learning (ML) models across various domains, ensuring user privacy and data security has become a paramount concern. In compliance with data privacy regulations, such as GDPR, a secure machine learning framework should not only grant users the right to request the removal of their contributed data used for model training but also facilitates the elimination of sensitive data fingerprints within machine learning models to mitigate potential attack - a process referred to as machine unlearning. In this study, we present a novel unlearning mechanism designed to effectively remove the impact of specific data samples from a neural network while considering the performance of the unlearned model on the primary task. In achieving this goal, we crafted a novel loss function tailored to eliminate privacy-sensitive information from weights and activation values of the target model by combining target classification loss and membership inference loss. Our adaptable framework can easily incorporate various privacy leakage approximation mechanisms to guide the unlearning process. We provide empirical evidence of the effectiveness of our unlearning approach with a theoretical upper-bound analysis through a membership inference mechanism as a proof of concept. Our results showcase the superior performance of our approach in terms of unlearning efficacy and latency as well as the fidelity of the primary task, across four datasets and four deep learning architectures.
Authors: Ziyan Wang, Zhankun Xiong, Feng Huang, Xuan Liu, Wen Zhang
Abstract: Drug-drug interactions (DDIs) can result in various pharmacological changes, which can be categorized into different classes known as DDI events (DDIEs). In recent years, previously unobserved/unseen DDIEs have been emerging, posing a new classification task when unseen classes have no labelled instances in the training stage, which is formulated as a zero-shot DDIE prediction (ZS-DDIE) task. However, existing computational methods are not directly applicable to ZS-DDIE, which has two primary challenges: obtaining suitable DDIE representations and handling the class imbalance issue. To overcome these challenges, we propose a novel method named ZeroDDI for the ZS-DDIE task. Specifically, we design a biological semantic enhanced DDIE representation learning module, which emphasizes the key biological semantics and distills discriminative molecular substructure-related semantics for DDIE representation learning. Furthermore, we propose a dual-modal uniform alignment strategy to distribute drug pair representations and DDIE semantic representations uniformly in a unit sphere and align the matched ones, which can mitigate the issue of class imbalance. Extensive experiments showed that ZeroDDI surpasses the baselines and indicate that it is a promising tool for detecting unseen DDIEs. Our code has been released in https://github.com/wzy-Sarah/ZeroDDI.
Authors: Junfan Li, Shizhong Liao
Abstract: Online kernel selection is a fundamental problem of online kernel methods. In this paper, we study online kernel selection with memory constraint in which the memory of kernel selection and online prediction procedures is limited to a fixed budget. An essential question is what is the intrinsic relationship among online learnability, memory constraint and data complexity? To answer the question, it is necessary to show the trade-offs between regret bound and memory constraint. Previous work gives a worst-case lower bound depending on the data size,and shows learning is impossible within a small memory constraint. In contrast, we present a different result by providing data-dependent upper bounds depending on two data complexities, namely kernel alignment and the cumulative losses of competitive hypothesis. We propose an algorithmic framework giving data-dependent upper bounds for two types of loss functions. For the hinge loss function, our algorithm achieves an expected upper bound depending on kernel alignment. For smooth loss functions,our algorithm achieves a high-probability upper bound depending on the cumulative losses of competitive hypothesis. We also prove a matching lower bound for smooth loss functions. Our results show that if the two data complexities are sub-linear, then learning is possible within a small memory constraint. Our algorithmic framework depends on a new buffer maintaining framework and a reduction from online kernel selection to prediction with expert advice.Finally, we empirically verify the prediction performance of our algorithms on benchmark datasets.
Authors: Arnab Bhattacharyya, Davin Choo, Sutanu Gayen, Dimitrios Myrisiotis
Abstract: Bayes nets are extensively used in practice to efficiently represent joint probability distributions over a set of random variables and capture dependency relations. In a seminal paper, Chickering et al. (JMLR 2004) showed that given a distribution $P$, that is defined as the marginal distribution of a Bayes net, it is $\mathsf{NP}$-hard to decide whether there is a parameter-bounded Bayes net that represents $P$. They called this problem LEARN. In this work, we extend the $\mathsf{NP}$-hardness result of LEARN and prove the $\mathsf{NP}$-hardness of a promise search variant of LEARN, whereby the Bayes net in question is guaranteed to exist and one is asked to find such a Bayes net. We complement our hardness result with a positive result about the sample complexity that is sufficient to recover a parameter-bounded Bayes net that is close (in TV distance) to a given distribution $P$, that is represented by some parameter-bounded Bayes net, generalizing a degree-bounded sample complexity result of Brustle et al. (EC 2020).
Authors: Songwei Liu, Chao Zeng, Lianqiang Li, Chenqian Yan, Lean Fu, Xing Mei, Fangmin Chen
Abstract: The demand for deploying large language models(LLMs) on mobile devices continues to increase, driven by escalating data security concerns and cloud costs. However, network bandwidth and memory limitations pose challenges for deploying billion-level models on mobile devices. In this study, we investigate the outputs of different layers across various scales of LLMs and found that the outputs of most layers exhibit significant similarity. Moreover, this similarity becomes more pronounced as the model size increases, indicating substantial redundancy in the depth direction of the LLMs. Based on this observation, we propose an efficient model volume compression strategy, termed FoldGPT, which combines block removal and block parameter sharing.This strategy consists of three parts: (1) Based on the learnable gating parameters, we determine the block importance ranking while modeling the coupling effect between blocks. Then we delete some redundant layers based on the given removal rate. (2) For the retained blocks, we apply a specially designed group parameter sharing strategy, where blocks within the same group share identical weights, significantly compressing the number of parameters and slightly reducing latency overhead. (3) After sharing these Blocks, we "cure" the mismatch caused by sparsity with a minor amount of fine-tuning and introduce a tail-layer distillation strategy to improve the performance. Experiments demonstrate that FoldGPT outperforms previous state-of-the-art(SOTA) methods in efficient model compression, demonstrating the feasibility of achieving model lightweighting through straightforward block removal and parameter sharing.
Authors: Qi Zhang, Tianqi Du, Haotian Huang, Yifei Wang, Yisen Wang
Abstract: In recent years, the rise of generative self-supervised learning (SSL) paradigms has exhibited impressive performance across visual, language, and multi-modal domains. While the varied designs of generative SSL objectives lead to distinct properties in downstream tasks, a theoretical understanding of these differences remains largely unexplored. In this paper, we establish the first theoretical comparisons between two leading generative SSL paradigms: autoregressive SSL and masked SSL. Through establishing theoretical frameworks, we elucidate the strengths and limitations of autoregressive and masked SSL within the primary evaluation tasks of classification and content generation. Our findings demonstrate that in classification tasks, the flexibility of targeted tokens in masked SSL fosters more inter-sample connections compared to the fixed position of target tokens in autoregressive SSL, which yields superior clustering performance. In content generation tasks, the misalignment between the flexible lengths of test samples and the fixed length of unmasked texts in masked SSL (vs. flexible lengths of conditional texts in autoregressive SSL) hinders its generation performance. To leverage each other's strengths and mitigate weaknesses, we propose diversity-enhanced autoregressive and variable-length masked objectives, which substantially improve the classification performance of autoregressive SSL and the generation performance of masked SSL. Code is available at https://github.com/PKU-ML/LookAheadLookAround.
Authors: Enshu Liu, Junyi Zhu, Zinan Lin, Xuefei Ning, Matthew B. Blaschko, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
Abstract: The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their substantial demands on memory, processing power, and energy consumption. Sparse Mixture-of-Experts (SMoE) architectures have emerged as a solution, activating only a subset of parameters per token, thereby achieving faster inference while maintaining performance. However, SMoE models still face limitations in broader deployment due to their large parameter counts and significant GPU memory requirements. In this work, we introduce a gradient-free evolutionary strategy named EEP (Efficient Expert P}runing) to enhance the pruning of experts in SMoE models. EEP relies solely on model inference (i.e., no gradient computation) and achieves greater sparsity while maintaining or even improving performance on downstream tasks. EEP can be used to reduce both the total number of experts (thus saving GPU memory) and the number of active experts (thus accelerating inference). For example, we demonstrate that pruning up to 75% of experts in Mixtral $8\times7$B-Instruct results in a substantial reduction in parameters with minimal performance loss. Remarkably, we observe improved performance on certain tasks, such as a significant increase in accuracy on the SQuAD dataset (from 53.4% to 75.4%), when pruning half of the experts. With these results, EEP not only lowers the barrier to deploying SMoE models,but also challenges the conventional understanding of model pruning by showing that fewer experts can lead to better task-specific performance without any fine-tuning. Code is available at https://github.com/imagination-research/EEP.
Authors: Ziyi Liu, Idan Attias, Daniel M. Roy
Abstract: In this work, we investigate the problem of adapting to the presence or absence of causal structure in multi-armed bandit problems. In addition to the usual reward signal, we assume the learner has access to additional variables, observed in each round after acting. When these variables $d$-separate the action from the reward, existing work in causal bandits demonstrates that one can achieve strictly better (minimax) rates of regret (Lu et al., 2020). Our goal is to adapt to this favorable "conditionally benign" structure, if it is present in the environment, while simultaneously recovering worst-case minimax regret, if it is not. Notably, the learner has no prior knowledge of whether the favorable structure holds. In this paper, we establish the Pareto optimal frontier of adaptive rates. We prove upper and matching lower bounds on the possible trade-offs in the performance of learning in conditionally benign and arbitrary environments, resolving an open question raised by Bilodeau et al. (2022). Furthermore, we are the first to obtain instance-dependent bounds for causal bandits, by reducing the problem to the linear bandit setting. Finally, we examine the common assumption that the marginal distributions of the post-action contexts are known and show that a nontrivial estimate is necessary for better-than-worst-case minimax rates.
Authors: Zheng Lin, Xuanjie Hu, Yuxin Zhang, Zhe Chen, Zihan Fang, Xianhao Chen, Ang Li, Praneeth Vepakomma, Yue Gao
Abstract: The scalability of large language models (LLMs) in handling high-complexity models and large-scale datasets has led to tremendous successes in pivotal domains. While there is an urgent need to acquire more training data for LLMs, a concerning reality is the depletion of high-quality public datasets within a few years. In view of this, the federated learning (FL) LLM fine-tuning paradigm recently has been proposed to facilitate collaborative LLM fine-tuning on distributed private data, where multiple data owners collaboratively fine-tune a shared LLM without sharing raw data. However, the staggering model size of LLMs imposes heavy computing and communication burdens on clients, posing significant barriers to the democratization of the FL LLM fine-tuning paradigm. To address this issue, split learning (SL) has emerged as a promising solution by offloading the primary training workload to a server via model partitioning while exchanging activation/activation's gradients with smaller data sizes rather than the entire LLM. Unfortunately, research on the SL LLM fine-tuning paradigm is still in its nascent stage. To fill this gap, in this paper, we propose the first SL LLM fine-tuning framework, named SplitLoRA. SplitLoRA is built on the split federated learning (SFL) framework, amalgamating the advantages of parallel training from FL and model splitting from SL and thus greatly enhancing the training efficiency. It is worth noting that SplitLoRA is the inaugural open-source benchmark for SL LLM fine-tuning, providing a foundation for research efforts dedicated to advancing SL LLM fine-tuning. Extensive simulations validate that SplitLoRA achieves target accuracy in significantly less time than state-of-the-art LLM fine-tuning frameworks, demonstrating the superior training performance of SplitLoRA. The project page is available at https://fduinc.github.io/splitlora/.
Authors: Han-Jia Ye, Si-Yang Liu, Hao-Run Cai, Qi-Le Zhou, De-Chuan Zhan
Abstract: Tabular data is prevalent across various domains in machine learning. Although Deep Neural Network (DNN)-based methods have shown promising performance comparable to tree-based ones, in-depth evaluation of these methods is challenging due to varying performance ranks across diverse datasets. In this paper, we propose a comprehensive benchmark comprising 300 tabular datasets, covering a wide range of task types, size distributions, and domains. We perform an extensive comparison between state-of-the-art deep tabular methods and tree-based methods, revealing the average rank of all methods and highlighting the key factors that influence the success of deep tabular methods. Next, we analyze deep tabular methods based on their training dynamics, including changes in validation metrics and other statistics. For each dataset-method pair, we learn a mapping from both the meta-features of datasets and the first part of the validation curve to the final validation set performance and even the evolution of validation curves. This mapping extracts essential meta-features that influence prediction accuracy, helping the analysis of tabular methods from novel aspects. Based on the performance of all methods on this large benchmark, we identify two subsets of 45 datasets each. The first subset contains datasets that favor either tree-based methods or DNN-based methods, serving as effective analysis tools to evaluate strategies (e.g., attribute encoding strategies) for improving deep tabular models. The second subset contains datasets where the ranks of methods are consistent with the overall benchmark, acting as a probe for tabular analysis. These ``tiny tabular benchmarks'' will facilitate further studies on tabular data.
Authors: Gautam Chandrasekaran, Adam Klivans, Vasilis Kontonis, Raghu Meka, Konstantinos Stavropoulos
Abstract: In traditional models of supervised learning, the goal of a learner -- given examples from an arbitrary joint distribution on $\mathbb{R}^d \times \{\pm 1\}$ -- is to output a hypothesis that is competitive (to within $\epsilon$) of the best fitting concept from some class. In order to escape strong hardness results for learning even simple concept classes, we introduce a smoothed-analysis framework that requires a learner to compete only with the best classifier that is robust to small random Gaussian perturbation. This subtle change allows us to give a wide array of learning results for any concept that (1) depends on a low-dimensional subspace (aka multi-index model) and (2) has a bounded Gaussian surface area. This class includes functions of halfspaces and (low-dimensional) convex sets, cases that are only known to be learnable in non-smoothed settings with respect to highly structured distributions such as Gaussians. Surprisingly, our analysis also yields new results for traditional non-smoothed frameworks such as learning with margin. In particular, we obtain the first algorithm for agnostically learning intersections of $k$-halfspaces in time $k^{poly(\frac{\log k}{\epsilon \gamma}) }$ where $\gamma$ is the margin parameter. Before our work, the best-known runtime was exponential in $k$ (Arriaga and Vempala, 1999).
Authors: Ahmet Cagri Duzgun, Samy Jelassi, Yuanzhi Li
Abstract: Overparameterization, the condition where models have more parameters than necessary to fit their training loss, is a crucial factor for the success of deep learning. However, the characteristics of the features learned by overparameterized networks are not well understood. In this work, we explore this question by comparing models with the same architecture but different widths. We first examine the expressivity of the features of these models, and show that the feature space of overparameterized networks cannot be spanned by concatenating many underparameterized features, and vice versa. This reveals that both overparameterized and underparameterized networks acquire some distinctive features. We then evaluate the performance of these models, and find that overparameterized networks outperform underparameterized networks, even when many of the latter are concatenated. We corroborate these findings using a VGG-16 and ResNet18 on CIFAR-10 and a Transformer on the MNLI classification dataset. Finally, we propose a toy setting to explain how overparameterized networks can learn some important features that the underparamaterized networks cannot learn.
Authors: Marek Grzesiak, Param Thakkar
Abstract: This study investigates the potential of quantum machine learning to improve flood forecasting we focus on daily flood events along Germany's Wupper River in 2023 our approach combines classical machine learning techniques with QML techniques this hybrid model leverages quantum properties like superposition and entanglement to achieve better accuracy and efficiency classical and QML models are compared based on training time accuracy and scalability results show that QML models offer competitive training times and improved prediction accuracy this research signifies a step towards utilizing quantum technologies for climate change adaptation we emphasize collaboration and continuous innovation to implement this model in real-world flood management ultimately enhancing global resilience against floods
Authors: Jiehui Zhou, Linxiao Yang, Xingyu Liu, Xinyue Gu, Liang Sun, Wei Chen
Abstract: In causal inference, estimating heterogeneous treatment effects (HTE) is critical for identifying how different subgroups respond to interventions, with broad applications in fields such as precision medicine and personalized advertising. Although HTE estimation methods aim to improve accuracy, how to provide explicit subgroup descriptions remains unclear, hindering data interpretation and strategic intervention management. In this paper, we propose CURLS, a novel rule learning method leveraging HTE, which can effectively describe subgroups with significant treatment effects. Specifically, we frame causal rule learning as a discrete optimization problem, finely balancing treatment effect with variance and considering the rule interpretability. We design an iterative procedure based on the minorize-maximization algorithm and solve a submodular lower bound as an approximation for the original. Quantitative experiments and qualitative case studies verify that compared with state-of-the-art methods, CURLS can find subgroups where the estimated and true effects are 16.1% and 13.8% higher and the variance is 12.0% smaller, while maintaining similar or better estimation accuracy and rule interpretability. Code is available at https://osf.io/zwp2k/.
URLs: https://osf.io/zwp2k/.
Authors: Yuning Chen, Kang Yang, Zhiyu An, Brady Holder, Luke Paloutzian, Khaled Bali, Wan Du
Abstract: The rapid decline in groundwater around the world poses a significant challenge to sustainable agriculture. To address this issue, agricultural managed aquifer recharge (Ag-MAR) is proposed to recharge the aquifer by artificially flooding agricultural lands using surface water. Ag-MAR requires a carefully selected flooding schedule to avoid affecting the oxygen absorption of crop roots. However, current Ag-MAR scheduling does not take into account complex environmental factors such as weather and soil oxygen, resulting in crop damage and insufficient recharging amounts. This paper proposes MARLP, the first end-to-end data-driven control system for Ag-MAR. We first formulate Ag-MAR as an optimization problem. To that end, we analyze four-year in-field datasets, which reveal the multi-periodicity feature of the soil oxygen level trends and the opportunity to use external weather forecasts and flooding proposals as exogenous clues for soil oxygen prediction. Then, we design a two-stage forecasting framework. In the first stage, it extracts both the cross-variate dependency and the periodic patterns from historical data to conduct preliminary forecasting. In the second stage, it uses weather-soil and flooding-soil causality to facilitate an accurate prediction of soil oxygen levels. Finally, we conduct model predictive control (MPC) for Ag-MAR flooding. To address the challenge of large action spaces, we devise a heuristic planning module to reduce the number of flooding proposals to enable the search for optimal solutions. Real-world experiments show that MARLP reduces the oxygen deficit ratio by 86.8% while improving the recharging amount in unit time by 35.8%, compared with the previous four years.
Authors: Youngmin Seo, Jinha Kim, Unsang Park
Abstract: We propose the Swish-T family, an enhancement of the existing non-monotonic activation function Swish. Swish-T is defined by adding a Tanh bias to the original Swish function. This modification creates a family of Swish-T variants, each designed to excel in different tasks, showcasing specific advantages depending on the application context. The Tanh bias allows for broader acceptance of negative values during initial training stages, offering a smoother non-monotonic curve than the original Swish. We ultimately propose the Swish-T$_{\textbf{C}}$ function, while Swish-T and Swish-T$_{\textbf{B}}$, byproducts of Swish-T$_{\textbf{C}}$, also demonstrate satisfactory performance. Furthermore, our ablation study shows that using Swish-T$_{\textbf{C}}$ as a non-parametric function can still achieve high performance. The superiority of the Swish-T family has been empirically demonstrated across various models and benchmark datasets, including MNIST, Fashion MNIST, SVHN, CIFAR-10, and CIFAR-100. The code is publicly available at "https://github.com/ictseoyoungmin/Swish-T-pytorch".
Authors: Masatoshi Hidaka, Tomohiro Hashimoto, Yuto Nishizawa, Tatsuya Harada
Abstract: We present "DistML.js", a library designed for training and inference of machine learning models within web browsers. Not only does DistML.js facilitate model training on local devices, but it also supports distributed learning through communication with servers. Its design and define-by-run API for deep learning model construction resemble PyTorch, thereby reducing the learning curve for prototyping. Matrix computations involved in model training and inference are executed on the backend utilizing WebGL, enabling high-speed calculations. We provide a comprehensive explanation of DistML.js's design, API, and implementation, alongside practical applications including data parallelism in learning. The source code is publicly available at https://github.com/mil-tokyo/distmljs.
Authors: Dan Peng, Zhihui Fu, Jun Wang
Abstract: Recent advancements in large language models (LLMs) have indeed showcased their impressive capabilities. On mobile devices, the wealth of valuable, non-public data generated daily holds great promise for locally fine-tuning personalized LLMs, while maintaining privacy through on-device processing. However, the constraints of mobile device resources pose challenges to direct on-device LLM fine-tuning, mainly due to the memory-intensive nature of derivative-based optimization required for saving gradients and optimizer states. To tackle this, we propose employing derivative-free optimization techniques to enable on-device fine-tuning of LLM, even on memory-limited mobile devices. Empirical results demonstrate that the RoBERTa-large model and OPT-1.3B can be fine-tuned locally on the OPPO Reno 6 smartphone using around 4GB and 6.5GB of memory respectively, using derivative-free optimization techniques. This highlights the feasibility of on-device LLM fine-tuning on mobile devices, paving the way for personalized LLMs on resource-constrained devices while safeguarding data privacy.
Authors: Jeremias Traub, Till J. Bungert, Carsten T. L\"uth, Michael Baumgartner, Klaus H. Maier-Hein, Lena Maier-Hein, Paul F Jaeger
Abstract: Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the $\mathrm{AUROC}$ in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility, and show how current approaches fail to meet them. We propose the Area under the Generalized Risk Coverage curve ($\mathrm{AUGRC}$), which meets all requirements and can be directly interpreted as the average risk of undetected failures. We empirically demonstrate the relevance of $\mathrm{AUGRC}$ on a comprehensive benchmark spanning 6 data sets and 13 confidence scoring functions. We find that the proposed metric substantially changes metric rankings on 5 out of the 6 data sets.
Authors: Yongqiang Cai, Gaohang Chen, Zhonghua Qiao
Abstract: The universal approximation property is fundamental to the success of neural networks, and has traditionally been achieved by training networks without any constraints on their parameters. However, recent experimental research proposed a novel permutation-based training method, which exhibited a desired classification performance without modifying the exact weight values. In this paper, we provide a theoretical guarantee of this permutation training method by proving its ability to guide a ReLU network to approximate one-dimensional continuous functions. Our numerical results further validate this method's efficiency in regression tasks with various initializations. The notable observations during weight permutation suggest that permutation training can provide an innovative tool for describing network learning behavior.
Authors: Artem Moskalev, Mangal Prakash, Rui Liao, Tommaso Mansi
Abstract: Modeling global geometric context while maintaining equivariance is crucial for accurate predictions in many fields such as biology, chemistry, or vision. Yet, this is challenging due to the computational demands of processing high-dimensional data at scale. Existing approaches such as equivariant self-attention or distance-based message passing, suffer from quadratic complexity with respect to sequence length, while localized methods sacrifice global information. Inspired by the recent success of state-space and long-convolutional models, in this work, we introduce SE(3)-Hyena operator, an equivariant long-convolutional model based on the Hyena operator. The SE(3)-Hyena captures global geometric context at sub-quadratic complexity while maintaining equivariance to rotations and translations. Evaluated on equivariant associative recall and n-body modeling, SE(3)-Hyena matches or outperforms equivariant self-attention while requiring significantly less memory and computational resources for long sequences. Our model processes the geometric context of 20k tokens x3.5 times faster than the equivariant transformer and allows x175 longer a context within the same memory budget.
Authors: Beatrice Alessandra Motetti, Matteo Risso, Alessio Burrello, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari
Abstract: The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory occupation improvements. These optimization techniques are usually applied independently. We propose a novel methodology to apply them jointly via a lightweight gradient-based search, and in a hardware-aware manner, greatly reducing the time required to generate Pareto-optimal DNNs in terms of accuracy versus cost (i.e., latency or memory). We test our approach on three edge-relevant benchmarks, namely CIFAR-10, Google Speech Commands, and Tiny ImageNet. When targeting the optimization of the memory footprint, we are able to achieve a size reduction of 47.50% and 69.54% at iso-accuracy with the baseline networks with all weights quantized at 8 and 2-bit, respectively. Our method surpasses a previous state-of-the-art approach with up to 56.17% size reduction at iso-accuracy. With respect to the sequential application of state-of-the-art pruning and mixed-precision optimizations, we obtain comparable or superior results, but with a significantly lowered training time. In addition, we show how well-tailored cost models can improve the cost versus accuracy trade-offs when targeting specific hardware for deployment.
Authors: Meng Ai, Zhuo Chen, Jibin Wang, Jing Shang, Tao Tao, Zhen Li
Abstract: In the commercial sphere, such as operations and maintenance, advertising, and marketing recommendations, intelligent decision-making utilizing data mining and neural network technologies is crucial, especially in resource allocation to optimize ROI. This study delves into the Cost-aware Binary Treatment Assignment Problem (C-BTAP) across different industries, with a focus on the state-of-the-art Direct ROI Prediction (DRP) method. However, the DRP model confronts issues like covariate shift and insufficient training data, hindering its real-world effectiveness. Addressing these challenges is essential for ensuring dependable and robust predictions in varied operational contexts. This paper presents a robust Direct ROI Prediction (rDRP) method, designed to address challenges in real-world deployment of neural network-based uplift models, particularly under conditions of covariate shift and insufficient training data. The rDRP method, enhancing the standard DRP model, does not alter the model's structure or require retraining. It utilizes conformal prediction and Monte Carlo dropout for interval estimation, adapting to model uncertainty and data distribution shifts. A heuristic calibration method, inspired by a Kaggle competition, combines point and interval estimates. The effectiveness of these approaches is validated through offline tests and online A/B tests in various settings, demonstrating significant improvements in target rewards compared to the state-of-the-art method.
Authors: Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Jingang Wang, Zhenyu Chen, Jieyu Zhao, Hui Xiong
Abstract: Recently, large language model (LLM)-based preference evaluation has been widely adopted to compare pairs of model responses. However, a severe bias towards lengthy responses has been observed, raising concerns about the reliability of this evaluation method. In this work, we designed a series of controlled experiments to study the major impacting factors of the metric of LLM-based preference evaluation, i.e., win rate, and conclude that the win rate is affected by two axes of model response: desirability and information mass, where the former is length-independent and related to trustworthiness, and the latter is length-dependent and can be represented by conditional entropy. We find that length impacts the existing evaluations by influencing information mass. However, a reliable evaluation metric should not only assess content quality but also ensure that the assessment is not confounded by extraneous factors such as response length. Therefore, we propose a simple yet effective adjustment, AdapAlpaca, to the existing practice of win rate measurement. Specifically, by adjusting the lengths of reference answers to match the test model's answers within the same interval, we debias information mass relative to length, ensuring a fair model evaluation.
Authors: Hao Wang, Zhichao Chen, Yuan Shen, Jiajun Fan, Zhaoran Liu, Degui Yang, Xinggao Liu, Haoxuan Li
Abstract: Heterogeneous treatment effect (HTE) estimation from observational data poses significant challenges due to treatment selection bias. Existing methods address this bias by minimizing distribution discrepancies between treatment groups in latent space, focusing on global alignment. However, the fruitful aspect of local proximity, where similar units exhibit similar outcomes, is often overlooked. In this study, we propose Proximity-aware Counterfactual Regression (PCR) to exploit proximity for representation balancing within the HTE estimation context. Specifically, we introduce a local proximity preservation regularizer based on optimal transport to depict the local proximity in discrepancy calculation. Furthermore, to overcome the curse of dimensionality that renders the estimation of discrepancy ineffective, exacerbated by limited data availability for HTE estimation, we develop an informative subspace projector, which trades off minimal distance precision for improved sample complexity. Extensive experiments demonstrate that PCR accurately matches units across different treatment groups, effectively mitigates treatment selection bias, and significantly outperforms competitors. Code is available at https://anonymous.4open.science/status/ncr-B697.
Authors: Andrej Tschalzev, Paul Nitschke, Lukas Kirchdorfer, Stefan L\"udtke, Christian Bartelt, Heiner Stuckenschmidt
Abstract: Neural networks often assume independence among input data samples, disregarding correlations arising from inherent clustering patterns in real-world datasets (e.g., due to different sites or repeated measurements). Recently, mixed effects neural networks (MENNs) which separate cluster-specific 'random effects' from cluster-invariant 'fixed effects' have been proposed to improve generalization and interpretability for clustered data. However, existing methods only allow for approximate quantification of cluster effects and are limited to regression and binary targets with only one clustering feature. We present MC-GMENN, a novel approach employing Monte Carlo methods to train Generalized Mixed Effects Neural Networks. We empirically demonstrate that MC-GMENN outperforms existing mixed effects deep learning models in terms of generalization performance, time complexity, and quantification of inter-cluster variance. Additionally, MC-GMENN is applicable to a wide range of datasets, including multi-class classification tasks with multiple high-cardinality categorical features. For these datasets, we show that MC-GMENN outperforms conventional encoding and embedding methods, simultaneously offering a principled methodology for interpreting the effects of clustering patterns.
Authors: Abdulaziz Alwalan, Miguel Arana-Catania
Abstract: In this work we demonstrate the possibility of estimating the wind environment of a UAV without specialised sensors, using only the UAV's trajectory, applying a causal machine learning approach. We implement the causal curiosity method which combines machine learning times series classification and clustering with a causal framework. We analyse three distinct wind environments: constant wind, shear wind, and turbulence, and explore different optimisation strategies for optimal UAV manoeuvres to estimate the wind conditions. The proposed approach can be used to design optimal trajectories in challenging weather conditions, and to avoid specialised sensors that add to the UAV's weight and compromise its functionality.
Authors: Yuanyang He, Zitong Huang, Xinxing Xu, Rick Siow Mong Goh, Salman Khan, Wangmeng Zuo, Yong Liu, Chun-Mei Feng
Abstract: Black-box tuning has attracted recent attention due to that the structure or inner parameters of advanced proprietary models are not accessible. Proxy-tuning provides a test-time output adjustment for tuning black-box language models. It applies the difference of the output logits before and after tuning a smaller white-box "proxy" model to improve the black-box model. However, this technique serves only as a decoding-time algorithm, leading to an inconsistency between training and testing which potentially limits overall performance. To address this problem, we introduce Consistent Proxy Tuning (CPT), a simple yet effective black-box tuning method. Different from Proxy-tuning, CPT additionally exploits the frozen large black-box model and another frozen small white-box model, ensuring consistency between training-stage optimization objective and test-time proxies. This consistency benefits Proxy-tuning and enhances model performance. Note that our method focuses solely on logit-level computation, which makes it model-agnostic and applicable to any task involving logit classification. Extensive experimental results demonstrate the superiority of our CPT in both black-box tuning of Large Language Models (LLMs) and Vision-Language Models (VLMs) across various datasets. The code is available at https://github.com/chunmeifeng/CPT.
Authors: Luca Pinchetti, Chang Qi, Oleh Lokshyn, Gaspard Olivers, Cornelius Emde, Mufeng Tang, Amine M'Charrak, Simon Frieder, Bayar Menzat, Rafal Bogacz, Thomas Lukasiewicz, Tommaso Salvatori
Abstract: In this work, we tackle the problems of efficiency and scalability for predictive coding networks in machine learning. To do so, we first propose a library called PCX, whose focus lies on performance and simplicity, and provides a user-friendly, deep-learning oriented interface. Second, we use PCX to implement a large set of benchmarks for the community to use for their experiments. As most works propose their own tasks and architectures, do not compare one against each other, and focus on small-scale tasks, a simple and fast open-source library adopted by the whole community would address all of these concerns. Third, we perform extensive benchmarks using multiple algorithms, setting new state-of-the-art results in multiple tasks and datasets, as well as highlighting limitations inherent to PC that should be addressed. Thanks to the efficiency of PCX, we are able to analyze larger architectures than commonly used, providing baselines to galvanize community efforts towards one of the main open problems in the field: scalability. The code for PCX is available at \textit{https://github.com/liukidar/pcax}.
Authors: Vladimir R. Kostic, Karim Lounici, Gregoire Pacreau, Pietro Novelli, Giacomo Turri, Massimiliano Pontil
Abstract: We introduce NCP (Neural Conditional Probability), a novel operator-theoretic approach for learning conditional distributions with a particular focus on inference tasks. NCP can be used to build conditional confidence regions and extract important statistics like conditional quantiles, mean, and covariance. It offers streamlined learning through a single unconditional training phase, facilitating efficient inference without the need for retraining even when conditioning changes. By tapping into the powerful approximation capabilities of neural networks, our method efficiently handles a wide variety of complex probability distributions, effectively dealing with nonlinear relationships between input and output variables. Theoretical guarantees ensure both optimization consistency and statistical accuracy of the NCP method. Our experiments show that our approach matches or beats leading methods using a simple Multi-Layer Perceptron (MLP) with two hidden layers and GELU activations. This demonstrates that a minimalistic architecture with a theoretically grounded loss function can achieve competitive results without sacrificing performance, even in the face of more complex architectures.
Authors: Amitoz Azad, Yuan Fang
Abstract: Geodesic distances on manifolds have numerous applications in image processing, computer graphics and computer vision. In this work, we introduce an approach called `LGGD' (Learned Generalized Geodesic Distances). This method involves generating node features by learning a generalized geodesic distance function through a training pipeline that incorporates training data, graph topology and the node content features. The strength of this method lies in the proven robustness of the generalized geodesic distances to noise and outliers. Our contributions encompass improved performance in node classification tasks, competitive results with state-of-the-art methods on real-world graph datasets, the demonstration of the learnability of parameters within the generalized geodesic equation on graph, and dynamic inclusion of new labels.
Authors: Zongshuo Li, Markus Meurer, Thomas Bergs
Abstract: Tool wear conditions impact the final quality of the workpiece. In this study, we propose a deep learning approach based on a convolutional neural network that incorporates cutting conditions as extra model inputs, aiming to improve tool wear estimation accuracy and fulfill industrial demands for zero-shot transferability. Through a series of milling experiments under various cutting parameters, we evaluate the model's performance in terms of tool wear estimation accuracy and its transferability to new fixed or variable cutting parameters. The results consistently highlight our approach's advantage over conventional models that omit cutting conditions, maintaining superior performance irrespective of the stability of the wear development or the limitation of the training dataset. This finding underscores its potential applicability in industrial scenarios.
Authors: Zongshuo Li, Markus Meurer, Thomas Bergs
Abstract: As an integral part of contemporary manufacturing, monitoring systems obtain valuable information during machining to oversee the condition of both the process and the machine. Recently, diverse algorithms have been employed to detect tool wear using single or multiple sources of measurements. In this study, a deep learning approach is proposed for estimating tool wear, considering cutting parameters. The model's accuracy and transferability in tool wear estimation were assessed with milling experiments conducted under varying cutting parameters. The results indicate that the proposed method outperforms conventional methods in terms of both transferability and rapid learning capabilities.
Authors: Jinwoo Kim, Olga Zaghen, Ayhan Suleymanzade, Youngmin Ryou, Seunghoon Hong
Abstract: We revisit a simple idea for machine learning on graphs, where a random walk on a graph produces a machine-readable record, and this record is processed by a deep neural network to directly make vertex-level or graph-level predictions. We refer to these stochastic machines as random walk neural networks, and show that we can design them to be isomorphism invariant while capable of universal approximation of graph functions in probability. A useful finding is that almost any kind of record of random walk guarantees probabilistic invariance as long as the vertices are anonymized. This enables us to record random walks in plain text and adopt a language model to read these text records to solve graph tasks. We further establish a parallelism to message passing neural networks using tools from Markov chain theory, and show that over-smoothing in message passing is alleviated by construction in random walk neural networks, while over-squashing manifests as probabilistic under-reaching. We show that random walk neural networks based on pre-trained language models can solve several hard problems on graphs, such as separating strongly regular graphs where the 3-WL test fails, counting substructures, and transductive classification on arXiv citation network without training. Code is available at https://github.com/jw9730/random-walk.
Authors: Yang Pan, Clemens Hutter, Helmut B\"olcskei
Abstract: This paper is concerned with the fundamental limits of nonlinear dynamical system learning from input-output traces. Specifically, we show that recurrent neural networks (RNNs) are capable of learning nonlinear systems that satisfy a Lipschitz property and forget past inputs fast enough in a metric-entropy optimal manner. As the sets of sequence-to-sequence maps realized by the dynamical systems we consider are significantly more massive than function classes generally considered in deep neural network approximation theory, a refined metric-entropy characterization is needed, namely in terms of order, type, and generalized dimension. We compute these quantities for the classes of exponentially-decaying and polynomially-decaying Lipschitz fading-memory systems and show that RNNs can achieve them.
Authors: Negin Yousefpour, Bo Wang
Abstract: This paper introduces scour physics-informed neural network algorithms (SPINNs), a hybrid physics-data-driven framework for bridge scour prediction using deep learning developed based on historical scour monitoring data. SPINNs integrate physics-based empirical equations into neural networks as supplementary loss components. We examined three architectures: LSTM, CNN, and NLinear. While CNN and LSTM have shown competitive real-time scour forecasting in previous studies, NLinear with a simple architecture demonstrated the highest accuracy and significantly lower computational cost. Despite varying error reduction margins across different base models and bridges, SPINNs showed promising scour prediction and generally outperformed pure data-driven models. In some bridge cases, SPINN reduced forecasting errors by up to 50\%. In this study, we also explored generalised models for bridge clusters by aggregating training datasets from multiple bridges in Alaska. Bridge/site-specific SPINNs incorporating HEC18 and time-dependent empirical equations provided more accurate predictions than SPINNs with generalised time-dependent equations. The three empirical equations derived from SPINN training in this study showed reasonable accuracy in estimating maximum scour depth. These deep learning derived empirical models can provide more accurate and reliable scour predictions than traditional HEC-18, particularly in scenarios lacking site-specific scour data. Comparing the HEC-18 model with both SPINNs and pure deep learning models highlights a substantial improvement in scour prediction accuracy, indicating a promising future for these hybrid machine learning methodologies for bridge scour design and maintenance.
Authors: YuRui Huang, Jie Zhang, HengDa Bao, Yang Yang, Jian Yang
Abstract: Estimated time of arrival (ETA) is a very important factor in the transportation system. It has attracted increasing attentions and has been widely used as a basic service in navigation systems and intelligent transportation systems. In this paper, we propose a novel solution to the ETA estimation problem, which is an ensemble on tree models and neural networks. We proved the accuracy and robustness of the solution on the A/B list and finally won first place in the SIGSPATIAL 2021 GISCUP competition.
Authors: Guangrui Yang, Jianfei Li, Ming Li, Han Feng, Ding-Xuan Zhou
Abstract: In this paper, we explore the approximation theory of functions defined on graphs. Our study builds upon the approximation results derived from the $K$-functional. We establish a theoretical framework to assess the lower bounds of approximation for target functions using Graph Convolutional Networks (GCNs) and examine the over-smoothing phenomenon commonly observed in these networks. Initially, we introduce the concept of a $K$-functional on graphs, establishing its equivalence to the modulus of smoothness. We then analyze a typical type of GCN to demonstrate how the high-frequency energy of the output decays, an indicator of over-smoothing. This analysis provides theoretical insights into the nature of over-smoothing within GCNs. Furthermore, we establish a lower bound for the approximation of target functions by GCNs, which is governed by the modulus of smoothness of these functions. This finding offers a new perspective on the approximation capabilities of GCNs. In our numerical experiments, we analyze several widely applied GCNs and observe the phenomenon of energy decay. These observations corroborate our theoretical results on exponential decay order.
Authors: Akash Dhasade, Paolo Dini, Elia Guerra, Anne-Marie Kermarrec, Marco Miozzo, Rafael Pires, Rishi Sharma, Martijn de Vos
Abstract: Decentralized learning (DL) offers a powerful framework where nodes collaboratively train models without sharing raw data and without the coordination of a central server. In the iterative rounds of DL, models are trained locally, shared with neighbors in the topology, and aggregated with other models received from neighbors. Sharing and merging models contribute to convergence towards a consensus model that generalizes better across the collective data captured at training time. In addition, the energy consumption while sharing and merging model parameters is negligible compared to the energy spent during the training phase. Leveraging this fact, we present SkipTrain, a novel DL algorithm, which minimizes energy consumption in decentralized learning by strategically skipping some training rounds and substituting them with synchronization rounds. These training-silent periods, besides saving energy, also allow models to better mix and finally produce models with superior accuracy than typical DL algorithms that train at every round. Our empirical evaluations with 256 nodes demonstrate that SkipTrain reduces energy consumption by 50% and increases model accuracy by up to 12% compared to D-PSGD, the conventional DL algorithm.
Authors: Menglin Yang, Harshit Verma, Delvin Ce Zhang, Jiahong Liu, Irwin King, Rex Ying
Abstract: Hyperbolic geometry have shown significant potential in modeling complex structured data, particularly those with underlying tree-like and hierarchical structures. Despite the impressive performance of various hyperbolic neural networks across numerous domains, research on adapting the Transformer to hyperbolic space remains limited. Previous attempts have mainly focused on modifying self-attention modules in the Transformer. However, these efforts have fallen short of developing a complete hyperbolic Transformer. This stems primarily from: (i) the absence of well-defined modules in hyperbolic space, including linear transformation layers, LayerNorm layers, activation functions, dropout operations, etc. (ii) the quadratic time complexity of the existing hyperbolic self-attention module w.r.t the number of input tokens, which hinders its scalability. To address these challenges, we propose, Hypformer, a novel hyperbolic Transformer based on the Lorentz model of hyperbolic geometry. In Hypformer, we introduce two foundational blocks that define the essential modules of the Transformer in hyperbolic space. Furthermore, we develop a linear self-attention mechanism in hyperbolic space, enabling hyperbolic Transformer to process billion-scale graph data and long-sequence inputs for the first time. Our experimental results confirm the effectiveness and efficiency of Hypformer across various datasets, demonstrating its potential as an effective and scalable solution for large-scale data representation and large models.
Authors: Gavin Abercrombie, Djalel Benbouzid, Paolo Giudici, Delaram Golpayegani, Julio Hernandez, Pierre Noro, Harshvardhan Pandit, Eva Paraschou, Charlie Pownall, Jyoti Prajapati, Mark A. Sayre, Ushnish Sengupta, Arthit Suriyawongful, Ruby Thelot, Sofia Vei, Laura Waltersdorfer
Abstract: This paper introduces a collaborative, human-centered taxonomy of AI, algorithmic and automation harms. We argue that existing taxonomies, while valuable, can be narrow, unclear, typically cater to practitioners and government, and often overlook the needs of the wider public. Drawing on existing taxonomies and a large repository of documented incidents, we propose a taxonomy that is clear and understandable to a broad set of audiences, as well as being flexible, extensible, and interoperable. Through iterative refinement with topic experts and crowdsourced annotation testing, we propose a taxonomy that can serve as a powerful tool for civil society organisations, educators, policymakers, product teams and the general public. By fostering a greater understanding of the real-world harms of AI and related technologies, we aim to increase understanding, empower NGOs and individuals to identify and report violations, inform policy discussions, and encourage responsible technology development and deployment.
Authors: Chenxi Li, Abhinav Kumar, Zhen Guo, Jie Hou, Reza Tourani
Abstract: The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inference Attacks (MIAs). Despite numerous MIA studies, significant knowledge gaps persist, particularly regarding the impact of hidden features (in isolation) on attack efficacy and insufficient justification for the root causes of attacks based on raw data features. In this paper, we aim to address these knowledge gaps by first exploring statistical approaches to identify the most informative neurons and quantifying the significance of the hidden activations from the selected neurons on attack accuracy, in isolation and combination. Additionally, we propose an attack-driven explainable framework by integrating the target and attack models to identify the most influential features of raw data that lead to successful membership inference attacks. Our proposed MIA shows an improvement of up to 26% on state-of-the-art MIA.
Authors: Perusha Moodley, Pramod Kaushik, Dhillu Thambi, Mark Trovinger, Praveen Paruchuri, Xia Hong, Benjamin Rosman
Abstract: Decision Transformers, in their vanilla form, struggle to perform on image-based environments with multi-discrete action spaces. Although enhanced Decision Transformer architectures have been developed to improve performance, these methods have not specifically addressed this problem of multi-discrete action spaces which hampers existing Decision Transformer architectures from learning good representations. To mitigate this, we propose Multi-State Action Tokenisation (M-SAT), an approach for tokenising actions in multi-discrete action spaces that enhances the model's performance in such environments. Our approach involves two key changes: disentangling actions to the individual action level and tokenising the actions with auxiliary state information. These two key changes also improve individual action level interpretability and visibility within the attention layers. We demonstrate the performance gains of M-SAT on challenging ViZDoom environments with multi-discrete action spaces and image-based state spaces, including the Deadly Corridor and My Way Home scenarios, where M-SAT outperforms the baseline Decision Transformer without any additional data or heavy computational overheads. Additionally, we find that removing positional encoding does not adversely affect M-SAT's performance and, in some cases, even improves it.
Authors: Mike Li, Hongseok Namkoong, Shangzhou Xia
Abstract: The performance of ML models degrades when the training population is different from that seen under operation. Towards assessing distributional robustness, we study the worst-case performance of a model over all subpopulations of a given size, defined with respect to core attributes Z. This notion of robustness can consider arbitrary (continuous) attributes Z, and automatically accounts for complex intersectionality in disadvantaged groups. We develop a scalable yet principled two-stage estimation procedure that can evaluate the robustness of state-of-the-art models. We prove that our procedure enjoys several finite-sample convergence guarantees, including dimension-free convergence. Instead of overly conservative notions based on Rademacher complexities, our evaluation error depends on the dimension of Z only through the out-of-sample error in estimating the performance conditional on Z. On real datasets, we demonstrate that our method certifies the robustness of a model and prevents deployment of unreliable models.
Authors: Haobo Song, Hao Zhao, Soumajit Majumder, Tao Lin
Abstract: Fine-tuning large pre-trained foundation models, such as the 175B GPT-3, has attracted more attention for downstream tasks recently. While parameter-efficient fine-tuning methods have been proposed and proven effective without retraining all model parameters, their performance is limited by the capacity of incremental modules, especially under constrained parameter budgets. \\ To overcome this challenge, we propose CapaBoost, a simple yet effective strategy that enhances model capacity by leveraging low-rank updates through parallel weight modules in target layers. By applying static random masks to the shared weight matrix, CapaBoost constructs a diverse set of weight matrices, effectively increasing the rank of incremental weights without adding parameters. Notably, our approach can be seamlessly integrated into various existing parameter-efficient fine-tuning methods. We extensively validate the efficacy of CapaBoost through experiments on diverse downstream tasks, including natural language understanding, question answering, and image classification. Our results demonstrate significant improvements over baselines, without incurring additional computation or storage costs. Our code is available at \url{https://github.com/LINs-lab/CapaBoost}.
Authors: Callum Rhys Tilbury, Claude Formanek, Louise Beyers, Jonathan P. Shock, Arnu Pretorius
Abstract: Offline multi-agent reinforcement learning (MARL) leverages static datasets of experience to learn optimal multi-agent control. However, learning from static data presents several unique challenges to overcome. In this paper, we focus on coordination failure and investigate the role of joint actions in multi-agent policy gradients with offline data, focusing on a common setting we refer to as the 'Best Response Under Data' (BRUD) approach. By using two-player polynomial games as an analytical tool, we demonstrate a simple yet overlooked failure mode of BRUD-based algorithms, which can lead to catastrophic coordination failure in the offline setting. Building on these insights, we propose an approach to mitigate such failure, by prioritising samples from the dataset based on joint-action similarity during policy learning and demonstrate its effectiveness in detailed experiments. More generally, however, we argue that prioritised dataset sampling is a promising area for innovation in offline MARL that can be combined with other effective approaches such as critic and policy regularisation. Importantly, our work shows how insights drawn from simplified, tractable games can lead to useful, theoretically grounded insights that transfer to more complex contexts. A core dimension of offering is an interactive notebook, from which almost all of our results can be reproduced, in a browser.
Authors: Christos Chatzis, Carla Schenker, Max Pfeffer, Evrim Acar
Abstract: Tensor factorizations have been widely used for the task of uncovering patterns in various domains. Often, the input is time-evolving, shifting the goal to tracking the evolution of underlying patterns instead. To adapt to this more complex setting, existing methods incorporate temporal regularization but they either have overly constrained structural requirements or lack uniqueness which is crucial for interpretation. In this paper, in order to capture the underlying evolving patterns, we introduce t(emporal)PARAFAC2 which utilizes temporal smoothness regularization on the evolving factors. We propose an algorithmic framework that employs Alternating Optimization (AO) and the Alternating Direction Method of Multipliers (ADMM) to fit the model. Furthermore, we extend the algorithmic framework to the case of partially observed data. Our numerical experiments on both simulated and real datasets demonstrate the effectiveness of the temporal smoothness regularization, in particular, in the case of data with missing entries. We also provide an extensive comparison of different approaches for handling missing data within the proposed framework.
Authors: Werner Zellinger
Abstract: Estimating the ratio of two probability densities from finitely many observations of the densities, is a central problem in machine learning and statistics. A large class of methods constructs estimators from binary classifiers which distinguish observations from the two densities. However, the error of these constructions depends on the choice of the binary loss function, raising the question of which loss function to choose based on desired error properties. In this work, we start from prescribed error measures in a class of Bregman divergences and characterize all loss functions that lead to density ratio estimators with a small error. Our characterization provides a simple recipe for constructing loss functions with certain properties, such as loss functions that prioritize an accurate estimation of large values. This contrasts with classical loss functions, such as the logistic loss or boosting loss, which prioritize accurate estimation of small values. We provide numerical illustrations with kernel methods and test their performance in applications of parameter selection for deep domain adaptation.
Authors: Dmitrii Volkov
Abstract: We show that extensive LLM safety fine-tuning is easily subverted when an attacker has access to model weights. We evaluate three state-of-the-art fine-tuning methods-QLoRA, ReFT, and Ortho-and show how algorithmic advances enable constant jailbreaking performance with cuts in FLOPs and optimisation power. We strip safety fine-tuning from Llama 3 8B in one minute and Llama 3 70B in 30 minutes on a single GPU, and sketch ways to reduce this further.
Authors: Wenchen Han, Shay Vargaftik, Michael Mitzenmacher, Brad Karp, Ran Ben Basat
Abstract: Gradient aggregation has long been identified as a major bottleneck in today's large-scale distributed machine learning training systems. One promising solution to mitigate such bottlenecks is gradient compression, directly reducing communicated gradient data volume. However, in practice, many gradient compression schemes do not achieve acceleration of the training process while also preserving accuracy. In this work, we identify several common issues in previous gradient compression systems and evaluation methods. These issues include excessive computational overheads; incompatibility with all-reduce; and inappropriate evaluation metrics, such as not using an end-to-end metric or using a 32-bit baseline instead of a 16-bit baseline. We propose several general design and evaluation techniques to address these issues and provide guidelines for future work. Our preliminary evaluation shows that our techniques enhance the system's performance and provide a clearer understanding of the end-to-end utility of gradient compression methods.
Authors: Boyuan Chen, Diego Marti Monso, Yilun Du, Max Simchowitz, Russ Tedrake, Vincent Sitzmann
Abstract: This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels. We apply Diffusion Forcing to sequence generative modeling by training a causal next-token prediction model to generate one or several future tokens without fully diffusing past ones. Our approach is shown to combine the strengths of next-token prediction models, such as variable-length generation, with the strengths of full-sequence diffusion models, such as the ability to guide sampling to desirable trajectories. Our method offers a range of additional capabilities, such as (1) rolling-out sequences of continuous tokens, such as video, with lengths past the training horizon, where baselines diverge and (2) new sampling and guiding schemes that uniquely profit from Diffusion Forcing's variable-horizon and causal architecture, and which lead to marked performance gains in decision-making and planning tasks. In addition to its empirical success, our method is proven to optimize a variational lower bound on the likelihoods of all subsequences of tokens drawn from the true joint distribution. Project website: https://boyuan.space/diffusion-forcing
Authors: Bugra Onal, Eren Dogan, Muhammad Hadir Khan, Matthew R. Guthaus
Abstract: The Rectilinear Steiner Minimum Tree (RSMT) problem is a fundamental problem in VLSI placement and routing and is known to be NP-hard. Traditional RSMT algorithms spend a significant amount of time on finding Steiner points to reduce the total wire length or use heuristics to approximate producing sub-optimal results. We show that Graph Neural Networks (GNNs) can be used to predict optimal Steiner points in RSMTs with high accuracy and can be parallelized on GPUs. In this paper, we propose GAT-Steiner, a graph attention network model that correctly predicts 99.846% of the nets in the ISPD19 benchmark with an average increase in wire length of only 0.480% on suboptimal wire length nets. On randomly generated benchmarks, GAT-Steiner correctly predicts 99.942% with an average increase in wire length of only 0.420% on suboptimal wire length nets.
Authors: Xiyuan Wei, Fanjiang Ye, Ori Yonay, Xingyu Chen, Baixi Sun, Dingwen Tao, Tianbao Yang
Abstract: Existing studies of training state-of-the-art Contrastive Language-Image Pretraining (CLIP) models on large-scale data involve hundreds of or even thousands of GPUs due to the requirement of a large batch size. However, such a large amount of resources is not accessible to most people. While advanced compositional optimization techniques for optimizing global contrastive losses have been demonstrated effective for removing the requirement of large batch size, their performance on large-scale data remains underexplored and not optimized. To bridge the gap, this paper explores several aspects of CLIP training with limited resources (e.g., up to tens of GPUs). First, we introduce FastCLIP, a general CLIP training framework built on advanced compositional optimization techniques while designed and optimized for the distributed setting. Our framework is equipped with an efficient gradient reduction strategy to reduce communication overhead. Second, to further boost training efficiency, we investigate three components of the framework from an optimization perspective: the schedule of the inner learning rate, the update rules of the temperature parameter and the model parameters, respectively. Experiments on different strategies for each component shed light on how to conduct CLIP training more efficiently. Finally, we benchmark the performance of FastCLIP and the state-of-the-art training baseline (OpenCLIP) on different compute scales up to 32 GPUs on 8 nodes, and three data scales ranging from 2.7 million, 9.1 million to 315 million image-text pairs to demonstrate the significant improvement of FastCLIP in the resource-limited setting. We release the code of FastCLIP at https://github.com/Optimization-AI/fast_clip .
Authors: Hong Jun Jeon, Benjamin Van Roy
Abstract: Neural scaling laws aim to characterize how out-of-sample error behaves as a function of model and training dataset size. Such scaling laws guide allocation of a computational resources between model and data processing to minimize error. However, existing theoretical support for neural scaling laws lacks rigor and clarity, entangling the roles of information and optimization. In this work, we develop rigorous information-theoretic foundations for neural scaling laws. This allows us to characterize scaling laws for data generated by a two-layer neural network of infinite width. We observe that the optimal relation between data and model size is linear, up to logarithmic factors, corroborating large-scale empirical investigations. Concise yet general results of the kind we establish may bring clarity to this topic and inform future investigations.
Authors: Jibang Wu, Siyu Chen, Mengdi Wang, Huazheng Wang, Haifeng Xu
Abstract: The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection. In this work, we propose a theoretical framework for aligning economic interests of different stakeholders in the online learning problems through contract design. The problem, termed \emph{contractual reinforcement learning}, naturally arises from the classic model of Markov decision processes, where a learning principal seeks to optimally influence the agent's action policy for their common interests through a set of payment rules contingent on the realization of next state. For the planning problem, we design an efficient dynamic programming algorithm to determine the optimal contracts against the far-sighted agent. For the learning problem, we introduce a generic design of no-regret learning algorithms to untangle the challenges from robust design of contracts to the balance of exploration and exploitation, reducing the complexity analysis to the construction of efficient search algorithms. For several natural classes of problems, we design tailored search algorithms that provably achieve $\tilde{O}(\sqrt{T})$ regret. We also present an algorithm with $\tilde{O}(T^{2/3})$ for the general problem that improves the existing analysis in online contract design with mild technical assumptions.
Authors: Pavan Katta
Abstract: Using results from scaling laws, this theoretical note argues that the following two statements cannot be simultaneously true: 1. Superposition hypothesis where sparse features are linearly represented across a layer is a complete theory of feature representation. 2. Features are universal, meaning two models trained on the same data and achieving equal performance will learn identical features.
Authors: Younghyun Koo, Maryam Rahnemoonfar
Abstract: The Ice-sheet and Sea-level System Model (ISSM) provides solutions for Stokes equations relevant to ice sheet dynamics by employing finite element and fine mesh adaption. However, since its finite element method is compatible only with Central Processing Units (CPU), the ISSM has limits on further economizing computational time. Thus, by taking advantage of Graphics Processing Units (GPUs), we design a graph convolutional network (GCN) as a fast emulator for ISSM. The GCN is trained and tested using the 20-year transient ISSM simulations in the Pine Island Glacier (PIG). The GCN reproduces ice thickness and velocity with a correlation coefficient greater than 0.998, outperforming the traditional convolutional neural network (CNN). Additionally, GCN shows 34 times faster computational speed than the CPU-based ISSM modeling. The GPU-based GCN emulator allows us to predict how the PIG will change in the future under different melting rate scenarios with high fidelity and much faster computational time.
Authors: Daniel Shalam, Simon Korman
Abstract: The Balanced-Pairwise-Affinities (BPA) feature transform is designed to upgrade the features of a set of input items to facilitate downstream matching or grouping related tasks. The transformed set encodes a rich representation of high order relations between the input features. A particular min-cost-max-flow fractional matching problem, whose entropy regularized version can be approximated by an optimal transport (OT) optimization, leads to a transform which is efficient, differentiable, equivariant, parameterless and probabilistically interpretable. While the Sinkhorn OT solver has been adapted extensively in many contexts, we use it differently by minimizing the cost between a set of features to $itself$ and using the transport plan's $rows$ as the new representation. Empirically, the transform is highly effective and flexible in its use and consistently improves networks it is inserted into, in a variety of tasks and training schemes. We demonstrate state-of-the-art results in few-shot classification, unsupervised image clustering and person re-identification. Code is available at \url{github.com/DanielShalam/BPA}.
Authors: Sayash Kapoor, Benedikt Stroebl, Zachary S. Siegel, Nitya Nadgir, Arvind Narayanan
Abstract: AI agents are an exciting new research direction, and agent development is driven by benchmarks. Our analysis of current agent benchmarks and evaluation practices reveals several shortcomings that hinder their usefulness in real-world applications. First, there is a narrow focus on accuracy without attention to other metrics. As a result, SOTA agents are needlessly complex and costly, and the community has reached mistaken conclusions about the sources of accuracy gains. Our focus on cost in addition to accuracy motivates the new goal of jointly optimizing the two metrics. We design and implement one such optimization, showing its potential to greatly reduce cost while maintaining accuracy. Second, the benchmarking needs of model and downstream developers have been conflated, making it hard to identify which agent would be best suited for a particular application. Third, many agent benchmarks have inadequate holdout sets, and sometimes none at all. This has led to agents that are fragile because they take shortcuts and overfit to the benchmark in various ways. We prescribe a principled framework for avoiding overfitting. Finally, there is a lack of standardization in evaluation practices, leading to a pervasive lack of reproducibility. We hope that the steps we introduce for addressing these shortcomings will spur the development of agents that are useful in the real world and not just accurate on benchmarks.
Authors: Bingliang Zhang, Wenda Chu, Julius Berner, Chenlin Meng, Anima Anandkumar, Yang Song
Abstract: Diffusion models have recently achieved success in solving Bayesian inverse problems with learned data priors. Current methods build on top of the diffusion sampling process, where each denoising step makes small modifications to samples from the previous step. However, this process struggles to correct errors from earlier sampling steps, leading to worse performance in complicated nonlinear inverse problems, such as phase retrieval. To address this challenge, we propose a new method called Decoupled Annealing Posterior Sampling (DAPS) that relies on a novel noise annealing process. Specifically, we decouple consecutive steps in a diffusion sampling trajectory, allowing them to vary considerably from one another while ensuring their time-marginals anneal to the true posterior as we reduce noise levels. This approach enables the exploration of a larger solution space, improving the success rate for accurate reconstructions. We demonstrate that DAPS significantly improves sample quality and stability across multiple image restoration tasks, particularly in complicated nonlinear inverse problems. For example, we achieve a PSNR of 30.72dB on the FFHQ 256 dataset for phase retrieval, which is an improvement of 9.12dB compared to existing methods.
Authors: Jonathan Lorraine
Abstract: Gradient-based optimization has been critical to the success of machine learning, updating a single set of parameters to minimize a single loss. A growing number of applications rely on a generalization of this, where we have a bilevel or nested optimization of which subsets of parameters update on different objectives nested inside each other. We focus on motivating examples of hyperparameter optimization and generative adversarial networks. However, naively applying classical methods often fails when we look at solving these nested problems on a large scale. In this thesis, we build tools for nested optimization that scale to deep learning setups.
Authors: Peter M{\o}rch Groth, Mads Herbert Kerrn, Lars Olsen, Jesper Salomon, Wouter Boomsma
Abstract: Reliable prediction of variant effects in proteins has seen considerable progress in recent years. The increasing availability of data in this regime has improved both the prediction performance and our ability to track progress in the field, measured in terms of prediction accuracy averaged over many datasets. For practical use in protein engineering, it is important that we can also provide reliable uncertainty estimates for our predictions, but such metrics are rarely reported. We here provide a Gaussian process regression model, Kermut, which obtains state-of-the-art performance for protein property prediction while also offering estimates of uncertainty through its posterior. We proceed by assessing the quality of these uncertainty estimates. Our results show that the model provides meaningful overall calibration, but that accurate instance-specific uncertainty quantification remains challenging. We hope that this will encourage future work in this promising direction.
Authors: Ayush Noori, I\~naki Arango, William E. Byrd, Nada Amin
Abstract: The strict selectivity of the blood-brain barrier (BBB) represents one of the most formidable challenges to successful central nervous system (CNS) drug delivery. Computational methods to generate BBB permeable drugs in silico may be valuable tools in the CNS drug design pipeline. However, in real-world applications, BBB penetration alone is insufficient; rather, after transiting the BBB, molecules must bind to a specific target or receptor in the brain and must also be safe and non-toxic. To discover small molecules that concurrently satisfy these constraints, we use multi-objective generative AI to synthesize drug-like BBB-permeable small molecules. Specifically, we computationally synthesize molecules with predicted binding affinity against dopamine receptor D2, the primary target for many clinically effective antipsychotic drugs. After training several graph neural network-based property predictors, we adapt SyntheMol (Swanson et al., 2024), a recently developed Monte Carlo Tree Search-based algorithm for antibiotic design, to perform a multi-objective guided traversal over an easily synthesizable molecular space. We design a library of 26,581 novel and diverse small molecules containing hits with high predicted BBB permeability and favorable predicted safety and toxicity profiles, and that could readily be synthesized for experimental validation in the wet lab. We also validate top scoring molecules with molecular docking simulation against the D2 receptor and demonstrate predicted binding affinity on par with risperidone, a clinically prescribed D2-targeting antipsychotic. In the future, the SyntheMol-based computational approach described here may enable the discovery of novel neurotherapeutics for currently intractable disorders of the CNS.
Authors: Antonios Makris, Theodoros Theodoropoulos, Evangelos Psomakelis, Emanuele Carlini, Matteo Mordacchini, Patrizio Dazzi, Konstantinos Tserpes
Abstract: The shift from Cloud Computing to a Cloud-Edge continuum presents new opportunities and challenges for data-intensive and interactive applications. Edge computing has garnered a lot of attention from both industry and academia in recent years, emerging as a key enabler for meeting the increasingly strict demands of Next Generation applications. In Edge computing the computations are placed closer to the end-users, to facilitate low-latency and high-bandwidth applications and services. However, the distributed, dynamic, and heterogeneous nature of Edge computing, presents a significant challenge for service placement. A critical aspect of Edge computing involves managing the placement of applications within the network system to minimize each application's runtime, considering the resources available on system devices and the capabilities of the system's network. The placement of application images must be proactively planned to minimize image tranfer time, and meet the strict demands of the applications. In this regard, this paper proposes an approach for proactive image placement that combines Graph Neural Networks and actor-critic Reinforcement Learning, which is evaluated empirically and compared against various solutions. The findings indicate that although the proposed approach may result in longer execution times in certain scenarios, it consistently achieves superior outcomes in terms of application placement.
Authors: Asif Hamid, Danish Rafiq, Shahkar Ahmad Nahvi, Mohammad Abid Bazaz
Abstract: Complex systems often show macroscopic coherent behavior due to the interactions of microscopic agents like molecules, cells, or individuals in a population with their environment. However, simulating such systems poses several computational challenges during simulation as the underlying dynamics vary and span wide spatiotemporal scales of interest. To capture the fast-evolving features, finer time steps are required while ensuring that the simulation time is long enough to capture the slow-scale behavior, making the analyses computationally unmanageable. This paper showcases how deep learning techniques can be used to develop a precise time-stepping approach for multiscale systems using the joint discovery of coordinates and flow maps. While the former allows us to represent the multiscale dynamics on a representative basis, the latter enables the iterative time-stepping estimation of the reduced variables. The resulting framework achieves state-of-the-art predictive accuracy while incurring lesser computational costs. We demonstrate this ability of the proposed scheme on the large-scale Fitzhugh Nagumo neuron model and the 1D Kuramoto-Sivashinsky equation in the chaotic regime.
Authors: Feibo Jiang, Chuanguo Tang, Li Dong, Kezhi Wang, Kun Yang, Cunhua Pan
Abstract: Semantic Communication (SC) has emerged as a novel communication paradigm in recent years, successfully transcending the Shannon physical capacity limits through innovative semantic transmission concepts. Nevertheless, extant Image Semantic Communication (ISC) systems face several challenges in dynamic environments, including low semantic density, catastrophic forgetting, and uncertain Signal-to-Noise Ratio (SNR). To address these challenges, we propose a novel Vision-Language Model-based Cross-modal Semantic Communication (VLM-CSC) system. The VLM-CSC comprises three novel components: (1) Cross-modal Knowledge Base (CKB) is used to extract high-density textual semantics from the semantically sparse image at the transmitter and reconstruct the original image based on textual semantics at the receiver. The transmission of high-density semantics contributes to alleviating bandwidth pressure. (2) Memory-assisted Encoder and Decoder (MED) employ a hybrid long/short-term memory mechanism, enabling the semantic encoder and decoder to overcome catastrophic forgetting in dynamic environments when there is a drift in the distribution of semantic features. (3) Noise Attention Module (NAM) employs attention mechanisms to adaptively adjust the semantic coding and the channel coding based on SNR, ensuring the robustness of the CSC system. The experimental simulations validate the effectiveness, adaptability, and robustness of the CSC system.
Authors: Vikranth Srivatsa, Zijian He, Reyna Abhyankar, Dongming Li, Yiying Zhang
Abstract: Prompts to large language models (LLMs) have evolved beyond simple user questions. For LLMs to solve complex problems, today's practices include domain-specific instructions, illustration of tool usages, and long context, such as textbook chapters in prompts. As such, many parts of prompts are repetitive across requests, and their attention computation results can be reused. However, today's LLM serving systems treat every request in isolation, missing the opportunity of computation reuse. This paper proposes Preble, the first distributed LLM serving platform that targets and optimizes for prompt sharing. We perform a study on five popular LLM workloads. Based on our study results, we designed a distributed scheduling system that co-optimizes computation reuse and load balancing. Our evaluation of Preble on two to 8 GPUs with real workloads and request arrival patterns on two open-source LLM models shows that Preble outperforms the state-of-the-art average latency by 1.5X to 14.5X and p99 by 2X to 10X.
Authors: Xinyu Shen, Qimin Zhang, Huili Zheng, Weiwei Qi
Abstract: This study evaluates the performance of various supervised machine learning models in analyzing highly correlated neural signaling data from the Adolescent Brain Cognitive Development (ABCD) Study, with a focus on predicting obsessive-compulsive disorder scales. We simulated a dataset to mimic the correlation structures commonly found in imaging data and evaluated logistic regression, elastic networks, random forests, and XGBoost on their ability to handle multicollinearity and accurately identify predictive features. Our study aims to guide the selection of appropriate machine learning methods for processing neuroimaging data, highlighting models that best capture underlying signals in high feature correlations and prioritize clinically relevant features associated with Obsessive-Compulsive Disorder (OCD).
Authors: Alwani Liyana Ahmad, Jose Sanchez-Bornot, Roberto C. Sotero, Damien Coyle, Zamzuri Idris, Ibrahima Faye
Abstract: Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that primarily affects the aging population by impairing cognitive and motor functions. Early detection of AD through accessible methodologies like magnetic resonance imaging (MRI) is vital for developing effective interventions to halt or slow the disease's progression. This study aims to perform a comprehensive analysis of machine learning techniques for selecting MRI-based biomarkers and classifying individuals into healthy controls (HC) and unstable controls (uHC) who later show mild cognitive impairment within five years. The research utilizes MRI data from the Alzheimer's Disease Neuroinformatics Initiative (ADNI) and the Open Access Series of Imaging Studies 3 (OASIS-3), focusing on both HC and uHC participants. The study addresses the challenges of imbalanced data by testing classification methods on balanced and unbalanced datasets, and harmonizes data using polynomial regression to mitigate nuisance variables like age, gender, and intracranial volume. Results indicate that Gaussian Naive Bayes and RusBoost classifiers shows an optimal performance, achieving accuracies of up to 76.46% and 72.48% respectively on the ADNI dataset. For the OASIS-3 dataset, Kernel Naive Bayes and RusBoost yield accuracies ranging from 64.66% to 75.71%, improving further in age-matched datasets. Brain regions like the entorhinal cortex, hippocampus, lateral ventricle, and lateral orbitofrontal cortex are identified as significantly impacted during early cognitive decline. Despite limitations such as small sample sizes, the study's harmonization approach enhances the robustness of biomarker selection, suggesting the potential of this semi-automatic machine learning pipeline for early AD detection using MRI.
Authors: Archit Patke, Dhemath Reddy, Saurabh Jha, Haoran Qiu, Christian Pinto, Shengkun Cui, Chandra Narayanaswami, Zbigniew Kalbarczyk, Ravishankar Iyer
Abstract: $ $Large language models (LLMs) have become an increasingly important workload for cloud providers catering to both enterprise and consumer applications. LLM inference requests from these applications have end-to-end latency SLOs that must be adhered to in production settings. However, existing LLM serving systems focus on optimization objectives such as request serving throughput or request execution latency rather than the end-to-end latency SLOs. Achieving end-to-end SLOs for latency-sensitive requests is challenging due to head-of-line (HOL) blocking in the request queue, which results from bursty arrival rates and insufficient resources. To address the above challenge, we propose QLM, a multi-model queue management framework for LLM serving. QLM uses stochastic programming to orchestrate the actions of multiple LLM Serving Operations (LSOs) to reduce HOL blocking and maximize SLO attainment. Specifically, QLM uses the following LSOs: model swapping, request eviction, GPU-CPU state swapping, load balancing, and warm model start. Evaluation on heterogeneous GPU devices and models with real-world LLM serving dataset shows that QLM improves SLO attainment by 40-90% and throughput by 20-400% while maintaining or improving device utilization compared to other state-of-the-art LLM serving systems.
Authors: Zhangyang Gao, Cheng Tan, Stan Z. Li
Abstract: The equivalent nature of 3D coordinates has posed long term challenges in protein structure representation learning, alignment, and generation. Can we create a compact and invariant language that equivalently represents protein structures? Towards this goal, we propose FoldToken2 to transfer equivariant structures into discrete tokens, while maintaining the recoverability of the original structures. From FoldToken1 to FoldToken2, we improve three key components: (1) invariant structure encoder, (2) vector-quantized compressor, and (3) equivalent structure decoder. We evaluate FoldToken2 on the protein structure reconstruction task and show that it outperforms previous FoldToken1 by 20\% in TMScore and 81\% in RMSD. FoldToken2 probably be the first method that works well on both single-chain and multi-chain protein structures quantization. We believe that FoldToken2 will inspire further improvement in protein structure representation learning, structure alignment, and structure generation tasks.
Authors: Giuseppe Serra, Peter Tino, Zhao Xu, Xin Yao
Abstract: Nowadays, neural network (NN) and deep learning (DL) techniques are widely adopted in many applications, including recommender systems. Given the sparse and stochastic nature of collaborative filtering (CF) data, recent works have critically analyzed the effective improvement of neural-based approaches compared to simpler and often transparent algorithms for recommendation. Previous results showed that NN and DL models can be outperformed by traditional algorithms in many tasks. Moreover, given the largely black-box nature of neural-based methods, interpretable results are not naturally obtained. Following on this debate, we first present a transparent probabilistic model that topologically organizes user and product latent classes based on the review information. In contrast to popular neural techniques for representation learning, we readily obtain a statistical, visualization-friendly tool that can be easily inspected to understand user and product characteristics from a textual-based perspective. Then, given the limitations of common embedding techniques, we investigate the possibility of using the estimated interpretable quantities as model input for a rating prediction task. To contribute to the recent debates, we evaluate our results in terms of both capacity for interpretability and predictive performances in comparison with popular text-based neural approaches. The results demonstrate that the proposed latent class representations can yield competitive predictive performances, compared to popular, but difficult-to-interpret approaches.
Authors: Rickard Br\"uel-Gabrielsson, Jiacheng Zhu, Onkar Bhardwaj, Leshem Choshen, Kristjan Greenewald, Mikhail Yurochkin, Justin Solomon
Abstract: Fine-tuning large language models (LLMs) with low-rank adapters (LoRAs) has become common practice, often yielding numerous copies of the same LLM differing only in their LoRA updates. This paradigm presents challenges for systems that serve real-time responses to queries that each involve a different LoRA. Prior works optimize the design of such systems but still require continuous loading and offloading of LoRAs, as it is infeasible to store thousands of LoRAs in GPU memory. To mitigate this issue, we investigate the efficacy of compression when serving LoRA adapters. We consider compressing adapters individually via SVD and propose a method for joint compression of LoRAs into a shared basis paired with LoRA-specific scaling matrices. Our experiments with up to 500 LoRAs demonstrate that compressed LoRAs preserve performance while offering major throughput gains in realistic serving scenarios with over a thousand LoRAs, maintaining 75% of the throughput of serving a single LoRA.
Authors: Arya Chakraborty
Abstract: While multivariate logistic regression classifiers are a great way of implementing collaborative filtering - a method of making automatic predictions about the interests of a user by collecting preferences or taste information from many other users, we can also achieve similar results using neural networks. A recommender system is a subclass of information filtering system that provide suggestions for items that are most pertinent to a particular user. A perceptron or a neural network is a machine learning model designed for fitting complex datasets using backpropagation and gradient descent. When coupled with advanced optimization techniques, the model may prove to be a great substitute for classical logistic classifiers. The optimizations include feature scaling, mean normalization, regularization, hyperparameter tuning and using stochastic/mini-batch gradient descent instead of regular gradient descent. In this use case, we will use the perceptron in the recommender system to fit the parameters i.e., the data from a multitude of users and use it to predict the preference/interest of a particular user.
Authors: Mert Esencan, Tarun Advaith Kumar, Ata Akbari Asanjan, P. Aaron Lott, Masoud Mohseni, Can Unlu, Davide Venturelli, Alan Ho
Abstract: Recent Large Language Models (LLMs) have demonstrated impressive capabilities at tasks that require human intelligence and are a significant step towards human-like artificial intelligence (AI). Yet the performance of LLMs at reasoning tasks have been subpar and the reasoning capability of LLMs is a matter of significant debate. While it has been shown that the choice of the prompting technique to the LLM can alter its performance on a multitude of tasks, including reasoning, the best performing techniques require human-made prompts with the knowledge of the tasks at hand. We introduce a framework for what we call Combinatorial Reasoning (CR), a fully-automated prompting method, where reasons are sampled from an LLM pipeline and mapped into a Quadratic Unconstrained Binary Optimization (QUBO) problem. The framework investigates whether QUBO solutions can be profitably used to select a useful subset of the reasons to construct a Chain-of-Thought style prompt. We explore the acceleration of CR with specialized solvers. We also investigate the performance of simpler zero-shot strategies such as linear majority rule or random selection of reasons. Our preliminary study indicates that coupling a combinatorial solver to generative AI pipelines is an interesting avenue for AI reasoning and elucidates design principles for future CR methods.
Authors: Anton Xue, Avishree Khare, Rajeev Alur, Surbhi Goel, Eric Wong
Abstract: We study how to subvert language models from following the rules. We model rule-following as inference in propositional Horn logic, a mathematical system in which rules have the form "if $P$ and $Q$, then $R$" for some propositions $P$, $Q$, and $R$. We prove that although transformers can faithfully abide by such rules, maliciously crafted prompts can nevertheless mislead even theoretically constructed models. Empirically, we find that attacks on our theoretical models mirror popular attacks on large language models. Our work suggests that studying smaller theoretical models can help understand the behavior of large language models in rule-based settings like logical reasoning and jailbreak attacks.
Authors: Rongzhe Wei, Eli Chien, Pan Li
Abstract: Graph diffusion, which iteratively propagates real-valued substances among the graph, is used in numerous graph/network-involved applications. However, releasing diffusion vectors may reveal sensitive linking information in the data such as transaction information in financial network data. However, protecting the privacy of graph data is challenging due to its interconnected nature. This work proposes a novel graph diffusion framework with edge-level different privacy guarantees by using noisy diffusion iterates. The algorithm injects Laplace noise per diffusion iteration and adopts a degree-based thresholding function to mitigate the high sensitivity induced by low-degree nodes. Our privacy loss analysis is based on Privacy Amplification by Iteration (PABI), which to our best knowledge, is the first effort that analyzes PABI with Laplace noise and provides relevant applications. We also introduce a novel Infinity-Wasserstein distance tracking method, which tightens the analysis of privacy leakage and makes PABI more applicable in practice. We evaluate this framework by applying it to Personalized Pagerank computation for ranking tasks. Experiments on real-world network data demonstrate the superiority of our method under stringent privacy conditions.
Authors: Mariam Yahya, Alexander Conzelmann, Setareh Maghsudi
Abstract: We study the problem of decentralized task offloading and load-balancing in a dense network with numerous devices and a set of edge servers. Solving this problem optimally is complicated due to the unknown network information and random task sizes. The shared network resources also influence the users' decisions and resource distribution. Our solution combines the mean field multi-agent multi-armed bandit (MAB) game with a load-balancing technique that adjusts the servers' rewards to achieve a target population profile despite the distributed user decision-making. Numerical results demonstrate the efficacy of our approach and the convergence to the target load distribution.
Authors: Masoud Shokrnezhad, Hamidreza Mazandarani, Tarik Taleb, Jaeseung Song, Richard Li
Abstract: In the context of emerging 6G services, the realization of everything-to-everything interactions involving a myriad of physical and digital entities presents a crucial challenge. This challenge is exacerbated by resource scarcity in communication infrastructures, necessitating innovative solutions for effective service implementation. Exploring the potential of Semantic Communications (SemCom) to enhance point-to-point physical layer efficiency shows great promise in addressing this challenge. However, achieving efficient SemCom requires overcoming the significant hurdle of knowledge sharing between semantic decoders and encoders, particularly in the dynamic and non-stationary environment with stringent end-to-end quality requirements. To bridge this gap in existing literature, this paper introduces the Knowledge Base Management And Orchestration (KB-MANO) framework. Rooted in the concepts of Computing-Network Convergence (CNC) and lifelong learning, KB-MANO is crafted for the allocation of network and computing resources dedicated to updating and redistributing KBs across the system. The primary objective is to minimize the impact of knowledge management activities on actual service provisioning. A proof-of-concept is proposed to showcase the integration of KB-MANO with resource allocation in radio access networks. Finally, the paper offers insights into future research directions, emphasizing the transformative potential of semantic-oriented communication systems in the realm of 6G technology.
Authors: Xiao Han, Chen Zhu, Xiao Hu, Chuan Qin, Xiangyu Zhao, Hengshu Zhu
Abstract: Job recommender systems are crucial for aligning job opportunities with job-seekers in online job-seeking. However, users tend to adjust their job preferences to secure employment opportunities continually, which limits the performance of job recommendations. The inherent frequency of preference drift poses a challenge to promptly and precisely capture user preferences. To address this issue, we propose a novel session-based framework, BISTRO, to timely model user preference through fusion learning of semantic and behavioral information. Specifically, BISTRO is composed of three stages: 1) coarse-grained semantic clustering, 2) fine-grained job preference extraction, and 3) personalized top-$k$ job recommendation. Initially, BISTRO segments the user interaction sequence into sessions and leverages session-based semantic clustering to achieve broad identification of person-job matching. Subsequently, we design a hypergraph wavelet learning method to capture the nuanced job preference drift. To mitigate the effect of noise in interactions caused by frequent preference drift, we innovatively propose an adaptive wavelet filtering technique to remove noisy interaction. Finally, a recurrent neural network is utilized to analyze session-based interaction for inferring personalized preferences. Extensive experiments on three real-world offline recruitment datasets demonstrate the significant performances of our framework. Significantly, BISTRO also excels in online experiments, affirming its effectiveness in live recruitment settings. This dual success underscores the robustness and adaptability of BISTRO. The source code is available at https://github.com/Applied-Machine-Learning-Lab/BISTRO.
URLs: https://github.com/Applied-Machine-Learning-Lab/BISTRO.
Authors: Thomas Mulc, Jennifer L. Steele
Abstract: Millions of people turn to Google Search each day for information on things as diverse as new cars or flu symptoms. The terms that they enter contain valuable information on their daily intent and activities, but the information in these search terms has been difficult to fully leverage. User-defined categorical filters have been the most common way to shrink the dimensionality of search data to a tractable size for analysis and modeling. In this paper we present a new approach to reducing the dimensionality of search data while retaining much of the information in the individual terms without user-defined rules. Our contributions are two-fold: 1) we introduce SLaM Compression, a way to quantify search terms using pre-trained language models and create a representation of search data that has low dimensionality, is memory efficient, and effectively acts as a summary of search, and 2) we present CoSMo, a Constrained Search Model for estimating real world events using only search data. We demonstrate the efficacy of our contributions by estimating with high accuracy U.S. automobile sales and U.S. flu rates using only Google Search data.
Authors: Ju-Seung Byun, Jiyun Chun, Jihyung Kil, Andrew Perrault
Abstract: Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by aligning them with specific preferences. These methods primarily use ranking-based feedback for entire generations. With advanced AI models (Teacher), such as GPT-4 and Claude 3 Opus, we can request various types of detailed feedback that are expensive for humans to provide. We propose a two-stage algorithm ARES that Alternates REinforcement Learning (RL) and Supervised Fine-Tuning (SFT). First, we request the Teacher to score how much each sentence contributes to solving the problem in a Chain-of-Thought (CoT). This sentence-level feedback allows us to consider individual valuable segments, providing more granular rewards for the RL procedure. Second, we ask the Teacher to correct the wrong reasoning after the RL stage. The RL procedure requires massive efforts for hyperparameter tuning and often generates errors like repetitive words and incomplete sentences. With the correction feedback, we stabilize the RL fine-tuned model through SFT. We conduct experiments on multi-model dataset ScienceQA and A-OKVQA to demonstrate the effectiveness of our proposal. ARES rationale reasoning achieves around 70% win rate against baseline models judged by GPT-4o. Additionally, we observe that the improved rationale reasoning leads to a 2.5% increase in inference answer accuracy on average for the multi-modal datasets.
Authors: Malay Haldar, Hongwei Zhang, Kedar Bellare, Sherry Chen, Soumyadip Banerjee, Xiaotang Wang, Mustafa Abdool, Huiji Gao, Pavan Tapadia, Liwei He, Sanjeev Katariya
Abstract: As a two-sided marketplace, Airbnb brings together hosts who own listings for rent with prospective guests from around the globe. Results from a guest's search for listings are displayed primarily through two interfaces: (1) as a list of rectangular cards that contain on them the listing image, price, rating, and other details, referred to as list-results (2) as oval pins on a map showing the listing price, called map-results. Both these interfaces, since their inception, have used the same ranking algorithm that orders listings by their booking probabilities and selects the top listings for display. But some of the basic assumptions underlying ranking, built for a world where search results are presented as lists, simply break down for maps. This paper describes how we rebuilt ranking for maps by revising the mathematical foundations of how users interact with search results. Our iterative and experiment-driven approach led us through a path full of twists and turns, ending in a unified theory for the two interfaces. Our journey shows how assumptions taken for granted when designing machine learning algorithms may not apply equally across all user interfaces, and how they can be adapted. The net impact was one of the largest improvements in user experience for Airbnb which we discuss as a series of experimental validations.
Authors: Yubai Yuan, Babak Shahbaba, Norbert Fortin, Keiland Cooper, Qing Nie, Annie Qu
Abstract: Detecting dynamic patterns of task-specific responses shared across heterogeneous datasets is an essential and challenging problem in many scientific applications in medical science and neuroscience. In our motivating example of rodent electrophysiological data, identifying the dynamical patterns in neuronal activity associated with ongoing cognitive demands and behavior is key to uncovering the neural mechanisms of memory. One of the greatest challenges in investigating a cross-subject biological process is that the systematic heterogeneity across individuals could significantly undermine the power of existing machine learning methods to identify the underlying biological dynamics. In addition, many technically challenging neurobiological experiments are conducted on only a handful of subjects where rich longitudinal data are available for each subject. The low sample sizes of such experiments could further reduce the power to detect common dynamic patterns among subjects. In this paper, we propose a novel heterogeneous data integration framework based on optimal transport to extract shared patterns in complex biological processes. The key advantages of the proposed method are that it can increase discriminating power in identifying common patterns by reducing heterogeneity unrelated to the signal by aligning the extracted latent spatiotemporal information across subjects. Our approach is effective even with a small number of subjects, and does not require auxiliary matching information for the alignment. In particular, our method can align longitudinal data across heterogeneous subjects in a common latent space to capture the dynamics of shared patterns while utilizing temporal dependency within subjects.
Authors: Daniil A. Boiko, Valentine P. Ananikov
Abstract: Mass spectrometry is a widely used method to study molecules and processes in medicine, life sciences, chemistry, catalysis, and industrial product quality control, among many other applications. One of the main features of some mass spectrometry techniques is the extensive level of characterization (especially when coupled with chromatography and ion mobility methods, or a part of tandem mass spectrometry experiment) and a large amount of generated data per measurement. Terabyte scales can be easily reached with mass spectrometry studies. Consequently, mass spectrometry has faced the challenge of a high level of data disappearance. Researchers often neglect and then altogether lose access to the rich information mass spectrometry experiments could provide. With the development of machine learning methods, the opportunity arises to unlock the potential of these data, enabling previously inaccessible discoveries. The present perspective highlights reevaluation of mass spectrometry data analysis in the new generation of methods and describes significant challenges in the field, particularly related to problems involving the use of electrospray ionization. We argue that further applications of machine learning raise new requirements for instrumentation (increasing throughput and information density, decreasing pricing, and making more automation-friendly software), and once met, the field may experience significant transformation.
Authors: Abraham G Taye, Sador Yemane, Eshetu Negash, Yared Minwuyelet, Moges Abebe, Melkamu Hunegnaw Asmare
Abstract: Malaria parasites pose a significant global health burden, causing widespread suffering and mortality. Detecting malaria infection accurately is crucial for effective treatment and control. However, existing automated detection techniques have shown limitations in terms of accuracy and generalizability. Many studies have focused on specific features without exploring more comprehensive approaches. In our case, we formulate a deep learning technique for malaria-infected cell classification using traditional CNNs and transfer learning models notably VGG19, InceptionV3, and Xception. The models were trained using NIH datasets and tested using different performance metrics such as accuracy, precision, recall, and F1-score. The test results showed that deep CNNs achieved the highest accuracy -- 97%, followed by Xception with an accuracy of 95%. A machine learning model SVM achieved an accuracy of 83%, while an Inception-V3 achieved an accuracy of 94%. Furthermore, the system can be accessed through a web interface, where users can upload blood smear images for malaria detection.
Authors: Sowmya Sankaran
Abstract: Animal populations worldwide are rapidly declining, and a technology that can accurately count endangered species could be vital for monitoring population changes over several years. This research focused on fine-tuning object detection models for drone images to create accurate counts of animal species. Hundreds of images taken using a drone and large, openly available drone-image datasets were used to fine-tune machine learning models with the baseline YOLOv8 architecture. We trained 30 different models, with the largest having 43.7 million parameters and 365 layers, and used hyperparameter tuning and data augmentation techniques to improve accuracy. While the state-of-the-art YOLOv8 baseline had only 0.7% accuracy on a dataset of safari animals, our models had 95% accuracy on the same dataset. Finally, we deployed the models on the Jetson Orin Nano for demonstration of low-power real-time species detection for easy inference on drones.
Authors: Ahsan Mahmood, Junier Oliva, Martin Styner
Abstract: Anomaly detection and localization in medical imaging remain critical challenges in healthcare. This paper introduces Spatial-MSMA (Multiscale Score Matching Analysis), a novel unsupervised method for anomaly localization in volumetric brain MRIs. Building upon the MSMA framework, our approach incorporates spatial information and conditional likelihoods to enhance anomaly detection capabilities. We employ a flexible normalizing flow model conditioned on patch positions and global image features to estimate patch-wise anomaly scores. The method is evaluated on a dataset of 1,650 T1- and T2-weighted brain MRIs from typically developing children, with simulated lesions added to the test set. Spatial-MSMA significantly outperforms existing methods, including reconstruction-based, generative-based, and interpretation-based approaches, in lesion detection and segmentation tasks. Our model achieves superior performance in both distance-based metrics (99th percentile Hausdorff Distance: $7.05 \pm 0.61$, Mean Surface Distance: $2.10 \pm 0.43$) and component-wise metrics (True Positive Rate: $0.83 \pm 0.01$, Positive Predictive Value: $0.96 \pm 0.01$). These results demonstrate Spatial-MSMA's potential for accurate and interpretable anomaly localization in medical imaging, with implications for improved diagnosis and treatment planning in clinical settings. Our code is available at~\url{https://github.com/ahsanMah/sade/}.
Authors: Leiv R{\o}nneberg, Vidhi Lalchand, Paul D. W. Kirk
Abstract: Dose-response prediction in cancer is an active application field in machine learning. Using large libraries of \textit{in-vitro} drug sensitivity screens, the goal is to develop accurate predictive models that can be used to guide experimental design or inform treatment decisions. Building on previous work that makes use of permutation invariant multi-output Gaussian Processes in the context of dose-response prediction for drug combinations, we develop a variational approximation to these models. The variational approximation enables a more scalable model that provides uncertainty quantification and naturally handles missing data. Furthermore, we propose using a deep generative model to encode the chemical space in a continuous manner, enabling prediction for new drugs and new combinations. We demonstrate the performance of our model in a simple setting using a high-throughput dataset and show that the model is able to efficiently borrow information across outputs.
Authors: Athira J Jacob, Puneet Sharma, Daniel Rueckert
Abstract: Segmentation is often the first step in many medical image analyses workflows. Deep learning approaches, while giving state-of-the-art accuracies, are data intensive and do not scale well to low data regimes. We introduce Deep Conditional Shape Models 2.0, which uses an edge detector, along with an implicit shape function conditioned on edge maps, to leverage cross-modality shape information. The shape function is trained exclusively on a source domain (contrasted CT) and applied to the target domain of interest (3D echocardiography). We demonstrate data efficiency in the target domain by varying the amounts of training data used in the edge detection stage. We observe that DCSM 2.0 outperforms the baseline at all data levels in terms of Hausdorff distances, and while using 50% or less of the training data in terms of average mesh distance, and at 10% or less of the data with the dice coefficient. The method scales well to low data regimes, with gains of up to 5% in dice coefficient, 2.58 mm in average surface distance and 21.02 mm in Hausdorff distance when using just 2% (22 volumes) of the training data.
Authors: Yifan Wang, Vikram Ravindra, Ananth Grama
Abstract: Task-specific functional MRI (fMRI) images provide excellent modalities for studying the neuronal basis of cognitive processes. We use fMRI data to formulate and solve the problem of deconvolving task-specific aggregate neuronal networks into a set of basic building blocks called canonical networks, to use these networks for functional characterization, and to characterize the physiological basis of these responses by mapping them to regions of the brain. Our results show excellent task-specificity of canonical networks, i.e., the expression of a small number of canonical networks can be used to accurately predict tasks; generalizability across cohorts, i.e., canonical networks are conserved across diverse populations, studies, and acquisition protocols; and that canonical networks have strong anatomical and physiological basis. From a methods perspective, the problem of identifying these canonical networks poses challenges rooted in the high dimensionality, small sample size, acquisition variability, and noise. Our deconvolution technique is based on non-negative matrix factorization (NMF) that identifies canonical networks as factors of a suitably constructed matrix. We demonstrate that our method scales to large datasets, yields stable and accurate factors, and is robust to noise.
Authors: Nat McAleese, Rai Michael Pokorny, Juan Felipe Ceron Uribe, Evgenia Nitishinskaya, Maja Trebacz, Jan Leike
Abstract: Reinforcement learning from human feedback (RLHF) is fundamentally limited by the capacity of humans to correctly evaluate model output. To improve human evaluation ability and overcome that limitation this work trains "critic" models that help humans to more accurately evaluate model-written code. These critics are themselves LLMs trained with RLHF to write natural language feedback highlighting problems in code from real-world assistant tasks. On code containing naturally occurring LLM errors model-written critiques are preferred over human critiques in 63% of cases, and human evaluation finds that models catch more bugs than human contractors paid for code review. We further confirm that our fine-tuned LLM critics can successfully identify hundreds of errors in ChatGPT training data rated as "flawless", even though the majority of those tasks are non-code tasks and thus out-of-distribution for the critic model. Critics can have limitations of their own, including hallucinated bugs that could mislead humans into making mistakes they might have otherwise avoided, but human-machine teams of critics and contractors catch similar numbers of bugs to LLM critics while hallucinating less than LLMs alone.
Authors: Kaveh Malek (Department of Mechanical Engineering, University of New Mexico, New Mexico), Fernando Moreu (Department of Civil, Construction and Environmental Engineering, University of New Mexico, New Mexico)
Abstract: Convolutional Neural Network (CNN) models often lack the ability to incorporate human input, which can be addressed by Augmented Reality (AR) headsets. However, current AR headsets face limitations in processing power, which has prevented researchers from performing real-time, complex image recognition tasks using CNNs in AR headsets. This paper presents a method to deploy CNN models on AR headsets by training them on computers and transferring the optimized weight matrices to the headset. The approach transforms the image data and CNN layers into a one-dimensional format suitable for the AR platform. We demonstrate this method by training the LeNet-5 CNN model on the MNIST dataset using PyTorch and deploying it on a HoloLens AR headset. The results show that the model maintains an accuracy of approximately 98%, similar to its performance on a computer. This integration of CNN and AR enables real-time image processing on AR headsets, allowing for the incorporation of human input into AI models.
Authors: Ekaterina Piotrovskaya, Leo Lobski, Fabio Zanasi
Abstract: We develop a learning algorithm for closed signal flow graphs - a graphical model of signal transducers. The algorithm relies on the correspondence between closed signal flow graphs and weighted finite automata on a singleton alphabet. We demonstrate that this procedure results in a genuine reduction of complexity: our algorithm fares better than existing learning algorithms for weighted automata restricted to the case of a singleton alphabet.
Authors: Ruochen Wang, Sohyun An, Minhao Cheng, Tianyi Zhou, Sung Ju Hwang, Cho-Jui Hsieh
Abstract: Large Language Models (LLMs) exhibit strong generalization capabilities to novel tasks when prompted with language instructions and in-context demos. Since this ability sensitively depends on the quality of prompts, various methods have been explored to automate the instruction design. While these methods demonstrated promising results, they also restricted the searched prompt to one instruction. Such simplification significantly limits their capacity, as a single demo-free instruction might not be able to cover the entire complex problem space of the targeted task. To alleviate this issue, we adopt the Mixture-of-Expert paradigm and divide the problem space into a set of sub-regions; Each sub-region is governed by a specialized expert, equipped with both an instruction and a set of demos. A two-phase process is developed to construct the specialized expert for each region: (1) demo assignment: Inspired by the theoretical connection between in-context learning and kernel regression, we group demos into experts based on their semantic similarity; (2) instruction assignment: A region-based joint search of an instruction per expert complements the demos assigned to it, yielding a synergistic effect. The resulting method, codenamed Mixture-of-Prompts (MoP), achieves an average win rate of 81% against prior arts across several major benchmarks.
Authors: Arianna Bunnell, Yannik Glaser, Dustin Valdez, Thomas Wolfgruber, Aleen Altamirano, Carol Zamora Gonz\'alez, Brenda Y. Hernandez, Peter Sadowski, John A. Shepherd
Abstract: Detecting and classifying lesions in breast ultrasound images is a promising application of artificial intelligence (AI) for reducing the burden of cancer in regions with limited access to mammography. Such AI systems are more likely to be useful in a clinical setting if their predictions can be explained to a radiologist. This work proposes an explainable AI model that provides interpretable predictions using a standard lexicon from the American College of Radiology's Breast Imaging and Reporting Data System (BI-RADS). The model is a deep neural network featuring a concept bottleneck layer in which known BI-RADS features are predicted before making a final cancer classification. This enables radiologists to easily review the predictions of the AI system and potentially fix errors in real time by modifying the concept predictions. In experiments, a model is developed on 8,854 images from 994 women with expert annotations and histological cancer labels. The model outperforms state-of-the-art lesion detection frameworks with 48.9 average precision on the held-out testing set, and for cancer classification, concept intervention is shown to increase performance from 0.876 to 0.885 area under the receiver operating characteristic curve. Training and evaluation code is available at https://github.com/hawaii-ai/bus-cbm.
Authors: Markus Grotz, Mohit Shridhar, Tamim Asfour, Dieter Fox
Abstract: Bimanual manipulation is challenging due to precise spatial and temporal coordination required between two arms. While there exist several real-world bimanual systems, there is a lack of simulated benchmarks with a large task diversity for systematically studying bimanual capabilities across a wide range of tabletop tasks. This paper addresses the gap by extending RLBench to bimanual manipulation. We open-source our code and benchmark comprising 13 new tasks with 23 unique task variations, each requiring a high degree of coordination and adaptability. To kickstart the benchmark, we extended several state-of-the art methods to bimanual manipulation and also present a language-conditioned behavioral cloning agent -- PerAct2, which enables the learning and execution of bimanual 6-DoF manipulation tasks. Our novel network architecture efficiently integrates language processing with action prediction, allowing robots to understand and perform complex bimanual tasks in response to user-specified goals. Project website with code is available at: http://bimanual.github.io
Authors: Zifan Zhang, Yuchen Liu, Zhiyuan Peng, Mingzhe Chen, Dongkuan Xu, Shuguang Cui
Abstract: Optimizing edge caching is crucial for the advancement of next-generation (nextG) wireless networks, ensuring high-speed and low-latency services for mobile users. Existing data-driven optimization approaches often lack awareness of the distribution of random data variables and focus solely on optimizing cache hit rates, neglecting potential reliability concerns, such as base station overload and unbalanced cache issues. This oversight can result in system crashes and degraded user experience. To bridge this gap, we introduce a novel digital twin-assisted optimization framework, called D-REC, which integrates reinforcement learning (RL) with diverse intervention modules to ensure reliable caching in nextG wireless networks. We first develop a joint vertical and horizontal twinning approach to efficiently create network digital twins, which are then employed by D-REC as RL optimizers and safeguards, providing ample datasets for training and predictive evaluation of our cache replacement policy. By incorporating reliability modules into a constrained Markov decision process, D-REC can adaptively adjust actions, rewards, and states to comply with advantageous constraints, minimizing the risk of network failures. Theoretical analysis demonstrates comparable convergence rates between D-REC and vanilla data-driven methods without compromising caching performance. Extensive experiments validate that D-REC outperforms conventional approaches in cache hit rate and load balancing while effectively enforcing predetermined reliability intervention modules.
Authors: Qing He, Wei Cai
Abstract: We propose a deep neural network architecture designed such that its output forms an invertible symplectomorphism of the input. This design draws an analogy to the real-valued non-volume-preserving (real NVP) method used in normalizing flow techniques. Utilizing this neural network type allows for learning tasks on unknown Hamiltonian systems without breaking the inherent symplectic structure of the phase space.
Authors: Gautham Vasan, Yan Wang, Fahim Shahriar, James Bergstra, Martin Jagersand, A. Rupam Mahmood
Abstract: Many real-world robot learning problems, such as pick-and-place or arriving at a destination, can be seen as a problem of reaching a goal state as soon as possible. These problems, when formulated as episodic reinforcement learning tasks, can easily be specified to align well with our intended goal: -1 reward every time step with termination upon reaching the goal state, called minimum-time tasks. Despite this simplicity, such formulations are often overlooked in favor of dense rewards due to their perceived difficulty and lack of informativeness. Our studies contrast the two reward paradigms, revealing that the minimum-time task specification not only facilitates learning higher-quality policies but can also surpass dense-reward-based policies on their own performance metrics. Crucially, we also identify the goal-hit rate of the initial policy as a robust early indicator for learning success in such sparse feedback settings. Finally, using four distinct real-robotic platforms, we show that it is possible to learn pixel-based policies from scratch within two to three hours using constant negative rewards.
Authors: Zi Iun Lai, Wai Kit Fung, Enquan Chew
Abstract: With emerging prevalence beyond traditionally endemic regions, the global burden of dengue disease is forecasted to be one of the fastest growing. With limited direct treatment or vaccination currently available, prevention through vector control is widely believed to be the most effective form of managing outbreaks. This study examines traditional state space models (moving average, autoregressive, ARIMA, SARIMA), supervised learning techniques (XGBoost, SVM, KNN) and deep networks (LSTM, CNN, ConvLSTM) for forecasting weekly dengue cases in Singapore. Meteorological data and search engine trends were included as features for ML techniques. Forecasts using CNNs yielded lowest RMSE in weekly cases in 2019.
Authors: Jiacheng Yao, Maolin Wang, Wanqi Chen, Chengxiang Jin, Jiajun Zhou, Shanqing Yu, Qi Xuan
Abstract: The wide application of Ethereum technology has brought technological innovation to traditional industries. As one of Ethereum's core applications, smart contracts utilize diverse contract codes to meet various functional needs and have gained widespread use. However, the non-tamperability of smart contracts, coupled with vulnerabilities caused by natural flaws or human errors, has brought unprecedented challenges to blockchain security. Therefore, in order to ensure the healthy development of blockchain technology and the stability of the blockchain community, it is particularly important to study the vulnerability detection techniques for smart contracts. In this paper, we propose a Dual-view Aware Smart Contract Vulnerability Detection Framework named DVDet. The framework initially converts the source code and bytecode of smart contracts into weighted graphs and control flow sequences, capturing potential risk features from these two perspectives and integrating them for analysis, ultimately achieving effective contract vulnerability detection. Comprehensive experiments on the Ethereum dataset show that our method outperforms others in detecting vulnerabilities.
Authors: Xiaolong He, April Tran, David M. Bortz, Youngsoo Choi
Abstract: The parametric greedy latent space dynamics identification (gLaSDI) framework has demonstrated promising potential for accurate and efficient modeling of high-dimensional nonlinear physical systems. However, it remains challenging to handle noisy data. To enhance robustness against noise, we incorporate the weak-form estimation of nonlinear dynamics (WENDy) into gLaSDI. In the proposed weak-form gLaSDI (WgLaSDI) framework, an autoencoder and WENDy are trained simultaneously to discover intrinsic nonlinear latent-space dynamics of high-dimensional data. Compared to the standard sparse identification of nonlinear dynamics (SINDy) employed in gLaSDI, WENDy enables variance reduction and robust latent space discovery, therefore leading to more accurate and efficient reduced-order modeling. Furthermore, the greedy physics-informed active learning in WgLaSDI enables adaptive sampling of optimal training data on the fly for enhanced modeling accuracy. The effectiveness of the proposed framework is demonstrated by modeling various nonlinear dynamical problems, including viscous and inviscid Burgers' equations, time-dependent radial advection, and the Vlasov equation for plasma physics. With data that contains 5-10% Gaussian white noise, WgLaSDI outperforms gLaSDI by orders of magnitude, achieving 1-7% relative errors. Compared with the high-fidelity models, WgLaSDI achieves 121 to 1,779x speed-up.
Authors: Mingrui Zhang, Chunyang Wang, Stephan Kramer, Joseph G. Wallwork, Siyi Li, Jiancheng Liu, Xiang Chen, Matthew D. Piggott
Abstract: Solving complex Partial Differential Equations (PDEs) accurately and efficiently is an essential and challenging problem in all scientific and engineering disciplines. Mesh movement methods provide the capability to improve the accuracy of the numerical solution without increasing the overall mesh degree of freedom count. Conventional sophisticated mesh movement methods are extremely expensive and struggle to handle scenarios with complex boundary geometries. However, existing learning-based methods require re-training from scratch given a different PDE type or boundary geometry, which limits their applicability, and also often suffer from robustness issues in the form of inverted elements. In this paper, we introduce the Universal Mesh Movement Network (UM2N), which -- once trained -- can be applied in a non-intrusive, zero-shot manner to move meshes with different size distributions and structures, for solvers applicable to different PDE types and boundary geometries. UM2N consists of a Graph Transformer (GT) encoder for extracting features and a Graph Attention Network (GAT) based decoder for moving the mesh. We evaluate our method on advection and Navier-Stokes based examples, as well as a real-world tsunami simulation case. Our method outperforms existing learning-based mesh movement methods in terms of the benchmarks described above. In comparison to the conventional sophisticated Monge-Amp\`ere PDE-solver based method, our approach not only significantly accelerates mesh movement, but also proves effective in scenarios where the conventional method fails. Our project page is at \url{https://erizmr.github.io/UM2N/}.
Authors: Denis Belomestny, John Schoenmakers
Abstract: We introduce a mesh-type approach for tackling discrete-time, finite-horizon Markov Decision Processes (MDPs) characterized by state and action spaces that are general, encompassing both finite and infinite (yet suitably regular) subsets of Euclidean space. In particular, for bounded state and action spaces, our algorithm achieves a computational complexity that is tractable in the sense of Novak and Wozniakowski, and is polynomial in the time horizon. For unbounded state space the algorithm is "semi-tractable" in the sense that the complexity is proportional to $\epsilon^{-c}$ with some dimension independent $c\geq2$, for achieving an accuracy $\epsilon$, and polynomial in the time horizon with degree linear in the underlying dimension. As such the proposed approach has some flavor of the randomization method by Rust which deals with infinite horizon MDPs and uniform sampling in compact state space. However, the present approach is essentially different due to the finite horizon and a simulation procedure due to general transition distributions, and more general in the sense that it encompasses unbounded state space. To demonstrate the effectiveness of our algorithm, we provide illustrations based on Linear-Quadratic Gaussian (LQG) control problems.
Authors: Krzysztof Nowak, J\k{e}drzej Zi\k{e}bura, Krzysztof Wr\'obel, Aleksander Smywi\'nski-Pohl
Abstract: This study introduces the eFontes models for automatic linguistic annotation of Medieval Latin texts, focusing on lemmatization, part-of-speech tagging, and morphological feature determination. Using the Transformers library, these models were trained on Universal Dependencies (UD) corpora and the newly developed eFontes corpus of Polish Medieval Latin. The research evaluates the models' performance, addressing challenges such as orthographic variations and the integration of Latinized vernacular terms. The models achieved high accuracy rates: lemmatization at 92.60%, part-of-speech tagging at 83.29%, and morphological feature determination at 88.57%. The findings underscore the importance of high-quality annotated corpora and propose future enhancements, including extending the models to Named Entity Recognition.
Authors: Sourish Dasgupta, Ankush Chander, Parth Borad, Isha Motiyani, Tanmoy Chakraborty
Abstract: Personalized summarization models cater to individuals' subjective understanding of saliency, as represented by their reading history and current topics of attention. Existing personalized text summarizers are primarily evaluated based on accuracy measures such as BLEU, ROUGE, and METEOR. However, a recent study argued that accuracy measures are inadequate for evaluating the degree of personalization of these models and proposed EGISES, the first metric to evaluate personalized text summaries. It was suggested that accuracy is a separate aspect and should be evaluated standalone. In this paper, we challenge the necessity of an accuracy leaderboard, suggesting that relying on accuracy-based aggregated results might lead to misleading conclusions. To support this, we delve deeper into EGISES, demonstrating both theoretically and empirically that it measures the degree of responsiveness, a necessary but not sufficient condition for degree-of-personalization. We subsequently propose PerSEval, a novel measure that satisfies the required sufficiency condition. Based on the benchmarking of ten SOTA summarization models on the PENS dataset, we empirically establish that -- (i) PerSEval is reliable w.r.t human-judgment correlation (Pearson's r = 0.73; Spearman's $\rho$ = 0.62; Kendall's $\tau$ = 0.42), (ii) PerSEval has high rank-stability, (iii) PerSEval as a rank-measure is not entailed by EGISES-based ranking, and (iv) PerSEval can be a standalone rank-measure without the need of any aggregated ranking.
Authors: Ruchi Bhatt, Pratibha Kumari, Dwarikanath Mahapatra, Abdulmotaleb El Saddik, Mukesh Saini
Abstract: Audio analysis is useful in many application scenarios. The state-of-the-art audio analysis approaches assume that the data distribution at training and deployment time will be the same. However, due to various real-life environmental factors, the data may encounter drift in its distribution or can encounter new classes in the late future. Thus, a one-time trained model might not perform adequately. In this paper, we characterize continual learning (CL) approaches in audio analysis. In this paper, we characterize continual learning (CL) approaches, intended to tackle catastrophic forgetting arising due to drifts. As there is no CL dataset for audio analysis, we use DCASE 2020 to 2023 datasets to create various CL scenarios for audio-based monitoring tasks. We have investigated the following CL and non-CL approaches: EWC, LwF, SI, GEM, A-GEM, GDumb, Replay, Naive, cumulative, and joint training. The study is very beneficial for researchers and practitioners working in the area of audio analysis for developing adaptive models. We observed that Replay achieved better results than other methods in the DCASE challenge data. It achieved an accuracy of 70.12% for the domain incremental scenario and an accuracy of 96.98% for the class incremental scenario.
Authors: Zhiyuan Wang, Jinhao Duan, Lu Cheng, Yue Zhang, Qingni Wang, Hengtao Shen, Xiaofeng Zhu, Xiaoshuang Shi, Kaidi Xu
Abstract: Uncertainty quantification (UQ) in natural language generation (NLG) tasks remains an open challenge, exacerbated by the intricate nature of the recent large language models (LLMs). This study investigates adapting conformal prediction (CP), which can convert any heuristic measure of uncertainty into rigorous theoretical guarantees by constructing prediction sets, for black-box LLMs in open-ended NLG tasks. We propose a sampling-based uncertainty measure leveraging self-consistency and develop a conformal uncertainty criterion by integrating the uncertainty condition aligned with correctness into the design of the CP algorithm. Experimental results indicate that our uncertainty measure generally surpasses prior state-of-the-art methods. Furthermore, we calibrate the prediction sets within the model's unfixed answer distribution and achieve strict control over the correctness coverage rate across 6 LLMs on 4 free-form NLG datasets, spanning general-purpose and medical domains, while the small average set size further highlights the efficiency of our method in providing trustworthy guarantees for practical open-ended NLG applications.
Authors: Alireza Moazeni, Shichong Peng, Ke Li
Abstract: Recent advancements in neural rendering have excelled at novel view synthesis from multi-view RGB images. However, they often lack the capability to edit the shading or colour of the scene at a detailed point-level, while ensuring consistency across different viewpoints. In this work, we address the challenge of point-level 3D scene albedo and shading editing from multi-view RGB images, focusing on detailed editing at the point-level rather than at a part or global level. While prior works based on volumetric representation such as NeRF struggle with achieving 3D consistent editing at the point level, recent advancements in point-based neural rendering show promise in overcoming this challenge. We introduce ``Intrinsic PAPR'', a novel method based on the recent point-based neural rendering technique Proximity Attention Point Rendering (PAPR). Unlike other point-based methods that model the intrinsic decomposition of the scene, our approach does not rely on complicated shading models or simplistic priors that may not universally apply. Instead, we directly model scene decomposition into albedo and shading components, leading to better estimation accuracy. Comparative evaluations against the latest point-based inverse rendering methods demonstrate that Intrinsic PAPR achieves higher-quality novel view rendering and superior point-level albedo and shading editing.
Authors: Mateusz Brzozowski, Artur Janicki
Abstract: This article presents a case study demonstrating a non-intrusive method for the well-being monitoring of elderly people. It is based on our real-time energy measurement system, which uses tiny beacons attached to electricity meters. Four participants aged 67-82 years took part in our study. We observed their electric power consumption for approx. a month, and then we analyzed them, taking into account the participants' notes on their activities. We created typical daily usage profiles for each participant and used anomaly detection to find unusual energy consumption. We found out that real-time energy measurement can give significant insight into someone's daily activities and, consequently, bring invaluable information to caregivers about the well-being of an elderly person, while being discreet and entirely non-intrusive.
Authors: Yonatan Urman, Zachary Shah, Ashwin Kumar, Bruno P. Soares, Kawin Setsompop
Abstract: MRI is a widely used ionization-free soft-tissue imaging modality, often employed repeatedly over a patient's lifetime. However, prolonged scanning durations, among other issues, can limit availability and accessibility. In this work, we aim to substantially reduce scan times by leveraging prior scans of the same patient. These prior scans typically contain considerable shared information with the current scan, thereby enabling higher acceleration rates when appropriately utilized. We propose a prior informed reconstruction method with a trained diffusion model in conjunction with data-consistency steps. Our method can be trained with unlabeled image data, eliminating the need for a dataset of either k-space measurements or paired longitudinal scans as is required of other learning-based methods. We demonstrate superiority of our method over previously suggested approaches in effectively utilizing prior information without over-biasing prior consistency, which we validate on both an open-source dataset of healthy patients as well as several longitudinal cases of clinical interest.
Authors: Siddharth Chandak, Ilai Bistritz, Nicholas Bambos
Abstract: Consider $N$ players each with a $d$-dimensional action set. Each of the players' utility functions includes their reward function and a linear term for each dimension, with coefficients that are controlled by the manager. We assume that the game is strongly monotone, so if each player runs gradient descent, the dynamics converge to a unique Nash equilibrium (NE). The NE is typically inefficient in terms of global performance. The resulting global performance of the system can be improved by imposing $K$-dimensional linear constraints on the NE. We therefore want the manager to pick the controlled coefficients that impose the desired constraint on the NE. However, this requires knowing the players' reward functions and their action sets. Obtaining this game structure information is infeasible in a large-scale network and violates the users' privacy. To overcome this, we propose a simple algorithm that learns to shift the NE of the game to meet the linear constraints by adjusting the controlled coefficients online. Our algorithm only requires the linear constraints violation as feedback and does not need to know the reward functions or the action sets. We prove that our algorithm, which is based on two time-scale stochastic approximation, guarantees convergence with probability 1 to the set of NE that meet target linear constraints. We then provide a mean square convergence rate of $O(t^{-1/4})$ for our algorithm. This is the first such bound for two time-scale stochastic approximation where the slower time-scale is a fixed point iteration with a non-expansive mapping. We demonstrate how our scheme can be applied to optimizing a global quadratic cost at NE and load balancing in resource allocation games. We provide simulations of our algorithm for these scenarios.
Authors: Xinglin Pan Wenxiang Lin, Shaohuai Shi, Xiaowen Chu, Weinong Sun, Bo Li
Abstract: Sparsely-activated Mixture-of-Expert (MoE) layers have found practical applications in enlarging the model size of large-scale foundation models, with only a sub-linear increase in computation demands. Despite the wide adoption of hybrid parallel paradigms like model parallelism, expert parallelism, and expert-sharding parallelism (i.e., MP+EP+ESP) to support MoE model training on GPU clusters, the training efficiency is hindered by communication costs introduced by these parallel paradigms. To address this limitation, we propose Parm, a system that accelerates MP+EP+ESP training by designing two dedicated schedules for placing communication tasks. The proposed schedules eliminate redundant computations and communications and enable overlaps between intra-node and inter-node communications, ultimately reducing the overall training time. As the two schedules are not mutually exclusive, we provide comprehensive theoretical analyses and derive an automatic and accurate solution to determine which schedule should be applied in different scenarios. Experimental results on an 8-GPU server and a 32-GPU cluster demonstrate that Parm outperforms the state-of-the-art MoE training system, DeepSpeed-MoE, achieving 1.13$\times$ to 5.77$\times$ speedup on 1296 manually configured MoE layers and approximately 3$\times$ improvement on two real-world MoE models based on BERT and GPT-2.
Authors: Quang P. M. Pham, Khoi T. N. Nguyen, Lan C. Ngo, Truong Do, Truong Son Hy
Abstract: Scene graphs have been proven to be useful for various scene understanding tasks due to their compact and explicit nature. However, existing approaches often neglect the importance of maintaining the symmetry-preserving property when generating scene graphs from 3D point clouds. This oversight can diminish the accuracy and robustness of the resulting scene graphs, especially when handling noisy, multi-view 3D data. This work, to the best of our knowledge, is the first to implement an Equivariant Graph Neural Network in semantic scene graph generation from 3D point clouds for scene understanding. Our proposed method, ESGNN, outperforms existing state-of-the-art approaches, demonstrating a significant improvement in scene estimation with faster convergence. ESGNN demands low computational resources and is easy to implement from available frameworks, paving the way for real-time applications such as robotics and computer vision.
Authors: Masoud Ataei, Vikas Dhiman
Abstract: Uncertainty-aware controllers that guarantee safety are critical for safety critical applications. Among such controllers, Control Barrier Functions (CBFs) based approaches are popular because they are fast, yet safe. However, most such works depend on Gaussian Processes (GPs) or MC-Dropout for learning and uncertainty estimation, and both approaches come with drawbacks: GPs are non-parametric methods that are slow, while MC-Dropout does not capture aleatoric uncertainty. On the other hand, modern Bayesian learning algorithms have shown promise in uncertainty quantification. The application of modern Bayesian learning methods to CBF-based controllers has not yet been studied. We aim to fill this gap by surveying uncertainty quantification algorithms and evaluating them on CBF-based safe controllers. We find that model variance-based algorithms (for example, Deep ensembles, MC-dropout, etc.) and direct estimation-based algorithms (such as DEUP) have complementary strengths. Algorithms in the former category can only estimate uncertainty accurately out-of-domain, while those in the latter category can only do so in-domain. We combine the two approaches to obtain more accurate uncertainty estimates both in- and out-of-domain. As measured by the failure rate of a simulated robot, this results in a safer CBF-based robot controller.
Authors: Jiawei Wang, Liping Yuan, Yuchen Zhang
Abstract: Generating fine-grained video descriptions is a fundamental challenge in video understanding. In this work, we introduce Tarsier, a family of large-scale video-language models designed to generate high-quality video descriptions. Tarsier employs CLIP-ViT to encode frames separately and then uses an LLM to model temporal relationships. Despite its simple architecture, we demonstrate that with a meticulously designed two-stage training procedure, the Tarsier models exhibit substantially stronger video description capabilities than any existing open-source model, showing a $+51.4\%$ advantage in human side-by-side evaluation over the strongest model. Additionally, they are comparable to state-of-the-art proprietary models, with a $+12.3\%$ advantage against GPT-4V and a $-6.7\%$ disadvantage against Gemini 1.5 Pro. Besides video description, Tarsier proves to be a versatile generalist model, achieving new state-of-the-art results across nine public benchmarks, including multi-choice VQA, open-ended VQA, and zero-shot video captioning. Our second contribution is the introduction of a new benchmark for evaluating video description models, consisting of a new challenging dataset featuring videos from diverse sources and varying complexity, along with an automatic method specifically designed to assess the quality of fine-grained video descriptions. We make our models and evaluation benchmark publicly available at \url{https://github.com/bytedance/tarsier}.
Authors: Rachmad Vidya Wicaksana Putra, Muhammad Shafique
Abstract: Spiking Neural Networks (SNNs) have shown capabilities for solving diverse machine learning tasks with ultra-low-power/energy computation. To further improve the performance and efficiency of SNN inference, the Compute-in-Memory (CIM) paradigm with emerging device technologies such as resistive random access memory is employed. However, most of SNN architectures are developed without considering constraints from the application and the underlying CIM hardware (e.g., memory, area, latency, and energy consumption). Moreover, most of SNN designs are derived from the Artificial Neural Networks, whose network operations are different from SNNs. These limitations hinder SNNs from reaching their full potential in accuracy and efficiency. Toward this, we propose HASNAS, a novel hardware-aware spiking neural architecture search (NAS) framework for neuromorphic CIM systems that finds an SNN that offers high accuracy under the given memory, area, latency, and energy constraints. To achieve this, HASNAS employs the following key steps: (1) optimizing SNN operations to achieve high accuracy, (2) developing an SNN architecture that facilitates an effective learning process, and (3) devising a systematic hardware-aware search algorithm to meet the constraints. The experimental results show that our HASNAS quickly finds an SNN that maintains high accuracy compared to the state-of-the-art by up to 11x speed-up, and meets the given constraints: 4x10^6 parameters of memory, 100mm^2 of area, 400ms of latency, and 120uJ energy consumption for CIFAR10 and CIFAR100; while the state-of-the-art fails to meet the constraints. In this manner, our HASNAS can enable efficient design automation for providing high-performance and energy-efficient neuromorphic CIM systems for diverse applications.
Authors: D. J. W. Touw, A. Alfons, P. J. F. Groenen, I. Wilms
Abstract: Graphical models serve as effective tools for visualizing conditional dependencies between variables. However, as the number of variables grows, interpretation becomes increasingly difficult, and estimation uncertainty increases due to the large number of parameters relative to the number of observations. To address these challenges, we introduce the Clusterpath estimator of the Gaussian Graphical Model (CGGM) that encourages variable clustering in the graphical model in a data-driven way. Through the use of a clusterpath penalty, we group variables together, which in turn results in a block-structured precision matrix whose block structure remains preserved in the covariance matrix. We present a computationally efficient implementation of the CGGM estimator by using a cyclic block coordinate descent algorithm. In simulations, we show that CGGM not only matches, but oftentimes outperforms other state-of-the-art methods for variable clustering in graphical models. We also demonstrate CGGM's practical advantages and versatility on a diverse collection of empirical applications.
Authors: Jen Ning Lim, Adam M. Johansen
Abstract: Semi-implicit variational inference (SIVI) enriches the expressiveness of variational families by utilizing a kernel and a mixing distribution to hierarchically define the variational distribution. Existing SIVI methods parameterize the mixing distribution using implicit distributions, leading to intractable variational densities. As a result, directly maximizing the evidence lower bound (ELBO) is not possible and so, they resort to either: optimizing bounds on the ELBO, employing costly inner-loop Markov chain Monte Carlo runs, or solving minimax objectives. In this paper, we propose a novel method for SIVI called Particle Variational Inference (PVI) which employs empirical measures to approximate the optimal mixing distributions characterized as the minimizer of a natural free energy functional via a particle approximation of an Euclidean--Wasserstein gradient flow. This approach means that, unlike prior works, PVI can directly optimize the ELBO; furthermore, it makes no parametric assumption about the mixing distribution. Our empirical results demonstrate that PVI performs favourably against other SIVI methods across various tasks. Moreover, we provide a theoretical analysis of the behaviour of the gradient flow of a related free energy functional: establishing the existence and uniqueness of solutions as well as propagation of chaos results.
Authors: Chun-Hsiang Wang, Chung-Che Wang, Jun-You Wang, Jyh-Shing Roger Jang, Yen-Hsun Chu
Abstract: Music source separation aims to separate polyphonic music into different types of sources. Most existing methods focus on enhancing the quality of separated results by using a larger model structure, rendering them unsuitable for deployment on edge devices. Moreover, these methods may produce low-quality output when the input duration is short, making them impractical for real-time applications. Therefore, the goal of this paper is to enhance a lightweight model, MMDenstNet, to strike a balance between separation quality and latency for real-time applications. Different directions of improvement are explored or proposed in this paper, including complex ideal ratio mask, self-attention, band-merge-split method, and feature look back. Source-to-distortion ratio, real-time factor, and optimal latency are employed to evaluate the performance. To align with our application requirements, the evaluation process in this paper focuses on the separation performance of the accompaniment part. Experimental results demonstrate that our improvement achieves low real-time factor and optimal latency while maintaining acceptable separation quality.
Authors: Gihun Lee, Minchan Jeong, Yujin Kim, Hojung Jung, Jaehoon Oh, Sangmook Kim, Se-Young Yun
Abstract: While learning to align Large Language Models (LLMs) with human preferences has shown remarkable success, aligning these models to meet the diverse user preferences presents further challenges in preserving previous knowledge. This paper examines the impact of personalized preference optimization on LLMs, revealing that the extent of knowledge loss varies significantly with preference heterogeneity. Although previous approaches have utilized the KL constraint between the reference model and the policy model, we observe that they fail to maintain general knowledge and alignment when facing personalized preferences. To this end, we introduce Base-Anchored Preference Optimization (BAPO), a simple yet effective approach that utilizes the initial responses of reference model to mitigate forgetting while accommodating personalized alignment. BAPO effectively adapts to diverse user preferences while minimally affecting global knowledge or general alignment. Our experiments demonstrate the efficacy of BAPO in various setups.
Authors: Anqi Zhou, Yezheng Liu, Yidong Chai, Hongyi Zhu, Xinyue Ge, Yuanchun Jiang, Meng Wang
Abstract: Federated Learning (FL) has garnered widespread adoption across various domains such as finance, healthcare, and cybersecurity. Nonetheless, FL remains under significant threat from backdoor attacks, wherein malicious actors insert triggers into trained models, enabling them to perform certain tasks while still meeting FL's primary objectives. In response, robust aggregation methods have been proposed, which can be divided into three types: ex-ante, ex-durante, and ex-post methods. Given the complementary nature of these methods, combining all three types is promising yet unexplored. Such a combination is non-trivial because it requires leveraging their advantages while overcoming their disadvantages. Our study proposes a novel whole-process certifiably robust aggregation (WPCRA) method for FL, which enhances robustness against backdoor attacks across three phases: ex-ante, ex-durante, and ex-post. Moreover, since the current geometric median estimation method fails to consider differences among clients, we propose a novel weighted geometric median estimation algorithm (WGME). This algorithm estimates the geometric median of model updates from clients based on each client's weight, further improving the robustness of WPCRA against backdoor attacks. We also theoretically prove that WPCRA offers improved certified robustness guarantees with a larger certified radius. We evaluate the advantages of our methods based on the task of loan status prediction. Comparison with baselines shows that our methods significantly improve FL's robustness against backdoor attacks. This study contributes to the literature with a novel WPCRA method and a novel WGME algorithm. Our code is available at https://github.com/brick-brick/WPCRAM.
Authors: Hai Shu
Abstract: A typical approach to the joint analysis of multiple high-dimensional data views is to decompose each view's data matrix into three parts: a low-rank common-source matrix generated by common latent factors of all data views, a low-rank distinctive-source matrix generated by distinctive latent factors of the corresponding data view, and an additive noise matrix. Existing decomposition methods often focus on the uncorrelatedness between the common latent factors and distinctive latent factors, but inadequately address the equally necessary uncorrelatedness between distinctive latent factors from different data views. We propose a novel decomposition method, called Decomposition of Common and Distinctive Latent Factors (D-CDLF), to effectively achieve both types of uncorrelatedness for two-view data. We also discuss the estimation of the D-CDLF under high-dimensional settings.
Authors: Qiuhao Lu, Rui Li, Andrew Wen, Jinlian Wang, Liwei Wang, Hongfang Liu
Abstract: Large Language Models (LLMs) have revolutionized various sectors, including healthcare where they are employed in diverse applications. Their utility is particularly significant in the context of rare diseases, where data scarcity, complexity, and specificity pose considerable challenges. In the clinical domain, Named Entity Recognition (NER) stands out as an essential task and it plays a crucial role in extracting relevant information from clinical texts. Despite the promise of LLMs, current research mostly concentrates on document-level NER, identifying entities in a more general context across entire documents, without extracting their precise location. Additionally, efforts have been directed towards adapting ChatGPT for token-level NER. However, there is a significant research gap when it comes to employing token-level NER for clinical texts, especially with the use of local open-source LLMs. This study aims to bridge this gap by investigating the effectiveness of both proprietary and local LLMs in token-level clinical NER. Essentially, we delve into the capabilities of these models through a series of experiments involving zero-shot prompting, few-shot prompting, retrieval-augmented generation (RAG), and instruction-fine-tuning. Our exploration reveals the inherent challenges LLMs face in token-level NER, particularly in the context of rare diseases, and suggests possible improvements for their application in healthcare. This research contributes to narrowing a significant gap in healthcare informatics and offers insights that could lead to a more refined application of LLMs in the healthcare sector.
Authors: Jiajun Hu, Zhen Lu, Yue Yang
Abstract: We propose a geometry-to-flow diffusion model that utilizes the input of obstacle shape to predict a flow field past the obstacle. The model is based on a learnable Markov transition kernel to recover the data distribution from the Gaussian distribution. The Markov process is conditioned on the obstacle geometry, estimating the noise to be removed at each step, implemented via a U-Net. A cross-attention mechanism incorporates the geometry as a prompt. We train the geometry-to-flow diffusion model using a dataset of flows past simple obstacles, including the circle, ellipse, rectangle, and triangle. For comparison, the CNN model is trained using the same dataset. Tests are carried out on flows past obstacles with simple and complex geometries, representing interpolation and extrapolation on the geometry condition, respectively. In the test set, challenging scenarios include a cross and characters `PKU'. Generated flow fields show that the geometry-to-flow diffusion model is superior to the CNN model in predicting instantaneous flow fields and handling complex geometries. Quantitative analysis of the model accuracy and divergence in the fields demonstrate the high robustness of the diffusion model, indicating that the diffusion model learns physical laws implicitly.
Authors: Yan Ge, Wu Wenjie, Chen Yuheng, Pan Kaisen, Lu Xudong, Zhou Zixiang, Wang Yuhan, Wang Ruocheng, Yan Junchi
Abstract: Quantum computing is regarded as a promising paradigm that may overcome the current computational power bottlenecks in the post-Moore era. The increasing maturity of quantum processors, especially superconducting ones, provides more possibilities for the development and implementation of quantum algorithms. As the crucial stages for quantum algorithm implementation, the logic circuit design and quantum compiling have also received significant attention, which covers key technologies such as quantum logic circuit synthesis (also widely known as quantum architecture search) and optimization, as well as qubit mapping and routing. Recent studies suggest that the scale and precision of related algorithms are steadily increasing, especially with the integration of artificial intelligence methods. In this survey, we systematically review and summarize a vast body of literature, exploring the feasibility of an integrated design and optimization scheme that spans from the algorithmic level to quantum hardware, combining the steps of logic circuit design and compilation optimization. Leveraging the exceptional cognitive and learning capabilities of AI algorithms, one can reduce manual design costs, enhance the precision and efficiency of execution, and facilitate the implementation and validation of the superiority of quantum algorithms on hardware.
Authors: Momir Ad\v{z}emovi\'c, Predrag Tadi\'c, Andrija Petrovi\'c, Mladen Nikoli\'c
Abstract: The goal of multi-object tracking is to detect and track all objects in a scene while maintaining unique identifiers for each, by associating their bounding boxes across video frames. This association relies on matching motion and appearance patterns of detected objects. This task is especially hard in case of scenarios involving dynamic and non-linear motion patterns. In this paper, we introduce DeepMoveSORT, a novel, carefully engineered multi-object tracker designed specifically for such scenarios. In addition to standard methods of appearance-based association, we improve motion-based association by employing deep learnable filters (instead of the most commonly used Kalman filter) and a rich set of newly proposed heuristics. Our improvements to motion-based association methods are severalfold. First, we propose a new transformer-based filter architecture, TransFilter, which uses an object's motion history for both motion prediction and noise filtering. We further enhance the filter's performance by careful handling of its motion history and accounting for camera motion. Second, we propose a set of heuristics that exploit cues from the position, shape, and confidence of detected bounding boxes to improve association performance. Our experimental evaluation demonstrates that DeepMoveSORT outperforms existing trackers in scenarios featuring non-linear motion, surpassing state-of-the-art results on three such datasets. We also perform a thorough ablation study to evaluate the contributions of different tracker components which we proposed. Based on our study, we conclude that using a learnable filter instead of the Kalman filter, along with appearance-based association is key to achieving strong general tracking performance.
Authors: Hye Ryung Son, Jay-Yoon Lee
Abstract: Recent approaches to controlled text generation (CTG) often involve manipulating the weights or logits of base language models (LMs) at decoding time. However, these methods are inapplicable to latest black-box LMs and ineffective at preserving the core semantics of the base LM's original generations. In this work, we propose Locate&Edit(L&E), an efficient and flexible energy-based approach to CTG, which edits text outputs from a base LM using off-the-shelf energy models. Given text outputs from the base LM, L&E first locates spans that are most relevant to constraints (e.g., toxicity) utilizing energy models, and then edits these spans by replacing them with more suitable alternatives. Importantly, our method is compatible with black-box LMs, as it requires only the text outputs. Also, since L&E doesn't mandate specific architecture for its component models, it can work with a diverse combination of available off-the-shelf models. Moreover, L&E preserves the base LM's original generations, by selectively modifying constraint-related aspects of the texts and leaving others unchanged. These targeted edits also ensure that L&E operates efficiently. Our experiments confirm that L&E achieves superior semantic preservation of the base LM generations and speed, while simultaneously obtaining competitive or improved constraint satisfaction. Furthermore, we analyze how the granularity of energy distribution impacts CTG performance and find that fine-grained, regression-based energy models improve constraint satisfaction, compared to conventional binary classifier energy models.
Authors: Dazhou Yu, Yuntong Hu, Yun Li, Liang Zhao
Abstract: Polygon representation learning is essential for diverse applications, encompassing tasks such as shape coding, building pattern classification, and geographic question answering. While recent years have seen considerable advancements in this field, much of the focus has been on single polygons, overlooking the intricate inner- and inter-polygonal relationships inherent in multipolygons. To address this gap, our study introduces a comprehensive framework specifically designed for learning representations of polygonal geometries, particularly multipolygons. Central to our approach is the incorporation of a heterogeneous visibility graph, which seamlessly integrates both inner- and inter-polygonal relationships. To enhance computational efficiency and minimize graph redundancy, we implement a heterogeneous spanning tree sampling method. Additionally, we devise a rotation-translation invariant geometric representation, ensuring broader applicability across diverse scenarios. Finally, we introduce Multipolygon-GNN, a novel model tailored to leverage the spatial and semantic heterogeneity inherent in the visibility graph. Experiments on five real-world and synthetic datasets demonstrate its ability to capture informative representations for polygonal geometries.
Authors: Filippo Torresan, Manuel Baltieri
Abstract: Complex adaptive agents consistently achieve their goals by solving problems that seem to require an understanding of causal information, information pertaining to the causal relationships that exist among elements of combined agent-environment systems. Causal cognition studies and describes the main characteristics of causal learning and reasoning in human and non-human animals, offering a conceptual framework to discuss cognitive performances based on the level of apparent causal understanding of a task. Despite the use of formal intervention-based models of causality, including causal Bayesian networks, psychological and behavioural research on causal cognition does not yet offer a computational account that operationalises how agents acquire a causal understanding of the world. Machine and reinforcement learning research on causality, especially involving disentanglement as a candidate process to build causal representations, represent on the one hand a concrete attempt at designing causal artificial agents that can shed light on the inner workings of natural causal cognition. In this work, we connect these two areas of research to build a unifying framework for causal cognition that will offer a computational perspective on studies of animal cognition, and provide insights in the development of new algorithms for causal reinforcement learning in AI.
Authors: Alexander Kim (University of Illinois Urbana-Champaign), Ryan Kim (William Fremd High School)
Abstract: The accurate classification of white blood cells and related blood components is crucial for medical diagnoses. While traditional manual examinations and automated hematology analyzers have been widely used, they are often slow and prone to errors. Recent advancements in deep learning have shown promise for addressing these limitations. Earlier studies have demonstrated the viability of convolutional neural networks such as DenseNet, ResNet, and VGGNet for this task. Building on these foundations, our work employs more recent and efficient models to achieve rapid and accurate results. Specifically, this study used state-of-the-art architectures, including MaxVit, EfficientVit, EfficientNet, EfficientNetV2, and MobileNetV3. This study aimed to evaluate the performance of these models in WBC classification, potentially offering a more efficient and reliable alternative to current methods. Our approach not only addresses the speed and accuracy concerns of traditional techniques but also explores the applicability of innovative deep learning models in hematological analysis.
Authors: Diksha Sharma, Vivek Balasaheb Sabale, Parvinder Singh, Atul Kumar
Abstract: In this study, we use cross-domain classification using quantum machine learning for quantum advantages to address the entanglement versus separability paradigm. We further demonstrate the efficient classification of Bell diagonal states into zero and non-zero discord classes. The inherited structure of quantum states and its relation with a particular class of quantum states are exploited to intuitively approach the classification of different domain testing states, referred here as crossdomain classification. In addition, we extend our analysis to evaluate the robustness of our model for the analyzed problem using random unitary transformations. Using numerical analysis, our results clearly demonstrate the potential of QSVM for classifying quantum states across the multidimensional Hilbert space.
Authors: Reda Igebaria, Eran Fainman, Sarai Mizrachi, Moran Beladev, Fengjun Wang
Abstract: User-generated reviews significantly influence consumer decisions, particularly in the travel domain when selecting accommodations. This paper contribution comprising two main elements. Firstly, we present a novel dataset of authentic guest reviews sourced from a prominent online travel platform, totaling over two million reviews from 50,000 distinct accommodations. Secondly, we propose an innovative approach for personalized review ranking. Our method employs contrastive learning to intricately capture the relationship between a review and the contextual information of its respective reviewer. Through a comprehensive experimental study, we demonstrate that our approach surpasses several baselines across all reported metrics. Augmented by a comparative analysis, we showcase the efficacy of our method in elevating personalized review ranking. The implications of our research extend beyond the travel domain, with potential applications in other sectors where personalized review ranking is paramount, such as online e-commerce platforms.
Authors: Kuratov Andrey (HSE University, Moscow)
Abstract: This research focuses on an innovative task of extracting equations from incomplete data, moving away from traditional methods used for complete solutions. The study addresses the challenge of extracting equations from data, particularly in the study of brain activity using electrophysiological data, which is often limited by insufficient information. The study provides a brief review of existing open-source equation derivation approaches in the context of modeling brain activity. The section below introduces a novel algorithm that employs incomplete data and prior domain knowledge to recover differential equations. The algorithm's practicality in real-world scenarios is demonstrated through its application on both synthetic and real datasets.
Authors: Lorenzo Bonasera, Emilio Carrizosa
Abstract: Tree ensemble methods represent a popular machine learning model, known for their effectiveness in supervised classification and regression tasks. Their performance derives from aggregating predictions of multiple decision trees, which are renowned for their interpretability properties. However, tree ensemble methods do not reliably exhibit interpretable output. Our work aims to extract an optimized list of rules from a trained tree ensemble, providing the user with a condensed, interpretable model that retains most of the predictive power of the full model. Our approach consists of solving a clean and neat set partitioning problem formulated through Integer Programming. The proposed method works with either tabular or time series data, for both classification and regression tasks, and does not require parameter tuning under the most common setting. Through rigorous computational experiments, we offer statistically significant evidence that our method is competitive with other rule extraction methods and effectively handles time series.
Authors: Sunyanan Choochotkaew, Chen Wang, Huamin Chen, Tatsuhiro Chiba, Marcelo Amaral, Eun Kyung Lee, Tamar Eilam
Abstract: Estimating power consumption in modern Cloud environments is essential for carbon quantification toward green computing. Specifically, it is important to properly account for the power consumed by each of the running applications, which are packaged as containers. This paper examines multiple challenges associated with this goal. The first challenge is that multiple customers are sharing the same hardware platform (multi-tenancy), where information on the physical servers is mostly obscured. The second challenge is the overhead in power consumption that the Cloud platform control plane induces. This paper addresses these challenges and introduces a novel pipeline framework for power model training. This allows versatile power consumption approximation of individual containers on the basis of available performance counters and other metrics. The proposed model utilizes machine learning techniques to predict the power consumed by the control plane and associated processes, and uses it for isolating the power consumed by the user containers, from the server power consumption. To determine how well the prediction results in an isolation, we introduce a metric termed isolation goodness. Applying the proposed power model does not require online power measurements, nor does it need information on the physical servers, configuration, or information on other tenants sharing the same machine. The results of cross-workload, cross-platform experiments demonstrated the higher accuracy of the proposed model when predicting power consumption of unseen containers on unknown platforms, including on virtual machines.
Authors: Hyunseok Oh, Juheon Yi, Youngki Lee
Abstract: Transformer-based models recently reached state-of-the-art single-channel speech separation accuracy; However, their extreme computational load makes it difficult to deploy them in resource-constrained mobile or IoT devices. We thus present Papez, a lightweight and computation-efficient single-channel speech separation model. Papez is based on three key techniques. We first replace the inter-chunk Transformer with small-sized auditory working memory. Second, we adaptively prune the input tokens that do not need further processing. Finally, we reduce the number of parameters through the recurrent transformer. Our extensive evaluation shows that Papez achieves the best resource and accuracy tradeoffs with a large margin. We publicly share our source code at \texttt{https://github.com/snuhcs/Papez}
Authors: Andrea Carriero, Davide Pettenuzzo, Shubhranshu Shekhar
Abstract: This paper presents a comparative analysis evaluating the accuracy of Large Language Models (LLMs) against traditional macro time series forecasting approaches. In recent times, LLMs have surged in popularity for forecasting due to their ability to capture intricate patterns in data and quickly adapt across very different domains. However, their effectiveness in forecasting macroeconomic time series data compared to conventional methods remains an area of interest. To address this, we conduct a rigorous evaluation of LLMs against traditional macro forecasting methods, using as common ground the FRED-MD database. Our findings provide valuable insights into the strengths and limitations of LLMs in forecasting macroeconomic time series, shedding light on their applicability in real-world scenarios
Authors: Nan Xu, Fei Wang, Sheng Zhang, Hoifung Poon, Muhao Chen
Abstract: Motivated by in-context learning (ICL) capabilities of Large Language models (LLMs), multimodal LLMs with additional visual modality are also exhibited with similar ICL abilities when multiple image-text pairs are provided as demonstrations. However, relatively less work has been done to investigate the principles behind how and why multimodal ICL works. We conduct a systematic and principled evaluation of multimodal ICL for models of different scales on a broad spectrum of new yet critical tasks. Through perturbations over different modality information, we show that modalities matter differently across tasks in multimodal ICL. Considering such modality impact, we further utilize modality-driven demonstration strategies to boost ICL performance. We also identify that demonstration selection is closely related to the models' ability to capture task inductive biases from multimodal ICL. Our principled analysis provides a comprehensive way of understanding the role of demonstrations in multimodal in-context learning, and sheds light on effectively improving multimodal ICL on a wide range of tasks even if those tasks are not seen in or even contradict pretraining data.
Authors: Yuming Zhang, Dongzhi Guan, Shouxin Zhang, Junhao Su, Yunzhi Han, Jiabin Liu
Abstract: Safety issues at construction sites have long plagued the industry, posing risks to worker safety and causing economic damage due to potential hazards. With the advancement of artificial intelligence, particularly in the field of computer vision, the automation of safety monitoring on construction sites has emerged as a solution to this longstanding issue. Despite achieving impressive performance, advanced object detection methods like YOLOv8 still face challenges in handling the complex conditions found at construction sites. To solve these problems, this study presents the Global Stability Optimization YOLO (GSO-YOLO) model to address challenges in complex construction sites. The model integrates the Global Optimization Module (GOM) and Steady Capture Module (SCM) to enhance global contextual information capture and detection stability. The innovative AIoU loss function, which combines CIoU and EIoU, improves detection accuracy and efficiency. Experiments on datasets like SODA, MOCS, and CIS show that GSO-YOLO outperforms existing methods, achieving SOTA performance.
Authors: Jiangqin Ma, Bilal Mawji, Franz Williams
Abstract: The modern saying, "You Are What You Eat" resonates on a profound level, reflecting the intricate connection between our identities and the food we consume. Our project, Deep Image-to-Recipe Translation, is an intersection of computer vision and natural language generation that aims to bridge the gap between cherished food memories and the art of culinary creation. Our primary objective involves predicting ingredients from a given food image. For this task, we first develop a custom convolutional network and then compare its performance to a model that leverages transfer learning. We pursue an additional goal of generating a comprehensive set of recipe steps from a list of ingredients. We frame this process as a sequence-to-sequence task and develop a recurrent neural network that utilizes pre-trained word embeddings. We address several challenges of deep learning including imbalanced datasets, data cleaning, overfitting, and hyperparameter selection. Our approach emphasizes the importance of metrics such as Intersection over Union (IoU) and F1 score in scenarios where accuracy alone might be misleading. For our recipe prediction model, we employ perplexity, a commonly used and important metric for language models. We find that transfer learning via pre-trained ResNet-50 weights and GloVe embeddings provide an exceptional boost to model performance, especially when considering training resource constraints. Although we have made progress on the image-to-recipe translation, there is an opportunity for future exploration with advancements in model architectures, dataset scalability, and enhanced user interaction.
Authors: Oguzhan Baser, Kaan Kale, Sandeep P. Chinchali
Abstract: Advancements in DeepFake (DF) audio models pose a significant threat to voice authentication systems, leading to unauthorized access and the spread of misinformation. We introduce a defense mechanism, SecureSpectra, addressing DF threats by embedding orthogonal, irreversible signatures within audio. SecureSpectra leverages the inability of DF models to replicate high-frequency content, which we empirically identify across diverse datasets and DF models. Integrating differential privacy into the pipeline protects signatures from reverse engineering and strikes a delicate balance between enhanced security and minimal performance compromises. Our evaluations on Mozilla Common Voice, LibriSpeech, and VoxCeleb datasets showcase SecureSpectra's superior performance, outperforming recent works by up to 71% in detection accuracy. We open-source SecureSpectra to benefit the research community.
Authors: Xinhao Deng, Qi Li, Ke Xu
Abstract: Website Fingerprinting (WF) attacks identify the websites visited by users by performing traffic analysis, compromising user privacy. Particularly, DL-based WF attacks demonstrate impressive attack performance. However, the effectiveness of DL-based WF attacks relies on the collected complete and pure traffic during the page loading, which impacts the practicality of these attacks. The WF performance is rather low under dynamic network conditions and various WF defenses, particularly when the analyzed traffic is only a small part of the complete traffic. In this paper, we propose Holmes, a robust and reliable early-stage WF attack. Holmes utilizes temporal and spatial distribution analysis of website traffic to effectively identify websites in the early stages of page loading. Specifically, Holmes develops adaptive data augmentation based on the temporal distribution of website traffic and utilizes a supervised contrastive learning method to extract the correlations between the early-stage traffic and the pre-collected complete traffic. Holmes accurately identifies traffic in the early stages of page loading by computing the correlation of the traffic with the spatial distribution information, which ensures robust and reliable detection according to early-stage traffic. We extensively evaluate Holmes using six datasets. Compared to nine existing DL-based WF attacks, Holmes improves the F1-score of identifying early-stage traffic by an average of 169.18%. Furthermore, we replay the traffic of visiting real-world dark web websites. Holmes successfully identifies dark web websites when the ratio of page loading on average is only 21.71%, with an average precision improvement of 169.36% over the existing WF attacks.
Authors: Tanush Chopra, Michael Li
Abstract: We propose a framework for evaluating strategic deception in large language models (LLMs). In this framework, an LLM acts as a game master in two scenarios: one with random game mechanics and another where it can choose between random or deliberate actions. As an example, we use blackjack because the action space nor strategies involve deception. We benchmark Llama3-70B, GPT-4-Turbo, and Mixtral in blackjack, comparing outcomes against expected distributions in fair play to determine if LLMs develop strategies favoring the "house." Our findings reveal that the LLMs exhibit significant deviations from fair play when given implicit randomness instructions, suggesting a tendency towards strategic manipulation in ambiguous scenarios. However, when presented with an explicit choice, the LLMs largely adhere to fair play, indicating that the framing of instructions plays a crucial role in eliciting or mitigating potentially deceptive behaviors in AI systems.
Authors: Nicy Scaria, Silvester John Joseph Kennedy, Deepak Subramani
Abstract: Small Language Models (SLMs) are generally considered to be more compact versions of large language models (LLMs), typically having fewer than 7 billion parameters. This study investigates the ability of small language models to learn, retain, and subsequently eliminate noise that is typically not found on the internet, where most pretraining datasets are sourced. For this, four pre-trained SLMs were utilized: Olmo 1B, Qwen1.5 1.8B, Gemma 2B, and Phi2 2.7B. The models were instruction-tuned without noise and tested for task execution with in-context learning. Afterward, noise patterns were introduced to evaluate the models' learning and unlearning capabilities. We evaluated the models' performance at various training levels. Phi consistently excelled with word-level noise but performed the worst with character-level noise. Despite being the smallest with approximately 1 billion parameters, Olmo performed consistently well on tasks.
Authors: Rahul Rathnakumar, Jiayu Huang, Hao Yan, Yongming Liu
Abstract: This paper addresses the need for deep learning models to integrate well-defined constraints into their outputs, driven by their application in surrogate models, learning with limited data and partial information, and scenarios requiring flexible model behavior to incorporate non-data sample information. We introduce Bayesian Entropy Neural Networks (BENN), a framework grounded in Maximum Entropy (MaxEnt) principles, designed to impose constraints on Bayesian Neural Network (BNN) predictions. BENN is capable of constraining not only the predicted values but also their derivatives and variances, ensuring a more robust and reliable model output. To achieve simultaneous uncertainty quantification and constraint satisfaction, we employ the method of multipliers approach. This allows for the concurrent estimation of neural network parameters and the Lagrangian multipliers associated with the constraints. Our experiments, spanning diverse applications such as beam deflection modeling and microstructure generation, demonstrate the effectiveness of BENN. The results highlight significant improvements over traditional BNNs and showcase competitive performance relative to contemporary constrained deep learning methods.
Authors: Pallavi Basu, Ron Berman
Abstract: A/B testers conducting large-scale tests prioritize lifts and want to be able to control false rejections of the null. This work develops a decision-theoretic framework for maximizing profits subject to false discovery rate (FDR) control. We build an empirical Bayes solution for the problem via the greedy knapsack approach. We derive an oracle rule based on ranking the ratio of expected lifts and the cost of wrong rejections using the local false discovery rate (lfdr) statistic. Our oracle decision rule is valid and optimal for large-scale tests. Further, we establish asymptotic validity for the data-driven procedure and demonstrate finite-sample validity in experimental studies. We also demonstrate the merit of the proposed method over other FDR control methods. Finally, we discuss an application to actual Optimizely experiments.
Authors: Changde Du, Kaicheng Fu, Bincheng Wen, Yi Sun, Jie Peng, Wei Wei, Ying Gao, Shengpei Wang, Chuncheng Zhang, Jinpeng Li, Shuang Qiu, Le Chang, Huiguang He
Abstract: The conceptualization and categorization of natural objects in the human mind have long intrigued cognitive scientists and neuroscientists, offering crucial insights into human perception and cognition. Recently, the rapid development of Large Language Models (LLMs) has raised the attractive question of whether these models can also develop human-like object representations through exposure to vast amounts of linguistic and multimodal data. In this study, we combined behavioral and neuroimaging analysis methods to uncover how the object concept representations in LLMs correlate with those of humans. By collecting large-scale datasets of 4.7 million triplet judgments from LLM and Multimodal LLM (MLLM), we were able to derive low-dimensional embeddings that capture the underlying similarity structure of 1,854 natural objects. The resulting 66-dimensional embeddings were found to be highly stable and predictive, and exhibited semantic clustering akin to human mental representations. Interestingly, the interpretability of the dimensions underlying these embeddings suggests that LLM and MLLM have developed human-like conceptual representations of natural objects. Further analysis demonstrated strong alignment between the identified model embeddings and neural activity patterns in many functionally defined brain ROIs (e.g., EBA, PPA, RSC and FFA). This provides compelling evidence that the object representations in LLMs, while not identical to those in the human, share fundamental commonalities that reflect key schemas of human conceptual knowledge. This study advances our understanding of machine intelligence and informs the development of more human-like artificial cognitive systems.
Authors: Jerry Yao-Chieh Hu, Weimin Wu, Zhuoru Li, Zhao Song, Han Liu
Abstract: We investigate the statistical and computational limits of latent \textbf{Di}ffusion \textbf{T}ransformers (\textbf{DiT}s) under the low-dimensional linear latent space assumption. Statistically, we study the universal approximation and sample complexity of the DiTs score function, as well as the distribution recovery property of the initial data. Specifically, under mild data assumptions, we derive an approximation error bound for the score network of latent DiTs, which is sub-linear in the latent space dimension. Additionally, we derive the corresponding sample complexity bound and show that the data distribution generated from the estimated score function converges toward a proximate area of the original one. Computationally, we characterize the hardness of both forward inference and backward computation of latent DiTs, assuming the Strong Exponential Time Hypothesis (SETH). For forward inference, we identify efficient criteria for all possible latent DiTs inference algorithms and showcase our theory by pushing the efficiency toward almost-linear time inference. For backward computation, we leverage the low-rank structure within the gradient computation of DiTs training for possible algorithmic speedup. Specifically, we show that such speedup achieves almost-linear time latent DiTs training by casting the DiTs gradient as a series of chained low-rank approximations with bounded error. Under the low-dimensional assumption, we show that the convergence rate and the computational efficiency are both dominated by the dimension of the subspace, suggesting that latent DiTs have the potential to bypass the challenges associated with the high dimensionality of initial data.
Authors: Ivan Drokin
Abstract: The emergence of Kolmogorov-Arnold Networks (KANs) has sparked significant interest and debate within the scientific community. This paper explores the application of KANs in the domain of computer vision (CV). We examine the convolutional version of KANs, considering various nonlinearity options beyond splines, such as Wavelet transforms and a range of polynomials. We propose a parameter-efficient design for Kolmogorov-Arnold convolutional layers and a parameter-efficient finetuning algorithm for pre-trained KAN models, as well as KAN convolutional versions of self-attention and focal modulation layers. We provide empirical evaluations conducted on MNIST, CIFAR10, CIFAR100, Tiny ImageNet, ImageNet1k, and HAM10000 datasets for image classification tasks. Additionally, we explore segmentation tasks, proposing U-Net-like architectures with KAN convolutions, and achieving state-of-the-art results on BUSI, GlaS, and CVC datasets. We summarized all of our findings in a preliminary design guide of KAN convolutional models for computer vision tasks. Furthermore, we investigate regularization techniques for KANs. All experimental code and implementations of convolutional layers and models, pre-trained on ImageNet1k weights are available on GitHub via this https://github.com/IvanDrokin/torch-conv-kan
Authors: Ziqi Wang, Hanlin Zhang, Xiner Li, Kuan-Hao Huang, Chi Han, Shuiwang Ji, Sham M. Kakade, Hao Peng, Heng Ji
Abstract: Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context. This bias often leads to unexpected model failures and hurts performance, robustness, and reliability across various applications. Our mechanistic analysis attributes the position bias to two components employed in nearly all state-of-the-art LMs: causal attention and relative positional encodings. Specifically, we find that causal attention generally causes models to favor distant content, while relative positional encodings like RoPE prefer nearby ones based on the analysis of retrieval-augmented question answering (QA). Further, our empirical study on object detection reveals that position bias is also present in vision-language models (VLMs). Based on the above analyses, we propose to ELIMINATE position bias caused by different input segment orders (e.g., options in LM-as-a-judge, retrieved documents in QA) in a TRAINING-FREE ZERO-SHOT manner. Our method changes the causal attention to bidirectional attention between segments and utilizes model attention values to decide the relative orders of segments instead of using the order provided in input prompts, therefore enabling Position-INvariant inferencE (PINE) at the segment level. By eliminating position bias, models achieve better performance and reliability in downstream tasks where position bias widely exists, such as LM-as-a-judge and retrieval-augmented QA. Notably, PINE is especially useful when adapting LMs for evaluating reasoning pairs: it consistently provides 8 to 10 percentage points performance gains in most cases, and makes Llama-3-70B-Instruct perform even better than GPT-4-0125-preview on the RewardBench reasoning subset.
Authors: Christoforus Yoga Haryanto, Minh Hieu Vu, Trung Duc Nguyen, Emily Lomempow, Yulia Nurliana, Sona Taheri
Abstract: The rapid advancement of Generative AI (GenAI) technologies offers transformative opportunities within Australia's critical technologies of national interest while introducing unique security challenges. This paper presents SecGenAI, a comprehensive security framework for cloud-based GenAI applications, with a focus on Retrieval-Augmented Generation (RAG) systems. SecGenAI addresses functional, infrastructure, and governance requirements, integrating end-to-end security analysis to generate specifications emphasizing data privacy, secure deployment, and shared responsibility models. Aligned with Australian Privacy Principles, AI Ethics Principles, and guidelines from the Australian Cyber Security Centre and Digital Transformation Agency, SecGenAI mitigates threats such as data leakage, adversarial attacks, and model inversion. The framework's novel approach combines advanced machine learning techniques with robust security measures, ensuring compliance with Australian regulations while enhancing the reliability and trustworthiness of GenAI systems. This research contributes to the field of intelligent systems by providing actionable strategies for secure GenAI implementation in industry, fostering innovation in AI applications, and safeguarding national interests.
Authors: Patrizio Giovannotti, Alexander Gammerman
Abstract: Quantifying the uncertainty of predictions made by large language models (LLMs) in binary text classification tasks remains a challenge. Calibration, in the context of LLMs, refers to the alignment between the model's predicted probabilities and the actual correctness of its predictions. A well-calibrated model should produce probabilities that accurately reflect the likelihood of its predictions being correct. We propose a novel approach that utilizes the inductive Venn--Abers predictor (IVAP) to calibrate the probabilities associated with the output tokens corresponding to the binary labels. Our experiments on the BoolQ dataset using the Llama 2 model demonstrate that IVAP consistently outperforms the commonly used temperature scaling method for various label token choices, achieving well-calibrated probabilities while maintaining high predictive quality. Our findings contribute to the understanding of calibration techniques for LLMs and provide a practical solution for obtaining reliable uncertainty estimates in binary question answering tasks, enhancing the interpretability and trustworthiness of LLM predictions.
Authors: Shaeke Salman, Md Montasir Bin Shams, Xiuwen Liu
Abstract: Utilizing a shared embedding space, emerging multimodal models exhibit unprecedented zero-shot capabilities. However, the shared embedding space could lead to new vulnerabilities if different modalities can be misaligned. In this paper, we extend and utilize a recently developed effective gradient-based procedure that allows us to match the embedding of a given text by minimally modifying an image. Using the procedure, we show that we can align the embeddings of distinguishable texts to any image through unnoticeable adversarial attacks in joint image-text models, revealing that semantically unrelated images can have embeddings of identical texts and at the same time visually indistinguishable images can be matched to the embeddings of very different texts. Our technique achieves 100\% success rate when it is applied to text datasets and images from multiple sources. Without overcoming the vulnerability, multimodal models cannot robustly align inputs from different modalities in a semantically meaningful way. \textbf{Warning: the text data used in this paper are toxic in nature and may be offensive to some readers.}
Authors: Hongkang Yang, Zehao Lin, Wenjin Wang, Hao Wu, Zhiyu Li, Bo Tang, Wenqiang Wei, Jinbo Wang, Zeyun Tang, Shichao Song, Chenyang Xi, Yu Yu, Kai Chen, Feiyu Xiong, Linpeng Tang, Weinan E
Abstract: The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory hierarchy of the human brain, we reduce this cost by equipping LLMs with explicit memory, a memory format cheaper than model parameters and text retrieval-augmented generation (RAG). Conceptually, with most of its knowledge externalized to explicit memories, the LLM can enjoy a smaller parameter size, training cost, and inference cost, all proportional to the amount of remaining "abstract knowledge". As a preliminary proof of concept, we train from scratch a 2.4B LLM, which achieves better performance than much larger LLMs as well as RAG models, and maintains higher decoding speed than RAG. The model is named $\text{Memory}^3$, since explicit memory is the third form of memory in LLMs after implicit memory (model parameters) and working memory (context key-values). We introduce a memory circuitry theory to support the externalization of knowledge, and present novel techniques including a memory sparsification mechanism that makes storage tractable and a two-stage pretraining scheme that facilitates memory formation.
Authors: Zongshuo Li, Ding Huo, Markus Meurer, Thomas Bergs
Abstract: Tool wear conditions impact the surface quality of the workpiece and its final geometric precision. In this research, we propose an efficient tool wear segmentation approach based on Segment Anything Model, which integrates U-Net as an automated prompt generator to streamline the processes of tool wear detection. Our evaluation covered three Point-of-Interest generation methods and further investigated the effects of variations in training dataset sizes and U-Net training intensities on resultant wear segmentation outcomes. The results consistently highlight our approach's advantage over U-Net, emphasizing its ability to achieve accurate wear segmentation even with limited training datasets. This feature underscores its potential applicability in industrial scenarios where datasets may be limited.
Authors: Wouter M. Kouw, Caspar Gruijthuijsen, Lennart Blanken, Enzo Evers, Timothy Rogers
Abstract: We propose a computational procedure for identifying convection in heat transfer dynamics. The procedure is based on a Gaussian process latent force model, consisting of a white-box component (i.e., known physics) for the conduction and linear convection effects and a Gaussian process that acts as a black-box component for the nonlinear convection effects. States are inferred through Bayesian smoothing and we obtain approximate posterior distributions for the kernel covariance function's hyperparameters using Laplace's method. The nonlinear convection function is recovered from the Gaussian process states using a Bayesian regression model. We validate the procedure by simulation error using the identified nonlinear convection function, on both data from a simulated system and measurements from a physical assembly.
Authors: Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong Sun, Xiaoshuai Song, Zhuoma GongQue, Shanglin Lei, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Yifan Zhang, Xiao Zong, Yida Xu, Muxi Diao, Zhimin Bao, Chen Li, Honggang Zhang
Abstract: Visual mathematical reasoning, as a fundamental visual reasoning ability, has received widespread attention from the Large Multimodal Models (LMMs) community. Existing benchmarks, such as MathVista and MathVerse, focus more on the result-oriented performance but neglect the underlying principles in knowledge acquisition and generalization. Inspired by human-like mathematical reasoning, we introduce WE-MATH, the first benchmark specifically designed to explore the problem-solving principles beyond end-to-end performance. We meticulously collect and categorize 6.5K visual math problems, spanning 67 hierarchical knowledge concepts and five layers of knowledge granularity. We decompose composite problems into sub-problems according to the required knowledge concepts and introduce a novel four-dimensional metric, namely Insufficient Knowledge (IK), Inadequate Generalization (IG), Complete Mastery (CM), and Rote Memorization (RM), to hierarchically assess inherent issues in LMMs' reasoning process. With WE-MATH, we conduct a thorough evaluation of existing LMMs in visual mathematical reasoning and reveal a negative correlation between solving steps and problem-specific performance. We confirm the IK issue of LMMs can be effectively improved via knowledge augmentation strategies. More notably, the primary challenge of GPT-4o has significantly transitioned from IK to IG, establishing it as the first LMM advancing towards the knowledge generalization stage. In contrast, other LMMs exhibit a marked inclination towards Rote Memorization - they correctly solve composite problems involving multiple knowledge concepts yet fail to answer sub-problems. We anticipate that WE-MATH will open new pathways for advancements in visual mathematical reasoning for LMMs. The WE-MATH data and evaluation code are available at https://github.com/We-Math/We-Math.
Authors: Kenichi Fujita, Takanori Ashihara, Marc Delcroix, Yusuke Ijima
Abstract: The advancements in zero-shot text-to-speech (TTS) methods, based on large-scale models, have demonstrated high fidelity in reproducing speaker characteristics. However, these models are too large for practical daily use. We propose a lightweight zero-shot TTS method using a mixture of adapters (MoA). Our proposed method incorporates MoA modules into the decoder and the variance adapter of a non-autoregressive TTS model. These modules enhance the ability to adapt a wide variety of speakers in a zero-shot manner by selecting appropriate adapters associated with speaker characteristics on the basis of speaker embeddings. Our method achieves high-quality speech synthesis with minimal additional parameters. Through objective and subjective evaluations, we confirmed that our method achieves better performance than the baseline with less than 40\% of parameters at 1.9 times faster inference speed. Audio samples are available on our demo page (https://ntt-hilab-gensp.github.io/is2024lightweightTTS/).
URLs: https://ntt-hilab-gensp.github.io/is2024lightweightTTS/).
Authors: Qiyuan Zhang, Fuyuan Lyu, Xue Liu, Chen Ma
Abstract: Comprehensively understanding and accurately predicting the performance of large language models across diverse downstream tasks has emerged as a pivotal challenge in NLP research. The pioneering scaling law on downstream works demonstrated intrinsic similarities within model families and utilized such similarities for performance prediction. However, they tend to overlook the similarities between model families and only consider design factors listed in the original scaling law. To overcome these limitations, we introduce a novel framework, Collaborative Performance Prediction (CPP), which significantly enhances prediction accuracy by leveraging the historical performance of various models on downstream tasks and other design factors for both model and task. We also collect a collaborative data sourced from online platforms containing both historical performance and additional design factors. With the support of the collaborative data, CPP not only surpasses traditional scaling laws in predicting the performance of scaled LLMs but also facilitates a detailed analysis of factor importance, an area previously overlooked.
Authors: Ana Carolina Alves, Andr\'e Ferreira, Behrus Puladi, Jan Egger, Victor Alves
Abstract: The development of magnetic resonance imaging (MRI) for medical imaging has provided a leap forward in diagnosis, providing a safe, non-invasive alternative to techniques involving ionising radiation exposure for diagnostic purposes. It was described by Block and Purcel in 1946, and it was not until 1980 that the first clinical application of MRI became available. Since that time the MRI has gone through many advances and has altered the way diagnosing procedures are performed. Due to its ability to improve constantly, MRI has become a commonly used practice among several specialisations in medicine. Particularly starting 0.55T and 7T MRI technologies have pointed out enhanced preservation of image detail and advanced tissue characterisation. This review examines the integration of deep learning (DL) techniques into these MRI modalities, disseminating and exploring the study applications. It highlights how DL contributes to 0.55T and 7T MRI data, showcasing the potential of DL in improving and refining these technologies. The review ends with a brief overview of how MRI technology will evolve in the coming years.
Authors: Roberto Alcover-Couso, Marcos Escudero-Vi\~nolo, Juan C. SanMiguel, Jesus Besc\'os
Abstract: In unsupervised domain adaptation (UDA), where models are trained on source data (e.g., synthetic) and adapted to target data (e.g., real-world) without target annotations, addressing the challenge of significant class imbalance remains an open issue. Despite considerable progress in bridging the domain gap, existing methods often experience performance degradation when confronted with highly imbalanced dense prediction visual tasks like semantic and panoptic segmentation. This discrepancy becomes especially pronounced due to the lack of equivalent priors between the source and target domains, turning class imbalanced techniques used for other areas (e.g., image classification) ineffective in UDA scenarios. This paper proposes a class-imbalance mitigation strategy that incorporates class-weights into the UDA learning losses, but with the novelty of estimating these weights dynamically through the loss gradient, defining a Gradient-based class weighting (GBW) learning. GBW naturally increases the contribution of classes whose learning is hindered by large-represented classes, and has the advantage of being able to automatically and quickly adapt to the iteration training outcomes, avoiding explicitly curricular learning patterns common in loss-weighing strategies. Extensive experimentation validates the effectiveness of GBW across architectures (convolutional and transformer), UDA strategies (adversarial, self-training and entropy minimization), tasks (semantic and panoptic segmentation), and datasets (GTA and Synthia). Analysing the source of advantage, GBW consistently increases the recall of low represented classes.
Authors: Jayneel Parekh, Quentin Bouniot, Pavlo Mozharovskyi, Alasdair Newson, Florence d'Alch\'e-Buc
Abstract: Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of concept representations to human communication. However, the visualization and understanding of the learnt unsupervised dictionary of concepts encounters major limitations, specially for large-scale images. We propose here a novel method that relies on mapping the concept features to the latent space of a pretrained generative model. The use of a generative model enables high quality visualization, and naturally lays out an intuitive and interactive procedure for better interpretation of the learnt concepts. Furthermore, leveraging pretrained generative models has the additional advantage of making the training of the system more efficient. We quantitatively ascertain the efficacy of our method in terms of accuracy of the interpretable prediction network, fidelity of reconstruction, as well as faithfulness and consistency of learnt concepts. The experiments are conducted on multiple image recognition benchmarks for large-scale images. Project page available at https://jayneelparekh.github.io/VisCoIN_project_page/
Authors: Kai Li
Abstract: Autonomous vehicles need to travel over 11 billion miles to ensure their safety. Therefore, the importance of simulation testing before real-world testing is self-evident. In recent years, the release of 3D simulators for autonomous driving, represented by Carla and CarSim, marks the transition of autonomous driving simulation testing environments from simple 2D overhead views to complex 3D models. During simulation testing, experimenters need to build static scenes and dynamic traffic flows, pedestrian flows, and other experimental elements to construct experimental scenarios. When building static scenes in 3D simulators, experimenters often need to manually construct 3D models, set parameters and attributes, which is time-consuming and labor-intensive. This thesis proposes an automated program generation framework. Based on deep reinforcement learning, this framework can generate different 2D ground script codes, on which 3D model files and map model files are built. The generated 3D ground scenes are displayed in the Carla simulator, where experimenters can use this scene for navigation algorithm simulation testing.
Authors: Pooya Fayyazsanavi, Antonios Anastasopoulos, Jana Ko\v{s}eck\'a
Abstract: Sign language translation from video to spoken text presents unique challenges owing to the distinct grammar, expression nuances, and high variation of visual appearance across different speakers and contexts. The intermediate gloss annotations of videos aim to guide the translation process. In our work, we focus on {\em Gloss2Text} translation stage and propose several advances by leveraging pre-trained large language models (LLMs), data augmentation, and novel label-smoothing loss function exploiting gloss translation ambiguities improving significantly the performance of state-of-the-art approaches. Through extensive experiments and ablation studies on the PHOENIX Weather 2014T dataset, our approach surpasses state-of-the-art performance in {\em Gloss2Text} translation, indicating its efficacy in addressing sign language translation and suggesting promising avenues for future research and development.
Authors: Caleb Koch, Carmen Strassle, Li-Yang Tan
Abstract: We consider the task of properly PAC learning decision trees with queries. Recent work of Koch, Strassle, and Tan showed that the strictest version of this task, where the hypothesis tree $T$ is required to be optimally small, is NP-hard. Their work leaves open the question of whether the task remains intractable if $T$ is only required to be close to optimal, say within a factor of 2, rather than exactly optimal. We answer this affirmatively and show that the task indeed remains NP-hard even if $T$ is allowed to be within any constant factor of optimal. More generally, our result allows for a smooth tradeoff between the hardness assumption and the inapproximability factor. As Koch et al.'s techniques do not appear to be amenable to such a strengthening, we first recover their result with a new and simpler proof, which we couple with a new XOR lemma for decision trees. While there is a large body of work on XOR lemmas for decision trees, our setting necessitates parameters that are extremely sharp, and are not known to be attainable by existing XOR lemmas. Our work also carries new implications for the related problem of Decision Tree Minimization.
Authors: Vitaly Bulgakov
Abstract: In this paper, we focus on methods to reduce the size and improve the quality of the prompt context required for question-answering systems. Attempts to increase the number of retrieved chunked documents and thereby enlarge the context related to the query can significantly complicate the processing and decrease the performance of a Large Language Model (LLM) when generating responses to queries. It is well known that a large set of documents retrieved from a database in response to a query may contain irrelevant information, which often leads to hallucinations in the resulting answers. Our goal is to select the most semantically relevant documents, treating the discarded ones as outliers. We propose and evaluate several methods for identifying outliers by creating features that utilize the distances of embedding vectors, retrieved from the vector database, to both the centroid and the query vectors. The methods were evaluated by comparing the similarities of the retrieved LLM responses to ground-truth answers obtained using the OpenAI GPT-4o model. It was found that the greatest improvements were achieved with increasing complexity of the questions and answers.
Authors: Maxwell Aladago, Lorenzo Torresani, Soroush Vosoughi
Abstract: In the field of vision-language contrastive learning, models such as CLIP capitalize on matched image-caption pairs as positive examples and leverage within-batch non-matching pairs as negatives. This approach has led to remarkable outcomes in zero-shot image classification, cross-modal retrieval, and linear evaluation tasks. We show that the zero-shot classification and retrieval capabilities of CLIP-like models can be improved significantly through the introduction of semantically composite examples during pretraining. Inspired by CutMix in vision categorization, we create semantically composite image-caption pairs by merging elements from two distinct instances in the dataset via a novel procedure. Our method fuses the captions and blends 50% of each image to form a new composite sample. This simple technique (termed CLIP-C for CLIP Compositions), devoid of any additional computational overhead or increase in model parameters, significantly improves zero-shot image classification and cross-modal retrieval. The benefits of CLIP-C are particularly pronounced in settings with relatively limited pretraining data.
Authors: Bo Ai, Stephen Tian, Haochen Shi, Yixuan Wang, Cheston Tan, Yunzhu Li, Jiajun Wu
Abstract: Tactile feedback is critical for understanding the dynamics of both rigid and deformable objects in many manipulation tasks, such as non-prehensile manipulation and dense packing. We introduce an approach that combines visual and tactile sensing for robotic manipulation by learning a neural, tactile-informed dynamics model. Our proposed framework, RoboPack, employs a recurrent graph neural network to estimate object states, including particles and object-level latent physics information, from historical visuo-tactile observations and to perform future state predictions. Our tactile-informed dynamics model, learned from real-world data, can solve downstream robotics tasks with model-predictive control. We demonstrate our approach on a real robot equipped with a compliant Soft-Bubble tactile sensor on non-prehensile manipulation and dense packing tasks, where the robot must infer the physics properties of objects from direct and indirect interactions. Trained on only an average of 30 minutes of real-world interaction data per task, our model can perform online adaptation and make touch-informed predictions. Through extensive evaluations in both long-horizon dynamics prediction and real-world manipulation, our method demonstrates superior effectiveness compared to previous learning-based and physics-based simulation systems.
Authors: Etienne Chollet, Ya\"el Balbastre, Chiara Mauri, Caroline Magnain, Bruce Fischl, Hui Wang
Abstract: Microvascular anatomy is known to be involved in various neurological disorders. However, understanding these disorders is hindered by the lack of imaging modalities capable of capturing the comprehensive three-dimensional vascular network structure at microscopic resolution. With a lateral resolution of $<=$20 {\textmu}m and ability to reconstruct large tissue blocks up to tens of cubic centimeters, serial-section optical coherence tomography (sOCT) is well suited for this task. This method uses intrinsic optical properties to visualize the vessels and therefore does not possess a specific contrast, which complicates the extraction of accurate vascular models. The performance of traditional vessel segmentation methods is heavily degraded in the presence of substantial noise and imaging artifacts and is sensitive to domain shifts, while convolutional neural networks (CNNs) require extensive labeled data and are also sensitive the precise intensity characteristics of the data that they are trained on. Building on the emerging field of synthesis-based training, this study demonstrates a synthesis engine for neurovascular segmentation in sOCT images. Characterized by minimal priors and high variance sampling, our highly generalizable method tested on five distinct sOCT acquisitions eliminates the need for manual annotations while attaining human-level precision. Our approach comprises two phases: label synthesis and label-to-image transformation. We demonstrate the efficacy of the former by comparing it to several more realistic sets of training labels, and the latter by an ablation study of synthetic noise and artifact models.
Authors: Normen Yu, Luciana Carreon, Gang Tan, Saeid Tizpaz-Niari
Abstract: Data-driven software solutions have significantly been used in critical domains with significant socio-economic, legal, and ethical implications. The rapid adoptions of data-driven solutions, however, pose major threats to the trustworthiness of automated decision-support software. A diminished understanding of the solution by the developer and historical/current biases in the data sets are primary challenges. To aid data-driven software developers and end-users, we present \toolname, a debugging tool to test and explain the fairness implications of data-driven solutions. \toolname visualizes the logic of datasets, trained models, and decisions for a given data point. In addition, it trains various models with varying fairness-accuracy trade-offs. Crucially, \toolname incorporates counterfactual fairness testing that finds bugs beyond the development datasets. We conducted two studies through \toolname that allowed us to measure false positives/negatives in prevalent counterfactual testing and understand the human perception of counterfactual test cases in a class survey. \toolname and its benchmarks are publicly available at~\url{https://github.com/Pennswood/FairLay-ML}. The live version of the tool is available at~\url{https://fairlayml-v2.streamlit.app/}. We provide a video demo of the tool at https://youtu.be/wNI9UWkywVU?t=127
URLs: https://github.com/Pennswood/FairLay-ML, https://fairlayml-v2.streamlit.app/, https://youtu.be/wNI9UWkywVU?t=127
Authors: Jeffrey Fairbanks
Abstract: Phishing is one of the main points of compromise, with email security and awareness being estimated at \$50-100B in 2022. There is great need for email forensics capability to quickly search for malicious content. A novel solution POST is proposed. POST is an API driven serverless email archival, processing, and flagging workflow for both large and small organizations that collects and parses all email, flags emails using state of the art Natural Language Processing and Machine Learning, allows full email searching on every aspect of an email, and provides a cost savings of up to 68.6%.
Authors: Subhajit Chaudhury, Soham Dan, Payel Das, Georgios Kollias, Elliot Nelson
Abstract: In this paper, we demonstrate the benefits of using memory augmented Large Language Model (LLM) architecture in improving the recall abilities of facts from a potentially long context. As a case study we test LARIMAR, a recently proposed LLM architecture which augments a LLM decoder with an external associative memory, on several long-context recall tasks, including passkey and needle-in-the-haystack tests. We demonstrate that the external memory can be adapted at test time to handle contexts much longer than those seen during training, while keeping readouts from the memory recognizable to the trained decoder and without increasing GPU memory footprint. Compared to alternative architectures for long-context recall tasks with models of a comparable parameter count, LARIMAR is able to maintain strong performance without any task-specific training.
Authors: Ebby Samson, Naveen Mellempudi, Wayne Luk, George A. Constantinides
Abstract: A number of companies recently worked together to release the new Open Compute Project MX standard for low-precision computation, aimed at efficient neural network implementation. In this paper, we describe and evaluate the first open-source FPGA implementation of the arithmetic defined in the standard. Our designs fully support all the standard's concrete formats for conversion into and out of MX formats and for the standard-defined arithmetic operations, as well as arbitrary fixed-point and floating-point formats. Certain elements of the standard are left as implementation-defined, and we present the first concrete FPGA-inspired choices for these elements, which we outline in the paper. Our library of optimized hardware components is available open source, and can be used to build larger systems. For this purpose, we also describe and release an open-source Pytorch library for quantization into the new standard, integrated with the Brevitas library so that the community can develop novel neural network designs quantized with MX formats in mind. We demonstrate the usability and efficacy of our libraries via the implementation of example neural networks such as ResNet-18 on the ImageNet ILSVRC12 dataset. Our testing shows that MX is very effective for formats such as INT5 or FP6 which are not natively supported on GPUs. This gives FPGAs an advantage as they have the flexibility to implement a custom datapath and take advantage of the smaller area footprints offered by these formats.
Authors: Jing Yu Koh, Stephen McAleer, Daniel Fried, Ruslan Salakhutdinov
Abstract: Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a key limitation remains: LMs, primarily optimized for natural language understanding and generation, struggle with multi-step reasoning, planning, and using environmental feedback when attempting to solve realistic computer tasks. Towards addressing this, we propose an inference-time search algorithm for LM agents to explicitly perform exploration and multi-step planning in interactive web environments. Our approach is a form of best-first tree search that operates within the actual environment space, and is complementary with most existing state-of-the-art agents. It is the first tree search algorithm for LM agents that shows effectiveness on realistic web tasks. On the challenging VisualWebArena benchmark, applying our search algorithm on top of a GPT-4o agent yields a 39.7% relative increase in success rate compared to the same baseline without search, setting a state-of-the-art success rate of 26.4%. On WebArena, search also yields a 28.0% relative improvement over a baseline agent, setting a competitive success rate of 19.2%. Our experiments highlight the effectiveness of search for web agents, and we demonstrate that performance scales with increased test-time compute. We conduct a thorough analysis of our results to highlight improvements from search, limitations, and promising directions for future work. Our code and models are publicly released at https://jykoh.com/search-agents.
Authors: Chunqiu Steven Xia, Yinlin Deng, Soren Dunn, Lingming Zhang
Abstract: Recent advancements in large language models (LLMs) have significantly advanced the automation of software development tasks, including code synthesis, program repair, and test generation. More recently, researchers and industry practitioners have developed various autonomous LLM agents to perform end-to-end software development tasks. These agents are equipped with the ability to use tools, run commands, observe feedback from the environment, and plan for future actions. However, the complexity of these agent-based approaches, together with the limited abilities of current LLMs, raises the following question: Do we really have to employ complex autonomous software agents? To attempt to answer this question, we build Agentless -- an agentless approach to automatically solve software development problems. Compared to the verbose and complex setup of agent-based approaches, Agentless employs a simplistic two-phase process of localization followed by repair, without letting the LLM decide future actions or operate with complex tools. Our results on the popular SWE-bench Lite benchmark show that surprisingly the simplistic Agentless is able to achieve both the highest performance (27.33%) and lowest cost (\$0.34) compared with all existing open-source software agents! Furthermore, we manually classified the problems in SWE-bench Lite and found problems with exact ground truth patch or insufficient/misleading issue descriptions. As such, we construct SWE-bench Lite-S by excluding such problematic issues to perform more rigorous evaluation and comparison. Our work highlights the current overlooked potential of a simple, interpretable technique in autonomous software development. We hope Agentless will help reset the baseline, starting point, and horizon for autonomous software agents, and inspire future work along this crucial direction.
Authors: Lu\'isa Shimabucoro, Sebastian Ruder, Julia Kreutzer, Marzieh Fadaee, Sara Hooker
Abstract: The widespread adoption of synthetic data raises new questions about how models generating the data can influence other large language models (LLMs) via distilled data. To start, our work exhaustively characterizes the impact of passive inheritance of model properties by systematically studying the consequences of synthetic data integration. We provide one of the most comprehensive studies to-date of how the source of synthetic data shapes models' internal biases, calibration and generations' textual attributes and preferences. We find that models are surprisingly sensitive towards certain attributes even when the synthetic data prompts appear "neutral". which invites the question whether this sensitivity can be exploited for good. Our findings invite the question can we explicitly steer the models towards the properties we want at test time by exploiting the data generation process? This would have historically been considered infeasible due to the cost of collecting data with a specific characteristic or objective in mind. However, improvement in the quality of synthetic data, as well as a shift towards general-purpose models designed to follow a diverse way of instructions, means this question is timely. We propose active inheritance as a term to describe intentionally constraining synthetic data according to a non-differentiable objective. We demonstrate how active inheritance can steer the generation profiles of models towards desirable non-differentiable attributes, e.g. high lexical diversity or low toxicity.
Authors: Zhiqiang Cai, Anastassia Doktorova, Robert D. Falgout, C\'esar Herrera
Abstract: This paper expands the damped block Newton (dBN) method introduced recently in [4] for 1D diffusion-reaction equations and least-squares data fitting problems. To determine the linear parameters (the weights and bias of the output layer) of the neural network (NN), the dBN method requires solving systems of linear equations involving the mass matrix. While the mass matrix for local hat basis functions is tri-diagonal and well-conditioned, the mass matrix for NNs is dense and ill-conditioned. For example, the condition number of the NN mass matrix for quasi-uniform meshes is at least ${\cal O}(n^4)$. We present a factorization of the mass matrix that enables solving the systems of linear equations in ${\cal O}(n)$ operations. To determine the non-linear parameters (the weights and bias of the hidden layer), one step of a damped Newton method is employed at each iteration. A Gauss-Newton method is used in place of Newton for the instances in which the Hessian matrices are singular. This modified dBN is referred to as dBGN. For both methods, the computational cost per iteration is ${\cal O}(n)$. Numerical results demonstrate the ability dBN and dBGN to efficiently achieve accurate results and outperform BFGS for select examples.
Authors: Scott H. Hawley
Abstract: Recent years have witnessed significant progress in generative models for music, featuring diverse architectures that balance output quality, diversity, speed, and user control. This study explores a user-friendly graphical interface enabling the drawing of masked regions for inpainting by an Hourglass Diffusion Transformer (HDiT) model trained on MIDI piano roll images. To enhance note generation in specified areas, masked regions can be "repainted" with extra noise. The non-latent HDiTs linear scaling with pixel count allows efficient generation in pixel space, providing intuitive and interpretable controls such as masking throughout the network and removing the need to operate in compressed latent spaces such as those provided by pretrained autoencoders. We demonstrate that, in addition to inpainting of melodies, accompaniment, and continuations, the use of repainting can help increase note density yielding musical structures closely matching user specifications such as rising, falling, or diverging melody and/or accompaniment, even when these lie outside the typical training data distribution. We achieve performance on par with prior results while operating at longer context windows, with no autoencoder, and can enable complex geometries for inpainting masks, increasing the options for machine-assisted composers to control the generated music.
Authors: John Payne, Aishwaryaprajna, Peter R. Lewis
Abstract: The sustainable foraging problem is a dynamic environment testbed for exploring the forms of agent cognition in dealing with social dilemmas in a multi-agent setting. The agents need to resist the temptation of individual rewards through foraging and choose the collective long-term goal of sustainability. We investigate methods of online learning in Neuro-Evolution and Deep Recurrent Q-Networks to enable agents to attempt the problem one-shot as is often required by wicked social problems. We further explore if learning temporal dependencies with Long Short-Term Memory may be able to aid the agents in developing sustainable foraging strategies in the long term. It was found that the integration of Long Short-Term Memory assisted agents in developing sustainable strategies for a single agent, however failed to assist agents in managing the social dilemma that arises in the multi-agent scenario.
Authors: Xuxin Cheng, Jialong Li, Shiqi Yang, Ge Yang, Xiaolong Wang
Abstract: Teleoperation serves as a powerful method for collecting on-robot data essential for robot learning from demonstrations. The intuitiveness and ease of use of the teleoperation system are crucial for ensuring high-quality, diverse, and scalable data. To achieve this, we propose an immersive teleoperation system Open-TeleVision that allows operators to actively perceive the robot's surroundings in a stereoscopic manner. Additionally, the system mirrors the operator's arm and hand movements on the robot, creating an immersive experience as if the operator's mind is transmitted to a robot embodiment. We validate the effectiveness of our system by collecting data and training imitation learning policies on four long-horizon, precise tasks (Can Sorting, Can Insertion, Folding, and Unloading) for 2 different humanoid robots and deploy them in the real world. The system is open-sourced at: https://robot-tv.github.io/
Authors: Pengcheng Shi, Jiesi Hu, Yanwu Yang, Zilve Gao, Wei Liu, Ting Ma
Abstract: Vascular segmentation in medical imaging plays a crucial role in analysing morphological and functional assessments. Traditional methods, like the centerline Dice (clDice) loss, ensure topology preservation but falter in capturing geometric details, especially under translation and deformation. The combination of clDice with traditional Dice loss can lead to diameter imbalance, favoring larger vessels. Addressing these challenges, we introduce the centerline boundary Dice (cbDice) loss function, which harmonizes topological integrity and geometric nuances, ensuring consistent segmentation across various vessel sizes. cbDice enriches the clDice approach by including boundary-aware aspects, thereby improving geometric detail recognition. It matches the performance of the boundary difference over union (B-DoU) loss through a mask-distance-based approach, enhancing traslation sensitivity. Crucially, cbDice incorporates radius information from vascular skeletons, enabling uniform adaptation to vascular diameter changes and maintaining balance in branch growth and fracture impacts. Furthermore, we conducted a theoretical analysis of clDice variants (cl-X-Dice). We validated cbDice's efficacy on three diverse vascular segmentation datasets, encompassing both 2D and 3D, and binary and multi-class segmentation. Particularly, the method integrated with cbDice demonstrated outstanding performance on the MICCAI 2023 TopCoW Challenge dataset. Our code is made publicly available at: https://github.com/PengchengShi1220/cbDice.
Authors: Hao Dong, Eleni Chatzi, Olga Fink
Abstract: The task of open-set domain generalization (OSDG) involves recognizing novel classes within unseen domains, which becomes more challenging with multiple modalities as input. Existing works have only addressed unimodal OSDG within the meta-learning framework, without considering multimodal scenarios. In this work, we introduce a novel approach to address Multimodal Open-Set Domain Generalization (MM-OSDG) for the first time, utilizing self-supervision. To this end, we introduce two innovative multimodal self-supervised pretext tasks: Masked Cross-modal Translation and Multimodal Jigsaw Puzzles. These tasks facilitate the learning of multimodal representative features, thereby enhancing generalization and open-class detection capabilities. Additionally, we propose a novel entropy weighting mechanism to balance the loss across different modalities. Furthermore, we extend our approach to tackle also the Multimodal Open-Set Domain Adaptation (MM-OSDA) problem, especially in scenarios where unlabeled data from the target domain is available. Extensive experiments conducted under MM-OSDG, MM-OSDA, and Multimodal Closed-Set DG settings on the EPIC-Kitchens and HAC datasets demonstrate the efficacy and versatility of the proposed approach. Our source code is available at https://github.com/donghao51/MOOSA.
Authors: Luke Koch, Sean Oesch, Amul Chaulagain, Jared Dixon, Matthew Dixon, Mike Huettal, Amir Sadovnik, Cory Watson, Brian Weber, Jacob Hartman, Richard Patulski
Abstract: A polyglot is a file that is valid in two or more formats. Polyglot files pose a problem for malware detection systems that route files to format-specific detectors/signatures, as well as file upload and sanitization tools. In this work we found that existing file-format and embedded-file detection tools, even those developed specifically for polyglot files, fail to reliably detect polyglot files used in the wild, leaving organizations vulnerable to attack. To address this issue, we studied the use of polyglot files by malicious actors in the wild, finding $30$ polyglot samples and $15$ attack chains that leveraged polyglot files. In this report, we highlight two well-known APTs whose cyber attack chains relied on polyglot files to bypass detection mechanisms. Using knowledge from our survey of polyglot usage in the wild -- the first of its kind -- we created a novel data set based on adversary techniques. We then trained a machine learning detection solution, PolyConv, using this data set. PolyConv achieves a precision-recall area-under-curve score of $0.999$ with an F1 score of $99.20$% for polyglot detection and $99.47$% for file-format identification, significantly outperforming all other tools tested. We developed a content disarmament and reconstruction tool, ImSan, that successfully sanitized $100$% of the tested image-based polyglots, which were the most common type found via the survey. Our work provides concrete tools and suggestions to enable defenders to better defend themselves against polyglot files, as well as directions for future work to create more robust file specifications and methods of disarmament.
Authors: Yixiao Wang, Yifei Zhang, Mingxiao Huo, Ran Tian, Xiang Zhang, Yichen Xie, Chenfeng Xu, Pengliang Ji, Wei Zhan, Mingyu Ding, Masayoshi Tomizuka
Abstract: The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and catastrophic forgetting when learning new tasks. To address these issues, we introduce a sparse, reusable, and flexible policy, Sparse Diffusion Policy (SDP). By adopting Mixture of Experts (MoE) within a transformer-based diffusion policy, SDP selectively activates experts and skills, enabling efficient and task-specific learning without retraining the entire model. SDP not only reduces the burden of active parameters but also facilitates the seamless integration and reuse of experts across various tasks. Extensive experiments on diverse tasks in both simulations and real world show that SDP 1) excels in multitask scenarios with negligible increases in active parameters, 2) prevents forgetting in continual learning of new tasks, and 3) enables efficient task transfer, offering a promising solution for advanced robotic applications. Demos and codes can be found in https://forrest-110.github.io/sparse_diffusion_policy/.
URLs: https://forrest-110.github.io/sparse_diffusion_policy/.
Authors: Roberto Esposito, Mattia Cerrato, Marco Locatelli
Abstract: In this paper we propose a variant of the linear least squares model allowing practitioners to partition the input features into groups of variables that they require to contribute similarly to the final result. The output allows practitioners to assess the importance of each group and of each variable in the group. We formally show that the new formulation is not convex and provide two alternative methods to deal with the problem: one non-exact method based on an alternating least squares approach; and one exact method based on a reformulation of the problem using an exponential number of sub-problems whose minimum is guaranteed to be the optimal solution. We formally show the correctness of the exact method and also compare the two solutions showing that the exact solution provides better results in a fraction of the time required by the alternating least squares solution (assuming that the number of partitions is small). For the sake of completeness, we also provide an alternative branch and bound algorithm that can be used in place of the exact method when the number of partitions is too large, and a proof of NP-completeness of the optimization problem introduced in this paper.
Authors: Tianfan Fu, Cao Xiao, Xinhao Li, Lucas M. Glass, Jimeng Sun
Abstract: Molecule optimization is a fundamental task for accelerating drug discovery, with the goal of generating new valid molecules that maximize multiple drug properties while maintaining similarity to the input molecule. Existing generative models and reinforcement learning approaches made initial success, but still face difficulties in simultaneously optimizing multiple drug properties. To address such challenges, we propose the MultI-constraint MOlecule SAmpling (MIMOSA) approach, a sampling framework to use input molecule as an initial guess and sample molecules from the target distribution. MIMOSA first pretrains two property agnostic graph neural networks (GNNs) for molecule topology and substructure-type prediction, where a substructure can be either atom or single ring. For each iteration, MIMOSA uses the GNNs' prediction and employs three basic substructure operations (add, replace, delete) to generate new molecules and associated weights. The weights can encode multiple constraints including similarity and drug property constraints, upon which we select promising molecules for next iteration. MIMOSA enables flexible encoding of multiple property- and similarity-constraints and can efficiently generate new molecules that satisfy various property constraints and achieved up to 49.6% relative improvement over the best baseline in terms of success rate. The code repository (including readme file, data preprocessing and model construction, evaluation) is available https://github.com/futianfan/MIMOSA.
Authors: Christian Raymond, Qi Chen, Bing Xue, Mengjie Zhang
Abstract: In this paper, we develop upon the emerging topic of loss function learning, which aims to learn loss functions that significantly improve the performance of the models trained under them. Specifically, we propose a new meta-learning framework for learning model-agnostic loss functions via a hybrid neuro-symbolic search approach. The framework first uses evolution-based methods to search the space of primitive mathematical operations to find a set of symbolic loss functions. Second, the set of learned loss functions are subsequently parameterized and optimized via an end-to-end gradient-based training procedure. The versatility of the proposed framework is empirically validated on a diverse set of supervised learning tasks. Results show that the meta-learned loss functions discovered by the newly proposed method outperform both the cross-entropy loss and state-of-the-art loss function learning methods on a diverse range of neural network architectures and datasets.
Authors: Aditya Gangrade, Tianrui Chen, Venkatesh Saligrama
Abstract: The safe linear bandit problem (SLB) is an online approach to linear programming with unknown objective and unknown roundwise constraints, under stochastic bandit feedback of rewards and safety risks of actions. We study the tradeoffs between efficacy and smooth safety costs of SLBs over polytopes, and the role of aggressive doubly-optimistic play in avoiding the strong assumptions made by extant pessimistic-optimistic approaches. We first elucidate an inherent hardness in SLBs due the lack of knowledge of constraints: there exist `easy' instances, for which suboptimal extreme points have large `gaps', but on which SLB methods must still incur $\Omega(\sqrt{T})$ regret or safety violations, due to an inability to resolve unknown optima to arbitrary precision. We then analyse a natural doubly-optimistic strategy for the safe linear bandit problem, DOSS, which uses optimistic estimates of both reward and safety risks to select actions, and show that despite the lack of knowledge of constraints or feasible points, DOSS simultaneously obtains tight instance-dependent $O(\log^2 T)$ bounds on efficacy regret, and $\tilde O(\sqrt{T})$ bounds on safety violations. Further, when safety is demanded to a finite precision, violations improve to $O(\log^2 T).$ These results rely on a novel dual analysis of linear bandits: we argue that \algoname proceeds by activating noisy versions of at least $d$ constraints in each round, which allows us to separately analyse rounds where a `poor' set of constraints is activated, and rounds where `good' sets of constraints are activated. The costs in the former are controlled to $O(\log^2 T)$ by developing new dual notions of gaps, based on global sensitivity analyses of linear programs, that quantify the suboptimality of each such set of constraints. The latter costs are controlled to $O(1)$ by explicitly analysing the solutions of optimistic play.
Authors: Abhishek Dey, Debayan Goswami, Rahul Roy, Susmita Ghosh, Yu Shrike Zhang, Jonathan H. Chan
Abstract: Purpose: Health recommenders act as important decision support systems, aiding patients and medical professionals in taking actions that lead to patients' well-being. These systems extract the information which may be of particular relevance to the end-user, helping them in making appropriate decisions. The present study proposes a feature recommender, as a part of a disease management system, that identifies and recommends the most important risk factors for an illness. Methods: A novel mutual information and ensemble-based feature ranking approach for identifying critical risk factors in healthcare prognosis is proposed. Results: To establish the effectiveness of the proposed method, experiments have been conducted on four benchmark datasets of diverse diseases (clear cell renal cell carcinoma (ccRCC), chronic kidney disease, Indian liver patient, and cervical cancer risk factors). The performance of the proposed recommender is compared with four state-of-the-art methods using recommender systems' performance metrics like average precision@K, precision@K, recall@K, F1@K, reciprocal rank@K. The method is able to recommend all relevant critical risk factors for ccRCC. It also attains a higher accuracy (96.6% and 98.6% using support vector machine and neural network, respectively) for ccRCC staging with a reduced feature set as compared to existing methods. Moreover, the top two features recommended using the proposed method with ccRCC, viz. size of tumor and metastasis status, are medically validated from the existing TNM system. Results are also found to be superior for the other three datasets. Conclusion: The proposed recommender can identify and recommend risk factors that have the most discriminating power for detecting diseases.
Authors: Antonio Longa, Steve Azzolin, Gabriele Santin, Giulia Cencetti, Pietro Li\`o, Bruno Lepri, Andrea Passerini
Abstract: Following a fast initial breakthrough in graph based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting the need for methods to understand their decision process. GNN explainers have started to emerge in recent years, with a multitude of methods both novel or adapted from other domains. To sort out this plethora of alternative approaches, several studies have benchmarked the performance of different explainers in terms of various explainability metrics. However, these earlier works make no attempts at providing insights into why different GNN architectures are more or less explainable, or which explainer should be preferred in a given setting. In this survey, we fill these gaps by devising a systematic experimental study, which tests ten explainers on eight representative architectures trained on six carefully designed graph and node classification datasets. With our results we provide key insights on the choice and applicability of GNN explainers, we isolate key components that make them usable and successful and provide recommendations on how to avoid common interpretation pitfalls. We conclude by highlighting open questions and directions of possible future research.
Authors: Aleksandrs Slivkins, Xingyu Zhou, Karthik Abinav Sankararaman, Dylan J. Foster
Abstract: We consider contextual bandits with linear constraints (CBwLC), a variant of contextual bandits in which the algorithm consumes multiple resources subject to linear constraints on total consumption. This problem generalizes contextual bandits with knapsacks (CBwK), allowing for packing and covering constraints, as well as positive and negative resource consumption. We provide the first algorithm for CBwLC (or CBwK) that is based on regression oracles. The algorithm is simple, computationally efficient, and statistically optimal under mild assumptions. Further, we provide the first vanishing-regret guarantees for CBwLC (or CBwK) that extend beyond the stochastic environment. We side-step strong impossibility results from prior work by identifying a weaker (and, arguably, fairer) benchmark to compare against. Our algorithm builds on LagrangeBwK (Immorlica et al., FOCS 2019), a Lagrangian-based technique for CBwK, and SquareCB (Foster and Rakhlin, ICML 2020), a regression-based technique for contextual bandits. Our analysis leverages the inherent modularity of both techniques.
Authors: Andreas Lohrer, Daniyal Kazempour, Maximilian H\"unem\"order, Peer Kr\"oger
Abstract: Unsupervised learning methods are well established in the area of anomaly detection and achieve state of the art performances on outlier datasets. Outliers play a significant role, since they bear the potential to distort the predictions of a machine learning algorithm on a given dataset. Especially among PCA-based methods, outliers have an additional destructive potential regarding the result: they may not only distort the orientation and translation of the principal components, they also make it more complicated to detect outliers. To address this problem, we propose the robust outlier detection algorithm CoMadOut, which satisfies two required properties: (1) being robust towards outliers and (2) detecting them. Our CoMadOut outlier detection variants using comedian PCA define, dependent on its variant, an inlier region with a robust noise margin by measures of in-distribution (variant CMO) and optimized scores by measures of out-of-distribution (variants CMO*), e.g. kurtosis-weighting by CMO+k. These measures allow distribution based outlier scoring for each principal component, and thus, an appropriate alignment of the degree of outlierness between normal and abnormal instances. Experiments comparing CoMadOut with traditional, deep and other comparable robust outlier detection methods showed that the performance of the introduced CoMadOut approach is competitive to well established methods related to average precision (AP), area under the precision recall curve (AUPRC) and area under the receiver operating characteristic (AUROC) curve. In summary our approach can be seen as a robust alternative for outlier detection tasks.
Authors: Han Wang, Aritra Mitra, Hamed Hassani, George J. Pappas, James Anderson
Abstract: We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem. Our setup involves $N$ agents interacting with environments that share the same state and action space but differ in their reward functions and state transition kernels. Assuming agents can communicate via a central server, we ask: Does exchanging information expedite the process of evaluating a common policy? To answer this question, we provide the first comprehensive finite-time analysis of a federated temporal difference (TD) learning algorithm with linear function approximation, while accounting for Markovian sampling, heterogeneity in the agents' environments, and multiple local updates to save communication. Our analysis crucially relies on several novel ingredients: (i) deriving perturbation bounds on TD fixed points as a function of the heterogeneity in the agents' underlying Markov decision processes (MDPs); (ii) introducing a virtual MDP to closely approximate the dynamics of the federated TD algorithm; and (iii) using the virtual MDP to make explicit connections to federated optimization. Putting these pieces together, we rigorously prove that in a low-heterogeneity regime, exchanging model estimates leads to linear convergence speedups in the number of agents.
Authors: Junfu Wang, Yuanfang Guo, Liang Yang, Yunhong Wang
Abstract: Graph Neural Networks (GNNs) have shown remarkable success in graph representation learning. Unfortunately, current weight assignment schemes in standard GNNs, such as the calculation based on node degrees or pair-wise representations, can hardly be effective in processing the networks with heterophily, in which the connected nodes usually possess different labels or features. Existing heterophilic GNNs tend to ignore the modeling of heterophily of each edge, which is also a vital part in tackling the heterophily problem. In this paper, we firstly propose a heterophily-aware attention scheme and reveal the benefits of modeling the edge heterophily, i.e., if a GNN assigns different weights to edges according to different heterophilic types, it can learn effective local attention patterns, which enable nodes to acquire appropriate information from distinct neighbors. Then, we propose a novel Heterophily-Aware Graph Attention Network (HA-GAT) by fully exploring and utilizing the local distribution as the underlying heterophily, to handle the networks with different homophily ratios. To demonstrate the effectiveness of the proposed HA-GAT, we analyze the proposed heterophily-aware attention scheme and local distribution exploration, by seeking for an interpretation from their mechanism. Extensive results demonstrate that our HA-GAT achieves state-of-the-art performances on eight datasets with different homophily ratios in both the supervised and semi-supervised node classification tasks.
Authors: Shangxi Wu, Qiuyang He, Jian Yu, Jitao Sang
Abstract: With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing methods face challenges such as poor utilization of data or intricate training requirements. In this work, we found that the backdoor attack can construct an artificial bias similar to the model bias derived in standard training. Considering the strong adjustability of backdoor triggers, we are motivated to mitigate the model bias by carefully designing reverse artificial bias created from backdoor attack. Based on this, we propose a backdoor debiasing framework based on knowledge distillation, which effectively reduces the model bias from original data and minimizes security risks from the backdoor attack. The proposed solution is validated on both image and structured datasets, showing promising results. This work advances the understanding of backdoor attacks and highlights its potential for beneficial applications. The code for the study can be found at \url{https://anonymous.4open.science/r/DwB-BC07/}.
Authors: Elif Ceren Gok Yildirim, Murat Onur Yildirim, Mert Kilickaya, Joaquin Vanschoren
Abstract: Class-Incremental Learning aims to update a deep classifier to learn new categories while maintaining or improving its accuracy on previously observed classes. Common methods to prevent forgetting previously learned classes include regularizing the neural network updates and storing exemplars in memory, which come with hyperparameters such as the learning rate, regularization strength, or the number of exemplars. However, these hyperparameters are usually only tuned at the start and then kept fixed throughout the learning sessions, ignoring the fact that newly encountered tasks may have varying levels of novelty or difficulty. This study investigates the necessity of hyperparameter `adaptivity' in Class-Incremental Learning: the ability to dynamically adjust hyperparameters such as the learning rate, regularization strength, and memory size according to the properties of the new task at hand. We propose AdaCL, a Bayesian Optimization-based approach to automatically and efficiently determine the optimal values for those parameters with each learning task. We show that adapting hyperpararmeters on each new task leads to improvement in accuracy, forgetting and memory. Code is available at https://github.com/ElifCerenGokYildirim/AdaCL.
Authors: Robert J. Moss, Mykel J. Kochenderfer, Maxime Gariel, Arthur Dubois
Abstract: Estimating the probability of failure is an important step in the certification of safety-critical systems. Efficient estimation methods are often needed due to the challenges posed by high-dimensional input spaces, risky test scenarios, and computationally expensive simulators. This work frames the problem of black-box safety validation as a Bayesian optimization problem and introduces a method that iteratively fits a probabilistic surrogate model to efficiently predict failures. The algorithm is designed to search for failures, compute the most-likely failure, and estimate the failure probability over an operating domain using importance sampling. We introduce three acquisition functions that aim to reduce uncertainty by covering the design space, optimize the analytically derived failure boundaries, and sample the predicted failure regions. Results show this Bayesian safety validation approach provides a more accurate estimate of failure probability with orders of magnitude fewer samples and performs well across various safety validation metrics. We demonstrate this approach on three test problems, a stochastic decision making system, and a neural network-based runway detection system. This work is open sourced (https://github.com/sisl/BayesianSafetyValidation.jl) and currently being used to supplement the FAA certification process of the machine learning components for an autonomous cargo aircraft.
Authors: Dongyoung Kim, Jinwoo Shin, Pieter Abbeel, Younggyo Seo
Abstract: A promising technique for exploration is to maximize the entropy of visited state distribution, i.e., state entropy, by encouraging uniform coverage of visited state space. While it has been effective for an unsupervised setup, it tends to struggle in a supervised setup with a task reward, where an agent prefers to visit high-value states to exploit the task reward. Such a preference can cause an imbalance between the distributions of high-value states and low-value states, which biases exploration towards low-value state regions as a result of the state entropy increasing when the distribution becomes more uniform. This issue is exacerbated when high-value states are narrowly distributed within the state space, making it difficult for the agent to complete the tasks. In this paper, we present a novel exploration technique that maximizes the value-conditional state entropy, which separately estimates the state entropies that are conditioned on the value estimates of each state, then maximizes their average. By only considering the visited states with similar value estimates for computing the intrinsic bonus, our method prevents the distribution of low-value states from affecting exploration around high-value states, and vice versa. We demonstrate that the proposed alternative to the state entropy baseline significantly accelerates various reinforcement learning algorithms across a variety of tasks within MiniGrid, DeepMind Control Suite, and Meta-World benchmarks. Source code is available at https://sites.google.com/view/rl-vcse.
Authors: Sameer Ambekar, Zehao Xiao, Jiayi Shen, Xiantong Zhen, Cees G. M. Snoek
Abstract: This paper strives for domain generalization, where models are trained exclusively on source domains before being deployed on unseen target domains. We follow the strict separation of source training and target testing, but exploit the value of the unlabeled target data itself during inference. We make three contributions. First, we propose probabilistic pseudo-labeling of target samples to generalize the source-trained model to the target domain at test time. We formulate the generalization at test time as a variational inference problem, by modeling pseudo labels as distributions, to consider the uncertainty during generalization and alleviate the misleading signal of inaccurate pseudo labels. Second, we learn variational neighbor labels that incorporate the information of neighboring target samples to generate more robust pseudo labels. Third, to learn the ability to incorporate more representative target information and generate more precise and robust variational neighbor labels, we introduce a meta-generalization stage during training to simulate the generalization procedure. Experiments on seven widely-used datasets demonstrate the benefits, abilities, and effectiveness of our proposal.
Authors: Kevin Scaman, Mathieu Even, Batiste Le Bars, Laurent Massouli\'e
Abstract: In this paper, our aim is to analyse the generalization capabilities of first-order methods for statistical learning in multiple, different yet related, scenarios including supervised learning, transfer learning, robust learning and federated learning. To do so, we provide sharp upper and lower bounds for the minimax excess risk of strongly convex and smooth statistical learning when the gradient is accessed through partial observations given by a data-dependent oracle. This novel class of oracles can query the gradient with any given data distribution, and is thus well suited to scenarios in which the training data distribution does not match the target (or test) distribution. In particular, our upper and lower bounds are proportional to the smallest mean square error achievable by gradient estimators, thus allowing us to easily derive multiple sharp bounds in the aforementioned scenarios using the extensive literature on parameter estimation.
Authors: Chaoyu Liu, Zhonghua Qiao, Chao Li, Carola-Bibiane Sch\"onlieb
Abstract: Traditional image processing methods employing partial differential equations (PDEs) offer a multitude of meaningful regularizers, along with valuable theoretical foundations for a wide range of image-related tasks. This makes their integration into neural networks a promising avenue. In this paper, we introduce a novel regularization approach inspired by the reverse process of PDE-based evolution models. Specifically, we propose inverse evolution layers (IELs), which serve as bad property amplifiers to penalize neural networks of which outputs have undesired characteristics. Using IELs, one can achieve specific regularization objectives and endow neural networks' outputs with corresponding properties of the PDE models. Our experiments, focusing on semantic segmentation tasks using heat-diffusion IELs, demonstrate their effectiveness in mitigating noisy label effects. Additionally, we develop curve-motion IELs to enforce convex shape regularization in neural network-based segmentation models for preventing the generation of concave outputs. Theoretical analysis confirms the efficacy of IELs as an effective regularization mechanism, particularly in handling training with label issues.
Authors: Shengli Jiang, Shiyi Qin, Reid C. Van Lehn, Prasanna Balaprakash, Victor M. Zavala
Abstract: Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This capability is crucial for ensuring the trustworthy use and deployment of models in downstream tasks. To that end, we introduce AutoGNNUQ, an automated uncertainty quantification (UQ) approach for molecular property prediction. AutoGNNUQ leverages architecture search to generate an ensemble of high-performing GNNs, enabling the estimation of predictive uncertainties. Our approach employs variance decomposition to separate data (aleatoric) and model (epistemic) uncertainties, providing valuable insights for reducing them. In our computational experiments, we demonstrate that AutoGNNUQ outperforms existing UQ methods in terms of both prediction accuracy and UQ performance on multiple benchmark datasets. Additionally, we utilize t-SNE visualization to explore correlations between molecular features and uncertainty, offering insight for dataset improvement. AutoGNNUQ has broad applicability in domains such as drug discovery and materials science, where accurate uncertainty quantification is crucial for decision-making.
Authors: Xueying Ding, Yue Zhao, Leman Akoglu
Abstract: Outlier detection (OD) finds many applications with a rich literature of numerous techniques. Deep neural network based OD (DOD) has seen a recent surge of attention thanks to the many advances in deep learning. In this paper, we consider a critical-yet-understudied challenge with unsupervised DOD, that is, effective hyperparameter (HP) tuning/model selection. While several prior work report the sensitivity of OD models to HPs, it becomes ever so critical for the modern DOD models that exhibit a long list of HPs. We introduce HYPER for tuning DOD models, tackling two fundamental challenges: (1) validation without supervision (due to lack of labeled anomalies), and (2) efficient search of the HP/model space (due to exponential growth in the number of HPs). A key idea is to design and train a novel hypernetwork (HN) that maps HPs onto optimal weights of the main DOD model. In turn, HYPER capitalizes on a single HN that can dynamically generate weights for many DOD models (corresponding to varying HPs), which offers significant speed-up. In addition, it employs meta-learning on historical OD tasks with labels to train a proxy validation function, likewise trained with our proposed HN efficiently. Extensive experiments on 35 OD tasks show that HYPER achieves high performance against 8 baselines with significant efficiency gains.
Authors: Camillo Maria Caruso, Valerio Guarrasi, Sara Ramella, Paolo Soda
Abstract: In the field of lung cancer research, particularly in the analysis of overall survival (OS), artificial intelligence (AI) serves crucial roles with specific aims. Given the prevalent issue of missing data in the medical domain, our primary objective is to develop an AI model capable of dynamically handling this missing data. Additionally, we aim to leverage all accessible data, effectively analyzing both uncensored patients who have experienced the event of interest and censored patients who have not, by embedding a specialized technique within our AI model, not commonly utilized in other AI tasks. Through the realization of these objectives, our model aims to provide precise OS predictions for non-small cell lung cancer (NSCLC) patients, thus overcoming these significant challenges. We present a novel approach to survival analysis with missing values in the context of NSCLC, which exploits the strengths of the transformer architecture to account only for available features without requiring any imputation strategy. More specifically, this model tailors the transformer architecture to tabular data by adapting its feature embedding and masked self-attention to mask missing data and fully exploit the available ones. By making use of ad-hoc designed losses for OS, it is able to account for both censored and uncensored patients, as well as changes in risks over time. We compared our method with state-of-the-art models for survival analysis coupled with different imputation strategies. We evaluated the results obtained over a period of 6 years using different time granularities obtaining a Ct-index, a time-dependent variant of the C-index, of 71.97, 77.58 and 80.72 for time units of 1 month, 1 year and 2 years, respectively, outperforming all state-of-the-art methods regardless of the imputation method used.
Authors: Monika Nagy-Huber, Volker Roth
Abstract: Partial differential equations (PDEs) are widely used to describe relevant phenomena in dynamical systems. In real-world applications, we commonly need to combine formal PDE models with (potentially noisy) observations. This is especially relevant in settings where we lack information about boundary or initial conditions, or where we need to identify unknown model parameters. In recent years, Physics-Informed Neural Networks (PINNs) have become a popular tool for this kind of problems. In high-dimensional settings, however, PINNs often suffer from computational problems because they usually require dense collocation points over the entire computational domain. To address this problem, we present Physics-Informed Boundary Integral Networks (PIBI-Nets) as a data-driven approach for solving PDEs in one dimension less than the original problem space. PIBI-Nets only require points at the computational domain boundary, while still achieving highly accurate results. Moreover, PIBI-Nets clearly outperform PINNs in several practical settings. Exploiting elementary properties of fundamental solutions of linear differential operators, we present a principled and simple way to handle point sources in inverse problems. We demonstrate the excellent performance of PIBI- Nets for the Laplace and Poisson equations, both on artificial datasets and within a real-world application concerning the reconstruction of groundwater flows.
Authors: Jishnu Mukhoti, Yarin Gal, Philip H. S. Torr, Puneet K. Dokania
Abstract: Pre-trained foundation models, due to their enormous capacity and exposure to vast amounts of data during pre-training, are known to have learned plenty of real-world concepts. An important step in making these pre-trained models effective on downstream tasks is to fine-tune them on related datasets. While various fine-tuning methods have been devised and have been shown to be highly effective, we observe that a fine-tuned model's ability to recognize concepts on tasks $\textit{different}$ from the downstream one is reduced significantly compared to its pre-trained counterpart. This is an undesirable effect of fine-tuning as a substantial amount of resources was used to learn these pre-trained concepts in the first place. We call this phenomenon ''concept forgetting'' and via experiments show that most end-to-end fine-tuning approaches suffer heavily from this side effect. To this end, we propose a simple fix to this problem by designing a new fine-tuning method called $\textit{LDIFS}$ (short for $\ell_2$ distance in feature space) that, while learning new concepts related to the downstream task, allows a model to preserve its pre-trained knowledge as well. Through extensive experiments on 10 fine-tuning tasks we show that $\textit{LDIFS}$ significantly reduces concept forgetting. Additionally, we show that LDIFS is highly effective in performing continual fine-tuning on a sequence of tasks as well, in comparison with both fine-tuning as well as continual learning baselines.
Authors: Alexander Marusov, Vsevolod Grabar, Yury Maximov, Nazar Sotiriadi, Alexander Bulkin, Alexey Zaytsev
Abstract: The problem of high-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. Yet, it is still unsolved with reasonable accuracy due to data complexity and aridity stochasticity. We tackle drought data by introducing an end-to-end approach that adopts a spatio-temporal neural network model with accessible open monthly climate data as the input. Our systematic research employs diverse proposed models and five distinct environmental regions as a testbed to evaluate the efficacy of the Palmer Drought Severity Index (PDSI) prediction. Key aggregated findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts. At the same time, the Convolutional LSTM excels in longer-term forecasting. Both models achieved high ROC AUC scores: 0.948 for one month ahead and 0.617 for twelve months ahead forecasts, becoming closer to perfect ROC-AUC by $54\%$ and $16\%$, respectively, c.t. classic approaches.
Authors: Quentin Bouniot, Ievgen Redko, Anton Mallasto, Charlotte Laclau, Karol Arndt, Oliver Struckmeier, Markus Heinonen, Ville Kyrki, Samuel Kaski
Abstract: In the last decade, we have witnessed the introduction of several novel deep neural network (DNN) architectures exhibiting ever-increasing performance across diverse tasks. Explaining the upward trend of their performance, however, remains difficult as different DNN architectures of comparable depth and width -- common factors associated with their expressive power -- may exhibit a drastically different performance even when trained on the same dataset. In this paper, we introduce the concept of the non-linearity signature of DNN, the first theoretically sound solution for approximately measuring the non-linearity of deep neural networks. Built upon a score derived from closed-form optimal transport mappings, this signature provides a better understanding of the inner workings of a wide range of DNN architectures and learning paradigms, with a particular emphasis on the computer vision task. We provide extensive experimental results that highlight the practical usefulness of the proposed non-linearity signature and its potential for long-reaching implications. The code for our work is available at https://github.com/qbouniot/AffScoreDeep
Authors: Jiawei Liu, Cheng Yang, Zhiyuan Lu, Junze Chen, Yibo Li, Mengmei Zhang, Ting Bai, Yuan Fang, Lichao Sun, Philip S. Yu, Chuan Shi
Abstract: Foundation models have emerged as critical components in a variety of artificial intelligence applications, and showcase significant success in natural language processing and several other domains. Meanwhile, the field of graph machine learning is witnessing a paradigm transition from shallow methods to more sophisticated deep learning approaches. The capabilities of foundation models to generalize and adapt motivate graph machine learning researchers to discuss the potential of developing a new graph learning paradigm. This paradigm envisions models that are pre-trained on extensive graph data and can be adapted for various graph tasks. Despite this burgeoning interest, there is a noticeable lack of clear definitions and systematic analyses pertaining to this new domain. To this end, this article introduces the concept of Graph Foundation Models (GFMs), and offers an exhaustive explanation of their key characteristics and underlying technologies. We proceed to classify the existing work related to GFMs into three distinct categories, based on their dependence on graph neural networks and large language models. In addition to providing a thorough review of the current state of GFMs, this article also outlooks potential avenues for future research in this rapidly evolving domain.
Authors: Thomas Falconer, Jalal Kazempour, Pierre Pinson
Abstract: Although machine learning tasks are highly sensitive to the quality of input data, relevant datasets can often be challenging for firms to acquire, especially when held privately by a variety of owners. For instance, if these owners are competitors in a downstream market, they may be reluctant to share information. Focusing on supervised learning for regression tasks, we develop a regression market to provide a monetary incentive for data sharing. Our mechanism adopts a Bayesian framework, allowing us to consider a more general class of regression tasks. We present a thorough exploration of the market properties, and show that similar proposals in literature expose the market agents to sizeable financial risks, which can be mitigated in our setup.
Authors: Yue Wan, Jialu Wu, Tingjun Hou, Chang-Yu Hsieh, Xiaowei Jia
Abstract: Reliable molecular property prediction is essential for various scientific endeavors and industrial applications, such as drug discovery. However, the data scarcity, combined with the highly non-linear causal relationships between physicochemical and biological properties and conventional molecular featurization schemes, complicates the development of robust molecular machine learning models. Self-supervised learning (SSL) has emerged as a popular solution, utilizing large-scale, unannotated molecular data to learn a foundational representation of chemical space that might be advantageous for downstream tasks. Yet, existing molecular SSL methods largely overlook chemical knowledge, including molecular structure similarity, scaffold composition, and the context-dependent aspects of molecular properties when operating over the chemical space. They also struggle to learn the subtle variations in structure-activity relationship. This paper introduces a novel pre-training framework that learns robust and generalizable chemical knowledge. It leverages the structural hierarchy within the molecule, embeds them through distinct pre-training tasks across channels, and aggregates channel information in a task-specific manner during fine-tuning. Our approach demonstrates competitive performance across various molecular property benchmarks and offers strong advantages in particularly challenging yet ubiquitous scenarios like activity cliffs.
Authors: Shivam Barwey, Hojin Kim, Romit Maulik
Abstract: Data-driven surrogate modeling has surged in capability in recent years with the emergence of graph neural networks (GNNs), which can operate directly on mesh-based representations of data. The goal of this work is to introduce an interpretable fine-tuning strategy for GNNs, with application to unstructured mesh-based fluid dynamics modeling. The end result is an enhanced fine-tuned model that isolates regions in physical space, corresponding to sub-graphs, that are intrinsically linked to the forecasting task while retaining the predictive capability of the baseline. These structures, identified by the fine-tuned GNNs, are adaptively produced in the forward pass and serve as explainable links between the baseline model architecture, the optimization goal, and known problem-specific physics. Additionally, through a regularization procedure, the fine-tuned GNNs can also be used to identify, during inference, graph nodes that correspond to a majority of the anticipated forecasting error, adding a novel interpretable error-tagging capability to baseline models. Demonstrations are performed using unstructured flow field data sourced from flow over a backward-facing step at high Reynolds numbers, with geometry extrapolations demonstrated for ramp and wall-mounted cube configurations.
Authors: Rui Pan, Shuo Xing, Shizhe Diao, Wenhe Sun, Xiang Liu, Kashun Shum, Renjie Pi, Jipeng Zhang, Tong Zhang
Abstract: Since the emergence of large language models, prompt learning has become a popular method for optimizing and customizing these models. Special prompts, such as Chain-of-Thought, have even revealed previously unknown reasoning capabilities within these models. However, the progress of discovering effective prompts has been slow, driving a desire for general prompt optimization methods. Unfortunately, few existing prompt learning methods satisfy the criteria of being truly "general", i.e., automatic, discrete, black-box, gradient-free, and interpretable all at once. In this paper, we introduce metaheuristics, a branch of discrete non-convex optimization methods with over 100 options, as a promising approach to prompt learning. Within our paradigm, we test six typical methods: hill climbing, simulated annealing, genetic algorithms with/without crossover, tabu search, and harmony search, demonstrating their effectiveness in white-box and black-box prompt learning. Furthermore, we show that these methods can be used to discover more human-understandable prompts that were previously unknown in both reasoning and image generation tasks, opening the door to a cornucopia of possibilities in prompt optimization. We release all the codes in \url{https://github.com/research4pan/Plum}.
Authors: Fahdi Kanavati, Lucy Katsnith, Masayuki Tsuneki
Abstract: Linear principal component analysis (PCA) learns (semi-)orthogonal transformations by orienting the axes to maximize variance. Consequently, it can only identify orthogonal axes whose variances are clearly distinct, but it cannot identify the subsets of axes whose variances are roughly equal. It cannot eliminate the subspace rotational indeterminacy: it fails to disentangle components with equal variances (eigenvalues), resulting, in each eigen subspace, in randomly rotated axes. In this paper, we propose $\sigma$-PCA, a method that (1) formulates a unified model for linear and nonlinear PCA, the latter being a special case of linear independent component analysis (ICA), and (2) introduces a missing piece into nonlinear PCA that allows it to eliminate, from the canonical linear PCA solution, the subspace rotational indeterminacy -- without whitening the inputs. Whitening, a preprocessing step which converts the inputs into unit-variance inputs, has generally been a prerequisite step for linear ICA methods, which meant that conventional nonlinear PCA could not necessarily preserve the orthogonality of the overall transformation, could not directly reduce dimensionality, and could not intrinsically order by variances. We offer insights on the relationship between linear PCA, nonlinear PCA, and linear ICA -- three methods with autoencoder formulations for learning special linear transformations from data, transformations that are (semi-)orthogonal for PCA, and arbitrary unit-variance for ICA. As part of our formulation, nonlinear PCA can be seen as a method that maximizes both variance and statistical independence, lying in the middle between linear PCA and linear ICA, serving as a building block for learning linear transformations that are identifiable.
Authors: Jinhao Li, Jiaming Xu, Shiyao Li, Shan Huang, Jun Liu, Yaoxiu Lian, Guohao Dai
Abstract: Large language models (LLMs) have demonstrated impressive abilities in various domains while the inference cost is expensive. Many previous studies exploit quantization methods to reduce LLM inference cost by reducing latency and memory consumption. Applying 2-bit single-precision weight quantization brings >3% accuracy loss, so the state-of-the-art methods use mixed-precision methods for LLMs (e.g. Llama2-7b, etc.) to improve the accuracy. However, challenges still exist: (1) Uneven distribution in weight matrix. (2) Large speed degradation by adding sparse outliers. (3) Time-consuming dequantization operations on GPUs. To tackle these challenges and enable fast and efficient LLM inference on GPUs, we propose the following techniques in this paper. (1) Intra-weight mixed-precision quantization. (2) Exclusive 2-bit sparse outlier with minimum speed degradation. (3) Asynchronous dequantization. We conduct extensive experiments on different model families (e.g. Llama3, etc.) and model sizes. We achieve 2.91-bit for each weight considering all scales/zeros for different models with negligible loss. As a result, with our 2/4/16 mixed-precision quantization for each weight matrix and asynchronous dequantization during inference, our design achieves an end-to-end speedup for Llama2-7b is 1.74x over the original model, and we reduce both runtime cost and total cost by up to 2.53x and 2.29x with less GPU requirements.
Authors: Jingran Shen, Nikos Tziritas, Georgios Theodoropoulos
Abstract: With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory constraints, models are commonly optimized using compression, pruning, and partitioning algorithms to become deployable onto resource-constrained devices. As the conditions in the computational platform change dynamically, the deployed optimization algorithms should accordingly adapt their solutions. To perform frequent evaluations of these solutions in a timely fashion, RMs (Regression Models) are commonly trained to predict the relevant solution quality metrics, such as the resulted DNN module inference latency, which is the focus of this paper. Existing prediction frameworks specify different RM training workflows, but none of them allow flexible configurations of the input parameters (e.g., batch size, device utilization rate) and of the selected RMs for different modules. In this paper, a deep learning module inference latency prediction framework is proposed, which i) hosts a set of customizable input parameters to train multiple different RMs per DNN module (e.g., convolutional layer) with self-generated datasets, and ii) automatically selects a set of trained RMs leading to the highest possible overall prediction accuracy, while keeping the prediction time / space consumption as low as possible. Furthermore, a new RM, namely MEDN (Multi-task Encoder-Decoder Network), is proposed as an alternative solution. Comprehensive experiment results show that MEDN is fast and lightweight, and capable of achieving the highest overall prediction accuracy and R-squared value. The Time/Space-efficient Auto-selection algorithm also manages to improve the overall accuracy by 2.5% and R-squared by 0.39%, compared to the MEDN single-selection scheme.
Authors: Haiming Yi, Lei Hou, Yuhong Jin, Nasser A. Saeed, Ali Kandil, Hao Duan
Abstract: Diffusion models have demonstrated powerful data generation capabilities in various research fields such as image generation. However, in the field of vibration signal generation, the criteria for evaluating the quality of the generated signal are different from that of image generation and there is a fundamental difference between them. At present, there is no research on the ability of diffusion model to generate vibration signal. In this paper, a Time Series Diffusion Method (TSDM) is proposed for vibration signal generation, leveraging the foundational principles of diffusion models. The TSDM uses an improved U-net architecture with attention block, ResBlock and TimeEmbedding to effectively segment and extract features from one-dimensional time series data. It operates based on forward diffusion and reverse denoising processes for time-series generation. Experimental validation is conducted using single-frequency, multi-frequency datasets, and bearing fault datasets. The results show that TSDM can accurately generate the single-frequency and multi-frequency features in the time series and retain the basic frequency features for the diffusion generation results of the bearing fault series. It is also found that the original DDPM could not generate high quality vibration signals, but the improved U-net in TSDM, which applied the combination of attention block and ResBlock, could effectively improve the quality of vibration signal generation. Finally, TSDM is applied to the small sample fault diagnosis of three public bearing fault datasets, and the results show that the accuracy of small sample fault diagnosis of the three datasets is improved by 32.380%, 18.355% and 9.298% at most, respectively.
Authors: Nabeel Seedat, Nicolas Huynh, Boris van Breugel, Mihaela van der Schaar
Abstract: Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem. Hence, data augmentation methods to increase the sample size of datasets needed for ML are key to unlocking the transformative potential of ML in data-deprived regions and domains. Unfortunately, the limited training set constrains traditional tabular synthetic data generators in their ability to generate a large and diverse augmented dataset needed for ML tasks. To address this challenge, we introduce CLLM, which leverages the prior knowledge of Large Language Models (LLMs) for data augmentation in the low-data regime. However, not all the data generated by LLMs will improve downstream utility, as for any generative model. Consequently, we introduce a principled curation mechanism, leveraging learning dynamics, coupled with confidence and uncertainty metrics, to obtain a high-quality dataset. Empirically, on multiple real-world datasets, we demonstrate the superior performance of CLLM in the low-data regime compared to conventional generators. Additionally, we provide insights into the LLM generation and curation mechanism, shedding light on the features that enable them to output high-quality augmented datasets.
Authors: Mehdi Zadem, Sergio Mover, Sao Mai Nguyen
Abstract: Goal representation affects the performance of Hierarchical Reinforcement Learning (HRL) algorithms by decomposing the complex learning problem into easier subtasks. Recent studies show that representations that preserve temporally abstract environment dynamics are successful in solving difficult problems and provide theoretical guarantees for optimality. These methods however cannot scale to tasks where environment dynamics increase in complexity i.e. the temporally abstract transition relations depend on larger number of variables. On the other hand, other efforts have tried to use spatial abstraction to mitigate the previous issues. Their limitations include scalability to high dimensional environments and dependency on prior knowledge. In this paper, we propose a novel three-layer HRL algorithm that introduces, at different levels of the hierarchy, both a spatial and a temporal goal abstraction. We provide a theoretical study of the regret bounds of the learned policies. We evaluate the approach on complex continuous control tasks, demonstrating the effectiveness of spatial and temporal abstractions learned by this approach. Find open-source code at https://github.com/cosynus-lix/STAR.
Authors: Xikun Zhang, Dongjin Song, Yixin Chen, Dacheng Tao
Abstract: Memory replay based techniques have shown great success for continual learning with incrementally accumulated Euclidean data. Directly applying them to continually expanding networks, however, leads to the potential memory explosion problem due to the need to buffer representative nodes and their associated topological neighborhood structures. To this end, we systematically analyze the key challenges in the memory explosion problem, and present a general framework, \textit{i.e.}, Parameter Decoupled Graph Neural Networks (PDGNNs) with Topology-aware Embedding Memory (TEM), to tackle this issue. The proposed framework not only reduces the memory space complexity from $\mathcal{O}(nd^L)$ to $\mathcal{O}(n)$~\footnote{$n$: memory budget, $d$: average node degree, $L$: the radius of the GNN receptive field}, but also fully utilizes the topological information for memory replay. Specifically, PDGNNs decouple trainable parameters from the computation ego-subnetwork via \textit{Topology-aware Embeddings} (TEs), which compress ego-subnetworks into compact vectors (\textit{i.e.}, TEs) to reduce the memory consumption. Based on this framework, we discover a unique \textit{pseudo-training effect} in continual learning on expanding networks and this effect motivates us to develop a novel \textit{coverage maximization sampling} strategy that can enhance the performance with a tight memory budget. Thorough empirical studies demonstrate that, by tackling the memory explosion problem and incorporating topological information into memory replay, PDGNNs with TEM significantly outperform state-of-the-art techniques, especially in the challenging class-incremental setting.
Authors: Erik Schultheis, Wojciech Kot{\l}owski, Marek Wydmuch, Rohit Babbar, Strom Borman, Krzysztof Dembczy\'nski
Abstract: We consider the optimization of complex performance metrics in multi-label classification under the population utility framework. We mainly focus on metrics linearly decomposable into a sum of binary classification utilities applied separately to each label with an additional requirement of exactly $k$ labels predicted for each instance. These "macro-at-$k$" metrics possess desired properties for extreme classification problems with long tail labels. Unfortunately, the at-$k$ constraint couples the otherwise independent binary classification tasks, leading to a much more challenging optimization problem than standard macro-averages. We provide a statistical framework to study this problem, prove the existence and the form of the optimal classifier, and propose a statistically consistent and practical learning algorithm based on the Frank-Wolfe method. Interestingly, our main results concern even more general metrics being non-linear functions of label-wise confusion matrices. Empirical results provide evidence for the competitive performance of the proposed approach.
Authors: Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato, Yuki Ichihara, Soichiro Nishimori, Akiyoshi Sannai, Sho Sonoda, Wataru Kumagai, Yutaka Matsuo
Abstract: We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theoretical literature on PD-RL algorithms for this problem only provides sublinear regret guarantees and fails to ensure convergence to optimal policies. In this paper, we introduce a novel policy gradient PD algorithm with uniform probably approximate correctness (Uniform-PAC) guarantees, simultaneously ensuring convergence to optimal policies, sublinear regret, and polynomial sample complexity for any target accuracy. Notably, this represents the first Uniform-PAC algorithm for the online CMDP problem. In addition to the theoretical guarantees, we empirically demonstrate in a simple CMDP that our algorithm converges to optimal policies, while baseline algorithms exhibit oscillatory performance and constraint violation.
Authors: Liang Qiao, Jun Shi, Xiaoyu Hao, Xi Fang, Minfan Zhao, Ziqi Zhu, Junshi Chen, Hong An, Bing Li, Honghui Yuan, Xinyang Wang, Xulong Tang
Abstract: Tensor program tuning is essential for the efficient deployment of deep neural networks. Search-based approaches have demonstrated scalability and effectiveness in automatically finding high-performance programs for specific hardware. However, the search process is often inefficient, taking hours or even days to discover optimal programs due to the exploration mechanisms guided by an accurate but slow learned cost model. Meanwhile, the learned cost model trained on one platform cannot seamlessly adapt online to another, which we call cross-platform online unawareness. In this work, we propose Pruner and MoA-Pruner. Pruner is a speculative exploration mechanism that accelerates the search process using a "Draft-then-Verify" paradigm. Instead of applying the complex learned cost model to all explored candidates, Pruner drafts small-scale speculative candidates by introducing a naive symbol analyzer (draft model), then identifies the best candidates by the learned cost model. MoA-Pruner introduces Momentum online Adaptation to address the cross-platform online unawareness. We incorporate these techniques into the Ansor and conduct extensive experiments on three GPU-based platforms. Results show that in online cost model tuning scenarios, Pruner and MoA-Pruner can achieve an average speedup of $2.6 \times$ and $4.82 \times$ compared to Ansor. In offline tuning scenarios, Pruner can achieve an average speedup of $4.75 \times$ and $4.05\times$ compared to TenSet and TLP, respectively. The code is available at https://github.com/qiaolian9/Pruner.
Authors: Tianle Zhang, Yuchen Zhang, Kun Wang, Kai Wang, Beining Yang, Kaipeng Zhang, Wenqi Shao, Ping Liu, Joey Tianyi Zhou, Yang You
Abstract: Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns. As one of the most promising directions, graph condensation methods address these issues by employing gradient matching, aiming to condense the full graph into a more concise yet information-rich synthetic set. Though encouraging, these strategies primarily emphasize matching directions of the gradients, which leads to deviations in the training trajectories. Such deviations are further magnified by the differences between the condensation and evaluation phases, culminating in accumulated errors, which detrimentally affect the performance of the condensed graphs. In light of this, we propose a novel graph condensation method named \textbf{C}raf\textbf{T}ing \textbf{R}ationa\textbf{L} trajectory (\textbf{CTRL}), which offers an optimized starting point closer to the original dataset's feature distribution and a more refined strategy for gradient matching. Theoretically, CTRL can effectively neutralize the impact of accumulated errors on the performance of condensed graphs. We provide extensive experiments on various graph datasets and downstream tasks to support the effectiveness of CTRL. Code is released at https://github.com/NUS-HPC-AI-Lab/CTRL.
Authors: Boyi Wei, Kaixuan Huang, Yangsibo Huang, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson
Abstract: Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by leveraging pruning and low-rank modifications. We develop methods to identify critical regions that are vital for safety guardrails, and that are disentangled from utility-relevant regions at both the neuron and rank levels. Surprisingly, the isolated regions we find are sparse, comprising about $3\%$ at the parameter level and $2.5\%$ at the rank level. Removing these regions compromises safety without significantly impacting utility, corroborating the inherent brittleness of the model's safety mechanisms. Moreover, we show that LLMs remain vulnerable to low-cost fine-tuning attacks even when modifications to the safety-critical regions are restricted. These findings underscore the urgent need for more robust safety strategies in LLMs.
Authors: Eliahu Horwitz, Jonathan Kahana, Yedid Hoshen
Abstract: The dominant paradigm in generative modeling consists of two steps: i) pre-training on a large-scale but unsafe dataset, ii) aligning the pre-trained model with human values via fine-tuning. This practice is considered safe, as no current method can recover the unsafe, pre-fine-tuning model weights. In this paper, we demonstrate that this assumption is often false. Concretely, we present Spectral DeTuning, a method that can recover the weights of the pre-fine-tuning model using a few low-rank (LoRA) fine-tuned models. In contrast to previous attacks that attempt to recover pre-fine-tuning capabilities, our method aims to recover the exact pre-fine-tuning weights. Our approach exploits this new vulnerability against large-scale models such as a personalized Stable Diffusion and an aligned Mistral.
Authors: Yuan Yuan, Jingtao Ding, Jie Feng, Depeng Jin, Yong Li
Abstract: Urban spatio-temporal prediction is crucial for informed decision-making, such as traffic management, resource optimization, and emergence response. Despite remarkable breakthroughs in pretrained natural language models that enable one model to handle diverse tasks, a universal solution for spatio-temporal prediction remains challenging Existing prediction approaches are typically tailored for specific spatio-temporal scenarios, requiring task-specific model designs and extensive domain-specific training data. In this study, we introduce UniST, a universal model designed for general urban spatio-temporal prediction across a wide range of scenarios. Inspired by large language models, UniST achieves success through: (i) utilizing diverse spatio-temporal data from different scenarios, (ii) effective pre-training to capture complex spatio-temporal dynamics, (iii) knowledge-guided prompts to enhance generalization capabilities. These designs together unlock the potential of building a universal model for various scenarios Extensive experiments on more than 20 spatio-temporal scenarios demonstrate UniST's efficacy in advancing state-of-the-art performance, especially in few-shot and zero-shot prediction. The datasets and code implementation are released on https://github.com/tsinghua-fib-lab/UniST.
Authors: Jannik Brinkmann, Abhay Sheshadri, Victor Levoso, Paul Swoboda, Christian Bartelt
Abstract: Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for behavioral studies. However, these studies do not provide insights into the internal mechanisms driving the observed capabilities. To improve our understanding of the internal mechanisms of transformers, we present a comprehensive mechanistic analysis of a transformer trained on a synthetic reasoning task. We identify a set of interpretable mechanisms the model uses to solve the task, and validate our findings using correlational and causal evidence. Our results suggest that it implements a depth-bounded recurrent mechanisms that operates in parallel and stores intermediate results in selected token positions. We anticipate that the motifs we identified in our synthetic setting can provide valuable insights into the broader operating principles of transformers and thus provide a basis for understanding more complex models.
Authors: Guoqi Yu, Jing Zou, Xiaowei Hu, Angelica I. Aviles-Rivero, Jing Qin, Shujun Wang
Abstract: Predicting multivariate time series is crucial, demanding precise modeling of intricate patterns, including inter-series dependencies and intra-series variations. Distinctive trend characteristics in each time series pose challenges, and existing methods, relying on basic moving average kernels, may struggle with the non-linear structure and complex trends in real-world data. Given that, we introduce a learnable decomposition strategy to capture dynamic trend information more reasonably. Additionally, we propose a dual attention module tailored to capture inter-series dependencies and intra-series variations simultaneously for better time series forecasting, which is implemented by channel-wise self-attention and autoregressive self-attention. To evaluate the effectiveness of our method, we conducted experiments across eight open-source datasets and compared it with the state-of-the-art methods. Through the comparison results, our Leddam (LEarnable Decomposition and Dual Attention Module) not only demonstrates significant advancements in predictive performance, but also the proposed decomposition strategy can be plugged into other methods with a large performance-boosting, from 11.87% to 48.56% MSE error degradation.
Authors: Haruka Ezoe, Kazuhiro Sato
Abstract: To implement deep learning models on edge devices, model compression methods have been widely recognized as useful. However, it remains unclear which model compression methods are effective for Structured State Space Sequence (S4) models incorporating Diagonal State Space (DSS) layers, tailored for processing long-sequence data. In this paper, we propose to use the balanced truncation, a prevalent model reduction technique in control theory, applied specifically to DSS layers in pre-trained S4 model as a novel model compression method. Moreover, we propose using the reduced model parameters obtained by the balanced truncation as initial parameters of S4 models with DSS layers during the main training process. Numerical experiments demonstrate that our trained models combined with the balanced truncation surpass conventionally trained models with Skew-HiPPO initialization in accuracy, even with fewer parameters. Furthermore, our observations reveal a positive correlation: higher accuracy in the original model consistently leads to increased accuracy in models trained using our model compression method, suggesting that our approach effectively leverages the strengths of the original model.
Authors: Kellen Kanarios, Qining Zhang, Lei Ying
Abstract: In this paper, we study a best arm identification problem with dual objects. In addition to the classic reward, each arm is associated with a cost distribution and the goal is to identify the largest reward arm using the minimum expected cost. We call it \emph{Cost Aware Best Arm Identification} (CABAI), which captures the separation of testing and implementation phases in product development pipelines and models the objective shift between phases, i.e., cost for testing and reward for implementation. We first derive a theoretical lower bound for CABAI and propose an algorithm called $\mathsf{CTAS}$ to match it asymptotically. To reduce the computation of $\mathsf{CTAS}$, we further propose a simple algorithm called \emph{Chernoff Overlap} (CO), based on a square-root rule, which we prove is optimal in simplified two-armed models and generalizes well in numerical experiments. Our results show that (i) ignoring the heterogeneous action cost results in sub-optimality in practice, and (ii) simple algorithms can deliver near-optimal performance over a wide range of problems.
Authors: Noboru Isobe, Masanori Koyama, Jinzhe Zhang, Kohei Hayashi, Kenji Fukumizu
Abstract: The task of conditional generation is one of the most important applications of generative models, and numerous methods have been developed to date based on the celebrated flow-based models. However, many flow-based models in use today are not built to allow one to introduce an explicit inductive bias to how the conditional distribution to be generated changes with respect to conditions. This can result in unexpected behavior in the task of style transfer, for example. In this research, we introduce extended flow matching (EFM), a direct extension of flow matching that learns a ``matrix field'' corresponding to the continuous map from the space of conditions to the space of distributions. We show that we can introduce inductive bias to the conditional generation through the matrix field and demonstrate this fact with MMOT-EFM, a version of EFM that aims to minimize the Dirichlet energy or the sensitivity of the distribution with respect to conditions. We will present our theory along with experimental results that support the competitiveness of EFM in conditional generation.
Authors: Emi Zeger, Yifei Wang, Aaron Mishkin, Tolga Ergen, Emmanuel Cand\`es, Mert Pilanci
Abstract: We prove that training neural networks on 1-D data is equivalent to solving a convex Lasso problem with a fixed, explicitly defined dictionary matrix of features. The specific dictionary depends on the activation and depth. We consider 2 and 3-layer networks with piecewise linear activations, and rectangular and tree networks with sign activation and arbitrary depth. Interestingly in absolute value and symmetrized ReLU networks, a third layer creates features that represent reflections of training data about themselves. The Lasso representation sheds insight to globally optimal networks and the solution landscape.
Authors: Qirui Huang, Marc Syndicus, J\'er\^ome Frisch, Christoph van Treeck
Abstract: Accurate occupancy information helps to improve building energy efficiency and occupant comfort. Occupancy detection methods based on CO2 sensors have received attention due to their low cost and low intrusiveness. In naturally ventilated buildings, the accuracy of CO2-based occupancy detection is generally low in related studies due to the complex ventilation behavior and the difficulty in measuring the actual air exchange through windows. In this study, we present two novel features for occupancy detection based on the spatial distribution of the CO2 concentration. After a quantitative analysis with Support Vector Machine (SVM) as classifier, it was found that the accuracy of occupancy state detection in naturally ventilated rooms could be improved by up to 14.8 percentage points compared to the baseline, reaching 83.2 % (F1 score 0.84) without any ventilation information. With ventilation information, the accuracy reached 87.6 % (F1 score 0.89). The performance of occupancy quantity detection was significantly improved by up to 25.3 percentage points versus baseline, reaching 56 %, with root mean square error (RMSE) of 11.44 occupants, using only CO2-related features. Additional ventilation information further enhanced the performance to 61.8 % (RMSE 9.02 occupants). By incorporating spatial features, the model using only CO2-related features revealed similar performance as the model containing additional ventilation information, resulting in a better low-cost occupancy detection method for naturally ventilated buildings.
Authors: Chongyu Fan, Jiancheng Liu, Alfred Hero, Sijia Liu
Abstract: The trustworthy machine learning (ML) community is increasingly recognizing the crucial need for models capable of selectively 'unlearning' data points after training. This leads to the problem of machine unlearning (MU), aiming to eliminate the influence of chosen data points on model performance, while still maintaining the model's utility post-unlearning. Despite various MU methods for data influence erasure, evaluations have largely focused on random data forgetting, ignoring the vital inquiry into which subset should be chosen to truly gauge the authenticity of unlearning performance. To tackle this issue, we introduce a new evaluative angle for MU from an adversarial viewpoint. We propose identifying the data subset that presents the most significant challenge for influence erasure, i.e., pinpointing the worst-case forget set. Utilizing a bi-level optimization principle, we amplify unlearning challenges at the upper optimization level to emulate worst-case scenarios, while simultaneously engaging in standard training and unlearning at the lower level, achieving a balance between data influence erasure and model utility. Our proposal offers a worst-case evaluation of MU's resilience and effectiveness. Through extensive experiments across different datasets (including CIFAR-10, 100, CelebA, Tiny ImageNet, and ImageNet) and models (including both image classifiers and generative models), we expose critical pros and cons in existing (approximate) unlearning strategies. Our results illuminate the complex challenges of MU in practice, guiding the future development of more accurate and robust unlearning algorithms. The code is available at https://github.com/OPTML-Group/Unlearn-WorstCase.
Authors: Yuanhang Zhang, Zhidi Lin, Yiyong Sun, Feng Yin, Carsten Fritsche
Abstract: Deep state-space models (DSSMs) have gained popularity in recent years due to their potent modeling capacity for dynamic systems. However, existing DSSM works are limited to single-task modeling, which requires retraining with historical task data upon revisiting a forepassed task. To address this limitation, we propose continual learning DSSMs (CLDSSMs), which are capable of adapting to evolving tasks without catastrophic forgetting. Our proposed CLDSSMs integrate mainstream regularization-based continual learning (CL) methods, ensuring efficient updates with constant computational and memory costs for modeling multiple dynamic systems. We also conduct a comprehensive cost analysis of each CL method applied to the respective CLDSSMs, and demonstrate the efficacy of CLDSSMs through experiments on real-world datasets. The results corroborate that while various competing CL methods exhibit different merits, the proposed CLDSSMs consistently outperform traditional DSSMs in terms of effectively addressing catastrophic forgetting, enabling swift and accurate parameter transfer to new tasks.
Authors: Shuyi Chen, Shixiang Zhu
Abstract: Machine learning models have shown exceptional prowess in solving complex issues across various domains. However, these models can sometimes exhibit biased decision-making, resulting in unequal treatment of different groups. Despite substantial research on counterfactual fairness, methods to reduce the impact of multivariate and continuous sensitive variables on decision-making outcomes are still underdeveloped. We propose a novel data pre-processing algorithm, Orthogonal to Bias (OB), which is designed to eliminate the influence of a group of continuous sensitive variables, thus promoting counterfactual fairness in machine learning applications. Our approach, based on the assumption of a jointly normal distribution within a structural causal model (SCM), demonstrates that counterfactual fairness can be achieved by ensuring the data is orthogonal to the observed sensitive variables. The OB algorithm is model-agnostic, making it applicable to a wide range of machine learning models and tasks. Additionally, it includes a sparse variant to improve numerical stability through regularization. Empirical evaluations on both simulated and real-world datasets, encompassing settings with both discrete and continuous sensitive variables, show that our methodology effectively promotes fairer outcomes without compromising accuracy.
Authors: Enzo Rucci, Gonzalo Tittarelli, Franco Ronchetti, Jorge F. Elgart, Laura Lanzarini, Juan Jos\'e Gagliardino
Abstract: Detecting Type 2 Diabetes (T2D) and Prediabetes (PD) is a real challenge for medicine due to the absence of pathogenic symptoms and the lack of known associated risk factors. Even though some proposals for machine learning models enable the identification of people at risk, the nature of the condition makes it so that a model suitable for one population may not necessarily be suitable for another. In this article, the development and assessment of predictive models to identify people at risk for T2D and PD specifically in Argentina are discussed. First, the database was thoroughly preprocessed and three specific datasets were generated considering a compromise between the number of records and the amount of available variables. After applying 5 different classification models, the results obtained show that a very good performance was observed for two datasets with some of these models. In particular, RF, DT, and ANN demonstrated great classification power, with good values for the metrics under consideration. Given the lack of this type of tool in Argentina, this work represents the first step towards the development of more sophisticated models.
Authors: Hsing-Huan Chung, Shravan Chaudhari, Yoav Wald, Xing Han, Joydeep Ghosh
Abstract: In real-world graph data, distribution shifts can manifest in various ways, such as the emergence of new categories and changes in the relative proportions of existing categories. It is often important to detect nodes of novel categories under such distribution shifts for safety or insight discovery purposes. We introduce a new approach, Recall-Constrained Optimization with Selective Link Prediction (RECO-SLIP), to detect nodes belonging to novel categories in attributed graphs under subpopulation shifts. By integrating a recall-constrained learning framework with a sample-efficient link prediction mechanism, RECO-SLIP addresses the dual challenges of resilience against subpopulation shifts and the effective exploitation of graph structure. Our extensive empirical evaluation across multiple graph datasets demonstrates the superior performance of RECO-SLIP over existing methods. The experimental code is available at https://github.com/hsinghuan/novel-node-category-detection.
URLs: https://github.com/hsinghuan/novel-node-category-detection.
Authors: Yue Wang, Tianfan Fu, Yinlong Xu, Zihan Ma, Hongxia Xu, Yingzhou Lu, Bang Du, Honghao Gao, Jian Wu
Abstract: Clinical trials are indispensable for medical research and the development of new treatments. However, clinical trials often involve thousands of participants and can span several years to complete, with a high probability of failure during the process. Recently, there has been a burgeoning interest in virtual clinical trials, which simulate real-world scenarios and hold the potential to significantly enhance patient safety, expedite development, reduce costs, and contribute to the broader scientific knowledge in healthcare. Existing research often focuses on leveraging electronic health records (EHRs) to support clinical trial outcome prediction. Yet, trained with limited clinical trial outcome data, existing approaches frequently struggle to perform accurate predictions. Some research has attempted to generate EHRs to augment model development but has fallen short in personalizing the generation for individual patient profiles. Recently, the emergence of large language models has illuminated new possibilities, as their embedded comprehensive clinical knowledge has proven beneficial in addressing medical issues. In this paper, we propose a large language model-based digital twin creation approach, called TWIN-GPT. TWIN-GPT can establish cross-dataset associations of medical information given limited data, generating unique personalized digital twins for different patients, thereby preserving individual patient characteristics. Comprehensive experiments show that using digital twins created by TWIN-GPT can boost the clinical trial outcome prediction, exceeding various previous prediction approaches.
Authors: Sandeep Nagar, Ehsan Farahbakhsh, Joseph Awange, Rohitash Chandra
Abstract: Supervised machine learning methods for geological mapping via remote sensing face limitations due to the scarcity of accurately labelled training data that can be addressed by unsupervised learning, such as dimensionality reduction and clustering. Dimensionality reduction methods have the potential to play a crucial role in improving the accuracy of geological maps. Although conventional dimensionality reduction methods may struggle with nonlinear data, unsupervised deep learning models such as autoencoders can model non-linear relationships. Stacked autoencoders feature multiple interconnected layers to capture hierarchical data representations useful for remote sensing data. This study presents an unsupervised machine learning-based framework for processing remote sensing data using stacked autoencoders for dimensionality reduction and k-means clustering for mapping geological units. We use Landsat 8, ASTER, and Sentinel-2 datasets to evaluate the framework for geological mapping of the Mutawintji region in Western New South Wales, Australia. We also compare stacked autoencoders with principal component analysis and canonical autoencoders. Our results reveal that the framework produces accurate and interpretable geological maps, efficiently discriminating rock units. We find that the accuracy of stacked autoencoders ranges from 86.6 % to 90 %, depending on the remote sensing data type, which is superior to their counterparts. We also find that the generated maps align with prior geological knowledge of the study area while providing novel insights into geological structures.
Authors: Arnaud Pannatier, Evann Courdier, Fran\c{c}ois Fleuret
Abstract: Autoregressive models, such as the GPT family, use a fixed order, usually left-to-right, to generate sequences. However, this is not a necessity. In this paper, we challenge this assumption and show that by simply adding a positional encoding for the output, this order can be modulated on-the-fly per-sample which offers key advantageous properties. It allows for the sampling of and conditioning on arbitrary subsets of tokens, and it also allows sampling in one shot multiple tokens dynamically according to a rejection strategy, leading to a sub-linear number of model evaluations. We evaluate our method across various domains, including language modeling, path-solving, and aircraft vertical rate prediction, decreasing the number of steps required for generation by an order of magnitude.
Authors: Avi Schwarzschild, Zhili Feng, Pratyush Maini, Zachary C. Lipton, J. Zico Kolter
Abstract: Large language models (LLMs) trained on web-scale datasets raise substantial concerns regarding permissible data usage. One major question is whether these models "memorize" all their training data or they integrate many data sources in some way more akin to how a human would learn and synthesize information. The answer hinges, to a large degree, on how we define memorization. In this work, we propose the Adversarial Compression Ratio (ACR) as a metric for assessing memorization in LLMs. A given string from the training data is considered memorized if it can be elicited by a prompt (much) shorter than the string itself -- in other words, if these strings can be "compressed" with the model by computing adversarial prompts of fewer tokens. The ACR overcomes the limitations of existing notions of memorization by (i) offering an adversarial view of measuring memorization, especially for monitoring unlearning and compliance; and (ii) allowing for the flexibility to measure memorization for arbitrary strings at a reasonably low compute. Our definition serves as a practical tool for determining when model owners may be violating terms around data usage, providing a potential legal tool and a critical lens through which to address such scenarios.
Authors: Linyu Liu, Yu Pan, Xiaocheng Li, Guanting Chen
Abstract: In this paper, we study the problem of uncertainty estimation and calibration for LLMs. We first formulate the uncertainty estimation problem for LLMs and then propose a supervised approach that takes advantage of the labeled datasets and estimates the uncertainty of the LLMs' responses. Based on the formulation, we illustrate the difference between the uncertainty estimation for LLMs and that for standard ML models and explain why the hidden neurons of the LLMs may contain uncertainty information. Our designed approach demonstrates the benefits of utilizing hidden activations to enhance uncertainty estimation across various tasks and shows robust transferability in out-of-distribution settings. We distinguish the uncertainty estimation task from the uncertainty calibration task and show that a better uncertainty estimation mode leads to a better calibration performance. Furthermore, our method is easy to implement and adaptable to different levels of model accessibility including black box, grey box, and white box.
Authors: Haizhou Shi, Zihao Xu, Hengyi Wang, Weiyi Qin, Wenyuan Wang, Yibin Wang, Zifeng Wang, Sayna Ebrahimi, Hao Wang
Abstract: The recent success of large language models (LLMs) trained on static, pre-collected, general datasets has sparked numerous research directions and applications. One such direction addresses the non-trivial challenge of integrating pre-trained LLMs into dynamic data distributions, task structures, and user preferences. Pre-trained LLMs, when tailored for specific needs, often experience significant performance degradation in previous knowledge domains -- a phenomenon known as "catastrophic forgetting". While extensively studied in the continual learning (CL) community, it presents new manifestations in the realm of LLMs. In this survey, we provide a comprehensive overview of the current research progress on LLMs within the context of CL. This survey is structured into four main sections: we first describe an overview of continually learning LLMs, consisting of two directions of continuity: vertical continuity (or vertical continual learning), i.e., continual adaptation from general to specific capabilities, and horizontal continuity (or horizontal continual learning), i.e., continual adaptation across time and domains (Section 3). We then summarize three stages of learning LLMs in the context of modern CL: Continual Pre-Training (CPT), Domain-Adaptive Pre-training (DAP), and Continual Fine-Tuning (CFT) (Section 4). Then we provide an overview of evaluation protocols for continual learning with LLMs, along with the current available data sources (Section 5). Finally, we discuss intriguing questions pertaining to continual learning for LLMs (Section 6). The full list of papers examined in this survey is available at https://github.com/Wang-ML-Lab/llm-continual-learning-survey.
URLs: https://github.com/Wang-ML-Lab/llm-continual-learning-survey.
Authors: Tianyi Chen, Zhi-Qin John Xu
Abstract: Neural networks have been extensively applied to a variety of tasks, achieving astounding results. Applying neural networks in the scientific field is an important research direction that is gaining increasing attention. In scientific applications, the scale of neural networks is generally moderate-size, mainly to ensure the speed of inference during application. Additionally, comparing neural networks to traditional algorithms in scientific applications is inevitable. These applications often require rapid computations, making the reduction of neural network sizes increasingly important. Existing work has found that the powerful capabilities of neural networks are primarily due to their non-linearity. Theoretical work has discovered that under strong non-linearity, neurons in the same layer tend to behave similarly, a phenomenon known as condensation. Condensation offers an opportunity to reduce the scale of neural networks to a smaller subnetwork with similar performance. In this article, we propose a condensation reduction algorithm to verify the feasibility of this idea in practical problems. Our reduction method can currently be applied to both fully connected networks and convolutional networks, achieving positive results. In complex combustion acceleration tasks, we reduced the size of the neural network to 41.7% of its original scale while maintaining prediction accuracy. In the CIFAR10 image classification task, we reduced the network size to 11.5% of the original scale, still maintaining a satisfactory validation accuracy. Our method can be applied to most trained neural networks, reducing computational pressure and improving inference speed.
Authors: Daniel Coquelin, Katherina Fl\"ugel, Marie Weiel, Nicholas Kiefer, Muhammed \"Oz, Charlotte Debus, Achim Streit, Markus G\"otz
Abstract: Communication bottlenecks severely hinder the scalability of distributed neural network training, particularly in high-performance computing (HPC) environments. We introduce AB-training, a novel data-parallel method that leverages low-rank representations and independent training groups to significantly reduce communication overhead. Our experiments demonstrate an average reduction in network traffic of approximately 70.31\% across various scaling scenarios, increasing the training potential of communication-constrained systems and accelerating convergence at scale. AB-training also exhibits a pronounced regularization effect at smaller scales, leading to improved generalization while maintaining or even reducing training time. We achieve a remarkable 44.14 : 1 compression ratio on VGG16 trained on CIFAR-10 with minimal accuracy loss, and outperform traditional data parallel training by 1.55\% on ResNet-50 trained on ImageNet-2012. While AB-training is promising, our findings also reveal that large batch effects persist even in low-rank regimes, underscoring the need for further research into optimized update mechanisms for massively distributed training.
Authors: Jarek Duda
Abstract: Biological neural networks seem qualitatively superior (e.g. in learning, flexibility, robustness) from current artificial like Multi-Layer Perceptron (MLP) or Kolmogorov-Arnold Network (KAN). Simultaneously, in contrast to them: have fundamentally multidirectional signal propagation~\cite{axon}, also of probability distributions e.g. for uncertainty estimation, and are believed not being able to use standard backpropagation training~\cite{backprop}. There are proposed novel artificial neurons based on HCR (Hierarchical Correlation Reconstruction) removing the above low level differences: with neurons containing local joint distribution model (of its connections), representing joint density on normalized variables as just linear combination among $(f_\mathbf{j})$ orthonormal polynomials: $\rho(\mathbf{x})=\sum_{\mathbf{j}\in B} a_\mathbf{j} f_\mathbf{j}(\mathbf{x})$ for $\mathbf{x} \in [0,1]^d$ and $B$ some chosen basis, with basis growth approaching complete description of joint distribution. By various index summations of such $(a_\mathbf{j})$ tensor as neuron parameters, we get simple formulas for e.g. conditional expected values for propagation in any direction, like $E[x|y,z]$, $E[y|x]$, which degenerate to KAN-like parametrization if restricting to pairwise dependencies. Such HCR network can also propagate probability distributions (also joint) like $\rho(y,z|x)$. It also allows for additional training approaches, like direct $(a_\mathbf{j})$ estimation, through tensor decomposition, or more biologically plausible information bottleneck training: layers directly influencing only neighbors, optimizing content to maximize information about the next layer, and minimizing about the previous to minimize the noise.
Authors: Maciej \.Zelaszczyk, Jacek Ma\'ndziuk
Abstract: This paper proposes a general interpretable predictive system with shared information. The system is able to perform predictions in a multi-task setting where distinct tasks are not bound to have the same input/output structure. Embeddings of input and output variables in a common space are obtained, where the input embeddings are produced through attending to a set of shared embeddings, reused across tasks. All the embeddings are treated as model parameters and learned. Specific restrictions on the space of shared embedings and the sparsity of the attention mechanism are considered. Experiments show that the introduction of shared embeddings does not deteriorate the results obtained from a vanilla variable embeddings method. We run a number of further ablations. Inducing sparsity in the attention mechanism leads to both an increase in accuracy and a significant decrease in the number of training steps required. Shared embeddings provide a measure of interpretability in terms of both a qualitative assessment and the ability to map specific shared embeddings to pre-defined concepts that are not tailored to the considered model. There seems to be a trade-off between accuracy and interpretability. The basic shared embeddings method favors interpretability, whereas the sparse attention method promotes accuracy. The results lead to the conclusion that variable embedding methods may be extended with shared information to provide increased interpretability and accuracy.
Authors: Xin-Chun Li, Jin-Lin Tang, Bo Zhang, Lan Li, De-Chuan Zhan
Abstract: Exploring the loss landscape offers insights into the inherent principles of deep neural networks (DNNs). Recent work suggests an additional asymmetry of the valley beyond the flat and sharp ones, yet without thoroughly examining its causes or implications. Our study methodically explores the factors affecting the symmetry of DNN valleys, encompassing (1) the dataset, network architecture, initialization, and hyperparameters that influence the convergence point; and (2) the magnitude and direction of the noise for 1D visualization. Our major observation shows that the {\it degree of sign consistency} between the noise and the convergence point is a critical indicator of valley symmetry. Theoretical insights from the aspects of ReLU activation and softmax function could explain the interesting phenomenon. Our discovery propels novel understanding and applications in the scenario of Model Fusion: (1) the efficacy of interpolating separate models significantly correlates with their sign consistency ratio, and (2) imposing sign alignment during federated learning emerges as an innovative approach for model parameter alignment.
Authors: Yihong Huang, Yuang Zhang, Liping Wang, Fan Zhang, Xuemin Lin
Abstract: Unsupervised Outlier Detection (UOD) is an important data mining task. With the advance of deep learning, deep Outlier Detection (OD) has received broad interest. Most deep UOD models are trained exclusively on clean datasets to learn the distribution of the normal data, which requires huge manual efforts to clean the real-world data if possible. Instead of relying on clean datasets, some approaches directly train and detect on unlabeled contaminated datasets, leading to the need for methods that are robust to such conditions. Ensemble methods emerged as a superior solution to enhance model robustness against contaminated training sets. However, the training time is greatly increased by the ensemble. In this study, we investigate the impact of outliers on the training phase, aiming to halt training on unlabeled contaminated datasets before performance degradation. Initially, we noted that blending normal and anomalous data causes AUC fluctuations, a label-dependent measure of detection accuracy. To circumvent the need for labels, we propose a zero-label entropy metric named Loss Entropy for loss distribution, enabling us to infer optimal stopping points for training without labels. Meanwhile, we theoretically demonstrate negative correlation between entropy metric and the label-based AUC. Based on this, we develop an automated early-stopping algorithm, EntropyStop, which halts training when loss entropy suggests the maximum model detection capability. We conduct extensive experiments on ADBench (including 47 real datasets), and the overall results indicate that AutoEncoder (AE) enhanced by our approach not only achieves better performance than ensemble AEs but also requires under 2\% of training time. Lastly, our proposed metric and early-stopping approach are evaluated on other deep OD models, exhibiting their broad potential applicability.
Authors: Ruiqi Li, Maowei Jiang, Kai Wang, Kaiduo Feng, Quangao Liu, Yue Sun, Xiufang Zhou
Abstract: Time Series Forecasting plays a crucial role in various fields such as industrial equipment maintenance, meteorology, energy consumption, traffic flow and financial investment. However, despite their considerable advantages over traditional statistical approaches, current deep learning-based predictive models often exhibit a significant deviation between their forecasting outcomes and the ground truth. This discrepancy is largely due to an insufficient emphasis on extracting the sequence's latent information, particularly its global information within the frequency domain and the relationship between different variables. To address this issue, we propose a novel model Frequency-domain Attention In Two Horizons, which decomposes time series into trend and seasonal components using a multi-scale sequence adaptive decomposition and fusion architecture, and processes them separately. FAITH utilizes Frequency Channel feature Extraction Module and Frequency Temporal feature Extraction Module to capture inter-channel relationships and temporal global information in the sequence, significantly improving its ability to handle long-term dependencies and complex patterns. Furthermore, FAITH achieves theoretically linear complexity by modifying the time-frequency domain transformation method, effectively reducing computational costs. Extensive experiments on 6 benchmarks for long-term forecasting and 3 benchmarks for short-term forecasting demonstrate that FAITH outperforms existing models in many fields, such as electricity, weather and traffic, proving its effectiveness and superiority both in long-term and short-term time series forecasting tasks. Our codes and data are available at https://github.com/LRQ577/FAITH.
Authors: Yunzheng Lyu, Feng Bao
Abstract: Kernel learning forward backward SDE filter is an iterative and adaptive meshfree approach to solve the nonlinear filtering problem. It builds from forward backward SDE for Fokker-Planker equation, which defines evolving density for the state variable, and employs KDE to approximate density. This algorithm has shown more superior performance than mainstream particle filter method, in both convergence speed and efficiency of solving high dimension problems. However, this method has only been shown to converge empirically. In this paper, we present a rigorous analysis to demonstrate its local and global convergence, and provide theoretical support for its empirical results.
Authors: Xianzhi Du, Tom Gunter, Xiang Kong, Mark Lee, Zirui Wang, Aonan Zhang, Nan Du, Ruoming Pang
Abstract: Mixture-of-Experts (MoE) enjoys performance gain by increasing model capacity while keeping computation cost constant. When comparing MoE to dense models, prior work typically adopt the following setting: 1) use FLOPs or activated parameters as a measure of model complexity; 2) train all models to the same number of tokens. We argue that this setting favors MoE as FLOPs and activated parameters do not accurately measure the communication overhead in sparse layers, leading to a larger actual training budget for MoE. In this work, we revisit the settings by adopting step time as a more accurate measure of model complexity, and by determining the total compute budget under the Chinchilla compute-optimal settings. To efficiently run MoE on modern accelerators, we adopt a 3D sharding method that keeps the dense-to-MoE step time increase within a healthy range. We evaluate MoE and dense LLMs on a set of nine 0-shot and two 1-shot English tasks, as well as MMLU 5-shot and GSM8K 8-shot across three model scales at 6.4B, 12.6B, and 29.6B. Experimental results show that even under these settings, MoE consistently outperform dense LLMs on the speed-accuracy trade-off curve with meaningful gaps. Our full model implementation and sharding strategy has been released at~\url{https://github.com/apple/axlearn}
Authors: Wuhao Wang, Zhiyong Chen, Lepeng Zhang
Abstract: Temporal difference (TD) learning is a fundamental technique in reinforcement learning that updates value estimates for states or state-action pairs using a TD target. This target represents an improved estimate of the true value by incorporating both immediate rewards and the estimated value of subsequent states. Traditionally, TD learning relies on the value of a single subsequent state. We propose an enhanced multi-state TD (MSTD) target that utilizes the estimated values of multiple subsequent states. Building on this new MSTD concept, we develop complete actor-critic algorithms that include management of replay buffers in two modes, and integrate with deep deterministic policy optimization (DDPG) and soft actor-critic (SAC). Experimental results demonstrate that algorithms employing the MSTD target significantly improve learning performance compared to traditional methods.The code is provided on GitHub.
Authors: Yonghong Li, Shan Qu, Xiuzhuang Zhou
Abstract: While existing depression prediction methods based on deep learning show promise, their practical application is hindered by the lack of trustworthiness, as these deep models are often deployed as \textit{black box} models, leaving us uncertain about the confidence of the model predictions. For high-risk clinical applications like depression prediction, uncertainty quantification is essential in decision-making. In this paper, we introduce conformal depression prediction (CDP), a depression prediction method with uncertainty quantification based on conformal prediction (CP), giving valid confidence intervals with theoretical coverage guarantees for the model predictions. CDP is a plug-and-play module that requires neither model retraining nor an assumption about the depression data distribution. As CDP provides only an average coverage guarantee across all inputs rather than per-input performance guarantee, we further propose CDP-ACC, an improved conformal prediction with approximate conditional coverage. CDP-ACC firstly estimates the prediction distribution through neighborhood relaxation, and then introduces a conformal score function by constructing nested sequences, so as to provide a tighter prediction interval for each specific input. We empirically demonstrate the application of CDP in uncertainty-aware depression prediction, as well as the effectiveness and superiority of CDP-ACC on the AVEC 2013 and AVEC 2014 datasets.
Authors: Qi Zhang, Peiyao Xiao, Kaiyi Ji, Shaofeng Zou
Abstract: Multi-objective optimization (MOO) is receiving more attention in various fields such as multi-task learning. Recent works provide some effective algorithms with theoretical analysis but they are limited by the standard $L$-smooth or bounded-gradient assumptions, which are typically unsatisfactory for neural networks, such as recurrent neural networks (RNNs) and transformers. In this paper, we study a more general and realistic class of $\ell$-smooth loss functions, where $\ell$ is a general non-decreasing function of gradient norm. We develop two novel single-loop algorithms for $\ell$-smooth MOO problems, Generalized Smooth Multi-objective Gradient descent (GSMGrad) and its stochastic variant, Stochastic Generalized Smooth Multi-objective Gradient descent (SGSMGrad), which approximate the conflict-avoidant (CA) direction that maximizes the minimum improvement among objectives. We provide a comprehensive convergence analysis of both algorithms and show that they converge to an $\epsilon$-accurate Pareto stationary point with a guaranteed $\epsilon$-level average CA distance (i.e., the gap between the updating direction and the CA direction) over all iterations, where totally $\mathcal{O}(\epsilon^{-2})$ and $\mathcal{O}(\epsilon^{-4})$ samples are needed for deterministic and stochastic settings, respectively. Our algorithms can also guarantee a tighter $\epsilon$-level CA distance in each iteration using more samples. Moreover, we propose a practical variant of GSMGrad named GSMGrad-FA using only constant-level time and space, while achieving the same performance guarantee as GSMGrad. Our experiments validate our theory and demonstrate the effectiveness of the proposed methods.
Authors: Mouad El Bouchattaoui, Myriam Tami, Benoit Lepetit, Paul-Henry Courn\`ede
Abstract: Estimating treatment effects over time holds significance in various domains, including precision medicine, epidemiology, economy, and marketing. This paper introduces a unique approach to counterfactual regression over time, emphasizing long-term predictions. Distinguishing itself from existing models like Causal Transformer, our approach highlights the efficacy of employing RNNs for long-term forecasting, complemented by Contrastive Predictive Coding (CPC) and Information Maximization (InfoMax). Emphasizing efficiency, we avoid the need for computationally expensive transformers. Leveraging CPC, our method captures long-term dependencies in the presence of time-varying confounders. Notably, recent models have disregarded the importance of invertible representation, compromising identification assumptions. To remedy this, we employ the InfoMax principle, maximizing a lower bound of mutual information between sequence data and its representation. Our method achieves state-of-the-art counterfactual estimation results using both synthetic and real-world data, marking the pioneering incorporation of Contrastive Predictive Encoding in causal inference.
Authors: Guy Amir, Osher Maayan, Tom Zelazny, Guy Katz, Michael Schapira
Abstract: Deep neural networks (DNNs) play a crucial role in the field of machine learning, demonstrating state-of-the-art performance across various application domains. However, despite their success, DNN-based models may occasionally exhibit challenges with generalization, i.e., may fail to handle inputs that were not encountered during training. This limitation is a significant challenge when it comes to deploying deep learning for safety-critical tasks, as well as in real-world settings characterized by substantial variability. We introduce a novel approach for harnessing DNN verification technology to identify DNN-driven decision rules that exhibit robust generalization to previously unencountered input domains. Our method assesses generalization within an input domain by measuring the level of agreement between independently trained deep neural networks for inputs in this domain. We also efficiently realize our approach by using off-the-shelf DNN verification engines, and extensively evaluate it on both supervised and unsupervised DNN benchmarks, including a deep reinforcement learning (DRL) system for Internet congestion control -- demonstrating the applicability of our approach for real-world settings. Moreover, our research introduces a fresh objective for formal verification, offering the prospect of mitigating the challenges linked to deploying DNN-driven systems in real-world scenarios.
Authors: Dominik Fuchsgruber, Tom Wollschl\"ager, Stephan G\"unnemann
Abstract: In domains with interdependent data, such as graphs, quantifying the epistemic uncertainty of a Graph Neural Network (GNN) is challenging as uncertainty can arise at different structural scales. Existing techniques neglect this issue or only distinguish between structure-aware and structure-agnostic uncertainty without combining them into a single measure. We propose GEBM, an energy-based model (EBM) that provides high-quality uncertainty estimates by aggregating energy at different structural levels that naturally arise from graph diffusion. In contrast to logit-based EBMs, we provably induce an integrable density in the data space by regularizing the energy function. We introduce an evidential interpretation of our EBM that significantly improves the predictive robustness of the GNN. Our framework is a simple and effective post hoc method applicable to any pre-trained GNN that is sensitive to various distribution shifts. It consistently achieves the best separation of in-distribution and out-of-distribution data on 6 out of 7 anomaly types while having the best average rank over shifts on \emph{all} datasets.
Authors: Junru Zhang, Lang Feng, Zhidan Liu, Yuhan Wu, Yang He, Yabo Dong, Duanqing Xu
Abstract: Existing domain generalization (DG) methods for cross-person generalization tasks often face challenges in capturing intra- and inter-domain style diversity, resulting in domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. This proposal aims to enrich the domain diversity by synthesizing intra- and inter-domain style data while maintaining robustness to class labels. We instantiate this concept using a conditional diffusion model and introduce a style-fused sampling strategy to enhance data generation diversity. In contrast to traditional condition-guided sampling, our style-fused sampling strategy allows for the flexible use of one or more random styles to guide data synthesis. This feature presents a notable advancement: it allows for the maximum utilization of possible permutations and combinations among existing styles to generate a broad spectrum of new style instances. Empirical evaluations on a broad range of datasets demonstrate that our generated data achieves remarkable diversity within the domain space. Both intra- and inter-domain generated data have proven to be significant and valuable, contributing to varying degrees of performance enhancements. Notably, our approach outperforms state-of-the-art DG methods in all human activity recognition tasks.
Authors: Virginia Aglietti, Ira Ktena, Jessica Schrouff, Eleni Sgouritsa, Francisco J. R. Ruiz, Alan Malek, Alexis Bellot, Silvia Chiappa
Abstract: The sample efficiency of Bayesian optimization algorithms depends on carefully crafted acquisition functions (AFs) guiding the sequential collection of function evaluations. The best-performing AF can vary significantly across optimization problems, often requiring ad-hoc and problem-specific choices. This work tackles the challenge of designing novel AFs that perform well across a variety of experimental settings. Based on FunSearch, a recent work using Large Language Models (LLMs) for discovery in mathematical sciences, we propose FunBO, an LLM-based method that can be used to learn new AFs written in computer code by leveraging access to a limited number of evaluations for a set of objective functions. We provide the analytic expression of all discovered AFs and evaluate them on various global optimization benchmarks and hyperparameter optimization tasks. We show how FunBO identifies AFs that generalize well in and out of the training distribution of functions, thus outperforming established general-purpose AFs and achieving competitive performance against AFs that are customized to specific function types and are learned via transfer-learning algorithms.
Authors: Christian Raymond
Abstract: Humans can often quickly and efficiently solve complex new learning tasks given only a small set of examples. In contrast, modern artificially intelligent systems often require thousands or millions of observations in order to solve even the most basic tasks. Meta-learning aims to resolve this issue by leveraging past experiences from similar learning tasks to embed the appropriate inductive biases into the learning system. Historically methods for meta-learning components such as optimizers, parameter initializations, and more have led to significant performance increases. This thesis aims to explore the concept of meta-learning to improve performance, through the often-overlooked component of the loss function. The loss function is a vital component of a learning system, as it represents the primary learning objective, where success is determined and quantified by the system's ability to optimize for that objective successfully.
Authors: Siemen Herremans, Ali Anwar, Siegfried Mercelis
Abstract: Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and safety in the learned policies. More specifically, an RL agent that trains in a certain Markov decision process (MDP) often struggles to perform well in nearly identical MDPs. To address this issue, we employ the framework of Robust MDPs (RMDPs) in a model-based setting and introduce a novel learned transition model. Our method specifically incorporates an auxiliary pessimistic model, updated adversarially, to estimate the worst-case MDP within a Kullback-Leibler uncertainty set. In comparison to several existing works, our work does not impose any additional conditions on the training environment, such as the need for a parametric simulator. To test the effectiveness of the proposed pessimistic model in enhancing policy robustness, we integrate it into a practical RL algorithm, called Robust Model-Based Policy Optimization (RMBPO). Our experimental results indicate a notable improvement in policy robustness on high-dimensional MuJoCo control tasks, with the auxiliary model enhancing the performance of the learned policy in distorted MDPs. We further explore the learned deviation between the proposed auxiliary world model and the nominal model, to examine how pessimism is achieved. By learning a pessimistic world model and demonstrating its role in improving policy robustness, our research contributes towards making (model-based) RL more robust.
Authors: Yaobin Ling, Xiaoqian Jiang, Yejin Kim
Abstract: In the era of big data, access to abundant data is crucial for driving research forward. However, such data is often inaccessible due to privacy concerns or high costs, particularly in healthcare domain. Generating synthetic (tabular) data can address this, but existing models typically require substantial amounts of data to train effectively, contradicting our objective to solve data scarcity. To address this challenge, we propose a novel framework to generate synthetic tabular data, powered by large language models (LLMs) that emulates the architecture of a Generative Adversarial Network (GAN). By incorporating data generation process as contextual information and utilizing LLM as the optimizer, our approach significantly enhance the quality of synthetic data generation in common scenarios with small sample sizes. Our experimental results on public and private datasets demonstrate that our model outperforms several state-of-art models regarding generating higher quality synthetic data for downstream tasks while keeping privacy of the real data.
Authors: Jiachen T. Wang, Prateek Mittal, Dawn Song, Ruoxi Jia
Abstract: Data Shapley provides a principled framework for attributing data's contribution within machine learning contexts. However, existing approaches require re-training models on different data subsets, which is computationally intensive, foreclosing their application to large-scale models. Furthermore, they produce the same attribution score for any models produced by running the learning algorithm, meaning they cannot perform targeted attribution towards a specific model obtained from a single run of the algorithm. This paper introduces In-Run Data Shapley, which addresses these limitations by offering scalable data attribution for a target model of interest. In its most efficient implementation, our technique incurs negligible additional runtime compared to standard model training. This dramatic efficiency improvement makes it possible to perform data attribution for the foundation model pretraining stage for the first time. We present several case studies that offer fresh insights into pretraining data's contribution and discuss their implications for copyright in generative AI and pretraining data curation.
Authors: Xiaohong Ji, Zhen Wang, Zhifeng Gao, Hang Zheng, Linfeng Zhang, Guolin Ke, Weinan E
Abstract: In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the expansion of model parameters and data size, a phenomenon now recognized as the scaling laws. However, research exploring scaling law in molecular pretraining models remains unexplored. In this work, we present Uni-Mol2 , an innovative molecular pretraining model that leverages a two-track transformer to effectively integrate features at the atomic level, graph level, and geometry structure level. Along with this, we systematically investigate the scaling law within molecular pretraining models, characterizing the power-law correlations between validation loss and model size, dataset size, and computational resources. Consequently, we successfully scale Uni-Mol2 to 1.1 billion parameters through pretraining on 800 million conformations, making it the largest molecular pretraining model to date. Extensive experiments show consistent improvement in the downstream tasks as the model size grows. The Uni-Mol2 with 1.1B parameters also outperforms existing methods, achieving an average 27% improvement on the QM9 and 14% on COMPAS-1D dataset.
Authors: Junkai Zhang, Weitong Zhang, Dongruo Zhou, Quanquan Gu
Abstract: Mastering multiple tasks through exploration and learning in an environment poses a significant challenge in reinforcement learning (RL). Unsupervised RL has been introduced to address this challenge by training policies with intrinsic rewards rather than extrinsic rewards. However, current intrinsic reward designs and unsupervised RL algorithms often overlook the heterogeneous nature of collected samples, thereby diminishing their sample efficiency. To overcome this limitation, in this paper, we propose a reward-free RL algorithm called \alg. The key idea behind our algorithm is an uncertainty-aware intrinsic reward for exploring the environment and an uncertainty-weighted learning process to handle heterogeneous uncertainty in different samples. Theoretically, we show that in order to find an $\epsilon$-optimal policy, GFA-RFE needs to collect $\tilde{O} (H^2 \log N_{\mathcal F} (\epsilon) \mathrm{dim} (\mathcal F) / \epsilon^2 )$ number of episodes, where $\mathcal F$ is the value function class with covering number $N_{\mathcal F} (\epsilon)$ and generalized eluder dimension $\mathrm{dim} (\mathcal F)$. Such a result outperforms all existing reward-free RL algorithms. We further implement and evaluate GFA-RFE across various domains and tasks in the DeepMind Control Suite. Experiment results show that GFA-RFE outperforms or is comparable to the performance of state-of-the-art unsupervised RL algorithms.
Authors: Aditya Kashi, Arka Daw, Muralikrishnan Gopalakrishnan Meena, Hao Lu
Abstract: Neural operators such as the Fourier Neural Operator (FNO) have been shown to provide resolution-independent deep learning models that can learn mappings between function spaces. For example, an initial condition can be mapped to the solution of a partial differential equation (PDE) at a future time-step using a neural operator. Despite the popularity of neural operators, their use to predict solution functions over a domain given only data over the boundary (such as a spatially varying Dirichlet boundary condition) remains unexplored. In this paper, we refer to such problems as boundary-to-domain problems; they have a wide range of applications in areas such as fluid mechanics, solid mechanics, heat transfer etc. We present a novel FNO-based architecture, named Lifting Product FNO (or LP-FNO) which can map arbitrary boundary functions defined on the lower-dimensional boundary to a solution in the entire domain. Specifically, two FNOs defined on the lower-dimensional boundary are lifted into the higher dimensional domain using our proposed lifting product layer. We demonstrate the efficacy and resolution independence of the proposed LP-FNO for the 2D Poisson equation.
Authors: Yushun Zhang, Congliang Chen, Ziniu Li, Tian Ding, Chenwei Wu, Yinyu Ye, Zhi-Quan Luo, Ruoyu Sun
Abstract: We propose Adam-mini, an optimizer that achieves on-par or better performance than AdamW with 45% to 50% less memory footprint. Adam-mini reduces memory by cutting down the learning rate resources in Adam (i.e., $1/\sqrt{v}$). We find that $\geq$ 90% of these learning rates in $v$ could be harmlessly removed if we (1) carefully partition the parameters into blocks following our proposed principle on Hessian structure; (2) assign a single but good learning rate to each parameter block. We further find that, for each of these parameter blocks, there exists a single high-quality learning rate that can outperform Adam, provided that sufficient resources are available to search it out. We then provide one cost-effective way to find good learning rates and propose Adam-mini. Empirically, we verify that Adam-mini performs on par or better than AdamW on various language models sized from 125M to 7B for pre-training, supervised fine-tuning, and RLHF. The reduced memory footprint of Adam-mini also alleviates communication overheads among GPUs and CPUs, thereby increasing throughput. For instance, Adam-mini achieves 49.6% higher throughput than AdamW when pre-training Llama2-7B on $2\times$ A800-80GB GPUs, which saves 33% wall-clock time for pre-training.
Authors: Vyacheslav Kungurtsev, Apaar, Aarya Khandelwal, Parth Sandeep Rastogi, Bapi Chatterjee, Jakub Mare\v{c}ek
Abstract: In this work, we demonstrate the Empirical Bayes approach to learning a Dynamic Bayesian Network. By starting with several point estimates of structure and weights, we can use a data-driven prior to subsequently obtain a model to quantify uncertainty. This approach uses a recent development of Generalized Variational Inference, and indicates the potential of sampling the uncertainty of a mixture of DAG structures as well as a parameter posterior.
Authors: Roman Bresson, Giannis Nikolentzos, George Panagopoulos, Michail Chatzianastasis, Jun Pang, Michalis Vazirgiannis
Abstract: In recent years, Graph Neural Networks (GNNs) have become the de facto tool for learning node and graph representations. Most GNNs typically consist of a sequence of neighborhood aggregation (a.k.a., message passing) layers. Within each of these layers, the representation of each node is updated from an aggregation and transformation of its neighbours representations at the previous layer. The upper bound for the expressive power of message passing GNNs was reached through the use of MLPs as a transformation, due to their universal approximation capabilities. However, MLPs suffer from well-known limitations, which recently motivated the introduction of Kolmogorov-Arnold Networks (KANs). KANs rely on the Kolmogorov-Arnold representation theorem, rendering them a promising alternative to MLPs. In this work, we compare the performance of KANs against that of MLPs in graph learning tasks. We perform extensive experiments on node classification, graph classification and graph regression datasets. Our preliminary results indicate that while KANs are on-par with MLPs in classification tasks, they seem to have a clear advantage in the graph regression tasks. Code is available at https: //github.com/RomanBresson/KAGNN.
Authors: Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E. Gonzalez, M Waleed Kadous, Ion Stoica
Abstract: Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost. More powerful models, though effective, come with higher expenses, while less capable models are more cost-effective. To address this dilemma, we propose several efficient router models that dynamically select between a stronger and a weaker LLM during inference, aiming to optimize the balance between cost and response quality. We develop a training framework for these routers leveraging human preference data and data augmentation techniques to enhance performance. Our evaluation on widely-recognized benchmarks shows that our approach significantly reduces costs-by over 2 times in certain cases-without compromising the quality of responses. Interestingly, our router models also demonstrate significant transfer learning capabilities, maintaining their performance even when the strong and weak models are changed at test time. This highlights the potential of these routers to provide a cost-effective yet high-performance solution for deploying LLMs.
Authors: Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hannaneh Hajishirzi, Noah A. Smith, Simon Du
Abstract: Aligning language models (LMs) to human preferences has emerged as a critical pursuit, enabling these models to better serve diverse user needs. Existing methods primarily focus on optimizing LMs for a single reward function, limiting their adaptability to varied objectives. Here, we propose $\textbf{multi-objective decoding (MOD)}$, a decoding-time algorithm that outputs the next token from a linear combination of predictions of all base models, for any given weightings over different objectives. We exploit a common form among a family of $f$-divergence regularized alignment approaches (such as PPO, DPO, and their variants) to identify a closed-form solution by Legendre transform, and derive an efficient decoding strategy. Theoretically, we show why existing approaches can be sub-optimal even in natural settings and obtain optimality guarantees for our method. Empirical results demonstrate the effectiveness of the algorithm. For example, compared to a parameter-merging baseline, MOD achieves 12.8% overall reward improvement when equally optimizing towards $3$ objectives. Moreover, we experiment with MOD on combining three fully-finetuned LLMs of different model sizes, each aimed at different objectives such as safety, coding, and general user preference. Unlike traditional methods that require careful curation of a mixture of datasets to achieve comprehensive improvement, we can quickly experiment with preference weightings using MOD to find the best combination of models. Our best combination reduces toxicity on Toxigen to nearly 0% and achieves 7.9--33.3% improvement across other three metrics ($\textit{i.e.}$, Codex@1, GSM-COT, BBH-COT).
Authors: Wenke Huang, Guancheng Wan, Mang Ye, Bo Du
Abstract: Federated graph learning collaboratively learns a global graph neural network with distributed graphs, where the non-independent and identically distributed property is one of the major challenges. Most relative arts focus on traditional distributed tasks like images and voices, incapable of graph structures. This paper firstly reveals that local client distortion is brought by both node-level semantics and graph-level structure. First, for node-level semantics, we find that contrasting nodes from distinct classes is beneficial to provide a well-performing discrimination. We pull the local node towards the global node of the same class and push it away from the global node of different classes. Second, we postulate that a well-structural graph neural network possesses similarity for neighbors due to the inherent adjacency relationships. However, aligning each node with adjacent nodes hinders discrimination due to the potential class inconsistency. We transform the adjacency relationships into the similarity distribution and leverage the global model to distill the relation knowledge into the local model, which preserves the structural information and discriminability of the local model. Empirical results on three graph datasets manifest the superiority of the proposed method over its counterparts.
Authors: Emma Cramer, Bernd Frauenknecht, Ramil Sabirov, Sebastian Trimpe
Abstract: Combining Reinforcement Learning (RL) with a prior controller can yield the best out of two worlds: RL can solve complex nonlinear problems, while the control prior ensures safer exploration and speeds up training. Prior work largely blends both components with a fixed weight, neglecting that the RL agent's performance varies with the training progress and across regions in the state space. Therefore, we advocate for an adaptive strategy that dynamically adjusts the weighting based on the RL agent's current capabilities. We propose a new adaptive hybrid RL algorithm, Contextualized Hybrid Ensemble Q-learning (CHEQ). CHEQ combines three key ingredients: (i) a time-invariant formulation of the adaptive hybrid RL problem treating the adaptive weight as a context variable, (ii) a weight adaption mechanism based on the parametric uncertainty of a critic ensemble, and (iii) ensemble-based acceleration for data-efficient RL. Evaluating CHEQ on a car racing task reveals substantially stronger data efficiency, exploration safety, and transferability to unknown scenarios than state-of-the-art adaptive hybrid RL methods.
Authors: Alessio Ferrari, Thaide Huichapa, Paola Spoletini, Nicole Novielli, Davide Fucci, Daniela Girardi
Abstract: Capturing users' engagement is crucial for gathering feedback about the features of a software product. In a market-driven context, current approaches to collect and analyze users' feedback are based on techniques leveraging information extracted from product reviews and social media. These approaches are hardly applicable in bespoke software development, or in contexts in which one needs to gather information from specific users. In such cases, companies need to resort to face-to-face interviews to get feedback on their products. In this paper, we propose to utilize biometric data, in terms of physiological and voice features, to complement interviews with information about the engagement of the user on the discussed product-relevant topics. We evaluate our approach by interviewing users while gathering their physiological data (i.e., biofeedback) using an Empatica E4 wristband, and capturing their voice through the default audio-recorder of a common laptop. Our results show that we can predict users' engagement by training supervised machine learning algorithms on biometric data (F1=0.72), and that voice features alone are sufficiently effective (F1=0.71). Our work contributes with one the first studies in requirements engineering in which biometrics are used to identify emotions. This is also the first study in software engineering that considers voice analysis. The usage of voice features could be particularly helpful for emotion-aware requirements elicitation in remote communication, either performed by human analysts or voice-based chatbots, and can also be exploited to support the analysis of meetings in software engineering research.
Authors: Jay Whang, Alliot Nagle, Anish Acharya, Hyeji Kim, Alexandros G. Dimakis
Abstract: Distributed source coding (DSC) is the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically achieve the same compression rate as when the side information is available to it. While there is vast prior work on this topic, practical DSC has been limited to synthetic datasets and specific correlation structures. Here we present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. Rather than relying on hand-crafted source modeling, our method utilizes a conditional Vector-Quantized Variational Autoencoder (VQ-VAE) to learn the distributed encoder and decoder. We evaluate our method on multiple datasets and show that our method can handle complex correlations and achieves state-of-the-art PSNR. Our code is made available at https://github.com/acnagle/neural-dsc.
Authors: DongNyeong Heo, Heeyoul Choi
Abstract: Back-translation (BT) is an effective semi-supervised learning framework in neural machine translation (NMT). A pre-trained NMT model translates monolingual sentences and makes synthetic bilingual sentence pairs for the training of the other NMT model, and vice versa. Understanding the two NMT models as inference and generation models, respectively, the training method of variational auto-encoder (VAE) was applied in previous works, which is a mainstream framework of generative models. However, the discrete property of translated sentences prevents gradient information from flowing between the two NMT models. In this paper, we propose the categorical reparameterization trick (CRT) that makes NMT models generate differentiable sentences so that the VAE's training framework can work in an end-to-end fashion. Our BT experiment conducted on a WMT benchmark dataset demonstrates the superiority of our proposed CRT compared to the Gumbel-softmax trick, which is a popular reparameterization method for categorical variable. Moreover, our experiments conducted on multiple WMT benchmark datasets demonstrate that our proposed end-to-end training framework is effective in terms of BLEU scores not only compared to its counterpart baseline which is not trained in an end-to-end fashion, but also compared to other previous BT works. The code is available at the web.
Authors: Yaoyiran Li, Fangyu Liu, Nigel Collier, Anna Korhonen, Ivan Vuli\'c
Abstract: Word translation or bilingual lexicon induction (BLI) is a key cross-lingual task, aiming to bridge the lexical gap between different languages. In this work, we propose a robust and effective two-stage contrastive learning framework for the BLI task. At Stage C1, we propose to refine standard cross-lingual linear maps between static word embeddings (WEs) via a contrastive learning objective; we also show how to integrate it into the self-learning procedure for even more refined cross-lingual maps. In Stage C2, we conduct BLI-oriented contrastive fine-tuning of mBERT, unlocking its word translation capability. We also show that static WEs induced from the `C2-tuned' mBERT complement static WEs from Stage C1. Comprehensive experiments on standard BLI datasets for diverse languages and different experimental setups demonstrate substantial gains achieved by our framework. While the BLI method from Stage C1 already yields substantial gains over all state-of-the-art BLI methods in our comparison, even stronger improvements are met with the full two-stage framework: e.g., we report gains for 112/112 BLI setups, spanning 28 language pairs.
Authors: Yang Cai, Argyris Oikonomou, Weiqiang Zheng
Abstract: We study constrained comonotone min-max optimization, a structured class of nonconvex-nonconcave min-max optimization problems, and their generalization to comonotone inclusion. In our first contribution, we extend the Extra Anchored Gradient (EAG) algorithm, originally proposed by Yoon and Ryu (2021) for unconstrained min-max optimization, to constrained comonotone min-max optimization and comonotone inclusion, achieving an optimal convergence rate of $O\left(\frac{1}{T}\right)$ among all first-order methods. Additionally, we prove that the algorithm's iterations converge to a point in the solution set. In our second contribution, we extend the Fast Extra Gradient (FEG) algorithm, as developed by Lee and Kim (2021), to constrained comonotone min-max optimization and comonotone inclusion, achieving the same $O\left(\frac{1}{T}\right)$ convergence rate. This rate is applicable to the broadest set of comonotone inclusion problems yet studied in the literature. Our analyses are based on simple potential function arguments, which might be useful for analyzing other accelerated algorithms.
Authors: Florent Chiaroni, Malik Boudiaf, Amar Mitiche, Ismail Ben Ayed
Abstract: We explore clustering the softmax predictions of deep neural networks and introduce a novel probabilistic clustering method, referred to as k-sBetas. In the general context of clustering discrete distributions, the existing methods focused on exploring distortion measures tailored to simplex data, such as the KL divergence, as alternatives to the standard Euclidean distance. We provide a general maximum a posteriori (MAP) perspective of clustering distributions, emphasizing that the statistical models underlying the existing distortion-based methods may not be descriptive enough. Instead, we optimize a mixed-variable objective measuring data conformity within each cluster to the introduced sBeta density function, whose parameters are constrained and estimated jointly with binary assignment variables. Our versatile formulation approximates various parametric densities for modeling simplex data and enables the control of the cluster-balance bias. This yields highly competitive performances for the unsupervised adjustment of black-box model predictions in various scenarios. Our code and comparisons with the existing simplex-clustering approaches and our introduced softmax-prediction benchmarks are publicly available: https://github.com/fchiaroni/Clustering_Softmax_Predictions.
URLs: https://github.com/fchiaroni/Clustering_Softmax_Predictions.
Authors: Xianbang Chen, Yikui Liu, Lei Wu
Abstract: Generally, day-ahead unit commitment (UC) is conducted in a predict-then-optimize process: it starts by predicting the renewable energy source (RES) availability and system reserve requirements; given the predictions, the UC model is then optimized to determine the economic operation plans. In fact, predictions within the process are raw. In other words, if the predictions are further tailored to assist UC in making the economic operation plans against realizations of the RES and reserve requirements, UC economics will benefit significantly. To this end, this paper presents a cost-oriented tailor of RES-and-reserve predictions for UC, deployed as an add-on to the predict-then-optimize process. The RES-and-reserve tailor is trained by solving a bi-level mixed-integer programming model: the upper level trains the tailor based on its induced operating cost; the lower level, given tailored predictions, mimics the system operation process and feeds the induced operating cost back to the upper level; finally, the upper level evaluates the training quality according to the fed-back cost. Through this training, the tailor learns to customize the raw predictions into cost-oriented predictions. Moreover, the tailor can be embedded into the existing predict-then-optimize process as an add-on, improving the UC economics. Lastly, the presented method is compared to traditional, binary-relaxation, neural network-based, stochastic, and robust methods.
Authors: Dong-Young Lim, Ariel Neufeld, Sotirios Sabanis, Ying Zhang
Abstract: We introduce a new Langevin dynamics based algorithm, called e-TH$\varepsilon$O POULA, to solve optimization problems with discontinuous stochastic gradients which naturally appear in real-world applications such as quantile estimation, vector quantization, CVaR minimization, and regularized optimization problems involving ReLU neural networks. We demonstrate both theoretically and numerically the applicability of the e-TH$\varepsilon$O POULA algorithm. More precisely, under the conditions that the stochastic gradient is locally Lipschitz in average and satisfies a certain convexity at infinity condition, we establish non-asymptotic error bounds for e-TH$\varepsilon$O POULA in Wasserstein distances and provide a non-asymptotic estimate for the expected excess risk, which can be controlled to be arbitrarily small. Three key applications in finance and insurance are provided, namely, multi-period portfolio optimization, transfer learning in multi-period portfolio optimization, and insurance claim prediction, which involve neural networks with (Leaky)-ReLU activation functions. Numerical experiments conducted using real-world datasets illustrate the superior empirical performance of e-TH$\varepsilon$O POULA compared to SGLD, TUSLA, ADAM, and AMSGrad in terms of model accuracy.
Authors: Haoran Zhang, Junhui Wang
Abstract: Longitudinal network consists of a sequence of temporal edges among multiple nodes, where the temporal edges are observed in real time. It has become ubiquitous with the rise of online social platform and e-commerce, but largely under-investigated in literature. In this paper, we propose an efficient estimation framework for longitudinal network, leveraging strengths of adaptive network merging, tensor decomposition and point process. It merges neighboring sparse networks so as to enlarge the number of observed edges and reduce estimation variance, whereas the estimation bias introduced by network merging is controlled by exploiting local temporal structures for adaptive network neighborhood. A projected gradient descent algorithm is proposed to facilitate estimation, where the upper bound of the estimation error in each iteration is established. A thorough analysis is conducted to quantify the asymptotic behavior of the proposed method, which shows that it can significantly reduce the estimation error and also provides guideline for network merging under various scenarios. We further demonstrate the advantage of the proposed method through extensive numerical experiments on synthetic datasets and a militarized interstate dispute dataset.
Authors: Iskander Azangulov, Andrei Smolensky, Alexander Terenin, Viacheslav Borovitskiy
Abstract: Gaussian processes are arguably the most important class of spatiotemporal models within machine learning. They encode prior information about the modeled function and can be used for exact or approximate Bayesian learning. In many applications, particularly in physical sciences and engineering, but also in areas such as geostatistics and neuroscience, invariance to symmetries is one of the most fundamental forms of prior information one can consider. The invariance of a Gaussian process' covariance to such symmetries gives rise to the most natural generalization of the concept of stationarity to such spaces. In this work, we develop constructive and practical techniques for building stationary Gaussian processes on a very large class of non-Euclidean spaces arising in the context of symmetries. Our techniques make it possible to (i) calculate covariance kernels and (ii) sample from prior and posterior Gaussian processes defined on such spaces, both in a practical manner. This work is split into two parts, each involving different technical considerations: part I studies compact spaces, while part II studies non-compact spaces possessing certain structure. Our contributions make the non-Euclidean Gaussian process models we study compatible with well-understood computational techniques available in standard Gaussian process software packages, thereby making them accessible to practitioners.
Authors: Jung Hwan Heo, Seyedarmin Azizi, Arash Fayyazi, Massoud Pedram
Abstract: Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve token merging by adding the perspectives of 1) activation outliers and 2) hierarchical representations. Through a careful analysis of the attention behavior in ViTs, we characterize a delayed onset of the convergent attention phenomenon, which makes token merging undesirable in the bottom blocks of ViTs. Moreover, we augment token merging with a hierarchical processing scheme to capture multi-scale redundancy between visual tokens. Combining these two insights, we build a unified inference framework called DSM: Delayed Spatial Merging. We extensively evaluate DSM on various ViT model scales (Tiny to Huge) and tasks (ImageNet-1k and transfer learning), achieving up to 1.8$\times$ FLOP reduction and 1.6$\times$ throughput speedup at a negligible loss while being two orders of magnitude faster than existing methods.
Authors: Xinyang Liu, Dongsheng Wang, Bowei Fang, Miaoge Li, Zhibin Duan, Yishi Xu, Bo Chen, Mingyuan Zhou
Abstract: For downstream applications of vision-language pre-trained models, there has been significant interest in constructing effective prompts. Existing works on prompt engineering, which either require laborious manual designs or optimize the prompt tuning as a point estimation problem, may fail to describe diverse characteristics of categories and limit their applications. We introduce a Bayesian probabilistic resolution to prompt tuning, where the label-specific stochastic prompts are generated hierarchically by first sampling a latent vector from an underlying distribution and then employing a lightweight generative model. Importantly, we semantically regularize the tuning process by minimizing the statistical distance between the visual patches and linguistic prompts, which pushes the stochastic label representations to faithfully capture diverse visual concepts, instead of overfitting the training categories. We evaluate the effectiveness of our approach on four tasks: few-shot image recognition, base-to-new generalization, dataset transfer learning, and domain shifts. Extensive results over 15 datasets show promising transferability and generalization performance of our proposed model, both quantitatively and qualitatively.
Authors: Emilio Cruciani, Emanuela L. Giacomelli, Jinyeop Lee
Abstract: Complex networked systems in fields such as physics, biology, and social sciences often involve interactions that extend beyond simple pairwise ones. Hypergraphs serve as powerful modeling tools for describing and analyzing the intricate behaviors of systems with multi-body interactions. Herein, we investigate a discrete-time nonlinear averaging dynamics with three-body interactions: an underlying hypergraph, comprising triples as hyperedges, delineates the structure of these interactions, while the vertices update their states through a weighted, state-dependent average of neighboring pairs' states. This dynamics captures reinforcing group effects, such as peer pressure, and exhibits higher-order dynamical effects resulting from a complex interplay between initial states, hypergraph topology, and nonlinearity of the update. Differently from linear averaging dynamics on graphs with two-body interactions, this model does not converge to the average of the initial states but rather induces a shift. By assuming random initial states and by making some regularity and density assumptions on the hypergraph, we prove that the dynamics converges to a multiplicatively-shifted average of the initial states, with high probability. We further characterize the shift as a function of two parameters describing the initial state and interaction strength, as well as the convergence time as a function of the hypergraph structure.
Authors: Jiechen Chen, Sangwoo Park, Osvaldo Simeone
Abstract: Spiking neural networks (SNNs) process time-series data via internal event-driven neural dynamics. The energy consumption of an SNN depends on the number of spikes exchanged between neurons over the course of the input presentation. Typically, decisions are produced after the entire input sequence has been processed. This results in latency and energy consumption levels that are fairly uniform across inputs. However, as explored in recent work, SNNs can produce an early decision when the SNN model is sufficiently ``confident'', adapting delay and energy consumption to the difficulty of each example. Existing techniques are based on heuristic measures of confidence that do not provide reliability guarantees, potentially exiting too early. In this paper, we introduce a novel delay-adaptive SNN-based inference methodology that, wrapping around any pre-trained SNN classifier, provides guaranteed reliability for the decisions produced at input-dependent stopping times. The approach, dubbed SpikeCP, leverages tools from conformal prediction (CP). It entails minimal complexity increase as compared to the underlying SNN, requiring only additional thresholding and counting operations at run time. SpikeCP is also extended to integrate a CP-aware training phase that targets delay performance. Variants of CP based on alternative confidence correction schemes, from Bonferroni to Simes, are explored, and extensive experiments are described using the MNIST-DVS data set, DVS128 Gesture dataset, and CIFAR-10 dataset.
Authors: Julia Herbinger, Marvin N. Wright, Thomas Nagler, Bernd Bischl, Giuseppe Casalicchio
Abstract: Global feature effect methods, such as partial dependence plots, provide an intelligible visualization of the expected marginal feature effect. However, such global feature effect methods can be misleading, as they do not represent local feature effects of single observations well when feature interactions are present. We formally introduce generalized additive decomposition of global effects (GADGET), which is a new framework based on recursive partitioning to find interpretable regions in the feature space such that the interaction-related heterogeneity of local feature effects is minimized. We provide a mathematical foundation of the framework and show that it is applicable to the most popular methods to visualize marginal feature effects, namely partial dependence, accumulated local effects, and Shapley additive explanations (SHAP) dependence. Furthermore, we introduce and validate a new permutation-based interaction test to detect significant feature interactions that is applicable to any feature effect method that fits into our proposed framework. We empirically evaluate the theoretical characteristics of the proposed methods based on various feature effect methods in different experimental settings. Moreover, we apply our introduced methodology to three real-world examples to showcase their usefulness.
Authors: Yuan Yuan, Kristen M. Altenburger
Abstract: The reliability of controlled experiments, commonly referred to as "A/B tests," is often compromised by network interference, where the outcomes of individual units are influenced by interactions with others. Significant challenges in this domain include the lack of accounting for complex social network structures and the difficulty in suitably characterizing network interference. To address these challenges, we propose a machine learning-based method. We introduce "causal network motifs" and utilize transparent machine learning models to characterize network interference patterns underlying an A/B test on networks. Our method's performance has been demonstrated through simulations on both a synthetic experiment and a large-scale test on Instagram. Our experiments show that our approach outperforms conventional methods such as design-based cluster randomization and conventional analysis-based neighborhood exposure mapping. Our approach provides a comprehensive and automated solution to address network interference for A/B testing practitioners. This aids in informing strategic business decisions in areas such as marketing effectiveness and product customization.
Authors: Diksha Bhandari, Jakiw Pidstrigach, Sebastian Reich
Abstract: We consider the problem of performing Bayesian inference for logistic regression using appropriate extensions of the ensemble Kalman filter. Two interacting particle systems are proposed that sample from an approximate posterior and prove quantitative convergence rates of these interacting particle systems to their mean-field limit as the number of particles tends to infinity. Furthermore, we apply these techniques and examine their effectiveness as methods of Bayesian approximation for quantifying predictive uncertainty in neural networks.
Authors: Vishakh Padmakumar, He He
Abstract: Large language models (LLMs) have led to a surge in collaborative writing with model assistance. As different users incorporate suggestions from the same model, there is a risk of decreased diversity in the produced content, potentially limiting diverse perspectives in public discourse. In this work, we measure the impact of co-writing on diversity via a controlled experiment, where users write argumentative essays in three setups -- using a base LLM (GPT3), a feedback-tuned LLM (InstructGPT), and writing without model help. We develop a set of diversity metrics and find that writing with InstructGPT (but not the GPT3) results in a statistically significant reduction in diversity. Specifically, it increases the similarity between the writings of different authors and reduces the overall lexical and content diversity. We additionally find that this effect is mainly attributable to InstructGPT contributing less diverse text to co-written essays. In contrast, the user-contributed text remains unaffected by model collaboration. This suggests that the recent improvement in generation quality from adapting models to human feedback might come at the cost of more homogeneous and less diverse content.
Authors: Alec Edwards, Andrea Peruffo, Alessandro Abate
Abstract: An emerging branch of control theory specialises in certificate learning, concerning the specification of a desired (possibly complex) system behaviour for an autonomous or control model, which is then analytically verified by means of a function-based proof. However, the synthesis of controllers abiding by these complex requirements is in general a non-trivial task and may elude the most expert control engineers. This results in a need for automatic techniques that are able to design controllers and to analyse a wide range of elaborate specifications. In this paper, we provide a general framework to encode system specifications and define corresponding certificates, and we present an automated approach to formally synthesise controllers and certificates. Our approach contributes to the broad field of safe learning for control, exploiting the flexibility of neural networks to provide candidate control and certificate functions, whilst using SMT-solvers to offer a formal guarantee of correctness. We test our framework by developing a prototype software tool, and assess its efficacy at verification via control and certificate synthesis over a large and varied suite of benchmarks.
Authors: Arnab Bhattacharyya, Sutanu Gayen, Kuldeep S. Meel, Dimitrios Myrisiotis, A. Pavan, N. V. Vinodchandran
Abstract: In this paper, we establish a novel connection between total variation (TV) distance estimation and probabilistic inference. In particular, we present an efficient, structure-preserving reduction from relative approximation of TV distance to probabilistic inference over directed graphical models. This reduction leads to a fully polynomial randomized approximation scheme (FPRAS) for estimating TV distances between same-structure distributions over any class of Bayes nets for which there is an efficient probabilistic inference algorithm. In particular, it leads to an FPRAS for estimating TV distances between distributions that are defined over a common Bayes net of small treewidth. Prior to this work, such approximation schemes only existed for estimating TV distances between product distributions. Our approach employs a new notion of $partial$ couplings of high-dimensional distributions, which might be of independent interest.
Authors: Daniel Seichter, Benedict Stephan, S\"ohnke Benedikt Fischedick, Steffen M\"uller, Leonard Rabes, Horst-Michael Gross
Abstract: As the application scenarios of mobile robots are getting more complex and challenging, scene understanding becomes increasingly crucial. A mobile robot that is supposed to operate autonomously in indoor environments must have precise knowledge about what objects are present, where they are, what their spatial extent is, and how they can be reached; i.e., information about free space is also crucial. Panoptic mapping is a powerful instrument providing such information. However, building 3D panoptic maps with high spatial resolution is challenging on mobile robots, given their limited computing capabilities. In this paper, we propose PanopticNDT - an efficient and robust panoptic mapping approach based on occupancy normal distribution transform (NDT) mapping. We evaluate our approach on the publicly available datasets Hypersim and ScanNetV2. The results reveal that our approach can represent panoptic information at a higher level of detail than other state-of-the-art approaches while enabling real-time panoptic mapping on mobile robots. Finally, we prove the real-world applicability of PanopticNDT with qualitative results in a domestic application.
Authors: Zhihan Liu, Hao Hu, Shenao Zhang, Hongyi Guo, Shuqi Ke, Boyi Liu, Zhaoran Wang
Abstract: Large language models (LLMs) demonstrate impressive reasoning abilities, but translating reasoning into actions in the real world remains challenging. In particular, it remains unclear how to complete a given task provably within a minimum number of interactions with the external environment, e.g., through an internal mechanism of reasoning. To this end, we propose a principled framework with provable regret guarantees to orchestrate reasoning and acting, which we call "reason for future, act for now" (\texttt{RAFA}). Specifically, we design a prompt template for reasoning that learns from the memory buffer and plans a future trajectory over a long horizon ("reason for future"). At each step, the LLM agent takes the initial action of the planned trajectory ("act for now"), stores the collected feedback in the memory buffer, and reinvokes the reasoning routine to replan the future trajectory from the new state. The key idea is to cast reasoning in LLMs as learning and planning in Bayesian adaptive Markov decision processes (MDPs). Correspondingly, we prompt LLMs to form an updated posterior of the unknown environment from the memory buffer (learning) and generate an optimal trajectory for multiple future steps that maximizes a value function (planning). The learning and planning subroutines are performed in an "in-context" manner to emulate the actor-critic update for MDPs. Our theoretical analysis proves that the novel combination of long-term reasoning and short-term acting achieves a $\sqrt{T}$ regret. Here, $T$ denotes the number of online interactions. In particular, the regret bound highlights an intriguing interplay between the prior knowledge obtained through pretraining and the uncertainty reduction achieved by reasoning and acting. Our empirical validation shows that it outperforms various existing frameworks and achieves nearly perfect scores on a few benchmarks.
Authors: Zander W. Blasingame, Chen Liu
Abstract: Diffusion Morphs (DiM) are a recent state-of-the-art method for creating high quality face morphs; however, they require a high number of network function evaluations (NFE) to create the morphs. We propose a new DiM pipeline, Fast-DiM, which can create morphs of a similar quality but with fewer NFE. We investigate the ODE solvers used to solve the Probability Flow ODE and the impact they have on the the creation of face morphs. Additionally, we employ an alternative method for encoding images into the latent space of the Diffusion model by solving the Probability Flow ODE as time runs forwards. Our experiments show that we can reduce the NFE by upwards of 85% in the encoding process while experiencing only 1.6\% reduction in Mated Morph Presentation Match Rate (MMPMR). Likewise, we showed we could cut NFE, in the sampling process, in half with only a maximal reduction of 0.23% in MMPMR.
Authors: Rui Yan, Gabriel Santos, Gethin Norman, David Parker, Marta Kwiatkowska
Abstract: Stochastic games are a well established model for multi-agent sequential decision making under uncertainty. In practical applications, though, agents often have only partial observability of their environment. Furthermore, agents increasingly perceive their environment using data-driven approaches such as neural networks trained on continuous data. We propose the model of neuro-symbolic partially-observable stochastic games (NS-POSGs), a variant of continuous-space concurrent stochastic games that explicitly incorporates neural perception mechanisms. We focus on a one-sided setting with a partially-informed agent using discrete, data-driven observations and another, fully-informed agent. We present a new method, called one-sided NS-HSVI, for approximate solution of one-sided NS-POSGs, which exploits the piecewise constant structure of the model. Using neural network pre-image analysis to construct finite polyhedral representations and particle-based representations for beliefs, we implement our approach and illustrate its practical applicability to the analysis of pedestrian-vehicle and pursuit-evasion scenarios.
Authors: Jana Gauss, Fabian Scheipl, Moritz Herrmann
Abstract: Whether class labels in a given data set correspond to meaningful clusters is crucial for the evaluation of clustering algorithms using real-world data sets. This property can be quantified by separability measures. The central aspects of separability for density-based clustering are between-class separation and within-class connectedness, and neither classification-based complexity measures nor cluster validity indices (CVIs) adequately incorporate them. A newly developed measure (density cluster separability index, DCSI) aims to quantify these two characteristics and can also be used as a CVI. Extensive experiments on synthetic data indicate that DCSI correlates strongly with the performance of DBSCAN measured via the adjusted Rand index (ARI) but lacks robustness when it comes to multi-class data sets with overlapping classes that are ill-suited for density-based hard clustering. Detailed evaluation on frequently used real-world data sets shows that DCSI can correctly identify touching or overlapping classes that do not correspond to meaningful density-based clusters.
Authors: Feng Chen, Liqin Wang, Julie Hong, Jiaqi Jiang, Li Zhou
Abstract: Objectives: Leveraging artificial intelligence (AI) in conjunction with electronic health records (EHRs) holds transformative potential to improve healthcare. Yet, addressing bias in AI, which risks worsening healthcare disparities, cannot be overlooked. This study reviews methods to detect and mitigate diverse forms of bias in AI models developed using EHR data. Methods: We conducted a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines, analyzing articles from PubMed, Web of Science, and IEEE published between January 1, 2010, and Dec 17, 2023. The review identified key biases, outlined strategies for detecting and mitigating bias throughout the AI model development process, and analyzed metrics for bias assessment. Results: Of the 450 articles retrieved, 20 met our criteria, revealing six major bias types: algorithmic, confounding, implicit, measurement, selection, and temporal. The AI models were primarily developed for predictive tasks in healthcare settings. Four studies concentrated on the detection of implicit and algorithmic biases employing fairness metrics like statistical parity, equal opportunity, and predictive equity. Sixty proposed various strategies for mitigating biases, especially targeting implicit and selection biases. These strategies, evaluated through both performance (e.g., accuracy, AUROC) and fairness metrics, predominantly involved data collection and preprocessing techniques like resampling, reweighting, and transformation. Discussion: This review highlights the varied and evolving nature of strategies to address bias in EHR-based AI models, emphasizing the urgent needs for the establishment of standardized, generalizable, and interpretable methodologies to foster the creation of ethical AI systems that promote fairness and equity in healthcare.
Authors: Emma A. M. Stanley, Raissa Souza, Anthony Winder, Vedant Gulve, Kimberly Amador, Matthias Wilms, Nils D. Forkert
Abstract: Artificial intelligence (AI) models trained using medical images for clinical tasks often exhibit bias in the form of disparities in performance between subgroups. Since not all sources of biases in real-world medical imaging data are easily identifiable, it is challenging to comprehensively assess how those biases are encoded in models, and how capable bias mitigation methods are at ameliorating performance disparities. In this article, we introduce a novel analysis framework for systematically and objectively investigating the impact of biases in medical images on AI models. We developed and tested this framework for conducting controlled in silico trials to assess bias in medical imaging AI using a tool for generating synthetic magnetic resonance images with known disease effects and sources of bias. The feasibility is showcased by using three counterfactual bias scenarios to measure the impact of simulated bias effects on a convolutional neural network (CNN) classifier and the efficacy of three bias mitigation strategies. The analysis revealed that the simulated biases resulted in expected subgroup performance disparities when the CNN was trained on the synthetic datasets. Moreover, reweighing was identified as the most successful bias mitigation strategy for this setup, and we demonstrated how explainable AI methods can aid in investigating the manifestation of bias in the model using this framework. Developing fair AI models is a considerable challenge given that many and often unknown sources of biases can be present in medical imaging datasets. In this work, we present a novel methodology to objectively study the impact of biases and mitigation strategies on deep learning pipelines, which can support the development of clinical AI that is robust and responsible.
Authors: Tal Schuster, Adam D. Lelkes, Haitian Sun, Jai Gupta, Jonathan Berant, William W. Cohen, Donald Metzler
Abstract: Recently proposed long-form question answering (QA) systems, supported by large language models (LLMs), have shown promising capabilities. Yet, attributing and verifying their generated abstractive answers can be difficult, and automatically evaluating their accuracy remains an ongoing challenge. In this work, we introduce a new QA task for answering multi-answer questions by summarizing multiple diverse sources in a semi-extractive fashion. Specifically, Semi-extractive Multi-source QA (SEMQA) requires models to output a comprehensive answer, while mixing factual quoted spans -- copied verbatim from given input sources -- and non-factual free-text connectors that glue these spans together into a single cohesive passage. This setting bridges the gap between the outputs of well-grounded but constrained extractive QA systems and more fluent but harder to attribute fully abstractive answers. Particularly, it enables a new mode for language models that leverages their advanced language generation capabilities, while also producing fine in-line attributions by-design that are easy to verify, interpret, and evaluate. To study this task, we create the first dataset of this kind, QuoteSum, with human-written semi-extractive answers to natural and generated questions, and define text-based evaluation metrics. Experimenting with several LLMs in various settings, we find this task to be surprisingly challenging, demonstrating the importance of QuoteSum for developing and studying such consolidation capabilities.
Authors: Han Guo, Philip Greengard, Eric P. Xing, Yoon Kim
Abstract: We propose a simple approach for memory-efficient adaptation of pretrained language models. Our approach uses an iterative algorithm to decompose each pretrained matrix into a high-precision low-rank component and a memory-efficient quantized component. During finetuning, the quantized component remains fixed and only the low-rank component is updated. We present an integer linear programming formulation of the quantization component which enables dynamic configuration of quantization parameters (e.g., bit-width, block size) for each matrix given an overall target memory budget. We further explore a data-aware version of the algorithm which uses an approximation of the Fisher information matrix to weight the reconstruction objective during matrix decomposition. Experiments on finetuning RoBERTa and LLaMA-2 (7B and 70B) demonstrate that our low-rank plus quantized matrix decomposition approach (LQ-LoRA) outperforms strong QLoRA and GPTQ-LoRA baselines and enables aggressive quantization to sub-3 bits with only minor performance degradations. When finetuned on a language modeling calibration dataset, LQ-LoRA can also be used for model compression; in this setting our 2.75-bit LLaMA-2-70B model (which has 2.85 bits on average when including the low-rank components and requires 27GB of GPU memory) performs respectably compared to the 16-bit baseline.
Authors: Yaran Chen, Wenbo Cui, Yuanwen Chen, Mining Tan, Xinyao Zhang, Dongbin Zhao, He Wang
Abstract: Robotic agents must master common sense and long-term sequential decisions to solve daily tasks through natural language instruction. The developments in Large Language Models (LLMs) in natural language processing have inspired efforts to use LLMs in complex robot planning. Despite LLMs' great generalization and comprehension of instruction tasks, LLMs-generated task plans sometimes lack feasibility and correctness. To address the problem, we propose a RoboGPT agent\footnote{our code and dataset will be released soon} for making embodied long-term decisions for daily tasks, with two modules: 1) LLMs-based planning with re-plan to break the task into multiple sub-goals; 2) RoboSkill individually designed for sub-goals to learn better navigation and manipulation skills. The LLMs-based planning is enhanced with a new robotic dataset and re-plan, called RoboGPT. The new robotic dataset of 67k daily instruction tasks is gathered for fine-tuning the Llama model and obtaining RoboGPT. RoboGPT planner with strong generalization can plan hundreds of daily instruction tasks. Additionally, a low-computational Re-Plan module is designed to allow plans to flexibly adapt to the environment, thereby addressing the nomenclature diversity challenge. The proposed RoboGPT agent outperforms SOTA methods on the ALFRED daily tasks. Moreover, RoboGPT planner exceeds SOTA LLM-based planners like ChatGPT in task-planning rationality for hundreds of unseen daily tasks, and even other domain tasks, while keeping the large model's original broad application and generality.
Authors: Carles Domingo-Enrich, Jiequn Han, Brandon Amos, Joan Bruna, Ricky T. Q. Chen
Abstract: Stochastic optimal control, which has the goal of driving the behavior of noisy systems, is broadly applicable in science, engineering and artificial intelligence. Our work introduces Stochastic Optimal Control Matching (SOCM), a novel Iterative Diffusion Optimization (IDO) technique for stochastic optimal control that stems from the same philosophy as the conditional score matching loss for diffusion models. That is, the control is learned via a least squares problem by trying to fit a matching vector field. The training loss, which is closely connected to the cross-entropy loss, is optimized with respect to both the control function and a family of reparameterization matrices which appear in the matching vector field. The optimization with respect to the reparameterization matrices aims at minimizing the variance of the matching vector field. Experimentally, our algorithm achieves lower error than all the existing IDO techniques for stochastic optimal control for three out of four control problems, in some cases by an order of magnitude. The key idea underlying SOCM is the path-wise reparameterization trick, a novel technique that may be of independent interest. Code at https://github.com/facebookresearch/SOC-matching
Authors: Bingbing Hu, Evangelos Kosinas, Adam Polak
Abstract: The problem of designing connectivity oracles supporting vertex failures is one of the basic data structures problems for undirected graphs. It is already well understood: previous works [Duan--Pettie STOC'10; Long--Saranurak FOCS'22] achieve query time linear in the number of failed vertices, and it is conditionally optimal as long as we require preprocessing time polynomial in the size of the graph and update time polynomial in the number of failed vertices. We revisit this problem in the paradigm of algorithms with predictions: we ask if the query time can be improved if the set of failed vertices can be predicted beforehand up to a small number of errors. More specifically, we design a data structure that, given a graph $G=(V,E)$ and a set of vertices predicted to fail $\widehat{D} \subseteq V$ of size $d=|\widehat{D}|$, preprocesses it in time $\tilde{O}(d|E|)$ and then can receive an update given as the symmetric difference between the predicted and the actual set of failed vertices $\widehat{D} \triangle D = (\widehat{D} \setminus D) \cup (D \setminus \widehat{D})$ of size $\eta = |\widehat{D} \triangle D|$, process it in time $\tilde{O}(\eta^4)$, and after that answer connectivity queries in $G \setminus D$ in time $O(\eta)$. Viewed from another perspective, our data structure provides an improvement over the state of the art for the \emph{fully dynamic subgraph connectivity problem} in the \emph{sensitivity setting} [Henzinger--Neumann ESA'16]. We argue that the preprocessing time and query time of our data structure are conditionally optimal under standard fine-grained complexity assumptions.
Authors: Zhongkun Liu, Zheng Chen, Mengqi Zhang, Zhaochun Ren, Pengjie Ren, Zhumin Chen
Abstract: Fine-tuning has been demonstrated to be an effective method to improve the domain performance of large language models (LLMs). However, LLMs might fit the dataset bias and shortcuts for prediction, leading to poor generation performance. Previous works have proven that LLMs are prone to exhibit position bias, i.e., leveraging information positioned at the beginning or end, or specific positional cues within the input. Existing debiasing methods for LLMs require external bias knowledge or annotated non-biased samples, which is lacking for position debiasing and impractical in reality. In this work, we propose a self-supervised position debiasing (SOD) framework to mitigate position bias for LLMs. SOD leverages unsupervised responses from pre-trained LLMs for debiasing without relying on any external knowledge. To improve the quality of unsupervised responses, we propose an objective alignment (OAM) module to prune these responses. Experiments on eight datasets and five tasks show that SOD consistently outperforms existing methods in mitigating three types of position biases. Besides, SOD achieves this by sacrificing only a small performance on biased samples, which is general and effective. To facilitate the reproducibility of the results, we share the code of all methods and datasets on https://github.com/LZKSKY/SOD.
Authors: Wang Chao, Jiaxuan Zhao, Licheng Jiao, Lingling Li, Fang Liu, Shuyuan Yang
Abstract: Pre-trained large language models (LLMs) have powerful capabilities for generating creative natural text. Evolutionary algorithms (EAs) can discover diverse solutions to complex real-world problems. Motivated by the common collective and directionality of text generation and evolution, this paper illustrates the parallels between LLMs and EAs, which includes multiple one-to-one key characteristics: token representation and individual representation, position encoding and fitness shaping, position embedding and selection, Transformers block and reproduction, and model training and parameter adaptation. By examining these parallels, we analyze existing interdisciplinary research, with a specific focus on evolutionary fine-tuning and LLM-enhanced EAs. Drawing from these insights, valuable future directions are presented for advancing the integration of LLMs and EAs, while highlighting key challenges along the way. These parallels not only reveal the evolution mechanism behind LLMs but also facilitate the development of evolved artificial agents that approach or surpass biological organisms.
Authors: Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
Abstract: Detecting text generated by modern large language models is thought to be hard, as both LLMs and humans can exhibit a wide range of complex behaviors. However, we find that a score based on contrasting two closely related language models is highly accurate at separating human-generated and machine-generated text. Based on this mechanism, we propose a novel LLM detector that only requires simple calculations using a pair of pre-trained LLMs. The method, called Binoculars, achieves state-of-the-art accuracy without any training data. It is capable of spotting machine text from a range of modern LLMs without any model-specific modifications. We comprehensively evaluate Binoculars on a number of text sources and in varied situations. Over a wide range of document types, Binoculars detects over 90% of generated samples from ChatGPT (and other LLMs) at a false positive rate of 0.01%, despite not being trained on any ChatGPT data.
Authors: Enzhi Li, Scott Nickleach, Bilal Fadlallah
Abstract: A hypergraph is a generalization of a graph that arises naturally when attribute-sharing among entities is considered. Compared to graphs, hypergraphs have the distinct advantage that they contain explicit communities and are more convenient to manipulate. An open problem in hypergraph research is how to accurately and efficiently calculate node distances on hypergraphs. Estimating node distances enables us to find a node's nearest neighbors, which has important applications in such areas as recommender system, targeted ads, etc. In this paper, we propose using expected hitting times of random walks to compute hypergraph node distances. We note that simple random walks (SRW) cannot accurately compute node distances on highly complex real-world hypergraphs, which motivates us to introduce frustrated random walks (FRW) for this task. We further benchmark our method against DeepWalk, and show that while the latter can achieve comparable results, FRW has a distinct computational advantage in cases where the number of targets is fairly small. For such cases, we show that FRW runs in significantly shorter time than DeepWalk. Finally, we analyze the time complexity of our method, and show that for large and sparse hypergraphs, the complexity is approximately linear, rendering it superior to the DeepWalk alternative.
Authors: Junxu Liu, Jian Lou, Li Xiong, Jinfei Liu, Xiaofeng Meng
Abstract: Federated learning (FL) enhanced by differential privacy has emerged as a popular approach to better safeguard the privacy of client-side data by protecting clients' contributions during the training process. Existing solutions typically assume a uniform privacy budget for all records and provide one-size-fits-all solutions that may not be adequate to meet each record's privacy requirement. In this paper, we explore the uncharted territory of cross-silo FL with record-level personalized differential privacy. We devise a novel framework named \textit{rPDP-FL}, employing a two-stage hybrid sampling scheme with both uniform client-level sampling and non-uniform record-level sampling to accommodate varying privacy requirements. A critical and non-trivial problem is how to determine the ideal per-record sampling probability $q$ given the personalized privacy budget $\varepsilon$. We introduce a versatile solution named \textit{Simulation-CurveFitting}, allowing us to uncover a significant insight into the nonlinear correlation between $q$ and $\varepsilon$ and derive an elegant mathematical model to tackle the problem. Our evaluation demonstrates that our solution can provide significant performance gains over the baselines that do not consider personalized privacy preservation.
Authors: Hamed Amini Amirkolaee, Miaojing Shi, Lianghua He, Mark Mulligan
Abstract: The process of estimating and counting tree density using only a single aerial or satellite image is a difficult task in the fields of photogrammetry and remote sensing. However, it plays a crucial role in the management of forests. The huge variety of trees in varied topography severely hinders tree counting models to perform well. The purpose of this paper is to propose a framework that is learnt from the source domain with sufficient labeled trees and is adapted to the target domain with only a limited number of labeled trees. Our method, termed as AdaTreeFormer, contains one shared encoder with a hierarchical feature extraction scheme to extract robust features from the source and target domains. It also consists of three subnets: two for extracting self-domain attention maps from source and target domains respectively and one for extracting cross-domain attention maps. For the latter, an attention-to-adapt mechanism is introduced to distill relevant information from different domains while generating tree density maps; a hierarchical cross-domain feature alignment scheme is proposed that progressively aligns the features from the source and target domains. We also adopt adversarial learning into the framework to further reduce the gap between source and target domains. Our AdaTreeFormer is evaluated on six designed domain adaptation tasks using three tree counting datasets, \ie Jiangsu, Yosemite, and London. Experimental results show that AdaTreeFormer significantly surpasses the state of the art, \eg in the cross domain from the Yosemite to Jiangsu dataset, it achieves a reduction of 15.9 points in terms of the absolute counting errors and an increase of 10.8\% in the accuracy of the detected trees' locations. The codes and datasets are available at https://github.com/HAAClassic/AdaTreeFormer.
Authors: Yatin Dandi, Emanuele Troiani, Luca Arnaboldi, Luca Pesce, Lenka Zdeborov\'a, Florent Krzakala
Abstract: We investigate the training dynamics of two-layer neural networks when learning multi-index target functions. We focus on multi-pass gradient descent (GD) that reuses the batches multiple times and show that it significantly changes the conclusion about which functions are learnable compared to single-pass gradient descent. In particular, multi-pass GD with finite stepsize is found to overcome the limitations of gradient flow and single-pass GD given by the information exponent (Ben Arous et al., 2021) and leap exponent (Abbe et al., 2023) of the target function. We show that upon re-using batches, the network achieves in just two time steps an overlap with the target subspace even for functions not satisfying the staircase property (Abbe et al., 2021). We characterize the (broad) class of functions efficiently learned in finite time. The proof of our results is based on the analysis of the Dynamical Mean-Field Theory (DMFT). We further provide a closed-form description of the dynamical process of the low-dimensional projections of the weights, and numerical experiments illustrating the theory.
Authors: Mohammad Hashemi, Shengbo Gong, Juntong Ni, Wenqi Fan, B. Aditya Prakash, Wei Jin
Abstract: Many real-world datasets can be naturally represented as graphs, spanning a wide range of domains. However, the increasing complexity and size of graph datasets present significant challenges for analysis and computation. In response, graph reduction, or graph summarization, has gained prominence for simplifying large graphs while preserving essential properties. In this survey, we aim to provide a comprehensive understanding of graph reduction methods, including graph sparsification, graph coarsening, and graph condensation. Specifically, we establish a unified definition for these methods and introduce a hierarchical taxonomy to categorize the challenges they address. Our survey then systematically reviews the technical details of these methods and emphasizes their practical applications across diverse scenarios. Furthermore, we outline critical research directions to ensure the continued effectiveness of graph reduction techniques, as well as provide a comprehensive paper list at \url{https://github.com/Emory-Melody/awesome-graph-reduction}. We hope this survey will bridge literature gaps and propel the advancement of this promising field.
URLs: https://github.com/Emory-Melody/awesome-graph-reduction
Authors: Natasha Butt, Blazej Manczak, Auke Wiggers, Corrado Rainone, David W. Zhang, Micha\"el Defferrard, Taco Cohen
Abstract: Large language models are increasingly solving tasks that are commonly believed to require human-level reasoning ability. However, these models still perform very poorly on benchmarks of general intelligence such as the Abstraction and Reasoning Corpus (ARC). In this paper, we approach ARC as a programming-by-examples problem, and introduce a novel and scalable method for language model self-improvement called Code Iteration (CodeIt). Our method iterates between 1) program sampling and hindsight relabeling, and 2) learning from prioritized experience replay. By relabeling the goal of an episode (i.e., the target program output given input) to the realized output produced by the sampled program, our method effectively deals with the extreme sparsity of rewards in program synthesis. Applying CodeIt to the ARC dataset, we demonstrate that prioritized hindsight replay, along with pre-training and data-augmentation, leads to successful inter-task generalization. CodeIt is the first neuro-symbolic approach that scales to the full ARC evaluation dataset. Our method solves 15% of ARC evaluation tasks, achieving state-of-the-art performance and outperforming existing neural and symbolic baselines. Our code is available at https://github.com/Qualcomm-AI-research/codeit .
Authors: Luca Masserano, Alex Shen, Michele Doro, Tommaso Dorigo, Rafael Izbicki, Ann B. Lee
Abstract: An open scientific challenge is how to classify events with reliable measures of uncertainty, when we have a mechanistic model of the data-generating process but the distribution over both labels and latent nuisance parameters is different between train and target data. We refer to this type of distributional shift as generalized label shift (GLS). Direct classification using observed data $\mathbf{X}$ as covariates leads to biased predictions and invalid uncertainty estimates of labels $Y$. We overcome these biases by proposing a new method for robust uncertainty quantification that casts classification as a hypothesis testing problem under nuisance parameters. The key idea is to estimate the classifier's receiver operating characteristic (ROC) across the entire nuisance parameter space, which allows us to devise cutoffs that are invariant under GLS. Our method effectively endows a pre-trained classifier with domain adaptation capabilities and returns valid prediction sets while maintaining high power. We demonstrate its performance on two challenging scientific problems in biology and astroparticle physics with data from realistic mechanistic models.
Authors: Gholamali Aminian, Yixuan He, Gesine Reinert, {\L}ukasz Szpruch, Samuel N. Cohen
Abstract: This work provides a theoretical framework for assessing the generalization error of graph neural networks in the over-parameterized regime, where the number of parameters surpasses the quantity of data points. We explore two widely utilized types of graph neural networks: graph convolutional neural networks and message passing graph neural networks. Prior to this study, existing bounds on the generalization error in the over-parametrized regime were uninformative, limiting our understanding of over-parameterized network performance. Our novel approach involves deriving upper bounds within the mean-field regime for evaluating the generalization error of these graph neural networks. We establish upper bounds with a convergence rate of $O(1/n)$, where $n$ is the number of graph samples. These upper bounds offer a theoretical assurance of the networks' performance on unseen data in the challenging over-parameterized regime and overall contribute to our understanding of their performance.
Authors: Ju-Hyung Lee, Dong-Ho Lee, Joohan Lee, Jay Pujara
Abstract: The burgeoning field of on-device AI communication, where devices exchange information directly through embedded foundation models, such as language models (LMs), requires robust, efficient, and generalizable communication frameworks. However, integrating these frameworks with existing wireless systems and effectively managing noise and bit errors pose significant challenges. In this work, we introduce a practical ondevice AI communication framework, integrated with physical layer (PHY) communication functions, demonstrated through its performance on a link-level simulator. Our framework incorporates end-to-end training with channel noise to enhance resilience, incorporates vector quantized variational autoencoders (VQ-VAE) for efficient and robust communication, and utilizes pre-trained encoder-decoder transformers for improved generalization capabilities. Simulations, across various communication scenarios, reveal that our framework achieves a 50% reduction in transmission size while demonstrating substantial generalization ability and noise robustness under standardized 3GPP channel models.
Authors: Hang Li, Tianlong Xu, Chaoli Zhang, Eason Chen, Jing Liang, Xing Fan, Haoyang Li, Jiliang Tang, Qingsong Wen
Abstract: The recent surge in generative AI technologies, such as large language models and diffusion models, has boosted the development of AI applications in various domains, including science, finance, and education. Concurrently, adaptive learning, a concept that has gained substantial interest in the educational sphere, has proven its efficacy in enhancing students' learning efficiency. In this position paper, we aim to shed light on the intersectional studies of these two methods, which combine generative AI with adaptive learning concepts. By presenting discussions about the benefits, challenges, and potentials in this field, we argue that this union will contribute significantly to the development of the next-stage learning format in education.
Authors: Zeyu He, Chieh-Yang Huang, Chien-Kuang Cornelia Ding, Shaurya Rohatgi, Ting-Hao 'Kenneth' Huang
Abstract: Recent studies indicated GPT-4 outperforms online crowd workers in data labeling accuracy, notably workers from Amazon Mechanical Turk (MTurk). However, these studies were criticized for deviating from standard crowdsourcing practices and emphasizing individual workers' performances over the whole data-annotation process. This paper compared GPT-4 and an ethical and well-executed MTurk pipeline, with 415 workers labeling 3,177 sentence segments from 200 scholarly articles using the CODA-19 scheme. Two worker interfaces yielded 127,080 labels, which were then used to infer the final labels through eight label-aggregation algorithms. Our evaluation showed that despite best practices, MTurk pipeline's highest accuracy was 81.5%, whereas GPT-4 achieved 83.6%. Interestingly, when combining GPT-4's labels with crowd labels collected via an advanced worker interface for aggregation, 2 out of the 8 algorithms achieved an even higher accuracy (87.5%, 87.0%). Further analysis suggested that, when the crowd's and GPT-4's labeling strengths are complementary, aggregating them could increase labeling accuracy.
Authors: Shengzhuang Chen, Jihoon Tack, Yunqiao Yang, Yee Whye Teh, Jonathan Richard Schwarz, Ying Wei
Abstract: Recent successes suggest that parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning. In trying to harness the best of both worlds, meta-tuning introduces a subsequent optimization stage of foundation models but has so far only shown limited success and crucially tends to underperform on out-of-distribution (OOD) tasks. In this paper, we introduce Sparse MetA-Tuning (SMAT), a method inspired by sparse mixture-of-experts approaches and trained to isolate subsets of pre-trained parameters automatically for meta-tuning on each task. SMAT successfully overcomes OOD sensitivity and delivers on the promise of enhancing the transfer abilities of vision foundation models beyond parameter-efficient fine-tuning. We establish new state-of-the-art results on a challenging combination of Meta-Dataset augmented with additional OOD tasks in both zero-shot and gradient-based adaptation settings. In addition, we provide a thorough analysis of the superiority of learned over hand-designed sparsity patterns for sparse expert methods and the pivotal importance of the sparsity level in balancing between in-distribution and out-of-distribution generalization. Our code is publicly available.
Authors: Samy Blusseau (CMM)
Abstract: Morphological neural networks, or layers, can be a powerful tool to boost the progress in mathematical morphology, either on theoretical aspects such as the representation of complete lattice operators, or in the development of image processing pipelines. However, these architectures turn out to be difficult to train when they count more than a few morphological layers, at least within popular machine learning frameworks which use gradient descent based optimization algorithms. In this paper we investigate the potential and limitations of differentiation based approaches and back-propagation applied to morphological networks, in light of the non-smooth optimization concept of Bouligand derivative. We provide insights and first theoretical guidelines, in particular regarding initialization and learning rates.
Authors: Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou, Shi Han, Zejian Yuan, Dongmei Zhang
Abstract: Large Language Models have revolutionized code generation ability by converting natural language descriptions into executable code. However, generating complex code within real-world scenarios remains challenging due to intricate structures, subtle bugs, understanding of advanced data types, and lack of supplementary contents. To address these challenges, we introduce the CoCoST framework, which enhances complex code generation by online searching for more information with planned queries and correctness testing for code refinement. Moreover, CoCoST serializes the complex inputs and outputs to improve comprehension and generates test cases to ensure the adaptability for real-world applications. CoCoST is validated through rigorous experiments on the DS-1000 and ClassEval datasets. Experimental results show that CoCoST substantially improves the quality of complex code generation, highlighting its potential to enhance the practicality of LLMs in generating complex code.
Authors: Simone Fiorellino, Claudio Battiloro, Emilio Calvanese Strinati, Paolo Di Lorenzo
Abstract: In future 6G wireless networks, semantic and effectiveness aspects of communications will play a fundamental role, incorporating meaning and relevance into transmissions. However, obstacles arise when devices employ diverse languages, logic, or internal representations, leading to semantic mismatches that might jeopardize understanding. In latent space communication, this challenge manifests as misalignment within high-dimensional representations where deep neural networks encode data. This paper presents a novel framework for goal-oriented semantic communication, leveraging relative representations to mitigate semantic mismatches via latent space alignment. We propose a dynamic optimization strategy that adapts relative representations, communication parameters, and computation resources for energy-efficient, low-latency, goal-oriented semantic communications. Numerical results demonstrate our methodology's effectiveness in mitigating mismatches among devices, while optimizing energy consumption, delay, and effectiveness.
Authors: Rahul Vaze, Jayakrishnan Nair
Abstract: An online non-convex optimization problem is considered where the goal is to minimize the flow time (total delay) of a set of jobs by modulating the number of active servers, but with a switching cost associated with changing the number of active servers over time. Each job can be processed by at most one fixed speed server at any time. Compared to the usual online convex optimization (OCO) problem with switching cost, the objective function considered is non-convex and more importantly, at each time, it depends on all past decisions and not just the present one. Both worst-case and stochastic inputs are considered; for both cases, competitive algorithms are derived.
Authors: Tarun Suresh, Shubham Ugare, Gagandeep Singh, Sasa Misailovic
Abstract: We present the first study of the robustness of existing watermarking techniques on Python code generated by large language models. Although existing works showed that watermarking can be robust for natural language, we show that it is easy to remove these watermarks on code by semantic-preserving transformations.
Authors: Bin Gao, Zhuomin He, Puru Sharma, Qingxuan Kang, Djordje Jevdjic, Junbo Deng, Xingkun Yang, Zhou Yu, Pengfei Zuo
Abstract: Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly compute the key-value (KV) caches of historical tokens, incurring high serving costs. To address the problem, this paper proposes CachedAttention, a new attention mechanism that enables reuse of KV caches across multi-turn conversations, significantly reducing the repetitive computation overheads. CachedAttention maintains a hierarchical KV caching system that leverages cost-effective memory/storage mediums to save KV caches for all requests. To reduce KV cache access overheads from slow mediums, CachedAttention employs layer-wise pre-loading and asynchronous saving schemes to overlap the KV cache access with the GPU computation. To ensure that the KV caches to be accessed are placed in the fastest hierarchy, CachedAttention employs scheduler-aware fetching and eviction schemes to consciously place the KV caches in different layers based on the hints from the inference job scheduler. To avoid the invalidation of the saved KV caches incurred by context window overflow, CachedAttention enables the saved KV caches to remain valid via decoupling the positional encoding and effectively truncating the KV caches. Extensive experimental results demonstrate that CachedAttention significantly decreases the time to the first token (TTFT) by up to 87%, improves the prompt prefilling throughput by up to 7.8$\times$ for multi-turn conversations, and reduces the end-to-end inference cost by up to 70%.
Authors: Alessio Ferrari, Sallam Abualhaija, Chetan Arora
Abstract: Complementing natural language (NL) requirements with graphical models can improve stakeholders' communication and provide directions for system design. However, creating models from requirements involves manual effort. The advent of generative large language models (LLMs), ChatGPT being a notable example, offers promising avenues for automated assistance in model generation. This paper investigates the capability of ChatGPT to generate a specific type of model, i.e., UML sequence diagrams, from NL requirements. We conduct a qualitative study in which we examine the sequence diagrams generated by ChatGPT for 28 requirements documents of various types and from different domains. Observations from the analysis of the generated diagrams have systematically been captured through evaluation logs, and categorized through thematic analysis. Our results indicate that, although the models generally conform to the standard and exhibit a reasonable level of understandability, their completeness and correctness with respect to the specified requirements often present challenges. This issue is particularly pronounced in the presence of requirements smells, such as ambiguity and inconsistency. The insights derived from this study can influence the practical utilization of LLMs in the RE process, and open the door to novel RE-specific prompting strategies targeting effective model generation.
Authors: Ruichen Zhang, Hongyang Du, Yinqiu Liu, Dusit Niyato, Jiawen Kang, Zehui Xiong, Abbas Jamalipour, Dong In Kim
Abstract: In response to the needs of 6G global communications, satellite communication networks have emerged as a key solution. However, the large-scale development of satellite communication networks is constrained by the complex system models, whose modeling is challenging for massive users. Moreover, transmission interference between satellites and users seriously affects communication performance. To solve these problems, this paper develops generative artificial intelligence (AI) agents for model formulation and then applies a mixture of experts (MoE) approach to design transmission strategies. Specifically, we leverage large language models (LLMs) to build an interactive modeling paradigm and utilize retrieval-augmented generation (RAG) to extract satellite expert knowledge that supports mathematical modeling. Afterward, by integrating the expertise of multiple specialized components, we propose an MoE-proximal policy optimization (PPO) approach to solve the formulated problem. Each expert can optimize the optimization variables at which it excels through specialized training through its own network and then aggregates them through the gating network to perform joint optimization. The simulation results validate the accuracy and effectiveness of employing a generative agent for problem formulation. Furthermore, the superiority of the proposed MoE-ppo approach over other benchmarks is confirmed in solving the formulated problem. The adaptability of MoE-PPO to various customized modeling problems has also been demonstrated.
Authors: Sho Kuno, Hiroshi Kori
Abstract: We tested the performance of reservoir computing (RC) in predicting the dynamics of a certain non-autonomous dynamical system. Specifically, we considered a van del Pol oscillator subjected to periodic external force with frequent phase shifts. The reservoir computer, which was trained and optimized with simulation data generated for a particular phase shift, was designed to predict the oscillation dynamics under periodic external forces with different phase shifts. The results suggest that if the training data have some complexity, it is possible to quantitatively predict the oscillation dynamics exposed to different phase shifts. The setting of this study was motivated by the problem of predicting the state of the circadian rhythm of shift workers and designing a better shift work schedule for each individual. Our results suggest that RC could be exploited for such applications.
Authors: Julia Gonski, Aseem Gupta, Haoyi Jia, Hyunjoon Kim, Lorenzo Rota, Larry Ruckman, Angelo Dragone, Ryan Herbst
Abstract: Embedded field programmable gate array (eFPGA) technology allows the implementation of reconfigurable logic within the design of an application-specific integrated circuit (ASIC). This approach offers the low power and efficiency of an ASIC along with the ease of FPGA configuration, particularly beneficial for the use case of machine learning in the data pipeline of next-generation collider experiments. An open-source framework called "FABulous" was used to design eFPGAs using 130 nm and 28 nm CMOS technology nodes, which were subsequently fabricated and verified through testing. The capability of an eFPGA to act as a front-end readout chip was assessed using simulation of high energy particles passing through a silicon pixel sensor. A machine learning-based classifier, designed for reduction of sensor data at the source, was synthesized and configured onto the eFPGA. A successful proof-of-concept was demonstrated through reproduction of the expected algorithm result on the eFPGA with perfect accuracy. Further development of the eFPGA technology and its application to collider detector readout is discussed.
Authors: Salvador Robles Herrera, Verya Monjezi, Vladik Kreinovich, Ashutosh Trivedi, Saeid Tizpaz-Niari
Abstract: This paper investigates the relationships between hyperparameters of machine learning and fairness. Data-driven solutions are increasingly used in critical socio-technical applications where ensuring fairness is important. Rather than explicitly encoding decision logic via control and data structures, the ML developers provide input data, perform some pre-processing, choose ML algorithms, and tune hyperparameters (HPs) to infer a program that encodes the decision logic. Prior works report that the selection of HPs can significantly influence fairness. However, tuning HPs to find an ideal trade-off between accuracy, precision, and fairness has remained an expensive and tedious task. Can we predict fairness of HP configuration for a given dataset? Are the predictions robust to distribution shifts? We focus on group fairness notions and investigate the HP space of 5 training algorithms. We first find that tree regressors and XGBoots significantly outperformed deep neural networks and support vector machines in accurately predicting the fairness of HPs. When predicting the fairness of ML hyperparameters under temporal distribution shift, the tree regressors outperforms the other algorithms with reasonable accuracy. However, the precision depends on the ML training algorithm, dataset, and protected attributes. For example, the tree regressor model was robust for training data shift from 2014 to 2018 on logistic regression and discriminant analysis HPs with sex as the protected attribute; but not for race and other training algorithms. Our method provides a sound framework to efficiently perform fine-tuning of ML training algorithms and understand the relationships between HPs and fairness.
Authors: Wandi Xu, Wei Xie
Abstract: To support mechanism online learning and facilitate digital twin development for biomanufacturing processes, this paper develops an efficient Bayesian inference approach for partially observed enzymatic stochastic reaction network (SRN), a fundamental building block of multi-scale bioprocess mechanistic model. To tackle the critical challenges brought by the nonlinear stochastic differential equations (SDEs)-based mechanistic model with partially observed state and having measurement errors, an interpretable Bayesian updating linear noise approximation (LNA) metamodel, incorporating the structure information of the mechanistic model, is proposed to approximate the likelihood of observations. Then, an efficient posterior sampling approach is developed by utilizing the gradients of the derived likelihood to speed up the convergence of Markov Chain Monte Carlo (MCMC). The empirical study demonstrates that the proposed approach has a promising performance.
Authors: Kwangho Kim, Jisu Kim, Edward H. Kennedy
Abstract: Causal effects are often characterized with population summaries. These might provide an incomplete picture when there are heterogeneous treatment effects across subgroups. Since the subgroup structure is typically unknown, it is more challenging to identify and evaluate subgroup effects than population effects. We propose a new solution to this problem: Causal k-Means Clustering, which harnesses the widely-used k-means clustering algorithm to uncover the unknown subgroup structure. Our problem differs significantly from the conventional clustering setup since the variables to be clustered are unknown counterfactual functions. We present a plug-in estimator which is simple and readily implementable using off-the-shelf algorithms, and study its rate of convergence. We also develop a new bias-corrected estimator based on nonparametric efficiency theory and double machine learning, and show that this estimator achieves fast root-n rates and asymptotic normality in large nonparametric models. Our proposed methods are especially useful for modern outcome-wide studies with multiple treatment levels. Further, our framework is extensible to clustering with generic pseudo-outcomes, such as partially observed outcomes or otherwise unknown functions. Finally, we explore finite sample properties via simulation, and illustrate the proposed methods in a study of treatment programs for adolescent substance abuse.
Authors: Josef Sabuda
Abstract: In this work, the concept of Braced Fourier Continuation and Regression (BFCR) is introduced. BFCR is a novel and computationally efficient means of finding nonlinear regressions or trend lines in arbitrary one-dimensional data sets. The Braced Fourier Continuation (BFC) and BFCR algorithms are first outlined, followed by a discussion of the properties of BFCR as well as demonstrations of how BFCR trend lines may be used effectively for anomaly detection both within and at the edges of arbitrary one-dimensional data sets. Finally, potential issues which may arise while using BFCR for anomaly detection as well as possible mitigation techniques are outlined and discussed. All source code and example data sets are either referenced or available via GitHub, and all associated code is written entirely in Python.
Authors: Nicholas Carlini
Abstract: Sabre is a defense to adversarial examples that was accepted at IEEE S&P 2024. We first reveal significant flaws in the evaluation that point to clear signs of gradient masking. We then show the cause of this gradient masking: a bug in the original evaluation code. By fixing a single line of code in the original repository, we reduce Sabre's robust accuracy to 0%. In response to this, the authors modify the defense and introduce a new defense component not described in the original paper. But this fix contains a second bug; modifying one more line of code reduces robust accuracy to below baseline levels. After we released the first version of our paper online, the authors introduced another change to the defense; by commenting out one line of code during attack we reduce the robust accuracy to 0% again.
Authors: Yihong Gu, Cong Fang, Peter B\"uhlmann, Jianqing Fan
Abstract: Pursuing causality from data is a fundamental problem in scientific discovery, treatment intervention, and transfer learning. This paper introduces a novel algorithmic method for addressing nonparametric invariance and causality learning in regression models across multiple environments, where the joint distribution of response variables and covariates varies, but the conditional expectations of outcome given an unknown set of quasi-causal variables are invariant. The challenge of finding such an unknown set of quasi-causal or invariant variables is compounded by the presence of endogenous variables that have heterogeneous effects across different environments, including even one of them in the regression would make the estimation inconsistent. The proposed Focused Adversial Invariant Regularization (FAIR) framework utilizes an innovative minimax optimization approach that breaks down the barriers, driving regression models toward prediction-invariant solutions through adversarial testing. Leveraging the representation power of neural networks, FAIR neural networks (FAIR-NN) are introduced for causality pursuit. It is shown that FAIR-NN can find the invariant variables and quasi-causal variables under a minimal identification condition and that the resulting procedure is adaptive to low-dimensional composition structures in a non-asymptotic analysis. Under a structural causal model, variables identified by FAIR-NN represent pragmatic causality and provably align with exact causal mechanisms under conditions of sufficient heterogeneity. Computationally, FAIR-NN employs a novel Gumbel approximation with decreased temperature and stochastic gradient descent ascent algorithm. The procedures are convincingly demonstrated using simulated and real-data examples.
Authors: Pengxiang Lan, Enneng Yang, Yuting Liu, Guibing Guo, Linying Jiang, Jianzhe Zhao, Xingwei Wang
Abstract: Prompt tuning is a promising method to fine-tune a pre-trained language model without retraining its large-scale parameters. Instead, it attaches a soft prompt to the input text, whereby downstream tasks can be well adapted by merely learning the embeddings of prompt tokens. Nevertheless, existing methods still suffer from two challenges: (i) they are hard to balance accuracy and efficiency. A longer (shorter) soft prompt generally leads to a better(worse) accuracy but at the cost of more (less) training time. (ii)The performance may not be consistent when adapting to different downstream tasks. We attribute it to the same embedding space but responsible for different requirements of downstream tasks. To address these issues, we propose an Efficient Prompt Tuning method (EPT) by multi-space projection and prompt fusion. Specifically, it decomposes a given soft prompt into a shorter prompt and two low-rank matrices, significantly reducing the training time. Accuracy is also enhanced by leveraging low-rank matrices and the short prompt as additional knowledge sources to enrich the semantics of the original short prompt. In addition, we project the soft prompt into multiple subspaces to improve the performance consistency, and then adaptively learn the combination weights of different spaces through a gating network. Experiments on 13 natural language processing downstream tasks show that our method significantly and consistently outperforms 11 comparison methods with the relative percentage of improvements up to 12.9%, and training time decreased by 14%.
Authors: Yaoyao Xu, Xinjian Zhao, Xiaozhuang Song, Benyou Wang, Tianshu Yu
Abstract: We introduce a pioneering methodology for boosting large language models in the domain of protein representation learning. Our primary contribution lies in the refinement process for correlating the over-reliance on co-evolution knowledge, in a way that networks are trained to distill invaluable insights from negative samples, constituted by protein pairs sourced from disparate categories. By capitalizing on this novel approach, our technique steers the training of transformer-based models within the attention score space. This advanced strategy not only amplifies performance but also reflects the nuanced biological behaviors exhibited by proteins, offering aligned evidence with traditional biological mechanisms such as protein-protein interaction. We experimentally observed improved performance on various tasks over datasets, on top of several well-established large protein models. This innovative paradigm opens up promising horizons for further progress in the realms of protein research and computational biology.
Authors: Renzhi Wu, Pramod Chunduri, Dristi J Shah, Ashmitha Julius Aravind, Ali Payani, Xu Chu, Joy Arulraj, Kexin Rong
Abstract: In this paper, we will present SketchQL, a video database management system (VDBMS) for retrieving video moments with a sketch-based query interface. This novel interface allows users to specify object trajectory events with simple mouse drag-and-drop operations. Users can use trajectories of single objects as building blocks to compose complex events. Using a pre-trained model that encodes trajectory similarity, SketchQL achieves zero-shot video moments retrieval by performing similarity searches over the video to identify clips that are the most similar to the visual query. In this demonstration, we introduce the graphic user interface of SketchQL and detail its functionalities and interaction mechanisms. We also demonstrate the end-to-end usage of SketchQL from query composition to video moments retrieval using real-world scenarios.
Authors: Shaohua Wang (Aerospace Information Research Institute, Chinese Academy of Sciences), Xing Xie (Microsoft Research Asia), Yong Li (Tsinghua University), Danhuai Guo (Beijing University of Chemical Technology), Zhi Cai (Beijing University of Technology), Yu Liu (Peking University), Yang Yue (Shenzhen University), Xiao Pan (Shijiazhuang Tiedao University), Feng Lu (Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences), Huayi Wu (Wuhan University), Zhipeng Gui (Wuhan University), Zhiming Ding (Institute of Software, Chinese Academy of Sciences), Bolong Zheng (Huazhong University of Science and Technology), Fuzheng Zhang (Kuaishou Natural Language Processing Center and Audio Center), Tao Qin (Microsoft Research Asia), Jingyuan Wang (Beijing University of Aeronautics and Astronautics), Chuang Tao (Shanghai Figure Interesting Information Technology Co., Ltd), Zhengchao Chen (Aerospace Information Research Institute, Chinese Academy of Sciences), Hao Lu (SuperMap Software Co., Ltd), Jiayi Li (Wuhan University), Hongyang Chen (Zhejiang Lab), Peng Yue (Wuhan University), Wenhao Yu (China University of Geosciences), Yao Yao (China University of Geosciences), Leilei Sun (Beijing University of Aeronautics and Astronautics), Yong Zhang (Beijing University of Technology), Longbiao Chen (Xiamen University), Xiaoping Du (Key Laboratory of Digital Earth, Chinese Academy of Sciences), Xiang Li (East China Normal University), Xueying Zhang (Nanjing Normal University), Kun Qin (Wuhan University), Zhaoya Gong (Peking University), Weihua Dong (Beijing Normal University), Xiaofeng Meng (Renmin University of China)
Abstract: This report focuses on spatial data intelligent large models, delving into the principles, methods, and cutting-edge applications of these models. It provides an in-depth discussion on the definition, development history, current status, and trends of spatial data intelligent large models, as well as the challenges they face. The report systematically elucidates the key technologies of spatial data intelligent large models and their applications in urban environments, aerospace remote sensing, geography, transportation, and other scenarios. Additionally, it summarizes the latest application cases of spatial data intelligent large models in themes such as urban development, multimodal systems, remote sensing, smart transportation, and resource environments. Finally, the report concludes with an overview and outlook on the development prospects of spatial data intelligent large models.
Authors: Qianrong Guo, Saiveth Hernandez-Hernandez, Pedro J Ballester
Abstract: Virtual Screening (VS) of vast compound libraries guided by Artificial Intelligence (AI) models is a highly productive approach to early drug discovery. Data splitting is crucial for better benchmarking of such AI models. Traditional random data splits produce similar molecules between training and test sets, conflicting with the reality of VS libraries which mostly contain structurally distinct compounds. Scaffold split, grouping molecules by shared core structure, is widely considered to reflect this real-world scenario. However, here we show that the scaffold split also overestimates VS performance. The reason is that molecules with different chemical scaffolds are often similar, which hence introduces unrealistically high similarities between training molecules and test molecules following a scaffold split. Our study examined three representative AI models on 60 NCI-60 datasets, each with approximately 30,000 to 50,000 molecules tested on a different cancer cell line. Each dataset was split with three methods: scaffold, Butina clustering and the more accurate Uniform Manifold Approximation and Projection (UMAP) clustering. Regardless of the model, model performance is much worse with UMAP splits from the results of the 2100 models trained and evaluated for each algorithm and split. These robust results demonstrate the need for more realistic data splits to tune, compare, and select models for VS. For the same reason, avoiding the scaffold split is also recommended for other molecular property prediction problems. The code to reproduce these results is available at https://github.com/ScaffoldSplitsOverestimateVS
Authors: Federico Mora, Justin Wong, Haley Lepe, Sahil Bhatia, Karim Elmaaroufi, George Varghese, Joseph E. Gonzalez, Elizabeth Polgreen, Sanjit A. Seshia
Abstract: Recent advances in large language models (LLMs) for code applications have demonstrated remarkable zero-shot fluency and instruction following on challenging code related tasks ranging from test case generation to self-repair. Unsurprisingly, however, models struggle to compose syntactically valid programs in programming languages unrepresented in pre-training, referred to as very low-resource Programming Languages (VLPLs). VLPLs appear in crucial settings, including domain-specific languages for internal tools and tool-chains for legacy languages. Inspired by an HCI technique called natural program elicitation, we propose designing an intermediate language that LLMs ``naturally'' know how to use and which can be automatically compiled to a target VLPL. When LLMs generate code that lies outside of this intermediate language, we use compiler techniques to repair the code into programs in the intermediate language. Overall, we introduce \emph{synthetic programming elicitation and compilation} (SPEAC), an approach that enables LLMs to generate syntactically valid code even for VLPLs. We empirically evaluate the performance of SPEAC in a case study and find that, compared to existing retrieval and fine-tuning baselines, SPEAC produces syntactically correct programs significantly more frequently without sacrificing semantic correctness.
Authors: Pranav Jeevan, Amit Sethi
Abstract: In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as feature extractors. Despite the widespread use of these pre-trained convolutional neural networks (CNNs), there remains a gap in understanding the performance of various resource-efficient backbones across diverse domains and dataset sizes. Our study systematically evaluates multiple lightweight, pre-trained CNN backbones under consistent training settings across a variety of datasets, including natural images, medical images, galaxy images, and remote sensing images. This comprehensive analysis aims to aid machine learning practitioners in selecting the most suitable backbone for their specific problem, especially in scenarios involving small datasets where fine-tuning a pre-trained network is crucial. Even though attention-based architectures are gaining popularity, we observed that they tend to perform poorly under low data finetuning tasks compared to CNNs. We also observed that some CNN architectures such as ConvNeXt, RegNet and EfficientNet performs well compared to others on a diverse set of domains consistently. Our findings provide actionable insights into the performance trade-offs and effectiveness of different backbones, facilitating informed decision-making in model selection for a broad spectrum of computer vision domains. Our code is available here: https://github.com/pranavphoenix/Backbones
Authors: Owen Dugan, Donato Manuel Jimenez Beneto, Charlotte Loh, Zhuo Chen, Rumen Dangovski, Marin Solja\v{c}i\'c
Abstract: Despite significant advancements in text generation and reasoning, Large Language Models (LLMs) still face challenges in accurately performing complex arithmetic operations. To achieve accurate calculations, language model systems often enable LLMs to generate code for arithmetic operations. However, this approach compromises speed and security and, if finetuning is involved, risks the language model losing prior capabilities. We propose a framework that enables exact arithmetic in \textit{a single autoregressive step}, providing faster, more secure, and more interpretable LLM systems with arithmetic capabilities. We use the hidden states of an LLM to control a symbolic architecture which performs arithmetic. Our implementation using Llama 3 8B Instruct with OccamNet as a symbolic model (OccamLlama) achieves 100\% accuracy on single arithmetic operations ($+,-,\times,\div,\sin{},\cos{},\log{},\exp{},\sqrt{}$), outperforming GPT 4o and on par with GPT 4o using a code interpreter. OccamLlama also outperforms GPT 4o both with and without a code interpreter on mathematical problem solving benchmarks involving challenging arithmetic, thus enabling small LLMs to match the arithmetic performance of even much larger models. We will make our code public shortly.
Authors: Jinxin Xu, Yue Wang, Ruisi Li, Ziyue Wang, Qian Zhao
Abstract: For one to guarantee higher-quality software development processes, risk management is essential. Furthermore, risks are those that could negatively impact an organization's operations or a project's progress. The appropriate prioritisation of software project risks is a crucial factor in ascertaining the software project's performance features and eventual success. They can be used harmoniously with the same training samples and have good complement and compatibility. We carried out in-depth tests on four benchmark datasets to confirm the efficacy of our CIA approach in closed-world and open-world scenarios, with and without defence. We also present a sequential augmentation parameter optimisation technique that captures the interdependencies of the latest deep learning state-of-the-art WF attack models. To achieve precise software risk assessment, the enhanced crow search algorithm (ECSA) is used to modify the ANFIS settings. Solutions that very slightly alter the local optimum and stay inside it are extracted using the ECSA. ANFIS variable when utilising the ANFIS technique. An experimental validation with NASA 93 dataset and 93 software project values was performed. This method's output presents a clear image of the software risk elements that are essential to achieving project performance. The results of our experiments show that, when compared to other current methods, our integrative fuzzy techniques may perform more accurately and effectively in the evaluation of software project risks.
Authors: Francisco Eiras, Aleksandar Petrov, Phillip H. S. Torr, M. Pawan Kumar, Adel Bibi
Abstract: Fine-tuning large language models on small, high-quality datasets can enhance their performance on specific downstream tasks. Recent research shows that fine-tuning on benign, instruction-following data can inadvertently undo the safety alignment process and increase a model's propensity to comply with harmful queries. Although critical, understanding and mitigating safety risks in well-defined tasks remains distinct from the instruction-following context due to structural differences in the data. Our work addresses the gap in our understanding of these risks across diverse types of data in closed models - where providers control how user data is utilized in the fine-tuning process. We demonstrate how malicious actors can subtly manipulate the structure of almost any task-specific dataset to foster significantly more dangerous model behaviors, while maintaining an appearance of innocuity and reasonable downstream task performance. To address this issue, we propose a novel mitigation strategy that mixes in safety data which mimics the task format and prompting style of the user data, showing this is more effective than existing baselines at re-establishing safety alignment while maintaining similar task performance.
Authors: Maximilian E. Tschuchnig, Philipp Steininger, Michael Gadermayr
Abstract: Cone-beam computed tomography (CBCT) is an important tool facilitating computer aided interventions, despite often suffering from artifacts that pose challenges for accurate interpretation. While the degraded image quality can affect downstream segmentation, the availability of high quality, preoperative scans represents potential for improvements. Here we consider a setting where preoperative CT and intraoperative CBCT scans are available, however, the alignment (registration) between the scans is imperfect. We propose a multimodal learning method that fuses roughly aligned CBCT and CT scans and investigate the effect of CBCT quality and misalignment on the final segmentation performance. For that purpose, we make use of a synthetically generated data set containing real CT and synthetic CBCT volumes. As an application scenario, we focus on liver and liver tumor segmentation. We show that the fusion of preoperative CT and simulated, intraoperative CBCT mostly improves segmentation performance (compared to using intraoperative CBCT only) and that even clearly misaligned preoperative data has the potential to improve segmentation performance.
Authors: Seonghun Park, Manish Bansal
Abstract: We study submodular optimization in adversarial context, applicable to machine learning problems such as feature selection using data susceptible to uncertainties and attacks. We focus on Stackelberg games between an attacker (or interdictor) and a defender where the attacker aims to minimize the defender's objective of maximizing a $k$-submodular function. We allow uncertainties arising from the success of attacks and inherent data noise, and address challenges due to incomplete knowledge of the probability distribution of random parameters. Specifically, we introduce Distributionally Risk-Averse $k$-Submodular Interdiction Problem (DRA $k$-SIP) and Distributionally Risk-Receptive $k$-Submodular Interdiction Problem (DRR $k$-SIP) along with finitely convergent exact algorithms for solving them. The DRA $k$-SIP solution allows risk-averse interdictor to develop robust strategies for real-world uncertainties. Conversely, DRR $k$-SIP solution suggests aggressive tactics for attackers, willing to embrace (distributional) risk to inflict maximum damage, identifying critical vulnerable components, which can be used for the defender's defensive strategies. The optimal values derived from both DRA $k$-SIP and DRR $k$-SIP offer a confidence interval-like range for the expected value of the defender's objective function, capturing distributional ambiguity. We conduct computational experiments using instances of feature selection and sensor placement problems, and Wisconsin breast cancer data and synthetic data, respectively.
Authors: Hejie Cui, Lingjun Mao, Xin Liang, Jieyu Zhang, Hui Ren, Quanzheng Li, Xiang Li, Carl Yang
Abstract: Recent advancements in multimodal foundation models have showcased impressive capabilities in understanding and reasoning with visual and textual information. Adapting these foundation models trained for general usage to specialized domains like biomedicine requires large-scale domain-specific instruction datasets. While existing works have explored curating such datasets automatically, the resultant datasets are not explicitly aligned with domain expertise. In this work, we propose a data-centric framework, Biomedical Visual Instruction Tuning with Clinician Preference Alignment (BioMed-VITAL), that incorporates clinician preferences into both stages of generating and selecting instruction data for tuning biomedical multimodal foundation models. First, during the generation stage, we prompt the GPT-4V generator with a diverse set of clinician-selected demonstrations for preference-aligned data candidate generation. Then, during the selection phase, we train a separate selection model, which explicitly distills clinician and policy-guided model preferences into a rating function to select high-quality data for medical instruction tuning. Results show that the model tuned with the instruction-following data from our method demonstrates a significant improvement in open visual chat (18.5% relatively) and medical VQA (win rate up to 81.73%). Our instruction-following data and models are available at BioMed-VITAL.github.io.
Authors: Jirui Qi, Gabriele Sarti, Raquel Fern\'andez, Arianna Bisazza
Abstract: Ensuring the verifiability of model answers is a fundamental challenge for retrieval-augmented generation (RAG) in the question answering (QA) domain. Recently, self-citation prompting was proposed to make large language models (LLMs) generate citations to supporting documents along with their answers. However, self-citing LLMs often struggle to match the required format, refer to non-existent sources, and fail to faithfully reflect LLMs' context usage throughout the generation. In this work, we present MIRAGE --Model Internals-based RAG Explanations -- a plug-and-play approach using model internals for faithful answer attribution in RAG applications. MIRAGE detects context-sensitive answer tokens and pairs them with retrieved documents contributing to their prediction via saliency methods. We evaluate our proposed approach on a multilingual extractive QA dataset, finding high agreement with human answer attribution. On open-ended QA, MIRAGE achieves citation quality and efficiency comparable to self-citation while also allowing for a finer-grained control of attribution parameters. Our qualitative evaluation highlights the faithfulness of MIRAGE's attributions and underscores the promising application of model internals for RAG answer attribution.
Authors: Amelie Gyrard, Seyedali Mohammadi, Manas Gaur, Antonio Kung
Abstract: Sustainable Development Goals (SDGs) give the UN a road map for development with Agenda 2030 as a target. SDG3 "Good Health and Well-Being" ensures healthy lives and promotes well-being for all ages. Digital technologies can support SDG3. Burnout and even depression could be reduced by encouraging better preventive health. Due to the lack of patient knowledge and focus to take care of their health, it is necessary to help patients before it is too late. New trends such as positive psychology and mindfulness are highly encouraged in the USA. Digital Twin (DT) can help with the continuous monitoring of emotion using physiological signals (e.g., collected via wearables). Digital twins facilitate monitoring and provide constant health insight to improve quality of life and well-being with better personalization. Healthcare DT challenges are standardizing data formats, communication protocols, and data exchange mechanisms. To achieve those data integration and knowledge challenges, we designed the Mental Health Knowledge Graph (ontology and dataset) to boost mental health. The Knowledge Graph (KG) acquires knowledge from ontology-based mental health projects classified within the LOV4IoT ontology catalog (Emotion, Depression, and Mental Health). Furthermore, the KG is mapped to standards (e.g., ontologies) when possible. Standards from ETSI SmartM2M, ITU/WHO, ISO, W3C, NIST, and IEEE are relevant to mental health.
Authors: Ilham Adi Panuntun, Ying-Nong Chen, Ilham Jamaluddin, Thi Linh Chi Tran
Abstract: In the rise of climate change, land cover mapping has become such an urgent need in environmental monitoring. The accuracy of land cover classification has gotten increasingly based on the improvement of remote sensing data. Land cover classification using satellite imageries has been explored and become more prevalent in recent years, but the methodologies remain some drawbacks of subjective and time-consuming. Some deep learning techniques have been utilized to overcome these limitations. However, most studies implemented just one image type to evaluate algorithms for land cover mapping. Therefore, our study conducted deep learning semantic segmentation in multispectral, hyperspectral, and high spatial aerial image datasets for landcover mapping. This research implemented a semantic segmentation method such as Unet, Linknet, FPN, and PSPnet for categorizing vegetation, water, and others (i.e., soil and impervious surface). The LinkNet model obtained high accuracy in IoU (Intersection Over Union) at 0.92 in all datasets, which is comparable with other mentioned techniques. In evaluation with different image types, the multispectral images showed higher performance with the IoU, and F1-score are 0.993 and 0.997, respectively. Our outcome highlighted the efficiency and broad applicability of LinkNet and multispectral image on land cover classification. This research contributes to establishing an approach on landcover segmentation via open source for long-term future application.
Authors: Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
Abstract: Inference with modern Large Language Models (LLMs) is expensive and time-consuming, and speculative sampling has proven to be an effective solution. Most speculative sampling methods such as EAGLE use a static draft tree, implicitly assuming that the acceptance rate of draft tokens depends only on their position. Interestingly, we found that the acceptance rate of draft tokens is also context-dependent. In this paper, building upon EAGLE, we propose EAGLE-2, which introduces a new technique of context-aware dynamic draft tree into drafting modeling. This improvement leverages the fact that the draft model of EAGLE is well-calibrated: the confidence scores from the draft model approximate acceptance rates with small errors. We conducted extensive evaluations on three series of LLMs and six tasks, with EAGLE-2 achieving speedup ratios 3.05x-4.26x, which is 20%-40% faster than EAGLE-1. EAGLE-2 also ensures that the distribution of the generated text remains unchanged, making it a lossless acceleration algorithm.
Authors: Jason Stock, Kyle Hilburn, Imme Ebert-Uphoff, Charles Anderson
Abstract: We introduce a transformer-based neural network to generate high-resolution (3km) synthetic radar reflectivity fields at scale from geostationary satellite imagery. This work aims to enhance short-term convective-scale forecasts of high-impact weather events and aid in data assimilation for numerical weather prediction over the United States. Compared to convolutional approaches, which have limited receptive fields, our results show improved sharpness and higher accuracy across various composite reflectivity thresholds. Additional case studies over specific atmospheric phenomena support our quantitative findings, while a novel attribution method is introduced to guide domain experts in understanding model outputs.
Authors: Ryan Liu, Jiayi Geng, Joshua C. Peterson, Ilia Sucholutsky, Thomas L. Griffiths
Abstract: In order for AI systems to communicate effectively with people, they must understand how we make decisions. However, people's decisions are not always rational, so the implicit internal models of human decision-making in Large Language Models (LLMs) must account for this. Previous empirical evidence seems to suggest that these implicit models are accurate -- LLMs offer believable proxies of human behavior, acting how we expect humans would in everyday interactions. However, by comparing LLM behavior and predictions to a large dataset of human decisions, we find that this is actually not the case: when both simulating and predicting people's choices, a suite of cutting-edge LLMs (GPT-4o & 4-Turbo, Llama-3-8B & 70B, Claude 3 Opus) assume that people are more rational than we really are. Specifically, these models deviate from human behavior and align more closely with a classic model of rational choice -- expected value theory. Interestingly, people also tend to assume that other people are rational when interpreting their behavior. As a consequence, when we compare the inferences that LLMs and people draw from the decisions of others using another psychological dataset, we find that these inferences are highly correlated. Thus, the implicit decision-making models of LLMs appear to be aligned with the human expectation that other people will act rationally, rather than with how people actually act.
Authors: Stefan Gl\"uge, Matthias Nyfeler, Ahmad Aghaebrahimian, Nicola Ramagnano, Christof Sch\"upbach
Abstract: The proliferation of drones, or unmanned aerial vehicles (UAVs), has raised significant safety concerns due to their potential misuse in activities such as espionage, smuggling, and infrastructure disruption. This paper addresses the critical need for effective drone detection and classification systems that operate independently of UAV cooperation. We evaluate various convolutional neural networks (CNNs) for their ability to detect and classify drones using spectrogram data derived from consecutive Fourier transforms of signal components. The focus is on model robustness in low signal-to-noise ratio (SNR) environments, which is critical for real-world applications. A comprehensive dataset is provided to support future model development. In addition, we demonstrate a low-cost drone detection system using a standard computer, software-defined radio (SDR) and antenna, validated through real-world field testing. On our development dataset, all models consistently achieved an average balanced classification accuracy of >= 85% at SNR > -12dB. In the field test, these models achieved an average balance accuracy of > 80%, depending on transmitter distance and antenna direction. Our contributions include: a publicly available dataset for model development, a comparative analysis of CNN for drone detection under low SNR conditions, and the deployment and field evaluation of a practical, low-cost detection system.
Authors: Boyi Wei, Weijia Shi, Yangsibo Huang, Noah A. Smith, Chiyuan Zhang, Luke Zettlemoyer, Kai Li, Peter Henderson
Abstract: Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content similar to their training data, posing potential concerns. Therefore, model creators are motivated to develop mitigation methods that prevent generating protected content. We term this procedure as copyright takedowns for LMs, noting the conceptual similarity to (but legal distinction from) the DMCA takedown This paper introduces the first evaluation of the feasibility and side effects of copyright takedowns for LMs. We propose CoTaEval, an evaluation framework to assess the effectiveness of copyright takedown methods, the impact on the model's ability to retain uncopyrightable factual knowledge from the training data whose recitation is embargoed, and how well the model maintains its general utility and efficiency. We examine several strategies, including adding system prompts, decoding-time filtering interventions, and unlearning approaches. Our findings indicate that no tested method excels across all metrics, showing significant room for research in this unique problem setting and indicating potential unresolved challenges for live policy proposals.
Authors: Jean Marie Tshimula, D'Jeff K. Nkashama, Jean Tshibangu Muabila, Ren\'e Manass\'e Galekwa, Hugues Kanda, Maximilien V. Dialufuma, Mbuyi Mukendi Didier, Kalala Kalonji, Serge Mundele, Patience Kinshie Lenye, Tighana Wenge Basele, Aristarque Ilunga, Christian N. Mayemba, Nathana\"el M. Kasoro, Selain K. Kasereka, Hardy Mikese, Pierre-Martin Tardif, Marc Frappier, Froduald Kabanza, Belkacem Chikhaoui, Shengrui Wang, Ali Mulenda Sumbu, Xavier Ndona, Raoul Kienge-Kienge Intudi
Abstract: The increasing sophistication of cyber threats necessitates innovative approaches to cybersecurity. In this paper, we explore the potential of psychological profiling techniques, particularly focusing on the utilization of Large Language Models (LLMs) and psycholinguistic features. We investigate the intersection of psychology and cybersecurity, discussing how LLMs can be employed to analyze textual data for identifying psychological traits of threat actors. We explore the incorporation of psycholinguistic features, such as linguistic patterns and emotional cues, into cybersecurity frameworks. Our research underscores the importance of integrating psychological perspectives into cybersecurity practices to bolster defense mechanisms against evolving threats.
Authors: Fuseini Mumuni, Alhassan Mumuni
Abstract: Grounding DINO and the Segment Anything Model (SAM) have achieved impressive performance in zero-shot object detection and image segmentation, respectively. Together, they have a great potential to revolutionize applications in zero-shot semantic segmentation or data annotation. Yet, in specialized domains like medical image segmentation, objects of interest (e.g., organs, tissues, and tumors) may not fall in existing class names. To address this problem, the referring expression comprehension (REC) ability of Grounding DINO is leveraged to detect arbitrary targets by their language descriptions. However, recent studies have highlighted severe limitation of the REC framework in this application setting owing to its tendency to make false positive predictions when the target is absent in the given image. And, while this bottleneck is central to the prospect of open-set semantic segmentation, it is still largely unknown how much improvement can be achieved by studying the prediction errors. To this end, we perform empirical studies on six publicly available datasets across different domains and reveal that these errors consistently follow a predictable pattern and can, thus, be mitigated by a simple strategy. Specifically, we show that false positive detections with appreciable confidence scores generally occupy large image areas and can usually be filtered by their relative sizes. More importantly, we expect these observations to inspire future research in improving REC-based detection and automated segmentation. Meanwhile, we evaluate the performance of SAM on multiple datasets from various specialized domains and report significant improvements in segmentation performance and annotation time savings over manual approaches.
Authors: Jitendra Bhandari, Animesh Basak Chowdhury, Mohammed Nabeel, Ozgur Sinanoglu, Siddharth Garg, Ramesh Karri, Johann Knechtel
Abstract: Power side-channel (PSC) analysis is pivotal for securing cryptographic hardware. Prior art focused on securing gate-level netlists obtained as-is from chip design automation, neglecting all the complexities and potential side-effects for security arising from the design automation process. That is, automation traditionally prioritizes power, performance, and area (PPA), sidelining security. We propose a "security-first" approach, refining the logic synthesis stage to enhance the overall resilience of PSC countermeasures. We introduce ASCENT, a learning-and-search-based framework that (i) drastically reduces the time for post-design PSC evaluation and (ii) explores the security-vs-PPA design space. Thus, ASCENT enables an efficient exploration of a large number of candidate netlists, leading to an improvement in PSC resilience compared to regular PPA-optimized netlists. ASCENT is up to 120x faster than traditional PSC analysis and yields a 3.11x improvement for PSC resilience of state-of-the-art PSC countermeasures
Authors: Yiding Lu, Haobin Li, Yunfan Li, Yijie Lin, Xi Peng
Abstract: Facilitated by the powerful feature extraction ability of neural networks, deep clustering has achieved great success in analyzing high-dimensional and complex real-world data. The performance of deep clustering methods is affected by various factors such as network structures and learning objectives. However, as pointed out in this survey, the essence of deep clustering lies in the incorporation and utilization of prior knowledge, which is largely ignored by existing works. From pioneering deep clustering methods based on data structure assumptions to recent contrastive clustering methods based on data augmentation invariances, the development of deep clustering intrinsically corresponds to the evolution of prior knowledge. In this survey, we provide a comprehensive review of deep clustering methods by categorizing them into six types of prior knowledge. We find that in general the prior innovation follows two trends, namely, i) from mining to constructing, and ii) from internal to external. Besides, we provide a benchmark on five widely-used datasets and analyze the performance of methods with diverse priors. By providing a novel prior knowledge perspective, we hope this survey could provide some novel insights and inspire future research in the deep clustering community.
Authors: Ryan P. Ringel, Zachary S. Charlick, Jiaxun Liu, Boxi Xia, Boyuan Chen
Abstract: Robot design has traditionally been costly and labor-intensive. Despite advancements in automated processes, it remains challenging to navigate a vast design space while producing physically manufacturable robots. We introduce Text2Robot, a framework that converts user text specifications and performance preferences into physical quadrupedal robots. Within minutes, Text2Robot can use text-to-3D models to provide strong initializations of diverse morphologies. Within a day, our geometric processing algorithms and body-control co-optimization produce a walking robot by explicitly considering real-world electronics and manufacturability. Text2Robot enables rapid prototyping and opens new opportunities for robot design with generative models.