Authors: Hanwen Ye, Tatiana Moreno, Adrianne Alpern, Louis Ehwerhemuepha, Annie Qu
Mental health diseases affect children's lives and well-beings which have received increased attention since the COVID-19 pandemic. Analyzing psychiatric clinical notes with topic models is critical to evaluate children's mental status over time. However, few topic models are built for longitudinal settings, and they fail to keep consistent topics and capture temporal trajectories for each document. To address these challenges, we develop a longitudinal topic model with time-invariant topics and individualized temporal dependencies on the evolving document metadata. Our model preserves the semantic meaning of discovered topics over time and incorporates heterogeneity among documents. In particular, when documents can be categorized, we propose an unsupervised topics learning approach to maximize topic heterogeneity across different document groups. We also present an efficient variational optimization procedure adapted for the multistage longitudinal setting. In this case study, we apply our method to the psychiatric clinical notes from a large tertiary pediatric hospital in Southern California and achieve a 38% increase in the overall coherence of extracted topics. Our real data analysis reveals that children tend to express more negative emotions during state shutdowns and more positive when schools reopen. Furthermore, it suggests that sexual and gender minority (SGM) children display more pronounced reactions to major COVID-19 events and a greater sensitivity to vaccine-related news than non-SGM children. This study examines the progression of children's mental health during the pandemic and offers clinicians valuable insights to recognize the disparities in children's mental health related to their sexual and gender identities.
Authors: Carl De Sousa Trias, Mihai Petru Mitrea, Attilio Fiandrotti, Marco Cagnazzo, Sumanta Chaudhuri, Enzo Tartaglione
Deep neural networks are characterized by multiple symmetrical, equi-loss solutions that are redundant. Thus, the order of neurons in a layer and feature maps can be given arbitrary permutations, without affecting (or minimally affecting) their output. If we shuffle these neurons, or if we apply to them some perturbations (like fine-tuning) can we put them back in the original order i.e. re-synchronize? Is there a possible corruption threat? Answering these questions is important for applications like neural network white-box watermarking for ownership tracking and integrity verification. We advance a method to re-synchronize the order of permuted neurons. Our method is also effective if neurons are further altered by parameter pruning, quantization, and fine-tuning, showing robustness to integrity attacks. Additionally, we provide theoretical and practical evidence for the usual means to corrupt the integrity of the model, resulting in a solution to counter it. We test our approach on popular computer vision datasets and models, and we illustrate the threat and our countermeasure on a popular white-box watermarking method.
Authors: Xiaodan Zhang, Sandeep Vemulapalli, Nabasmita Talukdar, Sumyeong Ahn, Jiankun Wang, Han Meng, Sardar Mehtab Bin Murtaza, Aakash Ajay Dave, Dmitry Leshchiner, Dimitri F. Joseph, Martin Witteveen-Lane, Dave Chesla, Jiayu Zhou, Bin Chen
This study assesses the ability of state-of-the-art large language models (LLMs) including GPT-3.5, GPT-4, Falcon, and LLaMA 2 to identify patients with mild cognitive impairment (MCI) from discharge summaries and examines instances where the models' responses were misaligned with their reasoning. Utilizing the MIMIC-IV v2.2 database, we focused on a cohort aged 65 and older, verifying MCI diagnoses against ICD codes and expert evaluations. The data was partitioned into training, validation, and testing sets in a 7:2:1 ratio for model fine-tuning and evaluation, with an additional metastatic cancer dataset from MIMIC III used to further assess reasoning consistency. GPT-4 demonstrated superior interpretative capabilities, particularly in response to complex prompts, yet displayed notable response-reasoning inconsistencies. In contrast, open-source models like Falcon and LLaMA 2 achieved high accuracy but lacked explanatory reasoning, underscoring the necessity for further research to optimize both performance and interpretability. The study emphasizes the significance of prompt engineering and the need for further exploration into the unexpected reasoning-response misalignment observed in GPT-4. The results underscore the promise of incorporating LLMs into healthcare diagnostics, contingent upon methodological advancements to ensure accuracy and clinical coherence of AI-generated outputs, thereby improving the trustworthiness of LLMs for medical decision-making.
Authors: Zirong Chen, Xutong Sun, Yuanhe Li, Meiyi Ma
Emergency and non-emergency response systems are essential services provided by local governments and critical to protecting lives, the environment, and property. The effective handling of (non-)emergency calls is critical for public safety and well-being. By reducing the burden through non-emergency callers, residents in critical need of assistance through 911 will receive a fast and effective response. Collaborating with the Department of Emergency Communications (DEC) in Nashville, we analyzed 11,796 non-emergency call recordings and developed Auto311, the first automated system to handle 311 non-emergency calls, which (1) effectively and dynamically predicts ongoing non-emergency incident types to generate tailored case reports during the call; (2) itemizes essential information from dialogue contexts to complete the generated reports; and (3) strategically structures system-caller dialogues with optimized confidence. We used real-world data to evaluate the system's effectiveness and deployability. The experimental results indicate that the system effectively predicts incident type with an average F-1 score of 92.54%. Moreover, the system successfully itemizes critical information from relevant contexts to complete reports, evincing a 0.93 average consistency score compared to the ground truth. Additionally, emulations demonstrate that the system effectively decreases conversation turns as the utterance size gets more extensive and categorizes the ongoing call with 94.49% mean accuracy.
Authors: Rahul Vishwakarma, Subhankar Mishra
Theorem proving is a fundamental task in mathematics. With the advent of large language models (LLMs) and interactive theorem provers (ITPs) like Lean, there has been growing interest in integrating LLMs and ITPs to automate theorem proving. In this approach, the LLM generates proof steps (tactics), and the ITP checks the applicability of the tactics at the current goal. The two systems work together to complete the proof. In this paper, we introduce DS-Prover, a novel dynamic sampling method for theorem proving. This method dynamically determines the number of tactics to apply to expand the current goal, taking into account the remaining time compared to the total allocated time for proving a theorem. This makes the proof search process more efficient by adjusting the balance between exploration and exploitation as time passes. We also augment the training dataset by decomposing simplification and rewrite tactics with multiple premises into tactics with single premises. This gives the model more examples to learn from and helps it to predict the tactics with premises more accurately. We perform our experiments using the Mathlib dataset of the Lean theorem prover and report the performance on two standard datasets, MiniF2F and ProofNet. Our methods achieve significant performance gains on both datasets. We achieved a state-of-the-art performance (Pass@1) of 14.2% on the ProofNet dataset and a performance of 29.8% on MiniF2F, slightly surpassing the best-reported Pass@1 of 29.6% using Lean.
Authors: Vasilis Belis, Patrick Odagiu, Thea Klæboe Årrestad
The detection of out-of-distribution data points is a common task in particle physics. It is used for monitoring complex particle detectors or for identifying rare and unexpected events that may be indicative of new phenomena or physics beyond the Standard Model. Recent advances in Machine Learning for anomaly detection have encouraged the utilization of such techniques on particle physics problems. This review article provides an overview of the state-of-the-art techniques for anomaly detection in particle physics using machine learning. We discuss the challenges associated with anomaly detection in large and complex data sets, such as those produced by high-energy particle colliders, and highlight some of the successful applications of anomaly detection in particle physics experiments.
Authors: Lesego Moloko, Pavel Bokov, Xu Wu, Kostadin Ivanov
The goal of this work is to develop accurate Machine Learning (ML) models for predicting the assembly axial neutron flux profiles in the SAFARI-1 research reactor, trained by measurement data from historical cycles. The data-driven nature of ML models makes them susceptible to uncertainties which are introduced by sources such as noise in training data, incomplete coverage of the domain, extrapolation and imperfect model architectures. To this end, we also aim at quantifying the approximation uncertainties of the ML model predictions. Previous work using Deep Neural Networks (DNNs) has been successful for fuel assemblies in SAFARI-1, however, not as accurate for control follower assemblies. The aim of this work is to improve the ML models for the control assemblies by a combination of supervised and unsupervised ML algorithms. The $k$-means and Affinity Propagation unsupervised ML algorithms are employed to identify clusters in the set of the measured axial neutron flux profiles. Then, regression-based supervised ML models using DNN (with prediction uncertainties quantified with Monte Carlo dropout) and Gaussian Process (GP) are trained for different clusters and the prediction uncertainty is estimated. It was found that applying the proposed procedure improves the prediction accuracy for the control assemblies and reduces the prediction uncertainty. Flux shapes predicted by DNN and GP are very close, and the overall accuracy became comparable to the fuel assemblies. The prediction uncertainty is however smaller for GP models.
Authors: Ellen M. Considine, Rachel C. Nethery, Gregory A. Wellenius, Francesca Dominici, Mauricio Tec
Alerting the public when heat may harm their health is a crucial service, especially considering that extreme heat events will be more frequent under climate change. Current practice for issuing heat alerts in the US does not take advantage of modern data science methods for optimizing local alert criteria. Specifically, application of reinforcement learning (RL) has the potential to inform more health-protective policies, accounting for regional and sociodemographic heterogeneity as well as sequential dependence of alerts. In this work, we formulate the issuance of heat alerts as a sequential decision making problem and develop modifications to the RL workflow to address challenges commonly encountered in environmental health settings. Key modifications include creating a simulator that pairs hierarchical Bayesian modeling of low-signal health effects with sampling of real weather trajectories (exogenous features), constraining the total number of alerts issued as well as preventing alerts on less-hot days, and optimizing location-specific policies. Post-hoc contrastive analysis offers insights into scenarios when using RL for heat alert issuance may protect public health better than the current or alternative policies. This work contributes to a broader movement of advancing data-driven policy optimization for public health and climate change adaptation.
Authors: Zhongyang Guo, Guanran Jiang, Zhongdan Zhang, Peng Li, Zhefeng Wang, Yinchun Wang
This paper introduces "Shai" a 10B level large language model specifically designed for the asset management industry, built upon an open-source foundational model. With continuous pre-training and fine-tuning using a targeted corpus, Shai demonstrates enhanced performance in tasks relevant to its domain, outperforming baseline models. Our research includes the development of an innovative evaluation framework, which integrates professional qualification exams, tailored tasks, open-ended question answering, and safety assessments, to comprehensively assess Shai's capabilities. Furthermore, we discuss the challenges and implications of utilizing large language models like GPT-4 for performance assessment in asset management, suggesting a combination of automated evaluation and human judgment. Shai's development, showcasing the potential and versatility of 10B-level large language models in the financial sector with significant performance and modest computational requirements, hopes to provide practical insights and methodologies to assist industry peers in their similar endeavors.
Authors: Wenhui Cui, Haleh Akrami, Ganning Zhao, Anand A. Joshi, Richard M. Leahy
Despite the impressive advancements achieved using deep-learning for functional brain activity analysis, the heterogeneity of functional patterns and scarcity of imaging data still pose challenges in tasks such as prediction of future onset of Post-Traumatic Epilepsy (PTE) from data acquired shortly after traumatic brain injury (TBI). Foundation models pre-trained on separate large-scale datasets can improve the performance from scarce and heterogeneous datasets. For functional Magnetic Resonance Imaging (fMRI), while data may be abundantly available from healthy controls, clinical data is often scarce, limiting the ability of foundation models to identify clinically-relevant features. We overcome this limitation by introducing a novel training strategy for our foundation model by integrating meta-learning with self-supervised learning to improve the generalization from normal to clinical features. In this way we enable generalization to other downstream clinical tasks, in our case prediction of PTE. To achieve this, we perform self-supervised training on the control dataset to focus on inherent features that are not limited to a particular supervised task while applying meta-learning, which strongly improves the model's generalizability using bi-level optimization. Through experiments on neurological disorder classification tasks, we demonstrate that the proposed strategy significantly improves task performance on small-scale clinical datasets. To explore the generalizability of the foundation model in downstream applications, we then apply the model to an unseen TBI dataset for prediction of PTE using zero-shot learning. Results further demonstrated the enhanced generalizability of our foundation model.
Authors: Giuseppe Habib, Ádám Horváth
This study proposes a physics-informed convolutional neural network (CNN) for identifying dynamical systems' time series near a fold bifurcation. The peculiarity of this work is that the CNN is trained with a relatively small amount of data and on a single, very simple system. In contrast, the CNN is validated on much more complicated systems. A similar task requires significant extrapolation capabilities, which are obtained by exploiting physics-based information. Physics-based information is provided through a specific pre-processing of the input data, consisting mostly of a transformation into polar coordinates, normalization, transformation into the logarithmic scale, and filtering through a moving mean. The results illustrate that such data pre-processing enables the CNN to grasp the important features related to approaching a fold bifurcation, namely, the trend of the oscillation amplitude, and neglect other characteristics that are not particularly relevant, such as the vibration frequency. The developed CNN was able to correctly classify trajectories near a fold for a mass-on-moving-belt system, a van der Pol-Duffing oscillator with an attached tuned mass damper, and a pitch-and-plunge wing profile. The results obtained pave the way for the development of similar CNNs effective in real-life applications.
Authors: Sankalp Gilda
Traditional spectral energy distribution (SED) fitting techniques face uncertainties due to assumptions in star formation histories and dust attenuation curves. We propose an advanced machine learning-based approach that enhances flexibility and uncertainty quantification in SED fitting. Unlike the fixed NGBoost model used in mirkwood, our approach allows for any sklearn-compatible model, including deterministic models. We incorporate conformalized quantile regression to convert point predictions into error bars, enhancing interpretability and reliability. Using CatBoost as the base predictor, we compare results with and without conformal prediction, demonstrating improved performance using metrics such as coverage and interval width. Our method offers a more versatile and accurate tool for deriving galaxy physical properties from observational data.
Authors: Haofeng Yuan, Lichang Fang, Shiji Song
Column generation (CG) is one of the most successful approaches for solving large-scale linear programming (LP) problems. Given an LP with a prohibitively large number of variables (i.e., columns), the idea of CG is to explicitly consider only a subset of columns and iteratively add potential columns to improve the objective value. While adding the column with the most negative reduced cost can guarantee the convergence of CG, it has been shown that adding multiple columns per iteration rather than a single column can lead to faster convergence. However, it remains a challenge to design a multiple-column selection strategy to select the most promising columns from a large number of candidate columns. In this paper, we propose a novel reinforcement-learning-based (RL) multiple-column selection strategy. To the best of our knowledge, it is the first RL-based multiple-column selection strategy for CG. The effectiveness of our approach is evaluated on two sets of problems: the cutting stock problem and the graph coloring problem. Compared to several widely used single-column and multiple-column selection strategies, our RL-based multiple-column selection strategy leads to faster convergence and achieves remarkable reductions in the number of CG iterations and runtime.
Authors: Chengyin Hu, Weiwen Shi
Deep neural network security is a persistent concern, with considerable research on visible light physical attacks but limited exploration in the infrared domain. Existing approaches, like white-box infrared attacks using bulb boards and QR suits, lack realism and stealthiness. Meanwhile, black-box methods with cold and hot patches often struggle to ensure robustness. To bridge these gaps, we propose Adversarial Infrared Curves (AdvIC). Using Particle Swarm Optimization, we optimize two Bezier curves and employ cold patches in the physical realm to introduce perturbations, creating infrared curve patterns for physical sample generation. Our extensive experiments confirm AdvIC's effectiveness, achieving 94.8\% and 67.2\% attack success rates for digital and physical attacks, respectively. Stealthiness is demonstrated through a comparative analysis, and robustness assessments reveal AdvIC's superiority over baseline methods. When deployed against diverse advanced detectors, AdvIC achieves an average attack success rate of 76.8\%, emphasizing its robust nature. we explore adversarial defense strategies against AdvIC and examine its impact under various defense mechanisms. Given AdvIC's substantial security implications for real-world vision-based applications, urgent attention and mitigation efforts are warranted.
Authors: Shaohan Sha, YaFeng Sun
Federated learning is a decentralized learning paradigm wherein a central server trains a global model iteratively by utilizing clients who possess a certain amount of private datasets. The challenge lies in the fact that the client side private data may not be identically and independently distributed, significantly impacting the accuracy of the global model. Existing methods commonly address the Non-IID challenge by focusing on optimization, client selection and data complement. However, most approaches tend to overlook the perspective of the private data itself due to privacy constraints.Intuitively, statistical distinctions among private data on the client side can help mitigate the Non-IID degree. Besides, the recent advancements in dataset condensation technology have inspired us to investigate its potential applicability in addressing Non-IID issues while maintaining privacy. Motivated by this, we propose DCFL which divides clients into groups by using the Centered Kernel Alignment (CKA) method, then uses dataset condensation methods with non-IID awareness to complete clients. The private data from clients within the same group is complementary and their condensed data is accessible to all clients in the group. Additionally, CKA-guided client selection strategy, filtering mechanisms, and data enhancement techniques are incorporated to efficiently and precisely utilize the condensed data, enhance model performance, and minimize communication time. Experimental results demonstrate that DCFL achieves competitive performance on popular federated learning benchmarks including MNIST, FashionMNIST, SVHN, and CIFAR-10 with existing FL protocol.
Authors: Yixuan Wang, Shuangyin Li, Shimin DI, Lei Chen
The single-cell RNA sequencing (scRNA-seq) technology enables researchers to study complex biological systems and diseases with high resolution. The central challenge is synthesizing enough scRNA-seq samples; insufficient samples can impede downstream analysis and reproducibility. While various methods have been attempted in past research, the resulting scRNA-seq samples were often of poor quality or limited in terms of useful specific cell subpopulations. To address these issues, we propose a novel method called Single-Cell Latent Diffusion (SCLD) based on the Diffusion Model. This method is capable of synthesizing large-scale, high-quality scRNA-seq samples, including both 'holistic' or targeted specific cellular subpopulations within a unified framework. A pre-guidance mechanism is designed for synthesizing specific cellular subpopulations, while a post-guidance mechanism aims to enhance the quality of scRNA-seq samples. The SCLD can synthesize large-scale and high-quality scRNA-seq samples for various downstream tasks. Our experimental results demonstrate state-of-the-art performance in cell classification and data distribution distances when evaluated on two scRNA-seq benchmarks. Additionally, visualization experiments show the SCLD's capability in synthesizing specific cellular subpopulations.
Authors: Michal K. Grzeszczyk, Tadeusz Satlawa, Angela Lungu, Andrew Swift, Andrew Narracott, Rod Hose, Tomasz Trzcinski, Arkadiusz Sitek
Pulmonary Hypertension (PH) is a severe disease characterized by an elevated pulmonary artery pressure. The gold standard for PH diagnosis is measurement of mean Pulmonary Artery Pressure (mPAP) during an invasive Right Heart Catheterization. In this paper, we investigate noninvasive approach to PH detection utilizing Magnetic Resonance Imaging, Computer Models and Machine Learning. We show using the ablation study, that physics-informed feature engineering based on models of blood circulation increases the performance of Gradient Boosting Decision Trees-based algorithms for classification of PH and regression of values of mPAP. We compare results of regression (with thresholding of estimated mPAP) and classification and demonstrate that metrics achieved in both experiments are comparable. The predicted mPAP values are more informative to the physicians than the probability of PH returned by classification models. They provide the intuitive explanation of the outcome of the machine learning model (clinicians are accustomed to the mPAP metric, contrary to the PH probability).
Authors: Jiangmeng Li, Yifan Jin, Hang Gao, Wenwen Qiang, Changwen Zheng, Fuchun Sun
Graph contrastive learning (GCL) aims to align the positive features while differentiating the negative features in the latent space by minimizing a pair-wise contrastive loss. As the embodiment of an outstanding discriminative unsupervised graph representation learning approach, GCL achieves impressive successes in various graph benchmarks. However, such an approach falls short of recognizing the topology isomorphism of graphs, resulting in that graphs with relatively homogeneous node features cannot be sufficiently discriminated. By revisiting classic graph topology recognition works, we disclose that the corresponding expertise intuitively complements GCL methods. To this end, we propose a novel hierarchical topology isomorphism expertise embedded graph contrastive learning, which introduces knowledge distillations to empower GCL models to learn the hierarchical topology isomorphism expertise, including the graph-tier and subgraph-tier. On top of this, the proposed method holds the feature of plug-and-play, and we empirically demonstrate that the proposed method is universal to multiple state-of-the-art GCL models. The solid theoretical analyses are further provided to prove that compared with conventional GCL methods, our method acquires the tighter upper bound of Bayes classification error. We conduct extensive experiments on real-world benchmarks to exhibit the performance superiority of our method over candidate GCL methods, e.g., for the real-world graph representation learning experiments, the proposed method beats the state-of-the-art method by 0.23\% on unsupervised representation learning setting, 0.43\% on transfer learning setting. Our code is available at https://github.com/jyf123/HTML.
Authors: Liyi Zhang, R. Thomas McCoy, Theodore R. Sumers, Jian-Qiao Zhu, Thomas L. Griffiths
Large language models (LLMs) can produce long, coherent passages of text, suggesting that LLMs, although trained on next-word prediction, must represent the latent structure that characterizes a document. Prior work has found that internal representations of LLMs encode one aspect of latent structure, namely syntax; here we investigate a complementary aspect, namely the document's topic structure. We motivate the hypothesis that LLMs capture topic structure by connecting LLM optimization to implicit Bayesian inference. De Finetti's theorem shows that exchangeable probability distributions can be represented as a mixture with respect to a latent generating distribution. Although text is not exchangeable at the level of syntax, exchangeability is a reasonable starting assumption for topic structure. We thus hypothesize that predicting the next token in text will lead LLMs to recover latent topic distributions. We examine this hypothesis using Latent Dirichlet Allocation (LDA), an exchangeable probabilistic topic model, as a target, and we show that the representations formed by LLMs encode both the topics used to generate synthetic data and those used to explain natural corpus data.
Authors: Kai Huang, Boyuan Yang, Wei Gao
On-device training is essential for neural networks (NNs) to continuously adapt to new online data, but can be time-consuming due to the device's limited computing power. To speed up on-device training, existing schemes select trainable NN portion offline or conduct unrecoverable selection at runtime, but the evolution of trainable NN portion is constrained and cannot adapt to the current need for training. Instead, runtime adaptation of on-device training should be fully elastic, i.e., every NN substructure can be freely removed from or added to the trainable NN portion at any time in training. In this paper, we present ElasticTrainer, a new technique that enforces such elasticity to achieve the required training speedup with the minimum NN accuracy loss. Experiment results show that ElasticTrainer achieves up to 3.5x more training speedup in wall-clock time and reduces energy consumption by 2x-3x more compared to the existing schemes, without noticeable accuracy loss.
With the wide adoption of AI applications, there is a pressing need of enabling real-time neural network (NN) inference on small embedded devices, but deploying NNs and achieving high performance of NN inference on these small devices is challenging due to their extremely weak capabilities. Although NN partitioning and offloading can contribute to such deployment, they are incapable of minimizing the local costs at embedded devices. Instead, we suggest to address this challenge via agile NN offloading, which migrates the required computations in NN offloading from online inference to offline learning. In this paper, we present AgileNN, a new NN offloading technique that achieves real-time NN inference on weak embedded devices by leveraging eXplainable AI techniques, so as to explicitly enforce feature sparsity during the training phase and minimize the online computation and communication costs. Experiment results show that AgileNN's inference latency is >6x lower than the existing schemes, ensuring that sensory data on embedded devices can be timely consumed. It also reduces the local device's resource consumption by >8x, without impairing the inference accuracy.
Authors: Mario De Florio, Ioannis G. Kevrekidis, George Em Karniadakis
Discovering mathematical models that characterize the observed behavior of dynamical systems remains a major challenge, especially for systems in a chaotic regime. The challenge is even greater when the physics underlying such systems is not yet understood, and scientific inquiry must solely rely on empirical data. Driven by the need to fill this gap, we develop a framework that learns mathematical expressions modeling complex dynamical behaviors by identifying differential equations from noisy and sparse observable data. We train a small neural network to learn the dynamics of a system, its rate of change in time, and missing model terms, which are used as input for a symbolic regression algorithm to autonomously distill the explicit mathematical terms. This, in turn, enables us to predict the future evolution of the dynamical behavior. The performance of this framework is validated by recovering the right-hand sides and unknown terms of certain complex, chaotic systems such as the well-known Lorenz system, a six-dimensional hyperchaotic system, and the non-autonomous Sprott chaotic system, and comparing them with their known analytical expressions.
Authors: Yuhui Wang, Junaid Farooq
The advent of fifth generation (5G) networks has opened new avenues for enhancing connectivity, particularly in challenging environments like remote areas or disaster-struck regions. Unmanned aerial vehicles (UAVs) have been identified as a versatile tool in this context, particularly for improving network performance through the Integrated access and backhaul (IAB) feature of 5G. However, existing approaches to UAV-assisted network enhancement face limitations in dynamically adapting to varying user locations and network demands. This paper introduces a novel approach leveraging deep reinforcement learning (DRL) to optimize UAV placement in real-time, dynamically adjusting to changing network conditions and user requirements. Our method focuses on the intricate balance between fronthaul and backhaul links, a critical aspect often overlooked in current solutions. The unique contribution of this work lies in its ability to autonomously position UAVs in a way that not only ensures robust connectivity to ground users but also maintains seamless integration with central network infrastructure. Through various simulated scenarios, we demonstrate how our approach effectively addresses these challenges, enhancing coverage and network performance in critical areas. This research fills a significant gap in UAV-assisted 5G networks, providing a scalable and adaptive solution for future mobile networks.
Authors: Yingzhou Lu, Minjie Shen, Yue Zhao, Chenhao Li, Fan Meng, Xiao Wang, David Herrington, Yue Wang, Tim Fu, Capucine Van Rechem
The surge in high-throughput omics data has reshaped the landscape of biological research, underlining the need for powerful, user-friendly data analysis and interpretation tools. This paper presents GenoCraft, a web-based comprehensive software solution designed to handle the entire pipeline of omics data processing. GenoCraft offers a unified platform featuring advanced bioinformatics tools, covering all aspects of omics data analysis. It encompasses a range of functionalities, such as normalization, quality control, differential analysis, network analysis, pathway analysis, and diverse visualization techniques. This software makes state-of-the-art omics data analysis more accessible to a wider range of users. With GenoCraft, researchers and data scientists have access to an array of cutting-edge bioinformatics tools under a user-friendly interface, making it a valuable resource for managing and analyzing large-scale omics data. The API with an interactive web interface is publicly available at https://genocraft.stanford. edu/. We also release all the codes in https://github.com/futianfan/GenoCraft.
Authors: Ram Dyuthi Sristi, Ofir Lindenbaum, Maria Lavzin, Jackie Schiller, Gal Mishne, Hadas Benisty
We study the problem of contextual feature selection, where the goal is to learn a predictive function while identifying subsets of informative features conditioned on specific contexts. Towards this goal, we generalize the recently proposed stochastic gates (STG) Yamada et al. [2020] by modeling the probabilistic gates as conditional Bernoulli variables whose parameters are predicted based on the contextual variables. Our new scheme, termed conditional-STG (c-STG), comprises two networks: a hypernetwork that establishes the mapping between contextual variables and probabilistic feature selection parameters and a prediction network that maps the selected feature to the response variable. Training the two networks simultaneously ensures the comprehensive incorporation of context and feature selection within a unified model. We provide a theoretical analysis to examine several properties of the proposed framework. Importantly, our model leads to improved flexibility and adaptability of feature selection and, therefore, can better capture the nuances and variations in the data. We apply c-STG to simulated and real-world datasets, including healthcare, housing, and neuroscience, and demonstrate that it effectively selects contextually meaningful features, thereby enhancing predictive performance and interpretability.
Authors: Osama A. Hanna, Merve Karakas, Lin F. Yang, Christina Fragouli
Multi-Armed Bandit (MAB) systems are witnessing an upswing in applications within multi-agent distributed environments, leading to the advancement of collaborative MAB algorithms. In such settings, communication between agents executing actions and the primary learner making decisions can hinder the learning process. A prevalent challenge in distributed learning is action erasure, often induced by communication delays and/or channel noise. This results in agents possibly not receiving the intended action from the learner, subsequently leading to misguided feedback. In this paper, we introduce novel algorithms that enable learners to interact concurrently with distributed agents across heterogeneous action erasure channels with different action erasure probabilities. We illustrate that, in contrast to existing bandit algorithms, which experience linear regret, our algorithms assure sub-linear regret guarantees. Our proposed solutions are founded on a meticulously crafted repetition protocol and scheduling of learning across heterogeneous channels. To our knowledge, these are the first algorithms capable of effectively learning through heterogeneous action erasure channels. We substantiate the superior performance of our algorithm through numerical experiments, emphasizing their practical significance in addressing issues related to communication constraints and delays in multi-agent environments.
Authors: Janvi Thakkar, Giulio Zizzo, Sergio Maffeis
Machine learning models are being used in an increasing number of critical applications; thus, securing their integrity and ownership is critical. Recent studies observed that adversarial training and watermarking have a conflicting interaction. This work introduces a novel framework to integrate adversarial training with watermarking techniques to fortify against evasion attacks and provide confident model verification in case of intellectual property theft. We use adversarial training together with adversarial watermarks to train a robust watermarked model. The key intuition is to use a higher perturbation budget to generate adversarial watermarks compared to the budget used for adversarial training, thus avoiding conflict. We use the MNIST and Fashion-MNIST datasets to evaluate our proposed technique on various model stealing attacks. The results obtained consistently outperform the existing baseline in terms of robustness performance and further prove the resilience of this defense against pruning and fine-tuning removal attacks.
Authors: Juncai He, Jinchao Xu
In this study, we establish that deep neural networks employing ReLU and ReLU$^2$ activation functions are capable of representing Lagrange finite element functions of any order on simplicial meshes across arbitrary dimensions. We introduce a novel global formulation of the basis functions for Lagrange elements, grounded in a geometric decomposition of these elements and leveraging two essential properties of high-dimensional simplicial meshes and barycentric coordinate functions. This representation theory facilitates a natural approximation result for such deep neural networks. Our findings present the first demonstration of how deep neural networks can systematically generate general continuous piecewise polynomial functions.
Authors: Xingfang Wu, Eric Laufer, Heng Li, Foutse Khomh, Santhosh Srinivasan, Jayden Luo
With the rapid growth of the developer community, the amount of posts on online technical forums has been growing rapidly, which poses difficulties for users to filter useful posts and find important information. Tags provide a concise feature dimension for users to locate their interested posts and for search engines to index the most relevant posts according to the queries. However, most tags are only focused on the technical perspective (e.g., program language, platform, tool). In most cases, forum posts in online developer communities reveal the author's intentions to solve a problem, ask for advice, share information, etc. The modeling of the intentions of posts can provide an extra dimension to the current tag taxonomy. By referencing previous studies and learning from industrial perspectives, we create a refined taxonomy for the intentions of technical forum posts. Through manual labeling and analysis on a sampled post dataset extracted from online forums, we understand the relevance between the constitution of posts (code, error messages) and their intentions. Furthermore, inspired by our manual study, we design a pre-trained transformer-based model to automatically predict post intentions. The best variant of our intention prediction framework, which achieves a Micro F1-score of 0.589, Top 1-3 accuracy of 62.6% to 87.8%, and an average AUC of 0.787, outperforms the state-of-the-art baseline approach. Our characterization and automated classification of forum posts regarding their intentions may help forum maintainers or third-party tool developers improve the organization and retrieval of posts on technical forums. We have released our annotated dataset and codes in our supplementary material package.
Authors: Sepideh Koohfar, Laura Dietz
Time series forecasting is a challenging task due to the existence of complex and dynamic temporal dependencies. This can lead to incorrect predictions by even the best forecasting models. Using more training data is one way to improve the accuracy, but this source is often limited. In contrast, we are building on successful denoising approaches for image generation by advocating for an end-to-end forecasting and denoising paradigm.
We propose an end-to-end forecast-blur-denoise forecasting framework by encouraging a division of labors between the forecasting and the denoising models. The initial forecasting model is directed to focus on accurately predicting the coarse-grained behavior, while the denoiser model focuses on capturing the fine-grained behavior that is locally blurred by integrating a Gaussian Process model. All three parts are interacting for the best end-to-end performance. Our extensive experiments demonstrate that our proposed approach is able to improve the forecasting accuracy of several state-of-the-art forecasting models as well as several other denoising approaches.
Authors: Michael Kuoch, Chi-Ning Chou, Nikhil Parthasarathy, Joel Dapello, James J. DiCarlo, Haim Sompolinsky, SueYeon Chung
Recently, growth in our understanding of the computations performed in both biological and artificial neural networks has largely been driven by either low-level mechanistic studies or global normative approaches. However, concrete methodologies for bridging the gap between these levels of abstraction remain elusive. In this work, we investigate the internal mechanisms of neural networks through the lens of neural population geometry, aiming to provide understanding at an intermediate level of abstraction, as a way to bridge that gap. Utilizing manifold capacity theory (MCT) from statistical physics and manifold alignment analysis (MAA) from high-dimensional statistics, we probe the underlying organization of task-dependent manifolds in deep neural networks and macaque neural recordings. Specifically, we quantitatively characterize how different learning objectives lead to differences in the organizational strategies of these models and demonstrate how these geometric analyses are connected to the decodability of task-relevant information. These analyses present a strong direction for bridging mechanistic and normative theories in neural networks through neural population geometry, potentially opening up many future research avenues in both machine learning and neuroscience.
Authors: Siddhant Bhambri, Mudit Verma, Anil Murthy, Subbarao Kambhampati
Preference-based Reinforcement Learning (PbRL) is an active area of research, and has made significant strides in single-agent actor and in observer human-in-the-loop scenarios. However, its application within the co-operative multi-agent RL frameworks, where humans actively participate and express preferences for agent behavior, remains largely uncharted. We consider a two-agent (Human-AI) cooperative setup where both the agents are rewarded according to human's reward function for the team. However, the agent does not have access to it, and instead, utilizes preference-based queries to elicit its objectives and human's preferences for the robot in the human-robot team. We introduce the notion of Human-Flexibility, i.e. whether the human partner is amenable to multiple team strategies, with a special case being Specified Orchestration where the human has a single team policy in mind (most constrained case). We propose a suite of domains to study PbRL for Human-AI cooperative setup which explicitly require forced cooperation. Adapting state-of-the-art single-agent PbRL algorithms to our two-agent setting, we conduct a comprehensive benchmarking study across our domain suite. Our findings highlight the challenges associated with high degree of Human-Flexibility and the limited access to the human's envisioned policy in PbRL for Human-AI cooperation. Notably, we observe that PbRL algorithms exhibit effective performance exclusively in the case of Specified Orchestration which can be seen as an upper bound PbRL performance for future research.
Authors: Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
Submodular maximization over a matroid constraint is a fundamental problem with various applications in machine learning. Some of these applications involve decision-making over datapoints with sensitive attributes such as gender or race. In such settings, it is crucial to guarantee that the selected solution is fairly distributed with respect to this attribute. Recently, fairness has been investigated in submodular maximization under a cardinality constraint in both the streaming and offline settings, however the more general problem with matroid constraint has only been considered in the streaming setting and only for monotone objectives. This work fills this gap. We propose various algorithms and impossibility results offering different trade-offs between quality, fairness, and generality.
Authors: Kellin Pelrine, Mohammad Taufeeque, Michał Zając, Euan McLean, Adam Gleave
Language model attacks typically assume one of two extreme threat models: full white-box access to model weights, or black-box access limited to a text generation API. However, real-world APIs are often more flexible than just text generation: these APIs expose ``gray-box'' access leading to new threat vectors. To explore this, we red-team three new functionalities exposed in the GPT-4 APIs: fine-tuning, function calling and knowledge retrieval. We find that fine-tuning a model on as few as 15 harmful examples or 100 benign examples can remove core safeguards from GPT-4, enabling a range of harmful outputs. Furthermore, we find that GPT-4 Assistants readily divulge the function call schema and can be made to execute arbitrary function calls. Finally, we find that knowledge retrieval can be hijacked by injecting instructions into retrieval documents. These vulnerabilities highlight that any additions to the functionality exposed by an API can create new vulnerabilities.
Authors: Yiming Li, Zeyu Li, Zhihui Gao, Tingjun Chen
Radio frequency (RF) signal mapping, which is the process of analyzing and predicting the RF signal strength and distribution across specific areas, is crucial for cellular network planning and deployment. Traditional approaches to RF signal mapping rely on statistical models constructed based on measurement data, which offer low complexity but often lack accuracy, or ray tracing tools, which provide enhanced precision for the target area but suffer from increased computational complexity. Recently, machine learning (ML) has emerged as a data-driven method for modeling RF signal propagation, which leverages models trained on synthetic datasets to perform RF signal mapping in "unseen" areas.
In this paper, we present Geo2SigMap, an ML-based framework for efficient and high-fidelity RF signal mapping using geographic databases. First, we develop an automated framework that seamlessly integrates three open-source tools: OpenStreetMap (geographic databases), Blender (computer graphics), and Sionna (ray tracing), enabling the efficient generation of large-scale 3D building maps and ray tracing models. Second, we propose a cascaded U-Net model, which is pre-trained on synthetic datasets and employed to generate detailed RF signal maps, leveraging environmental information and sparse measurement data. Finally, we evaluate the performance of Geo2SigMap via a real-world measurement campaign, where three types of user equipment (UE) collect over 45,000 data points related to cellular information from six LTE cells operating in the citizens broadband radio service (CBRS) band. Our results show that Geo2SigMap achieves an average root-mean-square-error (RMSE) of 6.04 dB for predicting the reference signal received power (RSRP) at the UE, representing an average RMSE improvement of 3.59 dB compared to existing methods.
Authors: Mahdi Chehimi, Samuel Yen-Chi Chen, Walid Saad, Shinjae Yoo
Quantum federated learning (QFL) can facilitate collaborative learning across multiple clients using quantum machine learning (QML) models, while preserving data privacy. Although recent advances in QFL span different tasks like classification while leveraging several data types, no prior work has focused on developing a QFL framework that utilizes temporal data to approximate functions useful to analyze the performance of distributed quantum sensing networks. In this paper, a novel QFL framework that is the first to integrate quantum long short-term memory (QLSTM) models with temporal data is proposed. The proposed federated QLSTM (FedQLSTM) framework is exploited for performing the task of function approximation. In this regard, three key use cases are presented: Bessel function approximation, sinusoidal delayed quantum feedback control function approximation, and Struve function approximation. Simulation results confirm that, for all considered use cases, the proposed FedQLSTM framework achieves a faster convergence rate under one local training epoch, minimizing the overall computations, and saving 25-33% of the number of communication rounds needed until convergence compared to an FL framework with classical LSTM models.
Authors: Justyna P. Zwolak, Jacob M. Taylor, Reed Andrews, Jared Benson, Garnett Bryant, Donovan Buterakos, Anasua Chatterjee, Sankar Das Sarma, Mark A. Eriksson, Eliška Greplová, Michael J. Gullans, Fabian Hader, Tyler J. Kovach, Pranav S. Mundada, Mick Ramsey, Torbjoern Rasmussen, Brandon Severin, Anthony Sigillito, Brennan Undseth, Brian Weber
Gate-defined quantum dots are a promising candidate system to realize scalable, coupled qubit systems and serve as a fundamental building block for quantum computers. However, present-day quantum dot devices suffer from imperfections that must be accounted for, which hinders the characterization, tuning, and operation process. Moreover, with an increasing number of quantum dot qubits, the relevant parameter space grows sufficiently to make heuristic control infeasible. Thus, it is imperative that reliable and scalable autonomous tuning approaches are developed. In this report, we outline current challenges in automating quantum dot device tuning and operation with a particular focus on datasets, benchmarking, and standardization. We also present ideas put forward by the quantum dot community on how to overcome them.
Authors: João B. S. Carvalho, Mengtao Zhang, Robin Geyer, Carlos Cotrini, Joachim M. Buhmann
Anomaly detection (AD) is the machine learning task of identifying highly discrepant abnormal samples by solely relying on the consistency of the normal training samples. Under the constraints of a distribution shift, the assumption that training samples and test samples are drawn from the same distribution breaks down. In this work, by leveraging tools from causal inference we attempt to increase the resilience of anomaly detection models to different kinds of distribution shifts. We begin by elucidating a simple yet necessary statistical property that ensures invariant representations, which is critical for robust AD under both domain and covariate shifts. From this property, we derive a regularization term which, when minimized, leads to partial distribution invariance across environments. Through extensive experimental evaluation on both synthetic and real-world tasks, covering a range of six different AD methods, we demonstrated significant improvements in out-of-distribution performance. Under both covariate and domain shift, models regularized with our proposed term showed marked increased robustness. Code is available at: https://github.com/JoaoCarv/invariant-anomaly-detection.
Authors: Sobhan Mohammadpour, Emmanuel Bengio, Emma Frejinger, Pierre-Luc Bacon
Generative Flow Networks (GFNs) have emerged as a powerful tool for sampling discrete objects from unnormalized distributions, offering a scalable alternative to Markov Chain Monte Carlo (MCMC) methods. While GFNs draw inspiration from maximum entropy reinforcement learning (RL), the connection between the two has largely been unclear and seemingly applicable only in specific cases. This paper addresses the connection by constructing an appropriate reward function, thereby establishing an exact relationship between GFNs and maximum entropy RL. This construction allows us to introduce maximum entropy GFNs, which, in contrast to GFNs with uniform backward policy, achieve the maximum entropy attainable by GFNs without constraints on the state space.
Authors: Gaël Gendron, Yang Chen, Mitchell Rogers, Yiping Liu, Mihailo Azhar, Shahrokh Heidari, David Arturo Soriano Valdez, Kobe Knowles, Padriac O'Leary, Simon Eyre, Michael Witbrock, Gillian Dobbie, Jiamou Liu, Patrice Delmas
Better understanding the natural world is a crucial task with a wide range of applications. In environments with close proximity between humans and animals, such as zoos, it is essential to better understand the causes behind animal behaviour and what interventions are responsible for changes in their behaviours. This can help to predict unusual behaviours, mitigate detrimental effects and increase the well-being of animals. There has been work on modelling the dynamics behind swarms of birds and insects but the complex social behaviours of mammalian groups remain less explored. In this work, we propose a method to build behavioural models using causal structure discovery and graph neural networks for time series. We apply this method to a mob of meerkats in a zoo environment and study its ability to predict future actions and model the behaviour distribution at an individual-level and at a group level. We show that our method can match and outperform standard deep learning architectures and generate more realistic data, while using fewer parameters and providing increased interpretability.
Authors: Qiaoyue Tang, Frederick Shpilevskiy, Mathias Lécuyer
The Adam optimizer is a popular choice in contemporary deep learning, due to its strong empirical performance. However we observe that in privacy sensitive scenarios, the traditional use of Differential Privacy (DP) with the Adam optimizer leads to sub-optimal performance on several tasks. We find that this performance degradation is due to a DP bias in Adam's second moment estimator, introduced by the addition of independent noise in the gradient computation to enforce DP guarantees. This DP bias leads to a different scaling for low variance parameter updates, that is inconsistent with the behavior of non-private Adam. We propose DP-AdamBC, an optimization algorithm which removes the bias in the second moment estimation and retrieves the expected behaviour of Adam. Empirically, DP-AdamBC significantly improves the optimization performance of DP-Adam by up to 3.5% in final accuracy in image, text, and graph node classification tasks.
Authors: Alexander Grushin
Today's most powerful machine learning approaches are typically designed to train stateless architectures with predefined layers and differentiable activation functions. While these approaches have led to unprecedented successes in areas such as natural language processing and image recognition, the trained models are also susceptible to making mistakes that a human would not. In this paper, we take the view that true intelligence may require the ability of a machine learning model to manage internal state, but that we have not yet discovered the most effective algorithms for training such models. We further postulate that such algorithms might not necessarily be based on gradient descent over a deep architecture, but rather, might work best with an architecture that has discrete activations and few initial topological constraints (such as multiple predefined layers). We present one attempt in our ongoing efforts to design such a training algorithm, applied to an architecture with binary activations and only a single matrix of weights, and show that it is able to form useful representations of natural language text, but is also limited in its ability to leverage large quantities of training data. We then provide ideas for improving the algorithm and for designing other training algorithms for similar architectures. Finally, we discuss potential benefits that could be gained if an effective training algorithm is found, and suggest experiments for evaluating whether these benefits exist in practice.
Authors: Allen Chang, Matthew C. Fontaine, Serena Booth, Maja J. Matarić, Stefanos Nikolaidis
Generative models can serve as surrogates for some real data sources by creating synthetic training datasets, but in doing so they may transfer biases to downstream tasks. We focus on protecting quality and diversity when generating synthetic training datasets. We propose quality-diversity generative sampling (QDGS), a framework for sampling data uniformly across a user-defined measure space, despite the data coming from a biased generator. QDGS is a model-agnostic framework that uses prompt guidance to optimize a quality objective across measures of diversity for synthetically generated data, without fine-tuning the generative model. Using balanced synthetic datasets generated by QDGS, we first debias classifiers trained on color-biased shape datasets as a proof-of-concept. By applying QDGS to facial data synthesis, we prompt for desired semantic concepts, such as skin tone and age, to create an intersectional dataset with a combined blend of visual features. Leveraging this balanced data for training classifiers improves fairness while maintaining accuracy on facial recognition benchmarks. Code available at: https://github.com/Cylumn/qd-generative-sampling
Authors: Z. Fu, C. Grant, D. M. Krawiec, A. Li, L. Winslow
The next generation of searches for neutrinoless double beta decay (0{\nu}\b{eta}\b{eta}) are poised to answer deep questions on the nature of neutrinos and the source of the Universe's matter-antimatter asymmetry. They will be looking for event rates of less than one event per ton of instrumented isotope per year. To claim discovery, accurate and efficient simulations of detector events that mimic 0{\nu}\b{eta}\b{eta} is critical. Traditional Monte Carlo (MC) simulations can be supplemented by machine-learning-based generative models. In this work, we describe the performance of generative models designed for monolithic liquid scintillator detectors like KamLAND to produce highly accurate simulation data without a predefined physics model. We demonstrate its ability to recover low-level features and perform interpolation. In the future, the results of these generative models can be used to improve event classification and background rejection by providing high-quality abundant generated data.
Authors: Anirudh S. Sundar, Chao-Han Huck Yang, David M. Chan, Shalini Ghosh, Venkatesh Ravichandran, Phani Sankar Nidadavolu
Training large foundation models using self-supervised objectives on unlabeled data, followed by fine-tuning on downstream tasks, has emerged as a standard procedure. Unfortunately, the efficacy of this approach is often constrained by both limited fine-tuning compute and scarcity in labeled downstream data. We introduce Multimodal Attention Merging (MAM), an attempt that facilitates direct knowledge transfer from attention matrices of models rooted in high resource modalities, text and images, to those in resource-constrained domains, speech and audio, employing a zero-shot paradigm. MAM reduces the relative Word Error Rate (WER) of an Automatic Speech Recognition (ASR) model by up to 6.70%, and relative classification error of an Audio Event Classification (AEC) model by 10.63%. In cases where some data/compute is available, we present Learnable-MAM, a data-driven approach to merging attention matrices, resulting in a further 2.90% relative reduction in WER for ASR and 18.42% relative reduction in AEC compared to fine-tuning.
Authors: Tiejin Chen, Yuanpu Cao, Yujia Wang, Cho-Jui Hsieh, Jinghui Chen
Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients, which leads to deteriorated model training performances. Prior works in this line of research mainly focus on utilizing last-step global model parameters/gradients or the linear combinations of the past model parameters/gradients, which do not fully exploit the potential of global information from the model training trajectory. In this paper, we propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data heterogeneity issue, which proposes a unique way to better extract the essential global information from the model training trajectory. Specifically, FedPTR allows local clients or the server to optimize an auxiliary (synthetic) dataset that mimics the learning dynamics of the recent model update and utilizes it to project the next-step model trajectory for local training regularization. We conduct rigorous theoretical analysis for our proposed framework under nonconvex stochastic settings to verify its fast convergence under heterogeneous data distributions. Experiments on various benchmark datasets and non-i.i.d. settings validate the effectiveness of our proposed framework.
Authors: Alicia Golden, Samuel Hsia, Fei Sun, Bilge Acun, Basil Hosmer, Yejin Lee, Zachary DeVito, Jeff Johnson, Gu-Yeon Wei, David Brooks, Carole-Jean Wu
As the development of large-scale Generative AI models evolve beyond text (1D) generation to include image (2D) and video (3D) generation, processing spatial and temporal information presents unique challenges to quality, performance, and efficiency. We present the first work towards understanding this new system design space for multi-modal text-to-image (TTI) and text-to-video (TTV) generation models. Current model architecture designs are bifurcated into 2 categories: Diffusion- and Transformer-based models. Our systematic performance characterization on a suite of eight representative TTI/TTV models shows that after state-of-the-art optimization techniques such as Flash Attention are applied, Convolution accounts for up to 44% of execution time for Diffusion-based TTI models, while Linear layers consume up to 49% of execution time for Transformer-based models. We additionally observe that Diffusion-based TTI models resemble the Prefill stage of LLM inference, and benefit from 1.1-2.5x greater speedup from Flash Attention than Transformer-based TTI models that resemble the Decode phase. Since optimizations designed for LLMs do not map directly onto TTI/TTV models, we must conduct a thorough characterization of these workloads to gain insights for new optimization opportunities. In doing so, we define sequence length in the context of TTI/TTV models and observe sequence length can vary up to 4x in Diffusion model inference. We additionally observe temporal aspects of TTV workloads pose unique system bottlenecks, with Temporal Attention accounting for over 60% of total Attention time. Overall, our in-depth system performance characterization is a critical first step towards designing efficient and deployable systems for emerging TTI/TTV workloads.
Authors: Qi Xu, Lijie Wang, Jing Wang, Song Chen, Lin Cheng, Yi Kang
In recent years, analog circuits have received extensive attention and are widely used in many emerging applications. The high demand for analog circuits necessitates shorter circuit design cycles. To achieve the desired performance and specifications, various geometrical symmetry constraints must be carefully considered during the analog layout process. However, the manual labeling of these constraints by experienced analog engineers is a laborious and time-consuming process. To handle the costly runtime issue, we propose a graph-based learning framework to automatically extract symmetric constraints in analog circuit layout. The proposed framework leverages the connection characteristics of circuits and the devices'information to learn the general rules of symmetric constraints, which effectively facilitates the extraction of device-level constraints on circuit netlists. The experimental results demonstrate that compared to state-of-the-art symmetric constraint detection approaches, our framework achieves higher accuracy and lower false positive rate.
Authors: Ze Yu Zhao (1), Zheng Zhu (1), Guilin Li (1), Wenhan Wang (1), Bo Wang (1) ((1) Tencent, WeChat Pay)
In this work, we introduce an innovative autoregressive model leveraging Generative Pretrained Transformer (GPT) architectures, tailored for fraud detection in payment systems. Our approach innovatively confronts token explosion and reconstructs behavioral sequences, providing a nuanced understanding of transactional behavior through temporal and contextual analysis. Utilizing unsupervised pretraining, our model excels in feature representation without the need for labeled data. Additionally, we integrate a differential convolutional approach to enhance anomaly detection, bolstering the security and efficacy of one of the largest online payment merchants in China. The scalability and adaptability of our model promise broad applicability in various transactional contexts.
Authors: Shashank Sule, Luke Evans, Maria Cameron
We obtain asymptotically sharp error estimates for the consistency error of the Target Measure Diffusion map (TMDmap) (Banisch et al. 2020), a variant of diffusion maps featuring importance sampling and hence allowing input data drawn from an arbitrary density. The derived error estimates include the bias error and the variance error. The resulting convergence rates are consistent with the approximation theory of graph Laplacians. The key novelty of our results lies in the explicit quantification of all the prefactors on leading-order terms. We also prove an error estimate for solutions of Dirichlet BVPs obtained using TMDmap, showing that the solution error is controlled by consistency error. We use these results to study an important application of TMDmap in the analysis of rare events in systems governed by overdamped Langevin dynamics using the framework of transition path theory (TPT). The cornerstone ingredient of TPT is the solution of the committor problem, a boundary value problem for the backward Kolmogorov PDE. Remarkably, we find that the TMDmap algorithm is particularly suited as a meshless solver to the committor problem due to the cancellation of several error terms in the prefactor formula. Furthermore, significant improvements in bias and variance errors occur when using a quasi-uniform sampling density. Our numerical experiments show that these improvements in accuracy are realizable in practice when using $\delta$-nets as spatially uniform inputs to the TMDmap algorithm.
Authors: Siqi Mao, Yaping Yuan, Yinpu Li, Ziren Wang, Yuanxin Yao, Yixin Kang
Energy conservation in buildings is a paramount concern to combat greenhouse gas emissions and combat climate change. The efficient management of room occupancy, involving actions like lighting control and climate adjustment, is a pivotal strategy to curtail energy consumption. In contexts where surveillance technology isn't viable, non-intrusive sensors are employed to estimate room occupancy. In this study, we present a predictive framework for room occupancy that leverages a diverse set of machine learning models, with Random Forest consistently achieving the highest predictive accuracy. Notably, this dataset encompasses both temporal and spatial dimensions, revealing a wealth of information. Intriguingly, our framework demonstrates robust performance even in the absence of explicit temporal modeling. These findings underscore the remarkable predictive power of traditional machine learning models. The success can be attributed to the presence of feature redundancy, the simplicity of linear spatial and temporal patterns, and the advantages of high-frequency data sampling. While these results are compelling, it's essential to remain open to the possibility that explicitly modeling the temporal dimension could unlock deeper insights or further enhance predictive capabilities in specific scenarios. In summary, our research not only validates the effectiveness of our prediction framework for continuous and classification tasks but also underscores the potential for improvements through the inclusion of temporal aspects. The study highlights the promise of machine learning in shaping energy-efficient practices and room occupancy management.
The recent emergence of large language models (LLMs) shows the potential for artificial general intelligence, revealing new opportunities in industry 4.0 and smart manufacturing. However, a notable gap exists in applying these LLMs in industry, primarily due to their training on general knowledge rather than domain-specific knowledge. Such specialized domain knowledge is vital for effectively addressing the complex needs of industrial applications. To bridge this gap, this paper proposes an Industrial Large Knowledge Model (ILKM) framework emphasizing their potential to revolutionize the industry in smart manufacturing. In addition, ILKMs and LLMs are compared from eight perspectives. Finally, "6S Principle" is proposed as the guideline for the development of ILKMs in smart manufacturing.
Authors: Jay Shenoy, Axel Levy, Frédéric Poitevin, Gordon Wetzstein
X-ray free-electron lasers (XFELs) offer unique capabilities for measuring the structure and dynamics of biomolecules, helping us understand the basic building blocks of life. Notably, high-repetition-rate XFELs enable single particle imaging (X-ray SPI) where individual, weakly scattering biomolecules are imaged under near-physiological conditions with the opportunity to access fleeting states that cannot be captured in cryogenic or crystallized conditions. Existing X-ray SPI reconstruction algorithms, which estimate the unknown orientation of a particle in each captured image as well as its shared 3D structure, are inadequate in handling the massive datasets generated by these emerging XFELs. Here, we introduce X-RAI, an online reconstruction framework that estimates the structure of a 3D macromolecule from large X-ray SPI datasets. X-RAI consists of a convolutional encoder, which amortizes pose estimation over large datasets, as well as a physics-based decoder, which employs an implicit neural representation to enable high-quality 3D reconstruction in an end-to-end, self-supervised manner. We demonstrate that X-RAI achieves state-of-the-art performance for small-scale datasets in simulation and challenging experimental settings and demonstrate its unprecedented ability to process large datasets containing millions of diffraction images in an online fashion. These abilities signify a paradigm shift in X-ray SPI towards real-time capture and reconstruction.
Authors: Souradip Chakraborty, Amisha Bhaskar, Anukriti Singh, Pratap Tokekar, Dinesh Manocha, Amrit Singh Bedi
In this work, we propose REBEL, an algorithm for sample efficient reward regularization based robotic reinforcement learning from human feedback (RRLHF). Reinforcement learning (RL) performance for continuous control robotics tasks is sensitive to the underlying reward function. In practice, the reward function often ends up misaligned with human intent, values, social norms, etc., leading to catastrophic failures in the real world. We leverage human preferences to learn regularized reward functions and eventually align the agents with the true intended behavior. We introduce a novel notion of reward regularization to the existing RRLHF framework, which is termed as agent preferences. So, we not only consider human feedback in terms of preferences, we also propose to take into account the preference of the underlying RL agent while learning the reward function. We show that this helps to improve the over-optimization associated with the design of reward functions in RL. We experimentally show that REBEL exhibits up to 70% improvement in sample efficiency to achieve a similar level of episodic reward returns as compared to the state-of-the-art methods such as PEBBLE and PEBBLE+SURF.
Authors: Bingheng Li, Erlin Pan, Zhao Kang
Recently, many carefully crafted graph representation learning methods have achieved impressive performance on either strong heterophilic or homophilic graphs, but not both. Therefore, they are incapable of generalizing well across real-world graphs with different levels of homophily. This is attributed to their neglect of homophily in heterophilic graphs, and vice versa. In this paper, we propose a two-fold filtering mechanism to extract homophily in heterophilic graphs and vice versa. In particular, we extend the graph heat equation to perform heterophilic aggregation of global information from a long distance. The resultant filter can be exactly approximated by the Possion-Charlier (PC) polynomials. To further exploit information at multiple orders, we introduce a powerful graph convolution PC-Conv and its instantiation PCNet for the node classification task. Compared with state-of-the-art GNNs, PCNet shows competitive performance on well-known homophilic and heterophilic graphs. Our implementation is available at https://github.com/uestclbh/PC-Conv.
Authors: Yilun Liu, Ruihong Qiu, Yanran Tang, Hongzhi Yin, Zi Huang
When handling streaming graphs, existing graph representation learning models encounter a catastrophic forgetting problem, where previously learned knowledge of these models is easily overwritten when learning with newly incoming graphs. In response, Continual Graph Learning emerges as a novel paradigm enabling graph representation learning from static to streaming graphs. Our prior work, CaT is a replay-based framework with a balanced continual learning procedure, which designs a small yet effective memory bank for replaying data by condensing incoming graphs. Although the CaT alleviates the catastrophic forgetting problem, there exist three issues: (1) The graph condensation algorithm derived in CaT only focuses on labelled nodes while neglecting abundant information carried by unlabelled nodes; (2) The continual training scheme of the CaT overemphasises on the previously learned knowledge, limiting the model capacity to learn from newly added memories; (3) Both the condensation process and replaying process of the CaT are time-consuming. In this paper, we propose a psudo-label guided memory bank (PUMA) CGL framework, extending from the CaT to enhance its efficiency and effectiveness by overcoming the above-mentioned weaknesses and limits. To fully exploit the information in a graph, PUMA expands the coverage of nodes during graph condensation with both labelled and unlabelled nodes. Furthermore, a training-from-scratch strategy is proposed to upgrade the previous continual learning scheme for a balanced training between the historical and the new graphs. Besides, PUMA uses a one-time prorogation and wide graph encoders to accelerate the graph condensation and the graph encoding process in the training stage to improve the efficiency of the whole framework. Extensive experiments on four datasets demonstrate the state-of-the-art performance and efficiency over existing methods.
Authors: Haz Sameen Shahgir, Xianghao Kong, Greg Ver Steeg, Yue Dong
The widespread use of Text-to-Image (T2I) models in content generation requires careful examination of their safety, including their robustness to adversarial attacks. Despite extensive research into this, the reasons for their effectiveness are underexplored. This paper presents an empirical study on adversarial attacks against T2I models, focusing on analyzing factors associated with attack success rates (ASRs). We introduce a new attack objective - entity swapping using adversarial suffixes and two gradient-based attack algorithms. Human and automatic evaluations reveal the asymmetric nature of ASRs on entity swap: for example, it is easier to replace "human" with "robot" in the prompt "a human dancing in the rain." with an adversarial suffix but is significantly harder in reverse. We further propose probing metrics to establish indicative signals from the model's beliefs to the adversarial ASR. We identify conditions resulting in a 60% success probability for adversarial attacks and others where this likelihood drops below 5%.
Authors: Chen Ding, Christopher Kanan, Dylan McKellips, Toranosuke Ozawa, Arian Shahmirza, Wesley Smith
The greatest demand for today's computing is machine learning. This paper analyzes three machine learning algorithms: transformers, spatial convolution, and FFT. The analysis is novel in three aspects. First, it measures the cost of memory access on an abstract memory hierarchy, instead of traditional time or space complexity. Second, the analysis is asymptotic and identifies the primary sources of the memory cost. Finally, the result is symbolic, which can be used to select algorithmic parameters such as the group size in grouped query attention for any dimension size and number of heads and the batch size for batched convolution for any image size and kernel size.
Authors: Soumya Suvra Ghosal, Yiyou Sun, Yixuan Li
Machine learning models deployed in the wild can be challenged by out-of-distribution (OOD) data from unknown classes. Recent advances in OOD detection rely on distance measures to distinguish samples that are relatively far away from the in-distribution (ID) data. Despite the promise, distance-based methods can suffer from the curse-of-dimensionality problem, which limits the efficacy in high-dimensional feature space. To combat this problem, we propose a novel framework, Subspace Nearest Neighbor (SNN), for OOD detection. In training, our method regularizes the model and its feature representation by leveraging the most relevant subset of dimensions (i.e. subspace). Subspace learning yields highly distinguishable distance measures between ID and OOD data. We provide comprehensive experiments and ablations to validate the efficacy of SNN. Compared to the current best distance-based method, SNN reduces the average FPR95 by 15.96% on the CIFAR-100 benchmark.
Authors: Chun-Ren Phang, Akimasa Hirata
Deep reinforcement learning (RL) algorithms enable the development of fully autonomous agents that can interact with the environment. Brain-computer interface (BCI) systems decipher human implicit brain signals regardless of the explicit environment. In this study, we integrated deep RL and BCI to improve beneficial human interventions in autonomous systems and the performance in decoding brain activities by considering environmental factors. Shared autonomy was allowed between the action command decoded from the electroencephalography (EEG) of the human agent and the action generated from the twin delayed DDPG (TD3) agent for a given environment. Our proposed copilot control scheme with a full blocker (Co-FB) significantly outperformed the individual EEG (EEG-NB) or TD3 control. The Co-FB model achieved a higher target approaching score, lower failure rate, and lower human workload than the EEG-NB model. The Co-FB control scheme had a higher invisible target score and level of allowed human intervention than the TD3 model. We also proposed a disparity d-index to evaluate the effect of contradicting agent decisions on the control accuracy and authority of the copilot model. We found a significant correlation between the control authority of the TD3 agent and the performance improvement of human EEG classification with respect to the d-index. We also observed that shifting control authority to the TD3 agent improved performance when BCI decoding was not optimal. These findings indicate that the copilot system can effectively handle complex environments and that BCI performance can be improved by considering environmental factors. Future work should employ continuous action space and different multi-agent approaches to evaluate copilot performance.
Authors: Sarthak Choudhary, Aashish Kolluri, Prateek Saxena
Training modern neural networks or models typically requires averaging over a sample of high-dimensional vectors. Poisoning attacks can skew or bias the average vectors used to train the model, forcing the model to learn specific patterns or avoid learning anything useful. Byzantine robust aggregation is a principled algorithmic defense against such biasing. Robust aggregators can bound the maximum bias in computing centrality statistics, such as mean, even when some fraction of inputs are arbitrarily corrupted. Designing such aggregators is challenging when dealing with high dimensions. However, the first polynomial-time algorithms with strong theoretical bounds on the bias have recently been proposed. Their bounds are independent of the number of dimensions, promising a conceptual limit on the power of poisoning attacks in their ongoing arms race against defenses.
In this paper, we show a new attack called HIDRA on practical realization of strong defenses which subverts their claim of dimension-independent bias. HIDRA highlights a novel computational bottleneck that has not been a concern of prior information-theoretic analysis. Our experimental evaluation shows that our attacks almost completely destroy the model performance, whereas existing attacks with the same goal fail to have much effect. Our findings leave the arms race between poisoning attacks and provable defenses wide open.
Authors: Honghao Wei, Xin Liu, Lei Ying
This paper studies safe Reinforcement Learning (safe RL) with linear function approximation and under hard instantaneous constraints where unsafe actions must be avoided at each step. Existing studies have considered safe RL with hard instantaneous constraints, but their approaches rely on several key assumptions: $(i)$ the RL agent knows a safe action set for {\it every} state or knows a {\it safe graph} in which all the state-action-state triples are safe, and $(ii)$ the constraint/cost functions are {\it linear}. In this paper, we consider safe RL with instantaneous hard constraints without assumption $(i)$ and generalize $(ii)$ to Reproducing Kernel Hilbert Space (RKHS). Our proposed algorithm, LSVI-AE, achieves $\tilde{\cO}(\sqrt{d^3H^4K})$ regret and $\tilde{\cO}(H \sqrt{dK})$ hard constraint violation when the cost function is linear and $\cO(H\gamma_K \sqrt{K})$ hard constraint violation when the cost function belongs to RKHS. Here $K$ is the learning horizon, $H$ is the length of each episode, and $\gamma_K$ is the information gain w.r.t the kernel used to approximate cost functions. Our results achieve the optimal dependency on the learning horizon $K$, matching the lower bound we provide in this paper and demonstrating the efficiency of LSVI-AE. Notably, the design of our approach encourages aggressive policy exploration, providing a unique perspective on safe RL with general cost functions and no prior knowledge of safe actions, which may be of independent interest.
Authors: Xuan Gong, Shanglin Li, Yuxiang Bao, Barry Yao, Yawen Huang, Ziyan Wu, Baochang Zhang, Yefeng Zheng, David Doermann
Federated learning (FL) is a machine learning paradigm in which distributed local nodes collaboratively train a central model without sharing individually held private data. Existing FL methods either iteratively share local model parameters or deploy co-distillation. However, the former is highly susceptible to private data leakage, and the latter design relies on the prerequisites of task-relevant real data. Instead, we propose a data-free FL framework based on local-to-central collaborative distillation with direct input and output space exploitation. Our design eliminates any requirement of recursive local parameter exchange or auxiliary task-relevant data to transfer knowledge, thereby giving direct privacy control to local users. In particular, to cope with the inherent data heterogeneity across locals, our technique learns to distill input on which each local model produces consensual yet unique results to represent each expertise. Our proposed FL framework achieves notable privacy-utility trade-offs with extensive experiments on image classification and segmentation tasks under various real-world heterogeneous federated learning settings on both natural and medical images.
Authors: Zheyuan Hu, Zekun Shi, George Em Karniadakis, Kenji Kawaguchi
Physics-Informed Neural Networks (PINNs) have proven effective in solving partial differential equations (PDEs), especially when some data are available by blending seamlessly data and physics. However, extending PINNs to high-dimensional and even high-order PDEs encounters significant challenges due to the computational cost associated with automatic differentiation in the residual loss. Herein, we address the limitations of PINNs in handling high-dimensional and high-order PDEs by introducing Hutchinson Trace Estimation (HTE). Starting with the second-order high-dimensional PDEs ubiquitous in scientific computing, HTE transforms the calculation of the entire Hessian matrix into a Hessian vector product (HVP). This approach alleviates the computational bottleneck via Taylor-mode automatic differentiation and significantly reduces memory consumption from the Hessian matrix to HVP. We further showcase HTE's convergence to the original PINN loss and its unbiased behavior under specific conditions. Comparisons with Stochastic Dimension Gradient Descent (SDGD) highlight the distinct advantages of HTE, particularly in scenarios with significant variance among dimensions. We further extend HTE to higher-order and higher-dimensional PDEs, specifically addressing the biharmonic equation. By employing tensor-vector products (TVP), HTE efficiently computes the colossal tensor associated with the fourth-order high-dimensional biharmonic equation, saving memory and enabling rapid computation. The effectiveness of HTE is illustrated through experimental setups, demonstrating comparable convergence rates with SDGD under memory and speed constraints. Additionally, HTE proves valuable in accelerating the Gradient-Enhanced PINN (gPINN) version as well as the Biharmonic equation. Overall, HTE opens up a new capability in scientific machine learning for tackling high-order and high-dimensional PDEs.
Authors: Hisaichi Shibata
Equivariance is an important feature in machine learning, including language models. It ensures that any sequences of phrases with the same meanings are interpreted consistently. For example, the sentence 'There is a cat on the table' should be interpreted by language models as it is, regardless of variations in its token-level expression. Building on this insight, I propose a new theory suggesting that insufficient equivariance in language models can lead to hallucinations. According to this theory, which is both intuitive and novel, language models trained on relatively small datasets tend to misinterpret input texts and/or generate incorrect texts (i.e., hallucinations). To test this theory, I developed a toy model known as 'dancing men', which is a character-level substitution cipher. Additionally, I propose a novel technique based on the T5 (Text To Text Transfer Transformer) model to efficiently decipher these codes without relying on frequency analysis. I have found that this T5 model can almost completely solve the cipher, demonstrating its ability to acquire equivariance in this frame. This method could be scaled up to word-level and sentence-level substitution ciphers, analogous to large language models without tokenizers or dictionaries. This scalability makes it suitable for investigating the proposed link between inadequate equivariance acquisition and the emergence of hallucinations.
Authors: Bernardo Torres (S2A, IDS, LTCI), Geoffroy Peeters (S2A, IDS, LTCI), Gaël Richard (S2A, IDS, LTCI)
In neural audio signal processing, pitch conditioning has been used to enhance the performance of synthesizers. However, jointly training pitch estimators and synthesizers is a challenge when using standard audio-to-audio reconstruction loss, leading to reliance on external pitch trackers. To address this issue, we propose using a spectral loss function inspired by optimal transportation theory that minimizes the displacement of spectral energy. We validate this approach through an unsupervised autoencoding task that fits a harmonic template to harmonic signals. We jointly estimate the fundamental frequency and amplitudes of harmonics using a lightweight encoder and reconstruct the signals using a differentiable harmonic synthesizer. The proposed approach offers a promising direction for improving unsupervised parameter estimation in neural audio applications.
Authors: Oscar Fontenla-Romero, Bertha Guijarro-Berdiñas, Elena Hernández-Pereira, Beatriz Pérez-Sánchez
Nowadays, machine learning algorithms continue to grow in complexity and require a substantial amount of computational resources and energy. For these reasons, there is a growing awareness of the development of new green algorithms and distributed AI can contribute to this. Federated learning (FL) is one of the most active research lines in machine learning, as it allows the training of collaborative models in a distributed way, an interesting option in many real-world environments, such as the Internet of Things, allowing the use of these models in edge computing devices. In this work, we present a FL method, based on a neural network without hidden layers, capable of generating a global collaborative model in a single training round, unlike traditional FL methods that require multiple rounds for convergence. This allows obtaining an effective and efficient model that simplifies the management of the training process. Moreover, this method preserve data privacy by design, a crucial aspect in current data protection regulations. We conducted experiments with large datasets and a large number of federated clients. Despite being based on a network model without hidden layers, it maintains in all cases competitive accuracy results compared to more complex state-of-the-art machine learning models. Furthermore, we show that the method performs equally well in both identically and non-identically distributed scenarios. Finally, it is an environmentally friendly algorithm as it allows significant energy savings during the training process compared to its centralized counterpart.
Authors: Jiaming Lu, Jingqing Ruan, Haoyuan Jiang, Ziyue Li, Hangyu Mao, Rui Zhao
Reinforcement learning has been revolutionizing the traditional traffic signal control task, showing promising power to relieve congestion and improve efficiency. However, the existing methods lack effective learning mechanisms capable of absorbing dynamic information inherent to a specific scenario and universally applicable dynamic information across various scenarios. Moreover, within each specific scenario, they fail to fully capture the essential empirical experiences about how to coordinate between neighboring and target intersections, leading to sub-optimal system-wide outcomes.
Viewing these issues, we propose DuaLight, which aims to leverage both the experiential information within a single scenario and the generalizable information across various scenarios for enhanced decision-making. Specifically, DuaLight introduces a scenario-specific experiential weight module with two learnable parts: Intersection-wise and Feature-wise, guiding how to adaptively utilize neighbors and input features for each scenario, thus providing a more fine-grained understanding of different intersections. Furthermore, we implement a scenario-shared Co-Train module to facilitate the learning of generalizable dynamics information across different scenarios. Empirical results on both real-world and synthetic scenarios show DuaLight achieves competitive performance across various metrics, offering a promising solution to alleviate traffic congestion, with 3-7\% improvements. The code is available under: https://github.com/lujiaming-12138/DuaLight.
Authors: Hongliu Cao, Ilias El Baamrani, Eoin Thomas
As the digitization of travel industry accelerates, analyzing and understanding travelers' behaviors becomes increasingly important. However, traveler data frequently exhibit high data sparsity due to the relatively low frequency of user interactions with travel providers. Compounding this effect the multiplication of devices, accounts and platforms while browsing travel products online also leads to data dispersion. To deal with these challenges, probabilistic traveler matching can be used. Most existing solutions for user matching are not suitable for traveler matching as a traveler's browsing history is typically short and URLs in the travel industry are very heterogeneous with many tokens. To deal with these challenges, we propose the similarity based multi-view information fusion to learn a better user representation from URLs by treating the URLs as multi-view data. The experimental results show that the proposed multi-view user representation learning can take advantage of the complementary information from different views, highlight the key information in URLs and perform significantly better than other representation learning solutions for the user matching task.
Authors: Junwei He, Qianqian Xu, Yangbangyan Jiang, Zitai Wang, Qingming Huang
Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Although existing reconstruction-based methods have achieved considerable success, they may face the \textit{Anomaly Overfitting} and \textit{Homophily Trap} problems caused by the abnormal patterns in the graph, breaking the assumption that normal nodes are often better reconstructed than abnormal ones. Our observations indicate that models trained on graphs with fewer anomalies exhibit higher detection performance. Based on this insight, we introduce a novel two-stage framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD). In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. We pretrain graph autoencoders on these augmented graphs at multiple levels, which enables the graph autoencoders to capture normal patterns. In the next stage, the decoders are retrained for detection on the original graph, benefiting from the multi-level representations learned in the previous stage. Meanwhile, we propose the node anomaly distribution regularization to further alleviate \textit{Anomaly Overfitting}. We validate the effectiveness of our approach through extensive experiments on both synthetic and real-world datasets.
Authors: Lukas Morand, Tarek Iraki, Johannes Dornheim, Stefan Sandfeld, Norbert Link, Dirk Helm
In recent years, there has been a growing interest in accelerated materials innovation in both, research and industry. However, to truly add value to the development of new advanced materials, it is inevitable to take into account manufacturing processes and thereby tailor materials design approaches to support downstream process design approaches. As a major step into this direction, we present a holistic optimization approach that covers the entire materials process-structure-property chain. Our approach specifically employs machine learning techniques to address two critical identification problems. The first is to solve a materials design problem, which involves identifying near-optimal material structures that exhibit desired macroscopic properties. The second is to solve a process design problem that is to find an optimal processing path to manufacture these material structures. Both identification problems are typically ill-posed, which presents a significant challenge for solution approaches. However, the non-unique nature of these problems also offers an important advantage for processing: By having several target structures that perform similarly well, the corresponding processes can be efficiently guided towards manufacturing the best reachable structure. In particular, we apply deep reinforcement learning for process design in combination with a multi-task learning-based optimization approach for materials design. The functionality of the approach will be demonstrated by using it to manufacture crystallographic textures with desired properties in a metal forming process.
Authors: Enikő Kevi, Kim-Thang Nguyen
Designing online algorithms with machine learning predictions is a recent technique beyond the worst-case paradigm for various practically relevant online problems (scheduling, caching, clustering, ski rental, etc.). While most previous learning-augmented algorithm approaches focus on integrating the predictions of a single oracle, we study the design of online algorithms with \emph{multiple} experts. To go beyond the popular benchmark of a static best expert in hindsight, we propose a new \emph{dynamic} benchmark (linear combinations of predictions that change over time). We present a competitive algorithm in the new dynamic benchmark with a performance guarantee of $O(\log K)$, where $K$ is the number of experts, for $0-1$ online optimization problems. Furthermore, our multiple-expert approach provides a new perspective on how to combine in an online manner several online algorithms - a long-standing central subject in the online algorithm research community.
Authors: Rui Pan, Yuxing Liu, Xiaoyu Wang, Tong Zhang
Heavy-ball momentum with decaying learning rates is widely used with SGD for optimizing deep learning models. In contrast to its empirical popularity, the understanding of its theoretical property is still quite limited, especially under the standard anisotropic gradient noise condition for quadratic regression problems. Although it is widely conjectured that heavy-ball momentum method can provide accelerated convergence and should work well in large batch settings, there is no rigorous theoretical analysis. In this paper, we fill this theoretical gap by establishing a non-asymptotic convergence bound for stochastic heavy-ball methods with step decay scheduler on quadratic objectives, under the anisotropic gradient noise condition. As a direct implication, we show that heavy-ball momentum can provide $\tilde{\mathcal{O}}(\sqrt{\kappa})$ accelerated convergence of the bias term of SGD while still achieving near-optimal convergence rate with respect to the stochastic variance term. The combined effect implies an overall convergence rate within log factors from the statistical minimax rate. This means SGD with heavy-ball momentum is useful in the large-batch settings such as distributed machine learning or federated learning, where a smaller number of iterations can significantly reduce the number of communication rounds, leading to acceleration in practice.
Authors: Marco Bjarne Schuster, Boris Wiegand, Jilles Vreeken
Although event logs are a powerful source to gain insight about the behavior of the underlying business process, existing work primarily focuses on finding patterns in the activity sequences of an event log, while ignoring event attribute data. Event attribute data has mostly been used to predict event occurrences and process outcome, but the state of the art neglects to mine succinct and interpretable rules how event attribute data changes during process execution. Subgroup discovery and rule-based classification approaches lack the ability to capture the sequential dependencies present in event logs, and thus lead to unsatisfactory results with limited insight into the process behavior.
Given an event log, we are interested in finding accurate yet succinct and interpretable if-then rules how the process modifies data. We formalize the problem in terms of the Minimum Description Length (MDL) principle, by which we choose the model with the best lossless description of the data. Additionally, we propose the greedy Moody algorithm to efficiently search for rules. By extensive experiments on both synthetic and real-world data, we show Moody indeed finds compact and interpretable rules, needs little data for accurate discovery, and is robust to noise.
Authors: Liang Peng, Songyue Cai, Zongqian Wu, Huifang Shang, Xiaofeng Zhu, Xiaoxiao Li
Prompt learning has demonstrated impressive efficacy in the fine-tuning of multimodal large models to a wide range of downstream tasks. Nonetheless, applying existing prompt learning methods for the diagnosis of neurological disorder still suffers from two issues: (i) existing methods typically treat all patches equally, despite the fact that only a small number of patches in neuroimaging are relevant to the disease, and (ii) they ignore the structural information inherent in the brain connection network which is crucial for understanding and diagnosing neurological disorders. To tackle these issues, we introduce a novel prompt learning model by learning graph prompts during the fine-tuning process of multimodal large models for diagnosing neurological disorders. Specifically, we first leverage GPT-4 to obtain relevant disease concepts and compute semantic similarity between these concepts and all patches. Secondly, we reduce the weight of irrelevant patches according to the semantic similarity between each patch and disease-related concepts. Moreover, we construct a graph among tokens based on these concepts and employ a graph convolutional network layer to extract the structural information of the graph, which is used to prompt the pre-trained multimodal large models for diagnosing neurological disorders. Extensive experiments demonstrate that our method achieves superior performance for neurological disorder diagnosis compared with state-of-the-art methods and validated by clinicians.
Authors: Stefano Peluchetti
The scope of this paper is generative modeling through diffusion processes. An approach falling within this paradigm is the work of Song et al. (2021), which relies on a time-reversal argument to construct a diffusion process targeting the desired data distribution. We show that the time-reversal argument, common to all denoising diffusion probabilistic modeling proposals, is not necessary. We obtain diffusion processes targeting the desired data distribution by taking appropriate mixtures of diffusion bridges. The resulting transport is exact by construction, allows for greater flexibility in choosing the dynamics of the underlying diffusion, and can be approximated by means of a neural network via novel training objectives. We develop a unifying view of the drift adjustments corresponding to our and to time-reversal approaches and make use of this representation to inspect the inner workings of diffusion-based generative models. Finally, we leverage on scalable simulation and inference techniques common in spatial statistics to move beyond fully factorial distributions in the underlying diffusion dynamics. The methodological advances contained in this work contribute toward establishing a general framework for generative modeling based on diffusion processes.
Authors: Zhenlin Su, Liyan Xu, Jin Xu, Jiangnan Li, Mingdu Huangfu
Identifying speakers of quotations in narratives is an important task in literary analysis, with challenging scenarios including the out-of-domain inference for unseen speakers, and non-explicit cases where there are no speaker mentions in surrounding context. In this work, we propose a simple and effective approach SIG, a generation-based method that verbalizes the task and quotation input based on designed prompt templates, which also enables easy integration of other auxiliary tasks that further bolster the speaker identification performance. The prediction can either come from direct generation by the model, or be determined by the highest generation probability of each speaker candidate. Based on our approach design, SIG supports out-of-domain evaluation, and achieves open-world classification paradigm that is able to accept any forms of candidate input. We perform both cross-domain evaluation and in-domain evaluation on PDNC, the largest dataset of this task, where empirical results suggest that SIG outperforms previous baselines of complicated designs, as well as the zero-shot ChatGPT, especially excelling at those hard non-explicit scenarios by up to 17% improvement. Additional experiments on another dataset WP further corroborate the efficacy of SIG.
Authors: Till Beemelmanns, Wassim Zahr, Lutz Eckstein
Vision Transformers (ViTs) have achieved state-of-the-art results on various computer vision tasks, including 3D object detection. However, their end-to-end implementation also makes ViTs less explainable, which can be a challenge for deploying them in safety-critical applications, such as autonomous driving, where it is important for authorities, developers, and users to understand the model's reasoning behind its predictions. In this paper, we propose a novel method for generating saliency maps for a DetR-like ViT with multiple camera inputs used for 3D object detection. Our method is based on the raw attention and is more efficient than gradient-based methods. We evaluate the proposed method on the nuScenes dataset using extensive perturbation tests and show that it outperforms other explainability methods in terms of visual quality and quantitative metrics. We also demonstrate the importance of aggregating attention across different layers of the transformer. Our work contributes to the development of explainable AI for ViTs, which can help increase trust in AI applications by establishing more transparency regarding the inner workings of AI models.
Authors: Taha Eghtesad, Sirui Li, Yevgeniy Vorobeychik, Aron Laszka
The increasing reliance of drivers on navigation applications has made transportation networks more susceptible to data-manipulation attacks by malicious actors. Adversaries may exploit vulnerabilities in the data collection or processing of navigation services to inject false information, and to thus interfere with the drivers' route selection. Such attacks can significantly increase traffic congestions, resulting in substantial waste of time and resources, and may even disrupt essential services that rely on road networks. To assess the threat posed by such attacks, we introduce a computational framework to find worst-case data-injection attacks against transportation networks. First, we devise an adversarial model with a threat actor who can manipulate drivers by increasing the travel times that they perceive on certain roads. Then, we employ hierarchical multi-agent reinforcement learning to find an approximate optimal adversarial strategy for data manipulation. We demonstrate the applicability of our approach through simulating attacks on the Sioux Falls, ND network topology.
Authors: Hongliu Cao
To comply with new legal requirements and policies committed to privacy protection, more and more companies start to deploy cross-silo Federated Learning at global scale, where several clients/silos collaboratively train a global model under the coordination of a central server. Instead of data sharing and transmission, clients train models using their private local data and exchange model updates. However, there is little understanding of the carbon emission impact of cross silo Federated Learning due to the lack of related works. In this study, we first analyze the sustainability aspect of cross-silo Federated Learning, across the AI product life cycle instead of focusing only on the model training, with the comparison to the centralized method. A more holistic quantitative cost and CO2 emission estimation method for real world cross-silo Federated Learning setting is proposed. Secondly, we propose a novel data and application management system using cross silo Federated Learning and analytics to make IT companies more sustainable and cost effective.
Authors: Yitong Deng, Hong-Xing Yu, Diyang Zhang, Jiajun Wu, Bo Zhu
We introduce Neural Flow Maps, a novel simulation method bridging the emerging paradigm of implicit neural representations with fluid simulation based on the theory of flow maps, to achieve state-of-the-art simulation of inviscid fluid phenomena. We devise a novel hybrid neural field representation, Spatially Sparse Neural Fields (SSNF), which fuses small neural networks with a pyramid of overlapping, multi-resolution, and spatially sparse grids, to compactly represent long-term spatiotemporal velocity fields at high accuracy. With this neural velocity buffer in hand, we compute long-term, bidirectional flow maps and their Jacobians in a mechanistically symmetric manner, to facilitate drastic accuracy improvement over existing solutions. These long-range, bidirectional flow maps enable high advection accuracy with low dissipation, which in turn facilitates high-fidelity incompressible flow simulations that manifest intricate vortical structures. We demonstrate the efficacy of our neural fluid simulation in a variety of challenging simulation scenarios, including leapfrogging vortices, colliding vortices, vortex reconnections, as well as vortex generation from moving obstacles and density differences. Our examples show increased performance over existing methods in terms of energy conservation, visual complexity, adherence to experimental observations, and preservation of detailed vortical structures.
Authors: Mohamed Badi, Chaouki Ben Issaid, Anis Elgabli, Mehdi Bennis
The growing number of wireless edge devices has magnified challenges concerning energy, bandwidth, latency, and data heterogeneity. These challenges have become bottlenecks for distributed learning. To address these issues, this paper presents a novel approach that ensures energy efficiency for distributionally robust federated learning (FL) with over air computation (AirComp). In this context, to effectively balance robustness with energy efficiency, we introduce a novel client selection method that integrates two complementary insights: a deterministic one that is designed for energy efficiency, and a probabilistic one designed for distributional robustness. Simulation results underscore the efficacy of the proposed algorithm, revealing its superior performance compared to baselines from both robustness and energy efficiency perspectives, achieving more than 3-fold energy savings compared to the considered baselines.
Authors: Hongda Sun, Hongzhan Lin, Rui Yan
Electronic health records (EHRs) have become the foundation of machine learning applications in healthcare, while the utility of real patient records is often limited by privacy and security concerns. Synthetic EHR generation provides an additional perspective to compensate for this limitation. Most existing methods synthesize new records based on real EHR data, without consideration of different types of events in EHR data, which cannot control the event combinations in line with medical common sense. In this paper, we propose MSIC, a Multi-visit health Status Inference model for Collaborative EHR synthesis to address these limitations. First, we formulate the synthetic EHR generation process as a probabilistic graphical model and tightly connect different types of events by modeling the latent health states. Then, we derive a health state inference method tailored for the multi-visit scenario to effectively utilize previous records to synthesize current and future records. Furthermore, we propose to generate medical reports to add textual descriptions for each medical event, providing broader applications for synthesized EHR data. For generating different paragraphs in each visit, we incorporate a multi-generator deliberation framework to collaborate the message passing of multiple generators and employ a two-phase decoding strategy to generate high-quality reports. Our extensive experiments on the widely used benchmarks, MIMIC-III and MIMIC-IV, demonstrate that MSIC advances state-of-the-art results on the quality of synthetic data while maintaining low privacy risks.
Authors: Alaa Saleh, Susanna Pirttikangas, Lauri Lovén
In today's digital world, Generative Artificial Intelligence (GenAI) such as Large Language Models (LLMs) is becoming increasingly prevalent, extending its reach across diverse applications. This surge in adoption has sparked a significant increase in demand for data-centric GenAI models, highlighting the necessity for robust data communication infrastructures. Central to this need are message brokers, which serve as essential channels for data transfer within various system components. This survey aims to delve into a comprehensive analysis of traditional and modern message brokers, offering a comparative study of prevalent platforms. Our study considers numerous criteria including, but not limited to, open-source availability, integrated monitoring tools, message prioritization mechanisms, capabilities for parallel processing, reliability, distribution and clustering functionalities, authentication processes, data persistence strategies, fault tolerance, and scalability. Furthermore, we explore the intrinsic constraints that the design and operation of each message broker might impose, recognizing that these limitations are crucial in understanding their real-world applicability. We then leverage these insights to propose a sophisticated message broker framework -- one designed with the adaptability and robustness necessary to meet the evolving requisites of GenAI applications. Finally, this study examines the enhancement of message broker mechanisms specifically for GenAI contexts, emphasizing the criticality of developing a versatile message broker framework. Such a framework would be poised for quick adaptation, catering to the dynamic and growing demands of GenAI in the foreseeable future. Through this dual-pronged approach, we intend to contribute a foundational compendium that can guide future innovations and infrastructural advancements in the realm of GenAI data communication.
Authors: Patricia A. Apellániz, Juan Parras, Santiago Zazo
As in many fields of medical research, survival analysis has witnessed a growing interest in the application of deep learning techniques to model complex, high-dimensional, heterogeneous, incomplete, and censored medical data. Current methods often make assumptions about the relations between data that may not be valid in practice. In response, we introduce SAVAE (Survival Analysis Variational Autoencoder), a novel approach based on Variational Autoencoders. SAVAE contributes significantly to the field by introducing a tailored ELBO formulation for survival analysis, supporting various parametric distributions for covariates and survival time (as long as the log-likelihood is differentiable). It offers a general method that consistently performs well on various metrics, demonstrating robustness and stability through different experiments. Our proposal effectively estimates time-to-event, accounting for censoring, covariate interactions, and time-varying risk associations. We validate our model in diverse datasets, including genomic, clinical, and demographic data, with varying levels of censoring. This approach demonstrates competitive performance compared to state-of-the-art techniques, as assessed by the Concordance Index and the Integrated Brier Score. SAVAE also offers an interpretable model that parametrically models covariates and time. Moreover, its generative architecture facilitates further applications such as clustering, data imputation, and the generation of synthetic patient data through latent space inference from survival data.
Authors: Syama Sundar Rangapuram, Jan Gasthaus, Lorenzo Stella, Valentin Flunkert, David Salinas, Yuyang Wang, Tim Januschowski
This paper presents non-parametric baseline models for time series forecasting. Unlike classical forecasting models, the proposed approach does not assume any parametric form for the predictive distribution and instead generates predictions by sampling from the empirical distribution according to a tunable strategy. By virtue of this, the model is always able to produce reasonable forecasts (i.e., predictions within the observed data range) without fail unlike classical models that suffer from numerical stability on some data distributions. Moreover, we develop a global version of the proposed method that automatically learns the sampling strategy by exploiting the information across multiple related time series. The empirical evaluation shows that the proposed methods have reasonable and consistent performance across all datasets, proving them to be strong baselines to be considered in one's forecasting toolbox.
Authors: Qianrui Zhou, Hua Xu, Hao Li, Hanlei Zhang, Xiaohan Zhang, Yifan Wang, Kai Gao
Multimodal intent recognition aims to leverage diverse modalities such as expressions, body movements and tone of speech to comprehend user's intent, constituting a critical task for understanding human language and behavior in real-world multimodal scenarios. Nevertheless, the majority of existing methods ignore potential correlations among different modalities and own limitations in effectively learning semantic features from nonverbal modalities. In this paper, we introduce a token-level contrastive learning method with modality-aware prompting (TCL-MAP) to address the above challenges. To establish an optimal multimodal semantic environment for text modality, we develop a modality-aware prompting module (MAP), which effectively aligns and fuses features from text, video and audio modalities with similarity-based modality alignment and cross-modality attention mechanism. Based on the modality-aware prompt and ground truth labels, the proposed token-level contrastive learning framework (TCL) constructs augmented samples and employs NT-Xent loss on the label token. Specifically, TCL capitalizes on the optimal textual semantic insights derived from intent labels to guide the learning processes of other modalities in return. Extensive experiments show that our method achieves remarkable improvements compared to state-of-the-art methods. Additionally, ablation analyses demonstrate the superiority of the modality-aware prompt over the handcrafted prompt, which holds substantial significance for multimodal prompt learning. The codes are released at https://github.com/thuiar/TCL-MAP.
Authors: Raffaele Marino, Lorenzo Buffoni, Lorenzo Chicchi, Lorenzo Giambagli, Duccio Fanelli
EODECA (Engineered Ordinary Differential Equations as Classification Algorithm) is a novel approach at the intersection of machine learning and dynamical systems theory, presenting a unique framework for classification tasks [1]. This method stands out with its dynamical system structure, utilizing ordinary differential equations (ODEs) to efficiently handle complex classification challenges. The paper delves into EODECA's dynamical properties, emphasizing its resilience against random perturbations and robust performance across various classification scenarios. Notably, EODECA's design incorporates the ability to embed stable attractors in the phase space, enhancing reliability and allowing for reversible dynamics. In this paper, we carry out a comprehensive analysis by expanding on the work [1], and employing a Euler discretization scheme. In particular, we evaluate EODECA's performance across five distinct classification problems, examining its adaptability and efficiency. Significantly, we demonstrate EODECA's effectiveness on the MNIST and Fashion MNIST datasets, achieving impressive accuracies of $98.06\%$ and $88.21\%$, respectively. These results are comparable to those of a multi-layer perceptron (MLP), underscoring EODECA's potential in complex data processing tasks. We further explore the model's learning journey, assessing its evolution in both pre and post training environments and highlighting its ability to navigate towards stable attractors. The study also investigates the invertibility of EODECA, shedding light on its decision-making processes and internal workings. This paper presents a significant step towards a more transparent and robust machine learning paradigm, bridging the gap between machine learning algorithms and dynamical systems methodologies.
Authors: Nicolas Boullé, Alex Townsend
Operator learning aims to discover properties of an underlying dynamical system or partial differential equation (PDE) from data. Here, we present a step-by-step guide to operator learning. We explain the types of problems and PDEs amenable to operator learning, discuss various neural network architectures, and explain how to employ numerical PDE solvers effectively. We also give advice on how to create and manage training data and conduct optimization. We offer intuition behind the various neural network architectures employed in operator learning by motivating them from the point-of-view of numerical linear algebra.
Authors: Naoufal El Bekri, Lucas Drumetz, Franck Vermet
The generative paradigm has become increasingly important in machine learning and deep learning models. Among popular generative models are normalizing flows, which enable exact likelihood estimation by transforming a base distribution through diffeomorphic transformations. Extending the normalizing flow framework to handle time-indexed flows gave dynamic normalizing flows, a powerful tool to model time series, stochastic processes, and neural stochastic differential equations (SDEs). In this work, we propose a novel variant of dynamic normalizing flows, a Time Changed Normalizing Flow (TCNF), based on time deformation of a Brownian motion which constitutes a versatile and extensive family of Gaussian processes. This approach enables us to effectively model some SDEs, that cannot be modeled otherwise, including standard ones such as the well-known Ornstein-Uhlenbeck process, and generalizes prior methodologies, leading to improved results and better inference and prediction capability.
Authors: Yifei Chen, Binfeng Zou, Zhaoxin Guo, Yiyu Huang, Yifan Huang, Feiwei Qin, Qinhai Li, Changmiao Wang
Pulmonary embolism (PE) is a prevalent lung disease that can lead to right ventricular hypertrophy and failure in severe cases, ranking second in severity only to myocardial infarction and sudden death. Pulmonary artery CT angiography (CTPA) is a widely used diagnostic method for PE. However, PE detection presents challenges in clinical practice due to limitations in imaging technology. CTPA can produce noises similar to PE, making confirmation of its presence time-consuming and prone to overdiagnosis. Nevertheless, the traditional segmentation method of PE can not fully consider the hierarchical structure of features, local and global spatial features of PE CT images. In this paper, we propose an automatic PE segmentation method called SCUNet++ (Swin Conv UNet++). This method incorporates multiple fusion dense skip connections between the encoder and decoder, utilizing the Swin Transformer as the encoder. And fuses features of different scales in the decoder subnetwork to compensate for spatial information loss caused by the inevitable downsampling in Swin-UNet or other state-of-the-art methods, effectively solving the above problem. We provide a theoretical analysis of this method in detail and validate it on publicly available PE CT image datasets FUMPE and CAD-PE. The experimental results indicate that our proposed method achieved a Dice similarity coefficient (DSC) of 83.47% and a Hausdorff distance 95th percentile (HD95) of 3.83 on the FUMPE dataset, as well as a DSC of 83.42% and an HD95 of 5.10 on the CAD-PE dataset. These findings demonstrate that our method exhibits strong performance in PE segmentation tasks, potentially enhancing the accuracy of automatic segmentation of PE and providing a powerful diagnostic tool for clinical physicians. Our source code and new FUMPE dataset are available at https://github.com/JustlfC03/SCUNet-plusplus.
Authors: Youssef Allouah, Rachid Guerraoui, John Stephan
The success of machine learning (ML) applications relies on vast datasets and distributed architectures, which, as they grow, present challenges for ML. In real-world scenarios, where data often contains sensitive information, issues like data poisoning and hardware failures are common. Ensuring privacy and robustness is vital for the broad adoption of ML in public life. This paper examines the costs associated with achieving these objectives in distributed architectures. We overview the meanings of privacy and robustness in distributed ML, and clarify how they can be achieved efficiently in isolation. However, we contend that the integration of these objectives entails a notable compromise in computational efficiency. We delve into this intricate balance, exploring the challenges and solutions for privacy, robustness, and computational efficiency in ML applications.
Authors: Thorsten Wittkopp, Alexander Acker, Odej Kao
The realm of AIOps is transforming IT landscapes with the power of AI and ML. Despite the challenge of limited labeled data, supervised models show promise, emphasizing the importance of leveraging labels for training, especially in deep learning contexts. This study enhances the field by introducing a taxonomy for log anomalies and exploring automated data labeling to mitigate labeling challenges. It goes further by investigating the potential of diverse anomaly detection techniques and their alignment with specific anomaly types. However, the exploration doesn't stop at anomaly detection. The study envisions a future where root cause analysis follows anomaly detection, unraveling the underlying triggers of anomalies. This uncharted territory holds immense potential for revolutionizing IT systems management. In essence, this paper enriches our understanding of anomaly detection, and automated labeling, and sets the stage for transformative root cause analysis. Together, these advances promise more resilient IT systems, elevating operational efficiency and user satisfaction in an ever-evolving technological landscape.
Authors: Alan Chan, Ben Bucknall, Herbie Bradley, David Krueger
Public release of the weights of pretrained foundation models, otherwise known as downloadable access \citep{solaiman_gradient_2023}, enables fine-tuning without the prohibitive expense of pretraining. Our work argues that increasingly accessible fine-tuning of downloadable models may increase hazards. First, we highlight research to improve the accessibility of fine-tuning. We split our discussion into research that A) reduces the computational cost of fine-tuning and B) improves the ability to share that cost across more actors. Second, we argue that increasingly accessible fine-tuning methods may increase hazard through facilitating malicious use and making oversight of models with potentially dangerous capabilities more difficult. Third, we discuss potential mitigatory measures, as well as benefits of more accessible fine-tuning. Given substantial remaining uncertainty about hazards, we conclude by emphasizing the urgent need for the development of mitigations.
Authors: Todd Hildebrant
This paper explores the application diffusion maps as graph shift operators in understanding the underlying geometry of graph signals. The study evaluates the improvements in graph learning when using diffusion map generated filters to the Markov Variation minimization problem. The paper showcases the effectiveness of this approach through examples involving synthetically generated and real-world temperature sensor data. These examples also compare the diffusion map graph signal model with other commonly used graph signal operators. The results provide new approaches for the analysis and understanding of complex, non-Euclidean data structures.
Authors: Long Shi, Lei Cao, Jun Wang, Badong Chen
Latent multi-view subspace clustering has been demonstrated to have desirable clustering performance. However, the original latent representation method vertically concatenates the data matrices from multiple views into a single matrix along the direction of dimensionality to recover the latent representation matrix, which may result in an incomplete information recovery. To fully recover the latent space representation, we in this paper propose an Enhanced Latent Multi-view Subspace Clustering (ELMSC) method. The ELMSC method involves constructing an augmented data matrix that enhances the representation of multi-view data. Specifically, we stack the data matrices from various views into the block-diagonal locations of the augmented matrix to exploit the complementary information. Meanwhile, the non-block-diagonal entries are composed based on the similarity between different views to capture the consistent information. In addition, we enforce a sparse regularization for the non-diagonal blocks of the augmented self-representation matrix to avoid redundant calculations of consistency information. Finally, a novel iterative algorithm based on the framework of Alternating Direction Method of Multipliers (ADMM) is developed to solve the optimization problem for ELMSC. Extensive experiments on real-world datasets demonstrate that our proposed ELMSC is able to achieve higher clustering performance than some state-of-art multi-view clustering methods.
Authors: Abiodun Finbarrs Oketunji, Muhammad Anas, Deepthi Saina
The Large Language Model Bias Index (LLMBI) is a pioneering approach designed to quantify and address biases inherent in large language models (LLMs), such as GPT-4. We recognise the increasing prevalence and impact of LLMs across diverse sectors. This research introduces a novel metric, LLMBI, to systematically measure and mitigate biases potentially skewing model responses. We formulated LLMBI using a composite scoring system incorporating multiple dimensions of bias, including but not limited to age, gender, and racial biases.
To operationalise this metric, we engaged in a multi-step process involving collecting and annotating LLM responses, applying sophisticated Natural Language Processing (NLP) techniques for bias detection, and computing the LLMBI score through a specially crafted mathematical formula. The formula integrates weighted averages of various bias dimensions, a penalty for dataset diversity deficiencies, and a correction for sentiment biases. Our empirical analysis, conducted using responses from OpenAI's API, employs advanced sentiment analysis as a representative method for bias detection.
The research reveals LLMs, whilst demonstrating impressive capabilities in text generation, exhibit varying degrees of bias across different dimensions. LLMBI provides a quantifiable measure to compare biases across models and over time, offering a vital tool for systems engineers, researchers and regulators in enhancing the fairness and reliability of LLMs. It highlights the potential of LLMs in mimicking unbiased human-like responses. Additionally, it underscores the necessity of continuously monitoring and recalibrating such models to align with evolving societal norms and ethical standards.
Authors: Nikolay O. Nikitin, Maiia Pinchuk, Valerii Pokrovskii, Peter Shevchenko, Andrey Getmanov, Yaroslav Aksenkin, Ilia Revin, Andrey Stebenkov, Ekaterina Poslavskaya, Anna V. Kalyuzhnaya
Automated machine learning (AutoML) systems propose an end-to-end solution to a given machine learning problem, creating either fixed or flexible pipelines. Fixed pipelines are task independent constructs: their general composition remains the same, regardless of the data. In contrast, the structure of flexible pipelines varies depending on the input, making them finely tailored to individual tasks. However, flexible pipelines can be structurally overcomplicated and have poor explainability. We propose the EVOSA approach that compensates for the negative points of flexible pipelines by incorporating a sensitivity analysis which increases the robustness and interpretability of the flexible solutions. EVOSA quantitatively estimates positive and negative impact of an edge or a node on a pipeline graph, and feeds this information to the evolutionary AutoML optimizer. The correctness and efficiency of EVOSA was validated in tabular, multimodal and computer vision tasks, suggesting generalizability of the proposed approach across domains.
Authors: Junli Fang, João F. C. Mota, Baoshan Lu, Weicheng Zhang, Xuemin Hong
The joint source coding and modulation (JSCM) framework was enabled by recent developments in deep learning, which allows to automatically learn from data, and in an end-to-end fashion, the best compression codes and modulation schemes. In this paper, we show the existence of a strict tradeoff between channel rate, distortion, perception, and classification accuracy in a JSCM scenario. We then propose two image compression methods to navigate that tradeoff: an inverse-domain generative adversarial network (ID-GAN), which achieves extreme compression, and a simpler, heuristic method that reveals insights about the performance of ID-GAN. Experiment results not only corroborate the theoretical findings, but also demonstrate that the proposed ID-GAN algorithm significantly improves system performance compared to traditional separation-based methods and recent deep JSCM architectures.
Authors: Sandra Benítez-Peña, Rafael Blanquero, Emilio Carrizosa, Pepa Ramírez-Cobo
Support Vector Machine (SVM) is a powerful tool in binary classification, known to attain excellent misclassification rates. On the other hand, many realworld classification problems, such as those found in medical diagnosis, churn or fraud prediction, involve misclassification costs which may be different in the different classes. However, it may be hard for the user to provide precise values for such misclassification costs, whereas it may be much easier to identify acceptable misclassification rates values. In this paper we propose a novel SVM model in which misclassification costs are considered by incorporating performance constraints in the problem formulation. Specifically, our aim is to seek the hyperplane with maximal margin yielding misclassification rates below given threshold values. Such maximal margin hyperplane is obtained by solving a quadratic convex problem with linear constraints and integer variables. The reported numerical experience shows that our model gives the user control on the misclassification rates in one class (possibly at the expense of an increase in misclassification rates for the other class) and is feasible in terms of running times.
Authors: Georgia Atkinson, Nick Wright, A. Stephen McGough, Per Berggren
In recent years generative adversarial networks (GANs) have been used to supplement datasets within the field of marine bioacoustics. This is driven by factors such as the cost to collect data, data sparsity and aid preprocessing. One notable challenge with marine bioacoustic data is the low signal-to-noise ratio (SNR) posing difficulty when applying deep learning techniques such as GANs. This work investigates the effect SNR has on the audio-based GAN performance and examines three different evaluation methodologies for GAN performance, yielding interesting results on the effects of SNR on GANs, specifically WaveGAN.
Authors: David de la Rosa, Antonio J Rivera, María J del Jesus, Francisco Charte
Photo-trapping cameras are widely employed for wildlife monitoring. Those cameras take photographs when motion is detected to capture images where animals appear. A significant portion of these images are empty - no wildlife appears in the image. Filtering out those images is not a trivial task since it requires hours of manual work from biologists. Therefore, there is a notable interest in automating this task. Automatic discarding of empty photo-trapping images is still an open field in the area of Machine Learning. Existing solutions often rely on state-of-the-art supervised convolutional neural networks that require the annotation of the images in the training phase. PARDINUS (Weakly suPervised discARDINg of photo-trapping empty images based on aUtoencoderS) is constructed on the foundation of weakly supervised learning and proves that this approach equals or even surpasses other fully supervised methods that require further labeling work.
Authors: Valérie Castin, Pierre Ablin, Gabriel Peyré
Transformers and their multi-head attention mechanism have completely changed the machine learning landscape in just a few years, by outperforming state-of-art models in a wide range of domains. Still, little is known about their robustness from a theoretical perspective. We tackle this problem by studying the local Lipschitz constant of self-attention, that provides an attack-agnostic way of measuring the robustness of a neural network. We adopt a measure-theoretic framework, by viewing inputs as probability measures equipped with the Wasserstein distance. This allows us to generalize attention to inputs of infinite length, and to derive an upper bound and a lower bound on the Lipschitz constant of self-attention on compact sets. The lower bound significantly improves prior results, and grows more than exponentially with the radius of the compact set, which rules out the possibility of obtaining robustness guarantees without any additional constraint on the input space. Our results also point out that measures with a high local Lipschitz constant are typically made of a few diracs, with a very unbalanced distribution of mass. Finally, we analyze the stability of self-attention under perturbations that change the number of tokens, which appears to be a natural question in the measure-theoretic framework. In particular, we show that for some inputs, attacks that duplicate tokens before perturbing them are more efficient than attacks that simply move tokens. We call this phenomenon mass splitting.
Authors: Augustin Parjadis, Quentin Cappart, Bistra Dilkina, Aaron Ferber, Louis-Martin Rousseau
Lagrangian relaxation is a versatile mathematical technique employed to relax constraints in an optimization problem, enabling the generation of dual bounds to prove the optimality of feasible solutions and the design of efficient propagators in constraint programming (such as the weighted circuit constraint). However, the conventional process of deriving Lagrangian multipliers (e.g., using subgradient methods) is often computationally intensive, limiting its practicality for large-scale or time-sensitive problems. To address this challenge, we propose an innovative unsupervised learning approach that harnesses the capabilities of graph neural networks to exploit the problem structure, aiming to generate accurate Lagrangian multipliers efficiently. We apply this technique to the well-known Held-Karp Lagrangian relaxation for the travelling salesman problem. The core idea is to predict accurate Lagrangian multipliers and to employ them as a warm start for generating Held-Karp relaxation bounds. These bounds are subsequently utilized to enhance the filtering process carried out by branch-and-bound algorithms. In contrast to much of the existing literature, which primarily focuses on finding feasible solutions, our approach operates on the dual side, demonstrating that learning can also accelerate the proof of optimality. We conduct experiments across various distributions of the metric travelling salesman problem, considering instances with up to 200 cities. The results illustrate that our approach can improve the filtering level of the weighted circuit global constraint, reduce the optimality gap by a factor two for unsolved instances up to a timeout, and reduce the execution time for solved instances by 10%.
Authors: Sam Alexander Martino, João Morado, Chenghao Li, Zhenghao Lu, Edina Rosta
Traditional clustering algorithms often struggle to capture the complex relationships within graphs and generalise to arbitrary clustering criteria. The emergence of graph neural networks (GNNs) as a powerful framework for learning representations of graph data provides new approaches to solving the problem. Previous work has shown GNNs to be capable of proposing partitionings using a variety of criteria, however, these approaches have not yet been extended to work on Markov chains or kinetic networks. These arise frequently in the study of molecular systems and are of particular interest to the biochemical modelling community. In this work, we propose several GNN-based architectures to tackle the graph partitioning problem for Markov Chains described as kinetic networks. This approach aims to minimize how much a proposed partitioning changes the Kemeny constant. We propose using an encoder-decoder architecture and show how simple GraphSAGE-based GNNs with linear layers can outperform much larger and more expressive attention-based models in this context. As a proof of concept, we first demonstrate the method's ability to cluster randomly connected graphs. We also use a linear chain architecture corresponding to a 1D free energy profile as our kinetic network. Subsequently, we demonstrate the effectiveness of our method through experiments on a data set derived from molecular dynamics. We compare the performance of our method to other partitioning techniques such as PCCA+. We explore the importance of feature and hyperparameter selection and propose a general strategy for large-scale parallel training of GNNs for discovering optimal graph partitionings.
Authors: Aiyinsi Zuo, Haixi Zhang, Zirui Li, Ce Zheng
Within the field of complicated multivariate time series forecasting (TSF), popular techniques frequently rely on intricate deep learning architectures, ranging from transformer-based designs to recurrent neural networks. However, recent findings suggest that simple Linear models can surpass sophisticated constructs on diverse datasets. These models directly map observation to multiple future time steps, thereby minimizing error accumulation in iterative multi-step prediction. Yet, these models fail to incorporate spatial and temporal information within the data, which is critical for capturing patterns and dependencies that drive insightful predictions. This oversight often leads to performance bottlenecks, especially under specific sequence lengths and dataset conditions, preventing their universal application. In response, we introduce the SpatioTemporal-Linear (STL) framework. STL seamlessly integrates time-embedded and spatially-informed bypasses to augment the Linear-based architecture. These extra routes offer a more robust and refined regression to the data, particularly when the amount of observation is limited and the capacity of simple linear layers to capture dependencies declines. Empirical evidence highlights STL's prowess, outpacing both Linear and Transformer benchmarks across varied observation and prediction durations and datasets. Such robustness accentuates its suitability across a spectrum of applications, including but not limited to, traffic trajectory and rare disease progression forecasting. Through this discourse, we not only validate the STL's distinctive capacities to become a more general paradigm in multivariate time-series prediction using deep-learning techniques but also stress the need to tackle data-scarce prediction scenarios for universal application. Code will be made available.
Authors: Filippos Christianos, Georgios Papoudakis, Matthieu Zimmer, Thomas Coste, Zhihao Wu, Jingxuan Chen, Khyati Khandelwal, James Doran, Xidong Feng, Jiacheng Liu, Zheng Xiong, Yicheng Luo, Jianye Hao, Kun Shao, Haitham Bou-Ammar, Jun Wang
A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly encounters severe problems, chief among them being its lack of generality across multiple tasks and the need for a large amount of training data. The leading cause is that it cannot effectively integrate prior information into the perception-action cycle when devising the policy. Large language models (LLMs) emerged as a fundamental way to incorporate cross-domain knowledge into AI agents but lack crucial learning and adaptation toward specific decision problems. This paper presents a general framework model for integrating and learning structured reasoning into AI agents' policies. Our methodology is motivated by the modularity found in the human brain. The framework utilises the construction of intrinsic and extrinsic functions to add previous understandings of reasoning structures. It also provides the adaptive ability to learn models inside every module or function, consistent with the modular structure of cognitive processes. We describe the framework in-depth and compare it with other AI pipelines and existing frameworks. The paper explores practical applications, covering experiments that show the effectiveness of our method. Our results indicate that AI agents perform and adapt far better when organised reasoning and prior knowledge are embedded. This opens the door to more resilient and general AI agent systems.
Authors: Shane Bergsma, Timothy Zeyl, Lei Guo
We propose SutraNets, a novel method for neural probabilistic forecasting of long-sequence time series. SutraNets use an autoregressive generative model to factorize the likelihood of long sequences into products of conditional probabilities. When generating long sequences, most autoregressive approaches suffer from harmful error accumulation, as well as challenges in modeling long-distance dependencies. SutraNets treat long, univariate prediction as multivariate prediction over lower-frequency sub-series. Autoregression proceeds across time and across sub-series in order to ensure coherent multivariate (and, hence, high-frequency univariate) outputs. Since sub-series can be generated using fewer steps, SutraNets effectively reduce error accumulation and signal path distances. We find SutraNets to significantly improve forecasting accuracy over competitive alternatives on six real-world datasets, including when we vary the number of sub-series and scale up the depth and width of the underlying sequence models.
Authors: Nathaël Da Costa, Marvin Pförtner, Lancelot Da Costa, Philipp Hennig
Gaussian processes (GPs) are the most common formalism for defining probability distributions over spaces of functions. While applications of GPs are myriad, a comprehensive understanding of GP sample paths, i.e. the function spaces over which they define a probability measure on, is lacking. In practice, GPs are not constructed through a probability measure, but instead through a mean function and a covariance kernel. In this paper we provide necessary and sufficient conditions on the covariance kernel for the sample paths of the corresponding GP to attain a given regularity. We use the framework of H\"older regularity as it grants us particularly straightforward conditions, which simplify further in the cases of stationary and isotropic GPs. We then demonstrate that our results allow for novel and unusually tight characterisations of the sample path regularities of the GPs commonly used in machine learning applications, such as the Mat\'ern GPs.
Authors: Balázs Csanád Csáji, László Györfi, Ambrus Tamás
In this paper we revisit the classical problem of classification, but impose privacy constraints. Under such constraints, the raw data $(X_1,Y_1),\ldots,(X_n,Y_n)$ cannot be directly observed, and all classifiers are functions of the randomised outcome of a suitable local differential privacy mechanism. The statistician is free to choose the form of this privacy mechanism, and here we add Laplace distributed noise to a discretisation of the location of each feature vector $X_i$ and to its label $Y_i$. The classification rule is the privatized version of the well-studied partitioning classification rule. In addition to the standard Lipschitz and margin conditions, a novel characteristic is introduced, by which the exact rate of convergence of the classification error probability is calculated, both for non-private and private data.
Authors: Lizhou Fan, Wenyue Hua, Lingyao Li, Haoyang Ling, Yongfeng Zhang, Libby Hemphill
Complex reasoning ability is one of the most important features of current LLMs, which has also been leveraged to play an integral role in complex decision-making tasks. Therefore, the investigation into the reasoning capabilities of Large Language Models (LLMs) is critical: numerous benchmarks have been established to assess the reasoning abilities of LLMs. However, current benchmarks are inadequate in offering a rigorous evaluation of the full extent of reasoning abilities that LLMs are capable of achieving. They are also prone to the risk of overfitting, as these benchmarks, being publicly accessible and static, allow models to potentially tailor their responses to specific benchmark metrics, thereby inflating their performance. Addressing these limitations, our research introduces a new benchmark, named NPHardEval. This benchmark is designed to evaluate the reasoning abilities of LLMs across a broad spectrum of 900 algorithmic questions, extending up to the NP-Hard complexity class. These questions are meticulously chosen to represent a wide range of complexity class below the NP-hard complexity class, offering a rigorous measure of the reasoning ability of LLMs. Through this study, we shed light on the current state of reasoning in LLMs, providing an objective and rigorous perspective through the comparison of LLMs' performance across complex classes. Moreover, this benchmark is designed with a dynamic update mechanism, where the datapoints are refreshed on a monthly basis. Such regular updates play a crucial role in mitigating the risk of LLMs overfitting to the benchmark, promoting a more accurate and reliable assessment of their reasoning capabilities. The benchmark dataset and code of NPHardEval are available at https://github.com/casmlab/NPHardEval.
Authors: Yevgeniy Men, Jonathan Fhima, Leo Anthony Celi, Lucas Zago Ribeiro, Luis Filipe Nakayama, Joachim A. Behar
Diabetic retinopathy (DR) is a prevalent complication of diabetes associated with a significant risk of vision loss. Timely identification is critical to curb vision impairment. Algorithms for DR staging from digital fundus images (DFIs) have been recently proposed. However, models often fail to generalize due to distribution shifts between the source domain on which the model was trained and the target domain where it is deployed. A common and particularly challenging shift is often encountered when the source- and target-domain supports do not fully overlap. In this research, we introduce DRStageNet, a deep learning model designed to mitigate this challenge. We used seven publicly available datasets, comprising a total of 93,534 DFIs that cover a variety of patient demographics, ethnicities, geographic origins and comorbidities. We fine-tune DINOv2, a pretrained model of self-supervised vision transformer, and implement a multi-source domain fine-tuning strategy to enhance generalization performance. We benchmark and demonstrate the superiority of our method to two state-of-the-art benchmarks, including a recently published foundation model. We adapted the grad-rollout method to our regression task in order to provide high-resolution explainability heatmaps. The error analysis showed that 59\% of the main errors had incorrect reference labels. DRStageNet is accessible at URL [upon acceptance of the manuscript].
Authors: Subhodip Panda, Prathosh AP
The heightened emphasis on the regulation of deep generative models, propelled by escalating concerns pertaining to privacy and compliance with regulatory frameworks, underscores the imperative need for precise control mechanisms over these models. This urgency is particularly underscored by instances in which generative models generate outputs that encompass objectionable, offensive, or potentially injurious content. In response, machine unlearning has emerged to selectively forget specific knowledge or remove the influence of undesirable data subsets from pre-trained models. However, modern machine unlearning approaches typically assume access to model parameters and architectural details during unlearning, which is not always feasible. In multitude of downstream tasks, these models function as black-box systems, with inaccessible pre-trained parameters, architectures, and training data. In such scenarios, the possibility of filtering undesired outputs becomes a practical alternative. The primary goal of this study is twofold: first, to elucidate the relationship between filtering and unlearning processes, and second, to formulate a methodology aimed at mitigating the display of undesirable outputs generated from models characterized as black-box systems. Theoretical analysis in this study demonstrates that, in the context of black-box models, filtering can be seen as a form of weak unlearning. Our proposed \textbf{\textit{Feature Aware Similarity Thresholding(FAST)}} method effectively suppresses undesired outputs by systematically encoding the representation of unwanted features in the latent space.
Authors: James Gunn, Zygmunt Lenyk, Anuj Sharma, Andrea Donati, Alexandru Buburuzan, John Redford, Romain Mueller
Combining complementary sensor modalities is crucial to providing robust perception for safety-critical robotics applications such as autonomous driving (AD). Recent state-of-the-art camera-lidar fusion methods for AD rely on monocular depth estimation which is a notoriously difficult task compared to using depth information from the lidar directly. Here, we find that this approach does not leverage depth as expected and show that naively improving depth estimation does not lead to improvements in object detection performance and that, strikingly, removing depth estimation altogether does not degrade object detection performance. This suggests that relying on monocular depth could be an unnecessary architectural bottleneck during camera-lidar fusion. In this work, we introduce a novel fusion method that bypasses monocular depth estimation altogether and instead selects and fuses camera and lidar features in a bird's-eye-view grid using a simple attention mechanism. We show that our model can modulate its use of camera features based on the availability of lidar features and that it yields better 3D object detection on the nuScenes dataset than baselines relying on monocular depth estimation.
Authors: Mithun Singh, Kapil Ahuja, Milind B. Ratnaparkhe
Phenotypic (or Physical) characteristics of plant species are commonly used to perform clustering. In one of our recent works (Shastri et al. (2021)), we used a probabilistically sampled (using pivotal sampling) and spectrally clustered algorithm to group soybean species. These techniques were used to obtain highly accurate clusterings at a reduced cost. In this work, we extend the earlier algorithm to cluster rice species. We improve the base algorithm in three ways. First, we propose a new function to build the similarity matrix in Spectral Clustering. Commonly, a natural exponential function is used for this purpose. Based upon the spectral graph theory and the involved Cheeger's inequality, we propose the use a base "a" exponential function instead. This gives a similarity matrix spectrum favorable for clustering, which we support via an eigenvalue analysis.
Second, the function used to build the similarity matrix in Spectral Clustering was earlier scaled with a fixed factor (called global scaling). Based upon the idea of Zelnik-Manor and Perona (2004), we now use a factor that varies with matrix elements (called local scaling) and works better. Third, to compute the inclusion probability of a specie in the pivotal sampling algorithm, we had earlier used the notion of deviation that captured how far specie's characteristic values were from their respective base values (computed over all species). A maximum function was used before to find the base values. We now use a median function, which is more intuitive. We support this choice using a statistical analysis. With experiments on 1865 rice species, we demonstrate that in terms of silhouette values, our new Sampled Spectral Clustering is 61% better than Hierarchical Clustering (currently prevalent). Also, our new algorithm is significantly faster than Hierarchical Clustering due to the involved sampling.
Authors: Eszter Székely, Lorenzo Bardone, Federica Gerace, Sebastian Goldt
Neural networks excel at discovering statistical patterns in high-dimensional data sets. In practice, higher-order cumulants, which quantify the non-Gaussian correlations between three or more variables, are particularly important for the performance of neural networks. But how efficient are neural networks at extracting features from higher-order cumulants? We study this question in the spiked cumulant model, where the statistician needs to recover a privileged direction or "spike" from the order-$p\ge 4$ cumulants of~$d$-dimensional inputs. We first characterise the fundamental statistical and computational limits of recovering the spike by analysing the number of samples~$n$ required to strongly distinguish between inputs from the spiked cumulant model and isotropic Gaussian inputs. We find that statistical distinguishability requires $n\gtrsim d$ samples, while distinguishing the two distributions in polynomial time requires $n \gtrsim d^2$ samples for a wide class of algorithms, i.e. those covered by the low-degree conjecture. These results suggest the existence of a wide statistical-to-computational gap in this problem. Numerical experiments show that neural networks learn to distinguish the two distributions with quadratic sample complexity, while "lazy" methods like random features are not better than random guessing in this regime. Our results show that neural networks extract information from higher-order correlations in the spiked cumulant model efficiently, and reveal a large gap in the amount of data required by neural networks and random features to learn from higher-order cumulants.
Authors: Guihong Li, Hsiang Hsu, Chun-Fu Chen, Radu Marculescu
The rapid growth of machine learning has spurred legislative initiatives such as ``the Right to be Forgotten,'' allowing users to request data removal. In response, ``machine unlearning'' proposes the selective removal of unwanted data without the need for retraining from scratch. While the Neural-Tangent-Kernel-based (NTK-based) unlearning method excels in performance, it suffers from significant computational complexity, especially for large-scale models and datasets. Our work introduces ``Fast-NTK,'' a novel NTK-based unlearning algorithm that significantly reduces the computational complexity by incorporating parameter-efficient fine-tuning methods, such as fine-tuning batch normalization layers in a CNN or visual prompts in a vision transformer. Our experimental results demonstrate scalability to much larger neural networks and datasets (e.g., 88M parameters; 5k images), surpassing the limitations of previous full-model NTK-based approaches designed for smaller cases (e.g., 8M parameters; 500 images). Notably, our approach maintains a performance comparable to the traditional method of retraining on the retain set alone. Fast-NTK can thus enable for practical and scalable NTK-based unlearning in deep neural networks.
Authors: Timo Kaufmann, Paul Weng, Viktor Bengs, Eyke Hüllermeier
Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of preference-based reinforcement learning (PbRL), it stands at the intersection of artificial intelligence and human-computer interaction. This positioning offers a promising avenue to enhance the performance and adaptability of intelligent systems while also improving the alignment of their objectives with human values. The training of Large Language Models (LLMs) has impressively demonstrated this potential in recent years, where RLHF played a decisive role in targeting the model's capabilities toward human objectives. This article provides a comprehensive overview of the fundamentals of RLHF, exploring the intricate dynamics between machine agents and human input. While recent focus has been on RLHF for LLMs, our survey adopts a broader perspective, examining the diverse applications and wide-ranging impact of the technique. We delve into the core principles that underpin RLHF, shedding light on the symbiotic relationship between algorithms and human feedback, and discuss the main research trends in the field. By synthesizing the current landscape of RLHF research, this article aims to provide researchers as well as practitioners with a comprehensive understanding of this rapidly growing field of research.
Authors: Rafael Gomes Mantovani, Tomáš Horváth, André L. D. Rossi, Ricardo Cerri, Sylvio Barbon Junior, Joaquin Vanschoren, André Carlos Ponce de Leon Ferreira de Carvalho
Machine learning algorithms often contain many hyperparameters (HPs) whose values affect the predictive performance of the induced models in intricate ways. Due to the high number of possibilities for these HP configurations and their complex interactions, it is common to use optimization techniques to find settings that lead to high predictive performance. However, insights into efficiently exploring this vast space of configurations and dealing with the trade-off between predictive and runtime performance remain challenging. Furthermore, there are cases where the default HPs fit the suitable configuration. Additionally, for many reasons, including model validation and attendance to new legislation, there is an increasing interest in interpretable models, such as those created by the Decision Tree (DT) induction algorithms. This paper provides a comprehensive approach for investigating the effects of hyperparameter tuning for the two DT induction algorithms most often used, CART and C4.5. DT induction algorithms present high predictive performance and interpretable classification models, though many HPs need to be adjusted. Experiments were carried out with different tuning strategies to induce models and to evaluate HPs' relevance using 94 classification datasets from OpenML. The experimental results point out that different HP profiles for the tuning of each algorithm provide statistically significant improvements in most of the datasets for CART, but only in one-third for C4.5. Although different algorithms may present different tuning scenarios, the tuning techniques generally required few evaluations to find accurate solutions. Furthermore, the best technique for all the algorithms was the IRACE. Finally, we found out that tuning a specific small subset of HPs is a good alternative for achieving optimal predictive performance.
Authors: Aude Sportisse (UCA, MAASAI), Matthieu Marbac (UR, ENSAI, CNRS, CREST), Fabien Laporte (Nantes Univ, CNRS, ITX-lab), Gilles Celeux (CELESTE), Claire Boyer (SU, LPSM (UMR\_8001), MOKAPLAN), Julie Josse (IDESP, PREMEDICAL), Christophe Biernacki (CNRS, MODAL)
Model-based unsupervised learning, as any learning task, stalls as soon as missing data occurs. This is even more true when the missing data are informative, or said missing not at random (MNAR). In this paper, we propose model-based clustering algorithms designed to handle very general types of missing data, including MNAR data. To do so, we introduce a mixture model for different types of data (continuous, count, categorical and mixed) to jointly model the data distribution and the MNAR mechanism, remaining vigilant to the relative degrees of freedom of each. Several MNAR models are discussed, for which the cause of the missingness can depend on both the values of the missing variable themselves and on the class membership. However, we focus on a specific MNAR model, called MNARz, for which the missingness only depends on the class membership. We first underline its ease of estimation, by showing that the statistical inference can be carried out on the data matrix concatenated with the missing mask considering finally a standard MAR mechanism. Consequently, we propose to perform clustering using the Expectation Maximization algorithm, specially developed for this simplified reinterpretation. Finally, we assess the numerical performances of the proposed methods on synthetic data and on the real medical registry TraumaBase as well.
Authors: Kaifeng Zhang, Rui Zhao, Ziming Zhang, Yang Gao
Reinforcement learning (RL) provides a powerful framework for decision-making, but its application in practice often requires a carefully designed reward function. Adversarial Imitation Learning (AIL) sheds light on automatic policy acquisition without access to the reward signal from the environment. In this work, we propose Auto-Encoding Adversarial Imitation Learning (AEAIL), a robust and scalable AIL framework. To induce expert policies from demonstrations, AEAIL utilizes the reconstruction error of an auto-encoder as a reward signal, which provides more information for optimizing policies than the prior discriminator-based ones. Subsequently, we use the derived objective functions to train the auto-encoder and the agent policy. Experiments show that our AEAIL performs superior compared to state-of-the-art methods on both state and image based environments. More importantly, AEAIL shows much better robustness when the expert demonstrations are noisy.
Authors: Brendan Leigh Ross, Gabriel Loaiza-Ganem, Anthony L. Caterini, Jesse C. Cresswell
Natural data observed in $\mathbb{R}^n$ is often constrained to an $m$-dimensional manifold $\mathcal{M}$, where $m < n$. This work focuses on the task of building theoretically principled generative models for such data. Current generative models learn $\mathcal{M}$ by mapping an $m$-dimensional latent variable through a neural network $f_\theta: \mathbb{R}^m \to \mathbb{R}^n$. These procedures, which we call pushforward models, incur a straightforward limitation: manifolds cannot in general be represented with a single parameterization, meaning that attempts to do so will incur either computational instability or the inability to learn probability densities within the manifold. To remedy this problem, we propose to model $\mathcal{M}$ as a neural implicit manifold: the set of zeros of a neural network. We then learn the probability density within $\mathcal{M}$ with a constrained energy-based model, which employs a constrained variant of Langevin dynamics to train and sample from the learned manifold. In experiments on synthetic and natural data, we show that our model can learn manifold-supported distributions with complex topologies more accurately than pushforward models.
Authors: Bo-Shi Zou, Ming-Kun Xie, Sheng-Jun Huang
Partial label learning (PLL) is a typical weakly supervised learning framework, where each training instance is associated with a candidate label set, among which only one label is valid. To solve PLL problems, typically methods try to perform disambiguation for candidate sets by either using prior knowledge, such as structure information of training data, or refining model outputs in a self-training manner. Unfortunately, these methods often fail to obtain a favorable performance due to the lack of prior information or unreliable predictions in the early stage of model training. In this paper, we propose a novel framework for partial label learning with meta objective guided disambiguation (MoGD), which aims to recover the ground-truth label from candidate labels set by solving a meta objective on a small validation set. Specifically, to alleviate the negative impact of false positive labels, we re-weight each candidate label based on the meta loss on the validation set. Then, the classifier is trained by minimizing the weighted cross entropy loss. The proposed method can be easily implemented by using various deep networks with the ordinary SGD optimizer. Theoretically, we prove the convergence property of meta objective and derive the estimation error bounds of the proposed method. Extensive experiments on various benchmark datasets and real-world PLL datasets demonstrate that the proposed method can achieve competent performance when compared with the state-of-the-art methods.
Authors: Daniel Alpay, Kamal Diki, Mihaela Vajiac
We study and introduce new gradient operators in the complex and bicomplex settings, inspired from the well-known Least Mean Square (LMS) algorithm invented in 1960 by Widrow and Hoff for Adaptive Linear Neuron (ADALINE).
These gradient operators will be used to formulate new learning rules for the Bicomplex Least Mean Square (BLMS) algorithms and we will also formulate these learning rules will for the case of multicomplex LMS algorithms (MLMS). This approach extends both the classical real and complex LMS algorithms.
Authors: Nicholas D. Sidiropoulos, Paris Karakasis, Aritra Konar
We consider the problem of finding the smallest or largest entry of a tensor of order N that is specified via its rank decomposition. Stated in a different way, we are given N sets of R-dimensional vectors and we wish to select one vector from each set such that the sum of the Hadamard product of the selected vectors is minimized or maximized. We show that this fundamental tensor problem is NP-hard for any tensor rank higher than one, and polynomial-time solvable in the rank-one case. We also propose a continuous relaxation and prove that it is tight for any rank. For low-enough ranks, the proposed continuous reformulation is amenable to low-complexity gradient-based optimization, and we propose a suite of gradient-based optimization algorithms drawing from projected gradient descent, Frank-Wolfe, or explicit parametrization of the relaxed constraints. We also show that our core results remain valid no matter what kind of polyadic tensor model is used to represent the tensor of interest, including Tucker, HOSVD/MLSVD, tensor train, or tensor ring. Next, we consider the class of problems that can be posed as special instances of the problem of interest. We show that this class includes the partition problem (and thus all NP-complete problems via polynomial-time transformation), integer least squares, integer linear programming, integer quadratic programming, sign retrieval (a special kind of mixed integer programming / restricted version of phase retrieval), and maximum likelihood decoding of parity check codes. We demonstrate promising experimental results on a number of hard problems, including state-of-art performance in decoding low density parity check codes and general parity check codes.
Authors: Yujia Huang, Ivan Dario Jimenez Rodriguez, Huan Zhang, Yuanyuan Shi, Yisong Yue
Forward invariance is a long-studied property in control theory that is used to certify that a dynamical system stays within some pre-specified set of states for all time, and also admits robustness guarantees (e.g., the certificate holds under perturbations). We propose a general framework for training and provably certifying robust forward invariance in Neural ODEs. We apply this framework to provide certified safety in robust continuous control. To our knowledge, this is the first instance of training Neural ODE policies with such non-vacuous certified guarantees. In addition, we explore the generality of our framework by using it to certify adversarial robustness for image classification.
Authors: Hugo Henri Joseph Senetaire, Damien Garreau, Jes Frellsen, Pierre-Alexandre Mattei
A wide variety of model explanation approaches have been proposed in recent years, all guided by very different rationales and heuristics. In this paper, we take a new route and cast interpretability as a statistical inference problem. We propose a general deep probabilistic model designed to produce interpretable predictions. The model parameters can be learned via maximum likelihood, and the method can be adapted to any predictor network architecture and any type of prediction problem. Our method is a case of amortized interpretability models, where a neural network is used as a selector to allow for fast interpretation at inference time. Several popular interpretability methods are shown to be particular cases of regularised maximum likelihood for our general model. We propose new datasets with ground truth selection which allow for the evaluation of the features importance map. Using these datasets, we show experimentally that using multiple imputation provides more reasonable interpretations.
Authors: Guoqing Luo, Yu Tong Han, Lili Mou, Mauajama Firdaus
Prompting approaches have been recently explored in text style transfer, where a textual prompt is used to query a pretrained language model to generate style-transferred texts word by word in an autoregressive manner. However, such a generation process is less controllable and early prediction errors may affect future word predictions. In this paper, we present a prompt-based editing approach for text style transfer. Specifically, we prompt a pretrained language model for style classification and use the classification probability to compute a style score. Then, we perform discrete search with word-level editing to maximize a comprehensive scoring function for the style-transfer task. In this way, we transform a prompt-based generation problem into a classification one, which is a training-free process and more controllable than the autoregressive generation of sentences. In our experiments, we performed both automatic and human evaluation on three style-transfer benchmark datasets, and show that our approach largely outperforms the state-of-the-art systems that have 20 times more parameters. Additional empirical analyses further demonstrate the effectiveness of our approach.
Authors: A. Feder Cooper, Wentao Guo, Khiem Pham, Tiancheng Yuan, Charlie F. Ruan, Yucheng Lu, Christopher De Sa
Recent research on online Gradient Balancing (GraB) has revealed that there exist permutation-based example orderings for SGD that are guaranteed to outperform random reshuffling (RR). Whereas RR arbitrarily permutes training examples, GraB leverages stale gradients from prior epochs to order examples -- achieving a provably faster convergence rate than RR. However, GraB is limited by design: while it demonstrates an impressive ability to scale-up training on centralized data, it does not naturally extend to modern distributed ML workloads. We therefore propose Coordinated Distributed GraB (CD-GraB), which uses insights from prior work on kernel thinning to translate the benefits of provably faster permutation-based example ordering to distributed settings. With negligible overhead, CD-GraB exhibits a linear speedup in convergence rate over centralized GraB and outperforms distributed RR on a variety of benchmark tasks.
Authors: Jared Fernandez, Jacob Kahn, Clara Na, Yonatan Bisk, Emma Strubell
Increased focus on the computational efficiency of NLP systems has motivated the design of efficient model architectures and improvements to underlying hardware accelerators. However, the resulting increases in computational throughput and reductions in floating point operations have not directly translated to improvements in wall-clock inference latency. We demonstrate that these discrepancies can be largely attributed to bottlenecks introduced by deep learning frameworks. We denote this phenomenon as the \textit{framework tax}, and observe that the disparity is growing as hardware speed increases over time. In this work, we examine this phenomenon through a series of case studies analyzing the effects of model design decisions, framework paradigms, and hardware platforms on total model latency. Code is available at https://github.com/JaredFern/Framework-Tax.
Authors: Hengxi Zhang, Zhendong Shi, Yuanquan Hu, Wenbo Ding, Ercan E. Kuruoglu, Xiao-Ping Zhang
Quantitative markets are characterized by swift dynamics and abundant uncertainties, making the pursuit of profit-driven stock trading actions inherently challenging. Within this context, reinforcement learning (RL), which operates on a reward-centric mechanism for optimal control, has surfaced as a potentially effective solution to the intricate financial decision-making conundrums presented. This paper delves into the fusion of two established financial trading strategies, namely the constant proportion portfolio insurance (CPPI) and the time-invariant portfolio protection (TIPP), with the multi-agent deep deterministic policy gradient (MADDPG) framework. As a result, we introduce two novel multi-agent RL (MARL) methods, CPPI-MADDPG and TIPP-MADDPG, tailored for probing strategic trading within quantitative markets. To validate these innovations, we implemented them on a diverse selection of 100 real-market shares. Our empirical findings reveal that the CPPI-MADDPG and TIPP-MADDPG strategies consistently outpace their traditional counterparts, affirming their efficacy in the realm of quantitative trading.
Authors: Stefano Peluchetti
The dynamic Schr\"odinger bridge problem seeks a stochastic process that defines a transport between two target probability measures, while optimally satisfying the criteria of being closest, in terms of Kullback-Leibler divergence, to a reference process. We propose a novel sampling-based iterative algorithm, the iterated diffusion bridge mixture (IDBM) procedure, aimed at solving the dynamic Schr\"odinger bridge problem. The IDBM procedure exhibits the attractive property of realizing a valid transport between the target probability measures at each iteration. We perform an initial theoretical investigation of the IDBM procedure, establishing its convergence properties. The theoretical findings are complemented by numerical experiments illustrating the competitive performance of the IDBM procedure. Recent advancements in generative modeling employ the time-reversal of a diffusion process to define a generative process that approximately transports a simple distribution to the data distribution. As an alternative, we propose utilizing the first iteration of the IDBM procedure as an approximation-free method for realizing this transport. This approach offers greater flexibility in selecting the generative process dynamics and exhibits accelerated training and superior sample quality over larger discretization intervals. In terms of implementation, the necessary modifications are minimally intrusive, being limited to the training loss definition.
Authors: Styliani I. Kampezidou, Justin Romberg, Kyriakos G. Vamvoudakis, Dimitri N. Mavris
In this work, a novel Stackelberg game theoretic framework is proposed for trading energy bidirectionally between the demand-response (DR) aggregator and the prosumers. This formulation allows for flexible energy arbitrage and additional monetary rewards while ensuring that the prosumers' desired daily energy demand is met. Then, a scalable (linear with the number of prosumers), decentralized, privacy-preserving algorithm is proposed to find approximate equilibria with online sampling and learning of the prosumers' cumulative best response, which finds applications beyond this energy game. Moreover, cost bounds are provided on the quality of the approximate equilibrium solution. Finally, real data from the California day-ahead market and the UC Davis campus building energy demands are utilized to demonstrate the efficacy of the proposed framework and algorithm.
Authors: Pierre Marza, Laetitia Matignon, Olivier Simonin, Dhruv Batra, Christian Wolf, Devendra Singh Chaplot
Implicit representations such as Neural Radiance Fields (NeRF) have been shown to be very effective at novel view synthesis. However, these models typically require manual and careful human data collection for training. In this paper, we present AutoNeRF, a method to collect data required to train NeRFs using autonomous embodied agents. Our method allows an agent to explore an unseen environment efficiently and use the experience to build an implicit map representation autonomously. We compare the impact of different exploration strategies including handcrafted frontier-based exploration, end-to-end and modular approaches composed of trained high-level planners and classical low-level path followers. We train these models with different reward functions tailored to this problem and evaluate the quality of the learned representations on four different downstream tasks: classical viewpoint rendering, map reconstruction, planning, and pose refinement. Empirical results show that NeRFs can be trained on actively collected data using just a single episode of experience in an unseen environment, and can be used for several downstream robotic tasks, and that modular trained exploration models outperform other classical and end-to-end baselines. Finally, we show that AutoNeRF can reconstruct large-scale scenes, and is thus a useful tool to perform scene-specific adaptation as the produced 3D environment models can be loaded into a simulator to fine-tune a policy of interest.
Authors: Dongyue Guo, Zheng Zhang, Zhen Yan, Jianwei Zhang, Yi Lin
Flight Trajectory Prediction (FTP) is an essential task in Air Traffic Control (ATC), which can assist air traffic controllers in managing airspace more safely and efficiently. Existing approaches generally perform multi-horizon FTP tasks in an autoregressive manner, thereby suffering from error accumulation and low-efficiency problems. In this paper, a novel framework, called FlightBERT++, is proposed to i) forecast multi-horizon flight trajectories directly in a non-autoregressive way, and ii) improve the limitation of the binary encoding (BE) representation in the FlightBERT. Specifically, the FlightBERT++ is implemented by a generalized encoder-decoder architecture, in which the encoder learns the temporal-spatial patterns from historical observations and the decoder predicts the flight status for the future horizons. Compared with conventional architecture, an innovative horizon-aware contexts generator is dedicatedly designed to consider the prior horizon information, which further enables non-autoregressive multi-horizon prediction. Moreover, a differential prompted decoder is proposed to enhance the capability of the differential predictions by leveraging the stationarity of the differential sequence. The experimental results on a real-world dataset demonstrated that the FlightBERT++ outperformed the competitive baselines in both FTP performance and computational efficiency.
Authors: Georg Siedel, Weijia Shao, Silvia Vock, Andrey Morozov
Robustness is a fundamental property of machine learning classifiers required to achieve safety and reliability. In the field of adversarial robustness of image classifiers, robustness is commonly defined as the stability of a model to all input changes within a p-norm distance. However, in the field of random corruption robustness, variations observed in the real world are used, while p-norm corruptions are rarely considered. This study investigates the use of random p-norm corruptions to augment the training and test data of image classifiers. We evaluate the model robustness against imperceptible random p-norm corruptions and propose a novel robustness metric. We empirically investigate whether robustness transfers across different p-norms and derive conclusions on which p-norm corruptions a model should be trained and evaluated. We find that training data augmentation with a combination of p-norm corruptions significantly improves corruption robustness, even on top of state-of-the-art data augmentation schemes.
Authors: Alexandre Maraval, Matthieu Zimmer, Antoine Grosnit, Haitham Bou Ammar
Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-learn either a surrogate model or an acquisition function independently, joint training of both components remains an open challenge. This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data. Early on, we notice that training transformer-based neural processes from scratch with RL is challenging due to insufficient supervision, especially when rewards are sparse. We formalise this claim with a combinatorial analysis showing that the widely used notion of regret as a reward signal exhibits a logarithmic sparsity pattern in trajectory lengths. To tackle this problem, we augment the RL objective with an auxiliary task that guides part of the architecture to learn a valid probabilistic model as an inductive bias. We demonstrate that our method achieves state-of-the-art regret results against various baselines in experiments on standard hyperparameter optimisation tasks and also outperforms others in the real-world problems of mixed-integer programming tuning, antibody design, and logic synthesis for electronic design automation.
Authors: Justin Domke, Guillaume Garrigos, Robert Gower
Black-box variational inference is widely used in situations where there is no proof that its stochastic optimization succeeds. We suggest this is due to a theoretical gap in existing stochastic optimization proofs: namely the challenge of gradient estimators with unusual noise bounds, and a composite non-smooth objective. For dense Gaussian variational families, we observe that existing gradient estimators based on reparameterization satisfy a quadratic noise bound and give novel convergence guarantees for proximal and projected stochastic gradient descent using this bound. This provides rigorous guarantees that methods similar to those used in practice converge on realistic inference problems.
Authors: Drago Plecko, Elias Bareinboim
Since the rise of fair machine learning as a critical field of inquiry, many different notions on how to quantify and measure discrimination have been proposed in the literature. Some of these notions, however, were shown to be mutually incompatible. Such findings make it appear that numerous different kinds of fairness exist, thereby making a consensus on the appropriate measure of fairness harder to reach, hindering the applications of these tools in practice. In this paper, we investigate one of these key impossibility results that relates the notions of statistical and predictive parity. Specifically, we derive a new causal decomposition formula for the fairness measures associated with predictive parity, and obtain a novel insight into how this criterion is related to statistical parity through the legal doctrines of disparate treatment, disparate impact, and the notion of business necessity. Our results show that through a more careful causal analysis, the notions of statistical and predictive parity are not really mutually exclusive, but complementary and spanning a spectrum of fairness notions through the concept of business necessity. Finally, we demonstrate the importance of our findings on a real-world example.
Authors: Afifa Khaled, Ahmed A. Mubarak, Kun He
Recent deep learning models have attracted substantial attention in infant brain analysis. These models have performed state-of-the-art performance, such as semi-supervised techniques (e.g., Temporal Ensembling, mean teacher). However, these models depend on an encoder-decoder structure with stacked local operators to gather long-range information, and the local operators limit the efficiency and effectiveness. Besides, the $MRI$ data contain different tissue properties ($TPs$) such as $T1$ and $T2$. One major limitation of these models is that they use both data as inputs to the segment process, i.e., the models are trained on the dataset once, and it requires much computational and memory requirements during inference. In this work, we address the above limitations by designing a new deep-learning model, called 3D-DenseUNet, which works as adaptable global aggregation blocks in down-sampling to solve the issue of spatial information loss. The self-attention module connects the down-sampling blocks to up-sampling blocks, and integrates the feature maps in three dimensions of spatial and channel, effectively improving the representation potential and discriminating ability of the model. Additionally, we propose a new method called Two Independent Teachers ($2IT$), that summarizes the model weights instead of label predictions. Each teacher model is trained on different types of brain data, $T1$ and $T2$, respectively. Then, a fuse model is added to improve test accuracy and enable training with fewer parameters and labels compared to the Temporal Ensembling method without modifying the network architecture. Empirical results demonstrate the effectiveness of the proposed method. The code is available at https://github.com/AfifaKhaled/Two-Independent-Teachers-are-Better-Role-Model.
Authors: Yinghua Gao, Yiming Li, Xueluan Gong, Zhifeng Li, Shu-Tao Xia, Qian Wang
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where the adversary manipulates a small portion of training data such that the victim model predicts normally on the benign samples but classifies the triggered samples as the target class. The backdoor attack is an emerging yet threatening training-phase threat, leading to serious risks in DNN-based applications. In this paper, we revisit the trigger patterns of existing backdoor attacks. We reveal that they are either visible or not sparse and therefore are not stealthy enough. More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack. To address this problem, we formulate the trigger generation as a bi-level optimization problem with sparsity and invisibility constraints and propose an effective method to solve it. The proposed method is dubbed sparse and invisible backdoor attack (SIBA). We conduct extensive experiments on benchmark datasets under different settings, which verify the effectiveness of our attack and its resistance to existing backdoor defenses. The codes for reproducing main experiments are available at \url{https://github.com/YinghuaGao/SIBA}.
Authors: Konstantinos Bousmalis, Giulia Vezzani, Dushyant Rao, Coline Devin, Alex X. Lee, Maria Bauza, Todor Davchev, Yuxiang Zhou, Agrim Gupta, Akhil Raju, Antoine Laurens, Claudio Fantacci, Valentin Dalibard, Martina Zambelli, Murilo Martins, Rugile Pevceviciute, Michiel Blokzijl, Misha Denil, Nathan Batchelor, Thomas Lampe, Emilio Parisotto, Konrad Żołna, Scott Reed, Sergio Gómez Colmenarejo, Jon Scholz, Abbas Abdolmaleki, Oliver Groth, Jean-Baptiste Regli, Oleg Sushkov, Tom Rothörl, José Enrique Chen, Yusuf Aytar, Dave Barker, Joy Ortiz, Martin Riedmiller, Jost Tobias Springenberg, Raia Hadsell, Francesco Nori, Nicolas Heess
The ability to leverage heterogeneous robotic experience from different robots and tasks to quickly master novel skills and embodiments has the potential to transform robot learning. Inspired by recent advances in foundation models for vision and language, we propose a multi-embodiment, multi-task generalist agent for robotic manipulation. This agent, named RoboCat, is a visual goal-conditioned decision transformer capable of consuming action-labelled visual experience. This data spans a large repertoire of motor control skills from simulated and real robotic arms with varying sets of observations and actions. With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples for the target task. We also show how a trained model itself can be used to generate data for subsequent training iterations, thus providing a basic building block for an autonomous improvement loop. We investigate the agent's capabilities, with large-scale evaluations both in simulation and on three different real robot embodiments. We find that as we grow and diversify its training data, RoboCat not only shows signs of cross-task transfer, but also becomes more efficient at adapting to new tasks.
Authors: Haitong Huang, Cheng Liu, Bo Liu, Xinghua Xue, Huawei Li, Xiaowei Li
To ensure resilient neural network processing on even unreliable hardware, comprehensive reliability analysis against various hardware faults is generally required before the deep neural network models are deployed, and efficient error injection tools are highly demanded. However, most existing fault injection tools remain rather limited to basic fault injection to neurons and fail to provide fine-grained vulnerability analysis capability. In addition, many of the fault injection tools still need to change the neural network models and make the fault injection closely coupled with normal neural network processing, which further complicates the use of the fault injection tools and slows down the fault simulation. In this work, we propose MRFI, a highly configurable multi-resolution fault injection tool for deep neural networks. It enables users to modify an independent fault configuration file rather than neural network models for the fault injection and vulnerability analysis. Particularly, it integrates extensive fault analysis functionalities from different perspectives and enables multi-resolution investigation of the vulnerability of neural networks. In addition, it does not modify the major neural network computing framework of PyTorch. Hence, it allows parallel processing on GPUs naturally and exhibits fast fault simulation according to our experiments.
Authors: Xiang 'Anthony' Chen, Jeff Burke, Ruofei Du, Matthew K. Hong, Jennifer Jacobs, Philippe Laban, Dingzeyu Li, Nanyun Peng, Karl D. D. Willis, Chien-Sheng Wu, Bolei Zhou
Through iterative, cross-disciplinary discussions, we define and propose next-steps for Human-centered Generative AI (HGAI). We contribute a comprehensive research agenda that lays out future directions of Generative AI spanning three levels: aligning with human values; assimilating human intents; and augmenting human abilities. By identifying these next-steps, we intend to draw interdisciplinary research teams to pursue a coherent set of emergent ideas in HGAI, focusing on their interested topics while maintaining a coherent big picture of the future work landscape.
Authors: Zachary Charles, Nicole Mitchell, Krishna Pillutla, Michael Reneer, Zachary Garrett
We introduce Dataset Grouper, a library to create large-scale group-structured (e.g., federated) datasets, enabling federated learning simulation at the scale of foundation models. This library facilitates the creation of group-structured versions of existing datasets based on user-specified partitions and directly leads to a variety of useful heterogeneous datasets that can be plugged into existing software frameworks. Dataset Grouper offers three key advantages. First, it scales to settings where even a single group's dataset is too large to fit in memory. Second, it provides flexibility, both in choosing the base (non-partitioned) dataset and in defining partitions. Finally, it is framework-agnostic. We empirically demonstrate that Dataset Grouper enables large-scale federated language modeling simulations on datasets that are orders of magnitude larger than in previous work, allowing for federated training of language models with hundreds of millions, and even billions, of parameters. Our experimental results show that algorithms like FedAvg operate more as meta-learning methods than as empirical risk minimization methods at this scale, suggesting their utility in downstream personalization and task-specific adaptation. Dataset Grouper is available at https://github.com/google-research/dataset_grouper.
Authors: Mustafa Shukor, Corentin Dancette, Alexandre Rame, Matthieu Cord
Large Language Models (LLMs) have made the ambitious quest for generalist agents significantly far from being a fantasy. A key hurdle for building such general models is the diversity and heterogeneity of tasks and modalities. A promising solution is unification, allowing the support of a myriad of tasks and modalities within one unified framework. While few large models (e.g., Flamingo (Alayrac et al., 2022), trained on massive datasets, can support more than two modalities, current small to mid-scale unified models are still limited to 2 modalities, usually image-text or video-text. The question that we ask is: is it possible to build efficiently a unified model that can support all modalities? To answer this, we propose UnIVAL, a step further towards this ambitious goal. Without relying on fancy datasets sizes or models with billions of parameters, the ~ 0.25B parameter UnIVAL model goes beyond two modalities and unifies text, images, video, and audio into a single model. Our model is efficiently pretrained on many tasks, based on task balancing and multimodal curriculum learning. UnIVAL shows competitive performance to existing state-of-the-art approaches, across image and video-text tasks. The feature representations learned from image and video-text modalities, allows the model to achieve competitive performance when finetuned on audio-text tasks, despite not being pretrained on audio. Thanks to the unified model, we propose a novel study on multimodal model merging via weight interpolation of models trained on different multimodal tasks, showing their benefits in particular for out-of-distribution generalization. Finally, we motivate unification by showing the synergy between tasks. The model weights and code are released here: https://github.com/mshukor/UnIVAL.
Authors: Xiaoli Chen, Beatrice W. Soh, Zi-En Ooi, Eleonore Vissol-Gaudin, Haijun Yu, Kostya S. Novoselov, Kedar Hippalgaonkar, Qianxiao Li
One of the most exciting applications of artificial intelligence (AI) is automated scientific discovery based on previously amassed data, coupled with restrictions provided by known physical principles, including symmetries and conservation laws. Such automated hypothesis creation and verification can assist scientists in studying complex phenomena, where traditional physical intuition may fail. Here we develop a platform based on a generalized Onsager principle to learn macroscopic dynamical descriptions of arbitrary stochastic dissipative systems directly from observations of their microscopic trajectories. Our method simultaneously constructs reduced thermodynamic coordinates and interprets the dynamics on these coordinates. We demonstrate its effectiveness by studying theoretically and validating experimentally the stretching of long polymer chains in an externally applied field. Specifically, we learn three interpretable thermodynamic coordinates and build a dynamical landscape of polymer stretching, including the identification of stable and transition states and the control of the stretching rate. Our general methodology can be used to address a wide range of scientific and technological applications.
Authors: Vasisht Duddu, Anudeep Das, Nora Khayata, Hossein Yalame, Thomas Schneider, N. Asokan
The success of machine learning (ML) has been accompanied by increased concerns about its trustworthiness. Several jurisdictions are preparing ML regulatory frameworks. One such concern is ensuring that model training data has desirable distributional properties for certain sensitive attributes. For example, draft regulations indicate that model trainers are required to show that training datasets have specific distributional properties, such as reflecting diversity of the population.
We propose the notion of property attestation allowing a prover (e.g., model trainer) to demonstrate relevant distributional properties of training data to a verifier (e.g., a customer) without revealing the data. We present an effective hybrid property attestation combining property inference with cryptographic mechanisms.
Authors: Hamzeh Ghasemzadeh, Robert E. Hillman, Daryush D. Mehta
This study's first purpose is to provide quantitative evidence that would incentivize researchers to instead use the more robust method of nested cross-validation. The second purpose is to present methods and MATLAB codes for doing power analysis for ML-based analysis during the design of a study. Monte Carlo simulations were used to quantify the interactions between the employed cross-validation method, the discriminative power of features, the dimensionality of the feature space, and the dimensionality of the model. Four different cross-validations (single holdout, 10-fold, train-validation-test, and nested 10-fold) were compared based on the statistical power and statistical confidence of the ML models. Distributions of the null and alternative hypotheses were used to determine the minimum required sample size for obtaining a statistically significant outcome ({\alpha}=0.05, 1-\b{eta}=0.8). Statistical confidence of the model was defined as the probability of correct features being selected and hence being included in the final model. Our analysis showed that the model generated based on the single holdout method had very low statistical power and statistical confidence and that it significantly overestimated the accuracy. Conversely, the nested 10-fold cross-validation resulted in the highest statistical confidence and the highest statistical power, while providing an unbiased estimate of the accuracy. The required sample size with a single holdout could be 50% higher than what would be needed if nested cross-validation were used. Confidence in the model based on nested cross-validation was as much as four times higher than the confidence in the single holdout-based model. A computational model, MATLAB codes, and lookup tables are provided to assist researchers with estimating the sample size during the design of their future studies.
Authors: Sarthak Kumar Maharana, Krishna Kamal Adidam, Shoumik Nandi, Ajitesh Srivastava
Acoustic-to-articulatory inversion (AAI) involves mapping from the acoustic to the articulatory space. Signal-processing features like the MFCCs, have been widely used for the AAI task. For subjects with dysarthric speech, AAI is challenging because of an imprecise and indistinct pronunciation. In this work, we perform AAI for dysarthric speech using representations from pre-trained self-supervised learning (SSL) models. We demonstrate the impact of different pre-trained features on this challenging AAI task, at low-resource conditions. In addition, we also condition x-vectors to the extracted SSL features to train a BLSTM network. In the seen case, we experiment with three AAI training schemes (subject-specific, pooled, and fine-tuned). The results, consistent across training schemes, reveal that DeCoAR, in the fine-tuned scheme, achieves a relative improvement of the Pearson Correlation Coefficient (CC) by ~1.81% and ~4.56% for healthy controls and patients, respectively, over MFCCs. We observe similar average trends for different SSL features in the unseen case. Overall, SSL networks like wav2vec, APC, and DeCoAR, trained with feature reconstruction or future timestep prediction tasks, perform well in predicting dysarthric articulatory trajectories.
Authors: Xu Weng, Keck Voon Ling, Haochen Liu
We present a neural network for mitigating biased errors in pseudoranges to improve localization performance with data collected from mobile phones. A satellite-wise Multilayer Perceptron (MLP) is designed to regress the pseudorange bias correction from six satellite, receiver, context-related features derived from Android raw Global Navigation Satellite System (GNSS) measurements. To train the MLP, we carefully calculate the target values of pseudorange bias using location ground truth and smoothing techniques and optimize a loss function involving the estimation residuals of smartphone clock bias. The corrected pseudoranges are then used by a model-based localization engine to compute locations. The Google Smartphone Decimeter Challenge (GSDC) dataset, which contains Android smartphone data collected from both rural and urban areas, is utilized for evaluation. Both fingerprinting and cross-trace localization results demonstrate that our proposed method outperforms model-based and state-of-the-art data-driven approaches.
Authors: Bingcong Li, Georgios B. Giannakis
Sharpness-aware minimization (SAM) has well documented merits in enhancing generalization of deep neural networks, even without sizable data augmentation. Embracing the geometry of the loss function, where neighborhoods of 'flat minima' heighten generalization ability, SAM seeks 'flat valleys' by minimizing the maximum loss caused by an adversary perturbing parameters within the neighborhood. Although critical to account for sharpness of the loss function, such an 'over-friendly adversary' can curtail the outmost level of generalization. The novel approach of this contribution fosters stabilization of adversaries through variance suppression (VaSSO) to avoid such friendliness. VaSSO's provable stability safeguards its numerical improvement over SAM in model-agnostic tasks, including image classification and machine translation. In addition, experiments confirm that VaSSO endows SAM with robustness against high levels of label noise.
Authors: Aakash Tripathi, Asim Waqas, Kavya Venkatesan, Yasin Yilmaz, Ghulam Rasool
The advancements in data acquisition, storage, and processing techniques have resulted in the rapid growth of heterogeneous medical data. Integrating radiological scans, histopathology images, and molecular information with clinical data is essential for developing a holistic understanding of the disease and optimizing treatment. The need for integrating data from multiple sources is further pronounced in complex diseases such as cancer for enabling precision medicine and personalized treatments. This work proposes Multimodal Integration of Oncology Data System (MINDS) - a flexible, scalable, and cost-effective metadata framework for efficiently fusing disparate data from public sources such as the Cancer Research Data Commons (CRDC) into an interconnected, patient-centric framework. MINDS offers an interface for exploring relationships across data types and building cohorts for developing large-scale multimodal machine learning models. By harmonizing multimodal data, MINDS aims to potentially empower researchers with greater analytical ability to uncover diagnostic and prognostic insights and enable evidence-based personalized care. MINDS tracks granular end-to-end data provenance, ensuring reproducibility and transparency. The cloud-native architecture of MINDS can handle exponential data growth in a secure, cost-optimized manner while ensuring substantial storage optimization, replication avoidance, and dynamic access capabilities. Auto-scaling, access controls, and other mechanisms guarantee pipelines' scalability and security. MINDS overcomes the limitations of existing biomedical data silos via an interoperable metadata-driven approach that represents a pivotal step toward the future of oncology data integration.
Authors: Xinyi Wang, Lucas Caccia, Oleksiy Ostapenko, Xingdi Yuan, Alessandro Sordoni
Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought reasoning. However, most of the existing approaches to enhance this ability rely heavily on data-driven methods, while neglecting the structural aspects of the model's reasoning capacity. We find that while LLMs can manage individual reasoning steps well, they struggle with maintaining consistency across an entire reasoning chain. To solve this, we introduce 'planning tokens' at the start of each reasoning step, serving as a guide for the model. These token embeddings are then fine-tuned along with the rest of the model parameters. Our approach requires a negligible increase in trainable parameters (just 0.001%) and can be applied through either full fine-tuning or a more parameter-efficient scheme. We demonstrate our method's effectiveness by applying it to three different LLMs, showing notable accuracy improvements across three math word problem datasets w.r.t. plain chain-of-thought fine-tuning baselines.
Authors: Bernard J. Giron Castro, Christophe Peucheret, Darko Zibar, Francesco Da Ros
Microring resonators (MRRs) are promising devices for time-delay photonic reservoir computing, but the impact of the different physical effects taking place in the MRRs on the reservoir computing performance is yet to be fully understood. We numerically analyze the impact of linear losses as well as thermo-optic and free-carrier effects relaxation times on the prediction error of the time-series task NARMA-10. We demonstrate the existence of three regions, defined by the input power and the frequency detuning between the optical source and the microring resonance, that reveal the cavity transition from linear to nonlinear regimes. One of these regions offers very low error in time-series prediction under relatively low input power and number of nodes while the other regions either lack nonlinearity or become unstable. This study provides insight into the design of the MRR and the optimization of its physical properties for improving the prediction performance of time-delay reservoir computing.
Authors: Weiye Zhao, Feihan Li, Yifan Sun, Rui Chen, Tianhao Wei, Changliu Liu
In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily emphasize improvement in expected performance, lacking the ability to control over the worst-case performance outcomes. To address this limitation, we introduce a novel objective function; by optimizing which, it will lead to guaranteed monotonic improvement in the lower bound of near-total performance samples (absolute performance). Considering this groundbreaking theoretical advancement, we then refine this theoretically grounded algorithm through a series of approximations, resulting in a practical solution called Absolute Policy Optimization (APO). Our experiments demonstrate the effectiveness of our approach across challenging continuous control benchmark tasks and extend its applicability to mastering Atari games. Our findings reveal that APO significantly outperforms state-of-the-art policy gradient algorithms, resulting in substantial improvements in both expected performance and worst-case performance.
Authors: Tianyue Chu, Mengwei Yang, Nikolaos Laoutaris, Athina Markopoulou
Federated learning (FL) is a paradigm that allows several client devices and a server to collaboratively train a global model, by exchanging only model updates, without the devices sharing their local training data. These devices are often constrained in terms of communication and computation resources, and can further benefit from model pruning -- a paradigm that is widely used to reduce the size and complexity of models. Intuitively, by making local models coarser, pruning is expected to also provide some protection against privacy attacks in the context of FL. However this protection has not been previously characterized, formally or experimentally, and it is unclear if it is sufficient against state-of-the-art attacks.
In this paper, we perform the first investigation of privacy guarantees for model pruning in FL. We derive information-theoretic upper bounds on the amount of information leaked by pruned FL models. We complement and validate these theoretical findings, with comprehensive experiments that involve state-of-the-art privacy attacks, on several state-of-the-art FL pruning schemes, using benchmark datasets. This evaluation provides valuable insights into the choices and parameters that can affect the privacy protection provided by pruning. Based on these insights, we introduce PriPrune -- a privacy-aware algorithm for local model pruning, which uses a personalized per-client defense mask and adapts the defense pruning rate so as to jointly optimize privacy and model performance. PriPrune is universal in that can be applied after any pruned FL scheme on the client, without modification, and protects against any inversion attack by the server. Our empirical evaluation demonstrates that PriPrune significantly improves the privacy-accuracy tradeoff compared to state-of-the-art pruned FL schemes that do not take privacy into account.
Authors: Wenhao Tang, Junding Sun, Shuihua Wang, Yudong Zhang
In recent years, the rapid development of deep learning has led to a wide range of applications in the field of medical image classification. The variants of neural network models with ever-increasing performance share some commonalities: to try to mitigate overfitting, improve generalization, avoid gradient vanishing and exploding, etc. AlexNet first utilizes the dropout technique to mitigate overfitting and the ReLU activation function to avoid gradient vanishing. Therefore, we focus our discussion on AlexNet, which has contributed greatly to the development of CNNs in 2012. After reviewing over 40 papers, including journal papers and conference papers, we give a narrative on the technical details, advantages, and application areas of AlexNet.
Authors: Xin Zhang, Jiawei Du, Yunsong Li, Weiying Xie, Joey Tianyi Zhou
Dataset pruning aims to construct a coreset capable of achieving performance comparable to the original, full dataset. Most existing dataset pruning methods rely on snapshot-based criteria to identify representative samples, often resulting in poor generalization across various pruning and cross-architecture scenarios. Recent studies have addressed this issue by expanding the scope of training dynamics considered, including factors such as forgetting event and probability change, typically using an averaging approach. However, these works struggle to integrate a broader range of training dynamics without overlooking well-generalized samples, which may not be sufficiently highlighted in an averaging manner. In this study, we propose a novel dataset pruning method termed as Temporal Dual-Depth Scoring (TDDS), to tackle this problem. TDDS utilizes a dual-depth strategy to achieve a balance between incorporating extensive training dynamics and identifying representative samples for dataset pruning. In the first depth, we estimate the series of each sample's individual contributions spanning the training progress, ensuring comprehensive integration of training dynamics. In the second depth, we focus on the variability of the sample-wise contributions identified in the first depth to highlight well-generalized samples. Extensive experiments conducted on CIFAR and ImageNet datasets verify the superiority of TDDS over previous SOTA methods. Specifically on CIFAR-100, our method achieves 54.51% accuracy with only 10% training data, surpassing random selection by 7.83% and other comparison methods by at least 12.69%.
Authors: Jay C. Rothenberger, Dimitrios I. Diochnos
In many practical computer vision scenarios unlabeled data is plentiful, but labels are scarce and difficult to obtain. As a result, semi-supervised learning which leverages unlabeled data to boost the performance of supervised classifiers have received significant attention in recent literature. One major class of semi-supervised algorithms is co-training. In co-training two different models leverage different independent and sufficient "views" of the data to jointly make better predictions. During co-training each model creates pseudo labels on unlabeled points which are used to improve the other model. We show that in the common case when independent views are not available we can construct such views inexpensively using pre-trained models. Co-training on the constructed views yields a performance improvement over any of the individual views we construct and performance comparable with recent approaches in semi-supervised learning, but has some undesirable properties. To alleviate the issues present with co-training we present Meta Co-Training which is an extension of the successful Meta Pseudo Labels approach to two views. Our method achieves new state-of-the-art performance on ImageNet-10% with very few training resources, as well as outperforming prior semi-supervised work on several other fine-grained image classification datasets.
Authors: Zengyi Qin, Wenliang Zhao, Xumin Yu, Xin Sun
We introduce OpenVoice, a versatile voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages. OpenVoice represents a significant advancement in addressing the following open challenges in the field: 1) Flexible Voice Style Control. OpenVoice enables granular control over voice styles, including emotion, accent, rhythm, pauses, and intonation, in addition to replicating the tone color of the reference speaker. The voice styles are not directly copied from and constrained by the style of the reference speaker. Previous approaches lacked the ability to flexibly manipulate voice styles after cloning. 2) Zero-Shot Cross-Lingual Voice Cloning. OpenVoice achieves zero-shot cross-lingual voice cloning for languages not included in the massive-speaker training set. Unlike previous approaches, which typically require extensive massive-speaker multi-lingual (MSML) dataset for all languages, OpenVoice can clone voices into a new language without any massive-speaker training data for that language. OpenVoice is also computationally efficient, costing tens of times less than commercially available APIs that offer even inferior performance. To foster further research in the field, we have made the source code and trained model publicly accessible. We also provide qualitative results in our demo website. Prior to its public release, our internal version of OpenVoice was used tens of millions of times by users worldwide between May and October 2023, serving as the backend of MyShell.
Authors: Keming Zhang, Joshua S. Bloom, Stéfan van der Walt, Nina Hernitschek
Despite the promise of Neural Posterior Estimation (NPE) methods in astronomy, the adaptation of NPE into the routine inference workflow has been slow. We identify three critical issues: the need for custom featurizer networks tailored to the observed data, the inference inexactness, and the under-specification of physical forward models. To address the first two issues, we introduce a new framework and open-source software nbi (Neural Bayesian Inference), which supports both amortized and sequential NPE. First, nbi provides built-in "featurizer" networks with demonstrated efficacy on sequential data, such as light curve and spectra, thus obviating the need for this customization on the user end. Second, we introduce a modified algorithm SNPE-IS, which facilities asymptotically exact inference by using the surrogate posterior under NPE only as a proposal distribution for importance sampling. These features allow nbi to be applied off-the-shelf to astronomical inference problems involving light curves and spectra. We discuss how nbi may serve as an effective alternative to existing methods such as Nested Sampling. Our package is at https://github.com/kmzzhang/nbi.
Authors: Christian Weihsbach, Christian N. Kruse, Alexander Bigalke, Mattias P. Heinrich
Applying pre-trained medical segmentation models on out-of-domain images often yields predictions of insufficient quality. Several strategies have been proposed to maintain model performance, such as finetuning or unsupervised- and source-free domain adaptation. These strategies set restrictive requirements for data availability. In this study, we propose to combine domain generalization and test-time adaptation to create a highly effective approach for reusing pre-trained models in unseen target domains. Domain-generalized pre-training on source data is used to obtain the best initial performance in the target domain. We introduce the MIND descriptor previously used in image registration tasks as a further technique to achieve generalization and present superior performance for small-scale datasets compared to existing approaches. At test-time, high-quality segmentation for every single unseen scan is ensured by optimizing the model weights for consistency given different image augmentations. That way, our method enables separate use of source and target data and thus removes current data availability barriers. Moreover, the presented method is highly modular as it does not require specific model architectures or prior knowledge of involved domains and labels. We demonstrate this by integrating it into the nnUNet, which is currently the most popular and accurate framework for medical image segmentation. We employ multiple datasets covering abdominal, cardiac, and lumbar spine scans and compose several out-of-domain scenarios in this study. We demonstrate that our method, combined with pre-trained whole-body CT models, can effectively segment MR images with high accuracy in all of the aforementioned scenarios. Open-source code can be found here: https://github.com/multimodallearning/DG-TTA
Authors: Avi Singh, John D. Co-Reyes, Rishabh Agarwal, Ankesh Anand, Piyush Patil, Xavier Garcia, Peter J. Liu, James Harrison, Jaehoon Lee, Kelvin Xu, Aaron Parisi, Abhishek Kumar, Alex Alemi, Alex Rizkowsky, Azade Nova, Ben Adlam, Bernd Bohnet, Gamaleldin Elsayed, Hanie Sedghi, Igor Mordatch, Isabelle Simpson, Izzeddin Gur, Jasper Snoek, Jeffrey Pennington, Jiri Hron, Kathleen Kenealy, Kevin Swersky, Kshiteej Mahajan, Laura Culp, Lechao Xiao, Maxwell L. Bileschi, Noah Constant, Roman Novak, Rosanne Liu, Tris Warkentin, Yundi Qian, Yamini Bansal, Ethan Dyer, Behnam Neyshabur, Jascha Sohl-Dickstein, Noah Fiedel
Fine-tuning language models~(LMs) on human-generated data remains a prevalent practice. However, the performance of such models is often limited by the quantity and diversity of high-quality human data. In this paper, we explore whether we can go beyond human data on tasks where we have access to scalar feedback, for example, on math problems where one can verify correctness. To do so, we investigate a simple self-training method based on expectation-maximization, which we call ReST$^{EM}$, where we (1) generate samples from the model and filter them using binary feedback, (2) fine-tune the model on these samples, and (3) repeat this process a few times. Testing on advanced MATH reasoning and APPS coding benchmarks using PaLM-2 models, we find that ReST$^{EM}$ scales favorably with model size and significantly surpasses fine-tuning only on human data. Overall, our findings suggest self-training with feedback can substantially reduce dependence on human-generated data.
Authors: Soham Bafana
Understanding object recognition patterns in mice is crucial for advancing behavioral neuroscience and has significant implications for human health, particularly in the realm of Alzheimer's research. This study is centered on the development, application, and evaluation of a state-of-the-art computational pipeline designed to analyze such behaviors, specifically focusing on Novel Object Recognition (NOR) and Spontaneous Location Recognition (SLR) tasks. The pipeline integrates three advanced computational models: Any-Maze for initial data collection, DeepLabCut for detailed pose estimation, and Convolutional Neural Networks (CNNs) for nuanced behavioral classification. Employed across four distinct mouse groups, this pipeline demonstrated high levels of accuracy and robustness. Despite certain challenges like video quality limitations and the need for manual calculations, the results affirm the pipeline's efficacy and potential for scalability. The study serves as a proof of concept for a multidimensional computational approach to behavioral neuroscience, emphasizing the pipeline's versatility and readiness for future, more complex analyses.
Authors: Shuyang Sun, Runjia Li, Philip Torr, Xiuye Gu, Siyang Li
Existing open-vocabulary image segmentation methods require a fine-tuning step on mask annotations and/or image-text datasets. Mask labels are labor-intensive, which limits the number of categories in segmentation datasets. As a result, the open-vocabulary capacity of pre-trained VLMs is severely reduced after fine-tuning. However, without fine-tuning, VLMs trained under weak image-text supervision tend to make suboptimal mask predictions when there are text queries referring to non-existing concepts in the image. To alleviate these issues, we introduce a novel recurrent framework that progressively filters out irrelevant texts and enhances mask quality without training efforts. The recurrent unit is a two-stage segmenter built upon a VLM with frozen weights. Thus, our model retains the VLM's broad vocabulary space and strengthens its segmentation capability. Experimental results show that our method outperforms not only the training-free counterparts, but also those fine-tuned with millions of additional data samples, and sets new state-of-the-art records for both zero-shot semantic and referring image segmentation tasks. Specifically, we improve the current record by 28.8, 16.0, and 6.9 mIoU on Pascal VOC, COCO Object, and Pascal Context.
Authors: Shufan Wang, Guojun Xiong, Jian Li
Restless multi-armed bandits (RMAB) have been widely used to model sequential decision making problems with constraints. The decision maker (DM) aims to maximize the expected total reward over an infinite horizon under an "instantaneous activation constraint" that at most B arms can be activated at any decision epoch, where the state of each arm evolves stochastically according to a Markov decision process (MDP). However, this basic model fails to provide any fairness guarantee among arms. In this paper, we introduce RMAB-F, a new RMAB model with "long-term fairness constraints", where the objective now is to maximize the long term reward while a minimum long-term activation fraction for each arm must be satisfied. For the online RMAB-F setting (i.e., the underlying MDPs associated with each arm are unknown to the DM), we develop a novel reinforcement learning (RL) algorithm named Fair-UCRL. We prove that Fair-UCRL ensures probabilistic sublinear bounds on both the reward regret and the fairness violation regret. Compared with off-the-shelf RL methods, our Fair-UCRL is much more computationally efficient since it contains a novel exploitation that leverages a low-complexity index policy for making decisions. Experimental results further demonstrate the effectiveness of our Fair-UCRL.
Authors: Borjan Geshkovski, Cyril Letrouit, Yury Polyanskiy, Philippe Rigollet
Transformers play a central role in the inner workings of large language models. We develop a mathematical framework for analyzing Transformers based on their interpretation as interacting particle systems, which reveals that clusters emerge in long time. Our study explores the underlying theory and offers new perspectives for mathematicians as well as computer scientists.
Authors: Abdallah Dib, Luiz Gustavo Hafemann, Emeline Got, Trevor Anderson, Amin Fadaeinejad, Rafael M. O. Cruz, Marc-Andre Carbonneau
Reconstructing an avatar from a portrait image has many applications in multimedia, but remains a challenging research problem. Extracting reflectance maps and geometry from one image is ill-posed: recovering geometry is a one-to-many mapping problem and reflectance and light are difficult to disentangle. Accurate geometry and reflectance can be captured under the controlled conditions of a light stage, but it is costly to acquire large datasets in this fashion. Moreover, training solely with this type of data leads to poor generalization with in-the-wild images. This motivates the introduction of MoSAR, a method for 3D avatar generation from monocular images. We propose a semi-supervised training scheme that improves generalization by learning from both light stage and in-the-wild datasets. This is achieved using a novel differentiable shading formulation. We show that our approach effectively disentangles the intrinsic face parameters, producing relightable avatars. As a result, MoSAR estimates a richer set of skin reflectance maps, and generates more realistic avatars than existing state-of-the-art methods. We also introduce a new dataset, named FFHQ-UV-Intrinsics, the first public dataset providing intrinsic face attributes at scale (diffuse, specular, ambient occlusion and translucency maps) for a total of 10k subjects. The project website and the dataset are available on the following link: https://ubisoft-laforge.github.io/character/mosar/
Authors: Anh Duc Nguyen, Tuan Dung Nguyen, Quang Minh Nguyen, Hoang H. Nguyen, Lam M. Nguyen, Kim-Chuan Toh
This paper studies the Partial Optimal Transport (POT) problem between two unbalanced measures with at most $n$ supports and its applications in various AI tasks such as color transfer or domain adaptation. There is hence the need for fast approximations of POT with increasingly large problem sizes in arising applications. We first theoretically and experimentally investigate the infeasibility of the state-of-the-art Sinkhorn algorithm for POT due to its incompatible rounding procedure, which consequently degrades its qualitative performance in real world applications like point-cloud registration. To this end, we propose a novel rounding algorithm for POT, and then provide a feasible Sinkhorn procedure with a revised computation complexity of $\mathcal{\widetilde O}(n^2/\varepsilon^4)$. Our rounding algorithm also permits the development of two first-order methods to approximate the POT problem. The first algorithm, Adaptive Primal-Dual Accelerated Gradient Descent (APDAGD), finds an $\varepsilon$-approximate solution to the POT problem in $\mathcal{\widetilde O}(n^{2.5}/\varepsilon)$, which is better in $\varepsilon$ than revised Sinkhorn. The second method, Dual Extrapolation, achieves the computation complexity of $\mathcal{\widetilde O}(n^2/\varepsilon)$, thereby being the best in the literature. We further demonstrate the flexibility of POT compared to standard OT as well as the practicality of our algorithms on real applications where two marginal distributions are unbalanced.