Authors: Leonid Schwenke, Martin Atzmueller
This paper targets two transformer attention based interpretability methods working with local abstraction and global representation, in the context of time series data. We distinguish local and global contexts, and provide a comprehensive framework for both general interpretation options. We discuss their specific instantiation via different methods in detail, also outlining their respective computational implementation and abstraction variants. Furthermore, we provide extensive experimentation demonstrating the efficacy of the presented approaches. In particular, we perform our experiments using a selection of univariate datasets from the UCR UEA time series repository where we both assess the performance of the proposed approaches, as well as their impact on explainability and interpretability/complexity. Here, with an extensive analysis of hyperparameters, the presented approaches demonstrate an significant improvement in interpretability/complexity, while capturing many core decisions of and maintaining a similar performance to the baseline model. Finally, we draw general conclusions outlining and guiding the application of the presented methods.
Authors: Huafeng Liu (1), Benjamin Dowdell (1), Todd Engelder (1), Zarah Pulmano (1), Nicolas Osa (1), Arko Barman (1) ((1) Rice University)
Glioblastoma is one of the most aggressive and deadliest types of brain cancer, with low survival rates compared to other types of cancer. Analysis of Magnetic Resonance Imaging (MRI) scans is one of the most effective methods for the diagnosis and treatment of brain cancers such as glioblastoma. Accurate tumor segmentation in MRI images is often required for treatment planning and risk assessment of treatment methods. Here, we propose a novel pipeline, Brain Radiology Aided by Intelligent Neural NETworks (BRAINNET), which leverages MaskFormer, a vision transformer model, and generates robust tumor segmentation maks. We use an ensemble of nine predictions from three models separately trained on each of the three orthogonal 2D slice directions (axial, sagittal, and coronal) of a 3D brain MRI volume. We train and test our models on the publicly available UPenn-GBM dataset, consisting of 3D multi-parametric MRI (mpMRI) scans from 611 subjects. Using Dice coefficient (DC) and 95% Hausdorff distance (HD) for evaluation, our models achieved state-of-the-art results in segmenting all three different tumor regions -- tumor core (DC = 0.894, HD = 2.308), whole tumor (DC = 0.891, HD = 3.552), and enhancing tumor (DC = 0.812, HD = 1.608).
Authors: Mao Po-Yuan, Shashank Kotyan, Tham Yik Foong, Danilo Vasconcellos Vargas
Recent advances in Conditional Diffusion Models have led to substantial capabilities in various domains. However, understanding the impact of variations in the initial seed vector remains an underexplored area of concern. Particularly, latent-based diffusion models display inconsistencies in image generation under standard conditions when initialized with suboptimal initial seed vectors. To understand the impact of the initial seed vector on generated samples, we propose a reliability evaluation framework that evaluates the generated samples of a diffusion model when the initial seed vector is subjected to various synthetic shifts. Our results indicate that slight manipulations to the initial seed vector of the state-of-the-art Stable Diffusion (Rombach et al., 2022) can lead to significant disturbances in the generated samples, consequently creating images without the effect of conditioning variables. In contrast, GLIDE (Nichol et al., 2022) stands out in generating reliable samples even when the initial seed vector is transformed. Thus, our study sheds light on the importance of the selection and the impact of the initial seed vector in the latent-based diffusion model.
Authors: Farideh Majidi
Energy consumption analysis plays a pivotal role in addressing the challenges of sustainability and resource management. This paper introduces a novel approach to effectively cluster monthly energy consumption patterns by integrating two powerful techniques: Self-organizing maps and K-means clustering. The proposed method aims to exploit the benefits of both of these algorithms to enhance the accuracy and interpretability of clustering results for a dataset in which finding patterns is difficult. The main focus of this study is on a selection of time series energy consumption data from the Smart meters in London dataset. The data was preprocessed and reduced in dimensionality to capture essential temporal patterns while retaining their underlying structures. The SOM algorithm was utilized to extract the central representatives of the consumption patterns for each one of the houses over the course of each month, effectively reducing the dimensionality of the dataset and making it easier for analysis. Subsequently, the obtained SOM centroids were clustered using K-means, a popular centroid-based clustering technique. The experimental results demonstrated a significant silhouette score of 66%, indicating strong intra-cluster cohesion and inter-cluster separation which confirms the effectiveness of the proposed approach in the clustering task.
Authors: Shuyu Y Chang, Zahra Ghahremani, Laura Manuel, Mohammad Erfani, Chaopeng Shen, Sagy Cohen, Kimberly Van Meter, Jennifer L Pierce, Ehab A Meselhe, Erfan Goharian
Hydraulic geometry parameters describing river hydrogeomorphic is important for flood forecasting. Although well-established, power-law hydraulic geometry curves have been widely used to understand riverine systems and mapping flooding inundation worldwide for the past 70 years, we have become increasingly aware of the limitations of these approaches. In the present study, we have moved beyond these traditional power-law relationships for river geometry, testing the ability of machine-learning models to provide improved predictions of river width and depth. For this work, we have used an unprecedentedly large river measurement dataset (HYDRoSWOT) as well as a suite of watershed predictor data to develop novel data-driven approaches to better estimate river geometries over the contiguous United States (CONUS). Our Random Forest, XGBoost, and neural network models out-performed the traditional, regionalized power law-based hydraulic geometry equations for both width and depth, providing R-squared values of as high as 0.75 for width and as high as 0.67 for depth, compared with R-squared values of 0.57 for width and 0.18 for depth from the regional hydraulic geometry equations. Our results also show diverse performance outcomes across stream orders and geographical regions for the different machine-learning models, demonstrating the value of using multi-model approaches to maximize the predictability of river geometry. The developed models have been used to create the newly publicly available STREAM-geo dataset, which provides river width, depth, width/depth ratio, and river and stream surface area (%RSSA) for nearly 2.7 million NHDPlus stream reaches across the rivers and streams across the contiguous US.
Authors: Koushik Biswas, Debesh Jha, Nikhil Kumar Tomar, Gorkem Durak, Alpay Medetalibeyoglu, Matthew Antalek, Yury Velichko, Daniela Ladner, Amir Bohrani, Ulas Bagci
In this study, we propose a new activation function, called Adaptive Smooth Activation Unit (ASAU), tailored for optimized gradient propagation, thereby enhancing the proficiency of convolutional networks in medical image analysis. We apply this new activation function to two important and commonly used general tasks in medical image analysis: automatic disease diagnosis and organ segmentation in CT and MRI. Our rigorous evaluation on the RadImageNet abdominal/pelvis (CT and MRI) dataset and Liver Tumor Segmentation Benchmark (LiTS) 2017 demonstrates that our ASAU-integrated frameworks not only achieve a substantial (4.80\%) improvement over ReLU in classification accuracy (disease detection) on abdominal CT and MRI but also achieves 1\%-3\% improvement in dice coefficient compared to widely used activations for `healthy liver tissue' segmentation. These improvements offer new baselines for developing a diagnostic tool, particularly for complex, challenging pathologies. The superior performance and adaptability of ASAU highlight its potential for integration into a wide range of image classification and segmentation tasks.
Authors: Hongjian Gu, Yaochen Hu, Yingxue Zhang
Graph-based collaborative filtering methods have prevailing performance for recommender systems since they can capture high-order information between users and items, in which the graphs are constructed from the observed user-item interactions that might miss links or contain spurious positive interactions in industrial scenarios. The Bayesian Graph Neural Network framework approaches this issue with generative models for the interaction graphs. The critical problem is to devise a proper family of graph generative models tailored to recommender systems. We propose an efficient generative model that jointly considers the preferences of users, the concurrence of items and some important graph structure information. Experiments on four popular benchmark datasets demonstrate the effectiveness of our proposed graph generative methods for recommender systems.
Authors: Daniel Cunnington, Flaviu Cipcigan, Rodrigo Neumann Barros Ferreira, Jonathan Booth
Discovering new materials is essential to solve challenges in climate change, sustainability and healthcare. A typical task in materials discovery is to search for a material in a database which maximises the value of a function. That function is often expensive to evaluate, and can rely upon a simulation or an experiment. Here, we introduce SyMDis, a sample efficient optimisation method based on symbolic learning, that discovers near-optimal materials in a large database. SyMDis performs comparably to a state-of-the-art optimiser, whilst learning interpretable rules to aid physical and chemical verification. Furthermore, the rules learned by SyMDis generalise to unseen datasets and return high performing candidates in a zero-shot evaluation, which is difficult to achieve with other approaches.
Authors: Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Bo Gao, Quyang Pan, Tianliu He, Xuefeng Jiang
Federated Learning (FL) enables training Artificial Intelligence (AI) models over end devices without compromising their privacy. As computing tasks are increasingly performed by a combination of cloud, edge, and end devices, FL can benefit from this End-Edge-Cloud Collaboration (EECC) paradigm to achieve collaborative device-scale expansion with real-time access. Although Hierarchical Federated Learning (HFL) supports multi-tier model aggregation suitable for EECC, prior works assume the same model structure on all computing nodes, constraining the model scale by the weakest end devices. To address this issue, we propose Agglomerative Federated Learning (FedAgg), which is a novel EECC-empowered FL framework that allows the trained models from end, edge, to cloud to grow larger in size and stronger in generalization ability. FedAgg recursively organizes computing nodes among all tiers based on Bridge Sample Based Online Distillation Protocol (BSBODP), which enables every pair of parent-child computing nodes to mutually transfer and distill knowledge extracted from generated bridge samples. This design enhances the performance by exploiting the potential of larger models, with privacy constraints of FL and flexibility requirements of EECC both satisfied. Experiments under various settings demonstrate that FedAgg outperforms state-of-the-art methods by an average of 4.53\% accuracy gains and remarkable improvements in convergence rate.
Authors: David R. Bellamy, Bhawesh Kumar, Cindy Wang, Andrew Beam
In this work we introduce Labrador, a pre-trained Transformer model for laboratory data. Labrador and BERT were pre-trained on a corpus of 100 million lab test results from electronic health records (EHRs) and evaluated on various downstream outcome prediction tasks. Both models demonstrate mastery of the pre-training task but neither consistently outperform XGBoost on downstream supervised tasks. Our ablation studies reveal that transfer learning shows limited effectiveness for BERT and achieves marginal success with Labrador. We explore the reasons for the failure of transfer learning and suggest that the data generating process underlying each patient cannot be characterized sufficiently using labs alone, among other factors. We encourage future work to focus on joint modeling of multiple EHR data categories and to include tree-based baselines in their evaluations.
Authors: Hao Li, Brandon Bennett
Text classification is an important topic in the field of natural language processing. It has been preliminarily applied in information retrieval, digital library, automatic abstracting, text filtering, word semantic discrimination and many other fields. The aim of this research is to use a variety of algorithms to test the ability to identify offensive posts and evaluate their performance against a variety of assessment methods. The motivation for this project is to reduce the harm of these languages to human censors by automating the screening of offending posts. The field is a new one, and despite much interest in the past two years, there has been no focus on the object of the offence. Through the experiment of this project, it should inspire future research on identification methods as well as identification content.
Authors: Milad Rogha
The unprecedented performance of machine learning models in recent years, particularly Deep Learning and transformer models, has resulted in their application in various domains such as finance, healthcare, and education. However, the models are error-prone and cannot be used autonomously, especially in decision-making scenarios where, technically or ethically, the cost of error is high. Moreover, because of the black-box nature of these models, it is frequently difficult for the end user to comprehend the models' outcomes and underlying processes to trust and use the model outcome to make a decision. Explainable Artificial Intelligence (XAI) aids end-user understanding of the model by utilizing approaches, including visualization techniques, to explain and interpret the inner workings of the model and how it arrives at a result. Although numerous research studies have been conducted recently focusing on the performance of models and the XAI approaches, less work has been done on the impact of explanations on human-AI team performance. This paper surveyed the recent empirical studies on XAI's impact on human-AI decision-making, identified the challenges, and proposed future research directions.
Authors: Pavlos Constas, Vikram Rawal, Matthew Honorio Oliveira, Andreas Constas, Aditya Khan, Kaison Cheung, Najma Sultani, Carrie Chen, Micol Altomare, Michael Akzam, Jiacheng Chen, Vhea He, Lauren Altomare, Heraa Murqi, Asad Khan, Nimit Amikumar Bhanshali, Youssef Rachad, Michael Guerzhoy
We propose a Reinforcement-Learning-based system that would automatically prescribe a hypothetical patient medications that may help the patient with their mental-health-related speech disfluency, and adjust the medication and the dosages in response to data from the patient. We demonstrate the components of the system: a module that detects and evaluates speech disfluency on a large dataset we built, and a Reinforcement Learning algorithm that automatically finds good combinations of medications. To support the two modules, we collect data on the effect of psychiatric medications for speech disfluency from the literature, and build a plausible patient simulation system. We demonstrate that the Reinforcement Learning system is, under some circumstances, able to converge to a good medication regime. We collect and label a dataset of people with possible speech disfluency and demonstrate our methods using that dataset. Our work is a proof of concept: we show that there is promise in the idea of using automatic data collection to address disfluency.
Authors: Thomas Paniagua, Ryan Grainger, Tianfu Wu
The adversarial vulnerability of Deep Neural Networks (DNNs) has been well-known and widely concerned, often under the context of learning top-$1$ attacks (e.g., fooling a DNN to classify a cat image as dog). This paper shows that the concern is much more serious by learning significantly more aggressive ordered top-$K$ clear-box~\footnote{ This is often referred to as white/black-box attacks in the literature. We choose to adopt neutral terminology, clear/opaque-box attacks in this paper, and omit the prefix clear-box for simplicity.} targeted attacks proposed in Adversarial Distillation. We propose a novel and rigorous quadratic programming (QP) method of learning ordered top-$K$ attacks with low computing cost, dubbed as \textbf{QuadAttac$K$}. Our QuadAttac$K$ directly solves the QP to satisfy the attack constraint in the feature embedding space (i.e., the input space to the final linear classifier), which thus exploits the semantics of the feature embedding space (i.e., the principle of class coherence). With the optimized feature embedding vector perturbation, it then computes the adversarial perturbation in the data space via the vanilla one-step back-propagation. In experiments, the proposed QuadAttac$K$ is tested in the ImageNet-1k classification using ResNet-50, DenseNet-121, and Vision Transformers (ViT-B and DEiT-S). It successfully pushes the boundary of successful ordered top-$K$ attacks from $K=10$ up to $K=20$ at a cheap budget ($1\times 60$) and further improves attack success rates for $K=5$ for all tested models, while retaining the performance for $K=1$.
Authors: Henry Bae, Aghyad Deeb, Alex Fleury, Kehang Zhu
We present ComplexityNet, a streamlined language model designed for assessing task complexity. This model predicts the likelihood of accurate output by various language models, each with different capabilities. Our initial application of ComplexityNet involves the Mostly Basic Python Problems (MBPP) dataset. We pioneered the creation of the first set of labels to define task complexity. ComplexityNet achieved a notable 79% accuracy in determining task complexity, a significant improvement over the 34% accuracy of the original, non fine-tuned model. Furthermore, ComplexityNet effectively reduces computational resource usage by 90% compared to using the highest complexity model, while maintaining a high code generation accuracy of 86.7%. This study demonstrates that fine-tuning smaller models to categorize tasks based on their complexity can lead to a more balanced trade-off between accuracy and efficiency in the use of Large Language Models. Our findings suggest a promising direction for optimizing LLM applications, especially in resource-constrained environments.
Authors: Ahmed Salem, Andrew Paverd, Boris Köpf
Prompt injection has emerged as a serious security threat to large language models (LLMs). At present, the current best-practice for defending against newly-discovered prompt injection techniques is to add additional guardrails to the system (e.g., by updating the system prompt or using classifiers on the input and/or output of the model.) However, in the same way that variants of a piece of malware are created to evade anti-virus software, variants of a prompt injection can be created to evade the LLM's guardrails. Ideally, when a new prompt injection technique is discovered, candidate defenses should be tested not only against the successful prompt injection, but also against possible variants.
In this work, we present, a tool to assist defenders in performing automated variant analysis of known prompt injection attacks. This involves solving two main challenges: (1) automatically generating variants of a given prompt according, and (2) automatically determining whether a variant was effective based only on the output of the model. This tool can also assist in generating datasets for jailbreak and prompt injection attacks, thus overcoming the scarcity of data in this domain.
We evaluate Maatphor on three different types of prompt injection tasks. Starting from an ineffective (0%) seed prompt, Maatphor consistently generates variants that are at least 60% effective within the first 40 iterations.
Authors: Keivan Alizadeh, Iman Mirzadeh, Dmitry Belenko, Karen Khatamifard, Minsik Cho, Carlo C Del Mundo, Mohammad Rastegari, Mehrdad Farajtabar
Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their intensive computational and memory requirements present challenges, especially for devices with limited DRAM capacity. This paper tackles the challenge of efficiently running LLMs that exceed the available DRAM capacity by storing the model parameters on flash memory but bringing them on demand to DRAM. Our method involves constructing an inference cost model that harmonizes with the flash memory behavior, guiding us to optimize in two critical areas: reducing the volume of data transferred from flash and reading data in larger, more contiguous chunks. Within this flash memory-informed framework, we introduce two principal techniques. First, "windowing'" strategically reduces data transfer by reusing previously activated neurons, and second, "row-column bundling", tailored to the sequential data access strengths of flash memory, increases the size of data chunks read from flash memory. These methods collectively enable running models up to twice the size of the available DRAM, with a 4-5x and 20-25x increase in inference speed compared to naive loading approaches in CPU and GPU, respectively. Our integration of sparsity awareness, context-adaptive loading, and a hardware-oriented design paves the way for effective inference of LLMs on devices with limited memory.
Authors: Md Abrar Jahin, Subrata Talapatra
This research delves into the intricate landscape of Musculoskeletal Disorder (MSD) risk factors, employing a novel fusion of Natural Language Processing (NLP) techniques and mode-based ranking methodologies. The primary objective is to advance the comprehension of MSD risk factors, their classification, and their relative severity, facilitating more targeted preventive and management interventions. The study utilizes eight diverse models, integrating pre-trained transformers, cosine similarity, and various distance metrics to classify risk factors into personal, biomechanical, workplace, psychological, and organizational classes. Key findings reveal that the BERT model with cosine similarity attains an overall accuracy of 28\%, while the sentence transformer, coupled with Euclidean, Bray-Curtis, and Minkowski distances, achieves a flawless accuracy score of 100\%. In tandem with the classification efforts, the research employs a mode-based ranking approach on survey data to discern the severity hierarchy of MSD risk factors. Intriguingly, the rankings align precisely with the previous literature, reaffirming the consistency and reliability of the approach. ``Working posture" emerges as the most severe risk factor, emphasizing the critical role of proper posture in preventing MSDs. The collective perceptions of survey participants underscore the significance of factors like ``Job insecurity," ``Effort reward imbalance," and ``Poor employee facility" in contributing to MSD risks. The convergence of rankings provides actionable insights for organizations aiming to reduce the prevalence of MSDs. The study concludes with implications for targeted interventions, recommendations for improving workplace conditions, and avenues for future research.
Authors: Oscar Chang, Lampros Flokas, Hod Lipson, Michael Spranger
SATNet is an award-winning MAXSAT solver that can be used to infer logical rules and integrated as a differentiable layer in a deep neural network. It had been shown to solve Sudoku puzzles visually from examples of puzzle digit images, and was heralded as an impressive achievement towards the longstanding AI goal of combining pattern recognition with logical reasoning. In this paper, we clarify SATNet's capabilities by showing that in the absence of intermediate labels that identify individual Sudoku digit images with their logical representations, SATNet completely fails at visual Sudoku (0% test accuracy). More generally, the failure can be pinpointed to its inability to learn to assign symbols to perceptual phenomena, also known as the symbol grounding problem, which has long been thought to be a prerequisite for intelligent agents to perform real-world logical reasoning. We propose an MNIST based test as an easy instance of the symbol grounding problem that can serve as a sanity check for differentiable symbolic solvers in general. Naive applications of SATNet on this test lead to performance worse than that of models without logical reasoning capabilities. We report on the causes of SATNet's failure and how to prevent them.
Authors: Andreas Bergmeister, Karolis Martinkus, Nathanaël Perraudin, Roger Wattenhofer
In the realm of generative models for graphs, extensive research has been conducted. However, most existing methods struggle with large graphs due to the complexity of representing the entire joint distribution across all node pairs and capturing both global and local graph structures simultaneously. To overcome these issues, we introduce a method that generates a graph by progressively expanding a single node to a target graph. In each step, nodes and edges are added in a localized manner through denoising diffusion, building first the global structure, and then refining the local details. The local generation avoids modeling the entire joint distribution over all node pairs, achieving substantial computational savings with subquadratic runtime relative to node count while maintaining high expressivity through multiscale generation. Our experiments show that our model achieves state-of-the-art performance on well-established benchmark datasets while successfully scaling to graphs with at least 5000 nodes. Our method is also the first to successfully extrapolate to graphs outside of the training distribution, showcasing a much better generalization capability over existing methods.
Authors: Ana Fernández Vilas, Rebeca P. Díaz Redondo, Keeley Crockett, Majdi Owda, Lewis Evans
There is a general consensus of the good sensing and novelty characteristics of Twitter as an information media for the complex financial market. This paper investigates the permeability of Twittersphere, the total universe of Twitter users and their habits, towards relevant events in the financial market. Analysis shows that a general purpose social media is permeable to financial-specific events and establishes Twitter as a relevant feeder for taking decisions regarding the financial market and event fraudulent activities in that market. However, the provenance of contributions, their different levels of credibility and quality and even the purpose or intention behind them should to be considered and carefully contemplated if Twitter is used as a single source for decision taking. With the overall aim of this research, to deploy an architecture for real-time monitoring of irregularities in the financial market, this paper conducts a series of experiments on the level of permeability and the permeable features of Twitter in the event of one of these irregularities. To be precise, Twitter data is collected concerning an event comprising of a specific financial action on the 27th January 2017:{~ }the announcement about the merge of two companies Tesco PLC and Booker Group PLC, listed in the main market of the London Stock Exchange (LSE), to create the UK's Leading Food Business. The experiment attempts to answer five key research questions which aim to characterize the features of Twitter permeability to the financial market. The experimental results confirm that a far-impacting financial event, such as the merger considered, caused apparent disturbances in all the features considered, that is, information volume, content and sentiment as well as geographical provenance. Analysis shows that despite, Twitter not being a specific financial forum, it is permeable to financial events.
Authors: Ana Fernández Vilas, Rebeca Díaz Redondo, Antón Lorenzo García
There is a consensus about the good sensing characteristics of Twitter to mine and uncover knowledge in financial markets, being considered a relevant feeder for taking decisions about buying or holding stock shares and even for detecting stock manipulation. Although Twitter hashtags allow to aggregate topic-related content, a specific mechanism for financial information also exists: Cashtag. However, the irruption of cryptocurrencies has resulted in a significant degradation on the cashtag-based aggregation of posts. Unfortunately, Twitter' users may use homonym tickers to refer to cryptocurrencies and to companies in stock markets, which means that filtering by cashtag may result on both posts referring to stock companies and cryptocurrencies. This research proposes automated classifiers to distinguish conflicting cashtags and, so, their container tweets by analyzing the distinctive features of tweets referring to stock companies and cryptocurrencies. As experiment, this paper analyses the interference between cryptocurrencies and company tickers in the London Stock Exchange (LSE), specifically, companies in the main and alternative market indices FTSE-100 and AIM-100. Heuristic-based as well as supervised classifiers are proposed and their advantages and drawbacks, including their ability to self-adapt to Twitter usage changes, are discussed. The experiment confirms a significant distortion in collected data when colliding or homonym cashtags exist, i.e., the same \$ acronym to refer to company tickers and cryptocurrencies. According to our results, the distinctive features of posts including cryptocurrencies or company tickers support accurate classification of colliding tweets (homonym cashtags) and Independent Models, as the most detached classifiers from training data, have the potential to be trans-applicability (in different stock markets) while retaining performance.
Authors: YoungJoon Yoo, Jongwon Choi
This paper introduces a novel approach for topic modeling utilizing latent codebooks from Vector-Quantized Variational Auto-Encoder~(VQ-VAE), discretely encapsulating the rich information of the pre-trained embeddings such as the pre-trained language model. From the novel interpretation of the latent codebooks and embeddings as conceptual bag-of-words, we propose a new generative topic model called Topic-VQ-VAE~(TVQ-VAE) which inversely generates the original documents related to the respective latent codebook. The TVQ-VAE can visualize the topics with various generative distributions including the traditional BoW distribution and the autoregressive image generation. Our experimental results on document analysis and image generation demonstrate that TVQ-VAE effectively captures the topic context which reveals the underlying structures of the dataset and supports flexible forms of document generation. Official implementation of the proposed TVQ-VAE is available at https://github.com/clovaai/TVQ-VAE.
Authors: Naman Agarwal, Satyen Kale, Karan Singh, Abhradeep Guha Thakurta
We study the task of $(\epsilon, \delta)$-differentially private online convex optimization (OCO). In the online setting, the release of each distinct decision or iterate carries with it the potential for privacy loss. This problem has a long history of research starting with Jain et al. [2012] and the best known results for the regime of {\epsilon} being very small are presented in Agarwal et al. [2023]. In this paper we improve upon the results of Agarwal et al. [2023] in terms of the dimension factors as well as removing the requirement of smoothness. Our results are now the best known rates for DP-OCO in this regime.
Our algorithms builds upon the work of [Asi et al., 2023] which introduced the idea of explicitly limiting the number of switches via rejection sampling. The main innovation in our algorithm is the use of sampling from a strongly log-concave density which allows us to trade-off the dimension factors better leading to improved results.
Authors: Litian Liu, Yao Qin
Efficient and effective Out-of-Distribution (OOD) detection is essential for the safe deployment of AI in latency-critical applications. Recently, studies have revealed that detecting OOD based on feature space information can be highly effective. Despite their effectiveness, however, exiting feature space OOD methods may incur non-negligible computational overhead, given their reliance on auxiliary models built from training features. In this paper, we aim to obviate auxiliary models to optimize computational efficiency while leveraging the rich information embedded in the feature space. We investigate from the novel perspective of decision boundaries and propose to detect OOD using the feature distance to decision boundaries. To minimize the cost of measuring the distance, we introduce an efficient closed-form estimation, analytically proven to tightly lower bound the distance. We observe that ID features tend to reside further from the decision boundaries than OOD features. Our observation aligns with the intuition that models tend to be more decisive on ID samples, considering that distance to decision boundaries quantifies model uncertainty. From our understanding, we propose a hyperparameter-free, auxiliary model-free OOD detector. Our OOD detector matches or surpasses the effectiveness of state-of-the-art methods across extensive experiments. Meanwhile, our OOD detector incurs practically negligible overhead in inference latency. Overall, we significantly enhance the efficiency-effectiveness trade-off in OOD detection.
Authors: Shangshang Zheng, He Bai, Yizhe Zhang, Yi Su, Xiaochuan Niu, Navdeep Jaitly
Current approaches to evaluating large language models (LLMs) with pre-existing Knowledge Graphs (KG) mostly ignore the structure of the KG and make arbitrary choices of which part of the graph to evaluate. In this paper, we introduce KGLens, a method to evaluate LLMs by generating natural language questions from a KG in a structure aware manner so that we can characterize its performance on a more aggregated level. KGLens uses a parameterized KG, where each edge is augmented with a beta distribution that guides how to sample edges from the KG for QA testing. As the evaluation proceeds, different edges of the parameterized KG are sampled and assessed appropriately, converging to a more global picture of the performance of the LLMs on the KG as a whole. In our experiments, we construct three domain-specific KGs for knowledge assessment, comprising over 19,000 edges, 700 relations, and 21,000 entities. The results demonstrate that KGLens can not only assess overall performance but also provide topic, temporal, and relation analyses of LLMs. This showcases the adaptability and customizability of KGLens, emphasizing its ability to focus the evaluation based on specific criteria.
Authors: Tatsuya Akutsu, Avraham A. Melkman, Atsuhiro Takasu
In this paper, we focus on the prediction phase of a random forest and study the problem of representing a bag of decision trees using a smaller bag of decision trees, where we only consider binary decision problems on the binary domain and simple decision trees in which an internal node is limited to querying the Boolean value of a single variable. As a main result, we show that the majority function of $n$ variables can be represented by a bag of $T$ ($< n$) decision trees each with polynomial size if $n-T$ is a constant, where $n$ and $T$ must be odd (in order to avoid the tie break). We also show that a bag of $n$ decision trees can be represented by a bag of $T$ decision trees each with polynomial size if $n-T$ is a constant and a small classification error is allowed. A related result on the $k$-out-of-$n$ functions is presented too.
Authors: Lebin Yu, Yunbo Qiu, Quanming Yao, Yuan Shen, Xudong Zhang, Jian Wang
Communication in multi-agent reinforcement learning (MARL) has been proven to effectively promote cooperation among agents recently. Since communication in real-world scenarios is vulnerable to noises and adversarial attacks, it is crucial to develop robust communicative MARL technique. However, existing research in this domain has predominantly focused on passive defense strategies, where agents receive all messages equally, making it hard to balance performance and robustness. We propose an active defense strategy, where agents automatically reduce the impact of potentially harmful messages on the final decision. There are two challenges to implement this strategy, that are defining unreliable messages and adjusting the unreliable messages' impact on the final decision properly. To address them, we design an Active Defense Multi-Agent Communication framework (ADMAC), which estimates the reliability of received messages and adjusts their impact on the final decision accordingly with the help of a decomposable decision structure. The superiority of ADMAC over existing methods is validated by experiments in three communication-critical tasks under four types of attacks.
Authors: Ruibin Zeng, Minglong Lei, Lingfeng Niu, Lan Cheng
Combinatorial optimization (CO) on graphs is a classic topic that has been extensively studied across many scientific and industrial fields. Recently, solving CO problems on graphs through learning methods has attracted great attention. Advanced deep learning methods, e.g., graph neural networks (GNNs), have been used to effectively assist the process of solving COs. However, current frameworks based on GNNs are mainly designed for certain CO problems, thereby failing to consider their transferable and generalizable abilities among different COs on graphs. Moreover, simply using original graphs to model COs only captures the direct correlations among objects, which does not consider the mathematical logicality and properties of COs. In this paper, we propose a unified pre-training and adaptation framework for COs on graphs with the help of the maximum satisfiability (Max-SAT) problem. We first use Max-SAT to bridge different COs on graphs since they can be converted to Max-SAT problems represented by standard formulas and clauses with logical information. Then, we further design a pre-training and domain adaptation framework to extract the transferable and generalizable features so that different COs can benefit from them. In the pre-training stage, Max-SAT instances are generated to initialize the parameters of the model. In the fine-tuning stage, instances from CO and Max-SAT problems are used for adaptation so that the transferable ability can be further improved. Numerical experiments on several datasets show that features extracted by our framework exhibit superior transferability and Max-SAT can boost the ability to solve COs on graphs.
Authors: Qihang Zhou, Shibo He, Haoyu Liu, Jiming Chen, Wenchao Meng
Anomaly detection in multivariate time series (MTS) has been widely studied in one-class classification (OCC) setting. The training samples in OCC are assumed to be normal, which is difficult to guarantee in practical situations. Such a case may degrade the performance of OCC-based anomaly detection methods which fit the training distribution as the normal distribution. In this paper, we propose MTGFlow, an unsupervised anomaly detection approach for MTS anomaly detection via dynamic Graph and entity-aware normalizing Flow. MTGFlow first estimates the density of the entire training samples and then identifies anomalous instances based on the density of the test samples within the fitted distribution. This relies on a widely accepted assumption that anomalous instances exhibit more sparse densities than normal ones, with no reliance on the clean training dataset. However, it is intractable to directly estimate the density due to complex dependencies among entities and their diverse inherent characteristics. To mitigate this, we utilize the graph structure learning model to learn interdependent and evolving relations among entities, which effectively captures complex and accurate distribution patterns of MTS. In addition, our approach incorporates the unique characteristics of individual entities by employing an entity-aware normalizing flow. This enables us to represent each entity as a parameterized normal distribution. Furthermore, considering that some entities present similar characteristics, we propose a cluster strategy that capitalizes on the commonalities of entities with similar characteristics, resulting in more precise and detailed density estimation. We refer to this cluster-aware extension as MTGFlow_cluster. Extensive experiments are conducted on six widely used benchmark datasets, in which MTGFlow and MTGFlow cluster demonstrate their superior detection performance.
Authors: Shreya Ghosh, Abu Shafin Mohammad Mahdee Jameel, Aly El Gamal
In this paper, we explore transferability in learning between different attack classes in a network intrusion detection setup. We evaluate transferability of attack classes by training a deep learning model with a specific attack class and testing it on a separate attack class. We observe the effects of real and synthetically generated data augmentation techniques on transferability. We investigate the nature of observed transferability relationships, which can be either symmetric or asymmetric. We also examine explainability of the transferability relationships using the recursive feature elimination algorithm. We study data preprocessing techniques to boost model performance. The code for this work can be found at https://github.com/ghosh64/transferability.
Authors: Longchao Da, Porter Jenkins, Trevor Schwantes, Jeffrey Dotson, Hua Wei
In practice, it is essential to compare and rank candidate policies offline before real-world deployment for safety and reliability. Prior work seeks to solve this offline policy ranking (OPR) problem through value-based methods, such as Off-policy evaluation (OPE). However, they fail to analyze special cases performance (e.g., worst or best cases), due to the lack of holistic characterization of policies performance. It is even more difficult to estimate precise policy values when the reward is not fully accessible under sparse settings. In this paper, we present Probabilistic Offline Policy Ranking (POPR), a framework to address OPR problems by leveraging expert data to characterize the probability of a candidate policy behaving like experts, and approximating its entire performance posterior distribution to help with ranking. POPR does not rely on value estimation, and the derived performance posterior can be used to distinguish candidates in worst, best, and average-cases. To estimate the posterior, we propose POPR-EABC, an Energy-based Approximate Bayesian Computation (ABC) method conducting likelihood-free inference. POPR-EABC reduces the heuristic nature of ABC by a smooth energy function, and improves the sampling efficiency by a pseudo-likelihood. We empirically demonstrate that POPR-EABC is adequate for evaluating policies in both discrete and continuous action spaces across various experiment environments, and facilitates probabilistic comparisons of candidate policies before deployment.
Authors: Ying-Ying Chang, Wei-Yao Wang, Wen-Chih Peng
In the dynamic and rapidly evolving world of social media, detecting anomalous users has become a crucial task to address malicious activities such as misinformation and cyberbullying. As the increasing number of anomalous users improves the ability to mimic normal users and evade detection, existing methods only focusing on bot detection are ineffective in terms of capturing subtle distinctions between users. To address these challenges, we proposed SeGA, preference-aware self-contrastive learning for anomalous user detection, which leverages heterogeneous entities and their relations in the Twittersphere to detect anomalous users with different malicious strategies. SeGA utilizes the knowledge of large language models to summarize user preferences via posts. In addition, integrating user preferences with prompts as pseudo-labels for preference-aware self-contrastive learning enables the model to learn multifaceted aspects for describing the behaviors of users. Extensive experiments on the proposed TwBNT benchmark demonstrate that SeGA significantly outperforms the state-of-the-art methods (+3.5\% ~ 27.6\%) and empirically validate the effectiveness of the model design and pre-training strategies. Our code and data are publicly available at https://github.com/ying0409/SeGA.
Authors: Harris Papadopoulos, Nestoras Georgiou, Charalambos Eliades, Andreas Konstantinidis
The impressive growth of smartphone devices in combination with the rising ubiquity of using mobile platforms for sensitive applications such as Internet banking, have triggered a rapid increase in mobile malware. In recent literature, many studies examine Machine Learning techniques, as the most promising approach for mobile malware detection, without however quantifying the uncertainty involved in their detections. In this paper, we address this problem by proposing a machine learning dynamic analysis approach that provides provably valid confidence guarantees in each malware detection. Moreover the particular guarantees hold for both the malicious and benign classes independently and are unaffected by any bias in the data. The proposed approach is based on a novel machine learning framework, called Conformal Prediction, combined with a random forests classifier. We examine its performance on a large-scale dataset collected by installing 1866 malicious and 4816 benign applications on a real android device. We make this collection of dynamic analysis data available to the research community. The obtained experimental results demonstrate the empirical validity, usefulness and unbiased nature of the outputs produced by the proposed approach.
Authors: Jiachuan Wang, Shimin Di, Lei Chen, Charles Wang Wai Ng
In the past 20 years, artificial neural networks have become dominant in various areas, continually growing in scale. However, the current analysis of large models has mainly focused on functionality, overlooking the influence of scale differences on their properties. To address this, we propose the concept of Emergence Learning, which emphasizes the significance of scale. By studying models of different scales, we have identified a key factor in achieving higher performance in large models: the decrease of monosemantic neurons. Building on this insight, we propose a proactive approach to inhibit monosemanticity for improved performance. Our solution involves a two-phase process that includes monosemantic neuron detection and inhibition, supported by theoretical analysis. Experimental results on various tasks and neural networks demonstrate the effectiveness of our proposed method.
Following the idea of Emergence Learning, though drawing inspiration from scaling phenomena, the applicability of our method is not restricted to large scale alone. Therefore, the experiment is self-contained. However, extending this research to very large-scale datasets is appealing yet impossible for research departments due to limited resources. We are delighted to share the first co-authorship and eagerly await collaboration from any AI company before submission.
Authors: Aryan Tyagi, Aryaman Rao, Shubhanshu Rao, Raj Kumar Singh
Chronic Obstructive Pulmonary Disorder (COPD) is a prevalent respiratory disease that significantly impacts the quality of life of affected individuals. This paper presents COPDFlowNet, a novel deep-learning framework that leverages a custom Generative Adversarial Network (GAN) to generate synthetic Computational Fluid Dynamics (CFD) velocity flow field images specific to the trachea of COPD patients. These synthetic images serve as a valuable resource for data augmentation and model training. Additionally, COPDFlowNet incorporates a custom Convolutional Neural Network (CNN) architecture to predict the location of the obstruction site.
Authors: Jiankai Sun, Chuanyang Zheng, Enze Xie, Zhengying Liu, Ruihang Chu, Jianing Qiu, Jiaqi Xu, Mingyu Ding, Hongyang Li, Mengzhe Geng, Yue Wu, Wenhai Wang, Junsong Chen, Zhangyue Yin, Xiaozhe Ren, Jie Fu, Junxian He, Wu Yuan, Qi Liu, Xihui Liu, Yu Li, Hao Dong, Yu Cheng, Ming Zhang, Pheng Ann Heng, Jifeng Dai, Ping Luo, Jingdong Wang, Ji-Rong Wen, Xipeng Qiu, Yike Guo, Hui Xiong, Qun Liu, Zhenguo Li
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation. It serves as a fundamental methodology in the field of Artificial General Intelligence (AGI). With the ongoing development of foundation models, there is a growing interest in exploring their abilities in reasoning tasks. In this paper, we introduce seminal foundation models proposed or adaptable for reasoning, highlighting the latest advancements in various reasoning tasks, methods, and benchmarks. We then delve into the potential future directions behind the emergence of reasoning abilities within foundation models. We also discuss the relevance of multimodal learning, autonomous agents, and super alignment in the context of reasoning. By discussing these future research directions, we hope to inspire researchers in their exploration of this field, stimulate further advancements in reasoning with foundation models, and contribute to the development of AGI.
Authors: Md. Jalal Uddin Chowdhury, Ashab Hussan
This research paper presents a comprehensive review-based study on various Text-to-Speech (TTS) technologies. TTS technology is an important aspect of human-computer interaction, enabling machines to convert written text into audible speech. The paper examines the different TTS technologies available, including concatenative TTS, formant synthesis TTS, and statistical parametric TTS. The study focuses on comparing the advantages and limitations of these technologies in terms of their naturalness of voice, the level of complexity of the system, and their suitability for different applications. In addition, the paper explores the latest advancements in TTS technology, including neural TTS and hybrid TTS. The findings of this research will provide valuable insights for researchers, developers, and users who want to understand the different TTS technologies and their suitability for specific applications.
Authors: Olamide Oladeji, Seyed Shahabeddin Mousavi
AI has been proposed as an important tool to support several efforts related to nature-based climate solutions such as the detection of wildfires that affect forests and vegetation-based offsets. While this and other use-cases provide important demonstrative value of the power of AI in climate change mitigation, such efforts have typically been undertaken in silos, without awareness of the integrative nature of real-world climate policy-making. In this paper, we propose a novel overarching framework for AI-aided integrated and comprehensive decision support for various aspects of nature-based climate decision-making. Focusing on vegetation-based solutions such as forests, we demonstrate how different AI-aided decision support models such as AI-aided wildfire detection, AI-aided vegetation carbon stock assessment, reversal risk mitigation, and disaster response planning can be integrated into a comprehensive framework. Rather than being disparate elements, we posit that the exchange of data and analytical results across elements of the framework, and careful mitigation of uncertainty propagation will provide tremendous value relative to the status-quo for real-world climate policy-making.
Authors: Zhihao Zhu, Rui Fan, Chenwang Wu, Yi Yang, Defu Lian, Enhong Chen
Recent studies have demonstrated the vulnerability of recommender systems to data privacy attacks. However, research on the threat to model privacy in recommender systems, such as model stealing attacks, is still in its infancy. Some adversarial attacks have achieved model stealing attacks against recommender systems, to some extent, by collecting abundant training data of the target model (target data) or making a mass of queries. In this paper, we constrain the volume of available target data and queries and utilize auxiliary data, which shares the item set with the target data, to promote model stealing attacks. Although the target model treats target and auxiliary data differently, their similar behavior patterns allow them to be fused using an attention mechanism to assist attacks. Besides, we design stealing functions to effectively extract the recommendation list obtained by querying the target model. Experimental results show that the proposed methods are applicable to most recommender systems and various scenarios and exhibit excellent attack performance on multiple datasets.
The most successful multi-domain text classification (MDTC) approaches employ the shared-private paradigm to facilitate the enhancement of domain-invariant features through domain-specific attributes. Additionally, they employ adversarial training to align marginal feature distributions. Nevertheless, these methodologies encounter two primary challenges: (1) Neglecting class-aware information during adversarial alignment poses a risk of misalignment; (2) The limited availability of labeled data across multiple domains fails to ensure adequate discriminative capacity for the model. To tackle these issues, we propose a method called Regularized Conditional Alignment (RCA) to align the joint distributions of domains and classes, thus matching features within the same category and amplifying the discriminative qualities of acquired features. Moreover, we employ entropy minimization and virtual adversarial training to constrain the uncertainty of predictions pertaining to unlabeled data and enhance the model's robustness. Empirical results on two benchmark datasets demonstrate that our RCA approach outperforms state-of-the-art MDTC techniques.
Authors: Abhinav Thorat, Ravi Kolla, Niranjan Pedanekar, Naoyuki Onoe
We study the problem of estimation of Individual Treatment Effects (ITE) in the context of multiple treatments and networked observational data. Leveraging the network information, we aim to utilize hidden confounders that may not be directly accessible in the observed data, thereby enhancing the practical applicability of the strong ignorability assumption. To achieve this, we first employ Graph Convolutional Networks (GCN) to learn a shared representation of the confounders. Then, our approach utilizes separate neural networks to infer potential outcomes for each treatment. We design a loss function as a weighted combination of two components: representation loss and Mean Squared Error (MSE) loss on the factual outcomes. To measure the representation loss, we extend existing metrics such as Wasserstein and Maximum Mean Discrepancy (MMD) from the binary treatment setting to the multiple treatments scenario. To validate the effectiveness of our proposed methodology, we conduct a series of experiments on the benchmark datasets such as BlogCatalog and Flickr. The experimental results consistently demonstrate the superior performance of our models when compared to baseline methods.
Authors: Rob Romijnders, Christos Louizos, Yuki M. Asano, Max Welling
The pandemic in 2020 and 2021 had enormous economic and societal consequences, and studies show that contact tracing algorithms can be key in the early containment of the virus. While large strides have been made towards more effective contact tracing algorithms, we argue that privacy concerns currently hold deployment back. The essence of a contact tracing algorithm constitutes the communication of a risk score. Yet, it is precisely the communication and release of this score to a user that an adversary can leverage to gauge the private health status of an individual. We pinpoint a realistic attack scenario and propose a contact tracing algorithm with differential privacy guarantees against this attack. The algorithm is tested on the two most widely used agent-based COVID19 simulators and demonstrates superior performance in a wide range of settings. Especially for realistic test scenarios and while releasing each risk score with epsilon=1 differential privacy, we achieve a two to ten-fold reduction in the infection rate of the virus. To the best of our knowledge, this presents the first contact tracing algorithm with differential privacy guarantees when revealing risk scores for COVID19.
Authors: Fabrizio Russo, Francesca Toni
Causal Structure Learning (CSL), amounting to extracting causal relations among the variables in a dataset, is widely perceived as an important step towards robust and transparent models. Constraint-based CSL leverages conditional independence tests to perform causal discovery. We propose Shapley-PC, a novel method to improve constraint-based CSL algorithms by using Shapley values over the possible conditioning sets to decide which variables are responsible for the observed conditional (in)dependences. We prove soundness and asymptotic consistency and demonstrate that it can outperform state-of-the-art constraint-based, search-based and functional causal model-based methods, according to standard metrics in CSL.
Authors: Chengyuan Zhu, Yiyuan Yang, Kaixiang Yang, Haifeng Zhang, Qinmin Yang, C. L. Philip Chen
The application of artificial intelligence technology has greatly enhanced and fortified the safety of energy pipelines, particularly in safeguarding against external threats. The predominant methods involve the integration of intelligent sensors to detect external vibration, enabling the identification of event types and locations, thereby replacing manual detection methods. However, practical implementation has exposed a limitation in current methods - their constrained ability to accurately discern the spatial dimensions of external signals, which complicates the authentication of threat events. Our research endeavors to overcome the above issues by harnessing deep learning techniques to achieve a more fine-grained recognition and localization process. This refinement is crucial in effectively identifying genuine threats to pipelines, thus enhancing the safety of energy transportation. This paper proposes a radial threat estimation method for energy pipelines based on distributed optical fiber sensing technology. Specifically, we introduce a continuous multi-view and multi-domain feature fusion methodology to extract comprehensive signal features and construct a threat estimation and recognition network. The utilization of collected acoustic signal data is optimized, and the underlying principle is elucidated. Moreover, we incorporate the concept of transfer learning through a pre-trained model, enhancing both recognition accuracy and training efficiency. Empirical evidence gathered from real-world scenarios underscores the efficacy of our method, notably in its substantial reduction of false alarms and remarkable gains in recognition accuracy. More generally, our method exhibits versatility and can be extrapolated to a broader spectrum of recognition tasks and scenarios.
Authors: Zhi Jin, Sheng Xu, Xiang Zhang, Tianze Ling, Nanqing Dong, Wanli Ouyang, Zhiqiang Gao, Cheng Chang, Siqi Sun
De novo peptide sequencing from mass spectrometry (MS) data is a critical task in proteomics research. Traditional de novo algorithms have encountered a bottleneck in accuracy due to the inherent complexity of proteomics data. While deep learning-based methods have shown progress, they reduce the problem to a translation task, potentially overlooking critical nuances between spectra and peptides. In our research, we present ContraNovo, a pioneering algorithm that leverages contrastive learning to extract the relationship between spectra and peptides and incorporates the mass information into peptide decoding, aiming to address these intricacies more efficiently. Through rigorous evaluations on two benchmark datasets, ContraNovo consistently outshines contemporary state-of-the-art solutions, underscoring its promising potential in enhancing de novo peptide sequencing. The source code is available at https://github.com/BEAM-Labs/ContraNovo.
Authors: Zhixuan Liang, Yao Mu, Hengbo Ma, Masayoshi Tomizuka, Mingyu Ding, Ping Luo
Diffusion models have demonstrated strong potential for robotic trajectory planning. However, generating coherent and long-horizon trajectories from high-level instructions remains challenging, especially for complex tasks requiring multiple sequential skills. We propose SkillDiffuser, an end-to-end hierarchical planning framework integrating interpretable skill learning with conditional diffusion planning to address this problem. At the higher level, the skill abstraction module learns discrete, human-understandable skill representations from visual observations and language instructions. These learned skill embeddings are then used to condition the diffusion model to generate customized latent trajectories aligned with the skills. It allows for generating diverse state trajectories that adhere to the learnable skills. By integrating skill learning with conditional trajectory generation, SkillDiffuser produces coherent behavior following abstract instructions across diverse tasks. Experiments on multi-task robotic manipulation benchmarks like Meta-World and LOReL demonstrate state-of-the-art performance and human-interpretable skill representations from SkillDiffuser.
Authors: Ranit Das, Gregor Kasieczka, David Shih
We present R-ANODE, a new method for data-driven, model-agnostic resonant anomaly detection that raises the bar for both performance and interpretability. The key to R-ANODE is to enhance the inductive bias of the anomaly detection task by fitting a normalizing flow directly to the small and unknown signal component, while holding fixed a background model (also a normalizing flow) learned from sidebands. In doing so, R-ANODE is able to outperform all classifier-based, weakly-supervised approaches, as well as the previous ANODE method which fit a density estimator to all of the data in the signal region instead of just the signal. We show that the method works equally well whether the unknown signal fraction is learned or fixed, and is even robust to signal fraction misspecification. Finally, with the learned signal model we can sample and gain qualitative insights into the underlying anomaly, which greatly enhances the interpretability of resonant anomaly detection and offers the possibility of simultaneously discovering and characterizing the new physics that could be hiding in the data.
Authors: Anne-Marie George, Christos Dimitrakakis
We formulate the problem of eliciting agents' preferences with the goal of finding a Kemeny ranking as a Dueling Bandits problem. Here the bandits' arms correspond to alternatives that need to be ranked and the feedback corresponds to a pairwise comparison between alternatives by a randomly sampled agent. We consider both sampling with and without replacement, i.e., the possibility to ask the same agent about some comparison multiple times or not.
We find approximation bounds for Kemeny rankings dependant on confidence intervals over estimated winning probabilities of arms. Based on these we state algorithms to find Probably Approximately Correct (PAC) solutions and elaborate on their sample complexity for sampling with or without replacement. Furthermore, if all agents' preferences are strict rankings over the alternatives, we provide means to prune confidence intervals and thereby guide a more efficient elicitation. We formulate several adaptive sampling methods that use look-aheads to estimate how much confidence intervals (and thus approximation guarantees) might be tightened. All described methods are compared on synthetic data.
Authors: Nishanth Anand, Doina Precup
Temporal difference (TD) learning is often used to update the estimate of the value function which is used by RL agents to extract useful policies. In this paper, we focus on value function estimation in continual reinforcement learning. We propose to decompose the value function into two components which update at different timescales: a permanent value function, which holds general knowledge that persists over time, and a transient value function, which allows quick adaptation to new situations. We establish theoretical results showing that our approach is well suited for continual learning and draw connections to the complementary learning systems (CLS) theory from neuroscience. Empirically, this approach improves performance significantly on both prediction and control problems.
Authors: Megan Kinniment, Lucas Jun Koba Sato, Haoxing Du, Brian Goodrich, Max Hasin, Lawrence Chan, Luke Harold Miles, Tao R. Lin, Hjalmar Wijk, Joel Burget, Aaron Ho, Elizabeth Barnes, Paul Christiano
In this report, we explore the ability of language model agents to acquire resources, create copies of themselves, and adapt to novel challenges they encounter in the wild. We refer to this cluster of capabilities as "autonomous replication and adaptation" or ARA. We believe that systems capable of ARA could have wide-reaching and hard-to-anticipate consequences, and that measuring and forecasting ARA may be useful for informing measures around security, monitoring, and alignment. Additionally, once a system is capable of ARA, placing bounds on a system's capabilities may become significantly more difficult.
We construct four simple example agents that combine language models with tools that allow them to take actions in the world. We then evaluate these agents on 12 tasks relevant to ARA. We find that these language model agents can only complete the easiest tasks from this list, although they make some progress on the more challenging tasks. Unfortunately, these evaluations are not adequate to rule out the possibility that near-future agents will be capable of ARA. In particular, we do not think that these evaluations provide good assurance that the ``next generation'' of language models (e.g. 100x effective compute scaleup on existing models) will not yield agents capable of ARA, unless intermediate evaluations are performed during pretraining. Relatedly, we expect that fine-tuning of the existing models could produce substantially more competent agents, even if the fine-tuning is not directly targeted at ARA.
Authors: Charles Rajan, Nishit Asnani, Shreya Singh
Multi-document summarization is the process of automatically generating a concise summary of multiple documents related to the same topic. This summary can help users quickly understand the key information from a large collection of documents. Multi-document summarization systems are more complex than single-document summarization systems due to the need to identify and combine information from multiple sources. In this paper, we have developed a machine learning model that generates a concise summary of a topic from multiple news documents. The model is designed to be unbiased by sampling its input equally from all the different aspects of the topic, even if the majority of the news sources lean one way.
Authors: Yesukhei Jagvaral, Francois Lanusse, Rachel Mandelbaum
Diffusion-based generative models represent the current state-of-the-art for image generation. However, standard diffusion models are based on Euclidean geometry and do not translate directly to manifold-valued data. In this work, we develop extensions of both score-based generative models (SGMs) and Denoising Diffusion Probabilistic Models (DDPMs) to the Lie group of 3D rotations, SO(3). SO(3) is of particular interest in many disciplines such as robotics, biochemistry and astronomy/cosmology science. Contrary to more general Riemannian manifolds, SO(3) admits a tractable solution to heat diffusion, and allows us to implement efficient training of diffusion models. We apply both SO(3) DDPMs and SGMs to synthetic densities on SO(3) and demonstrate state-of-the-art results. Additionally, we demonstrate the practicality of our model on pose estimation tasks and in predicting correlated galaxy orientations for astrophysics/cosmology.
Authors: Kyle Noordhoek, Christopher J. Bartel
The surface properties of solid-state materials often dictate their functionality, especially for applications where nanoscale effects become important. The relevant surface(s) and their properties are determined, in large part, by the materials synthesis or operating conditions. These conditions dictate thermodynamic driving forces and kinetic rates responsible for yielding the observed surface structure and morphology. Computational surface science methods have long been applied to connect thermochemical conditions to surface phase stability, particularly in the heterogeneous catalysis and thin film growth communities. This review provides a brief introduction to first-principles approaches to compute surface phase diagrams before introducing emerging data-driven approaches. The remainder of the review focuses on the application of machine learning, predominantly in the form of learned interatomic potentials, to study complex surfaces. As machine learning algorithms and large datasets on which to train them become more commonplace in materials science, computational methods are poised to become even more predictive and powerful for modeling the complexities of inorganic surfaces at the nanoscale.
Authors: Lucas Rosenblatt, Julia Stoyanovich, Christopher Musco
Differentially private (DP) mechanisms have been deployed in a variety of high-impact social settings (perhaps most notably by the U.S. Census). Since all DP mechanisms involve adding noise to results of statistical queries, they are expected to impact our ability to accurately analyze and learn from data, in effect trading off privacy with utility. Alarmingly, the impact of DP on utility can vary significantly among different sub-populations. A simple way to reduce this disparity is with stratification. First compute an independent private estimate for each group in the data set (which may be the intersection of several protected classes), then, to compute estimates of global statistics, appropriately recombine these group estimates. Our main observation is that naive stratification often yields high-accuracy estimates of population-level statistics, without the need for additional privacy budget. We support this observation theoretically and empirically. Our theoretical results center on the private mean estimation problem, while our empirical results center on extensive experiments on private data synthesis to demonstrate the effectiveness of stratification on a variety of private mechanisms. Overall, we argue that this straightforward approach provides a strong baseline against which future work on reducing utility disparities of DP mechanisms should be compared.
Authors: Yuansan Liu, Sudanthi Wijewickrema, Ang Li, Christofer Bester, Stephen O'Leary, James Bailey
Generating time series data is a promising approach to address data deficiency problems. However, it is also challenging due to the complex temporal properties of time series data, including local correlations as well as global dependencies. Most existing generative models have failed to effectively learn both the local and global properties of time series data. To address this open problem, we propose a novel time series generative model named 'Time-Transformer AAE', which consists of an adversarial autoencoder (AAE) and a newly designed architecture named 'Time-Transformer' within the decoder. The Time-Transformer first simultaneously learns local and global features in a layer-wise parallel design, combining the abilities of Temporal Convolutional Networks and Transformer in extracting local features and global dependencies respectively. Second, a bidirectional cross attention is proposed to provide complementary guidance across the two branches and achieve proper fusion between local and global features. Experimental results demonstrate that our model can outperform existing state-of-the-art models in 5 out of 6 datasets, specifically on those with data containing both global and local properties. Furthermore, we highlight our model's advantage on handling this kind of data via an artificial dataset. Finally, we show our model's ability to address a real-world problem: data augmentation to support learning with small datasets and imbalanced datasets.
Authors: Laila El Moujtahid, Sai Krishna Gottipati, Clodéric Mars, Matthew E. Taylor
Full automation is often not achievable or desirable in critical systems with high-stakes decisions. Instead, human-AI teams can achieve better results. To research, develop, evaluate, and validate algorithms suited for such teaming, lightweight experimentation platforms that enable interactions between humans and multiple AI agents are necessary. However, there are limited examples of such platforms for defense environments. To address this gap, we present the Cogment human-machine teaming experimentation platform, which implements human-machine teaming (HMT) use cases that features heterogeneous multi-agent systems and can involve learning AI agents, static AI agents, and humans. It is built on the Cogment platform and has been used for academic research, including work presented at the ALA workshop at AAMAS this year [1]. With this platform, we hope to facilitate further research on human-machine teaming in critical systems and defense environments.
Authors: Eugene Ku, Swetha Arunraj
Graph Neural Networks are notorious for its memory consumption. A recent Transformer based GNN called Graph Transformer are shown to obtain superior performances when long range dependencies exist. However, combining graph data and Transformer architecture led to a combinationally worse memory issue. We propose a novel version of "edge regularization technique" that alleviates the need for Positional Encoding and ultimately alleviate GT's out of memory issue. We observe that it is not clear whether having an edge regularization on top of positional encoding is helpful. However, it seems evident when no positional encoding is applied, edge regularization technique indeed stably improves GT's performance.
Authors: David D. Nguyen, David Liebowitz, Surya Nepal, Salil S. Kanhere
In many real-world applications, from robotics to pedestrian trajectory prediction, there is a need to predict multiple real-valued outputs to represent several potential scenarios. Current deep learning techniques to address multiple-output problems are based on two main methodologies: (1) mixture density networks, which suffer from poor stability at high dimensions, or (2) multiple choice learning (MCL), an approach that uses $M$ single-output functions, each only producing a point estimate hypothesis. This paper presents a Mixture of Multiple-Output functions (MoM) approach using a novel variant of dropout, Multiple Hypothesis Dropout. Unlike traditional MCL-based approaches, each multiple-output function not only estimates the mean but also the variance for its hypothesis. This is achieved through a novel stochastic winner-take-all loss which allows each multiple-output function to estimate variance through the spread of its subnetwork predictions. Experiments on supervised learning problems illustrate that our approach outperforms existing solutions for reconstructing multimodal output distributions. Additional studies on unsupervised learning problems show that estimating the parameters of latent posterior distributions within a discrete autoencoder significantly improves codebook efficiency, sample quality, precision and recall.
Authors: Zhenhao He, Dario Korolija, Yu Zhu, Benjamin Ramhorst, Tristan Laan, Lucian Petrica, Michaela Blott, Gustavo Alonso
FPGAs are increasingly prevalent in cloud deployments, serving as Smart NICs or network-attached accelerators. Despite their potential, developing distributed FPGA-accelerated applications remains cumbersome due to the lack of appropriate infrastructure and communication abstractions. To facilitate the development of distributed applications with FPGAs, in this paper we propose ACCL+, an open-source versatile FPGA-based collective communication library. Portable across different platforms and supporting UDP, TCP, as well as RDMA, ACCL+ empowers FPGA applications to initiate direct FPGA-to-FPGA collective communication. Additionally, it can serve as a collective offload engine for CPU applications, freeing the CPU from networking tasks. It is user-extensible, allowing new collectives to be implemented and deployed without having to re-synthesize the FPGA circuit. We evaluated ACCL+ on an FPGA cluster with 100 Gb/s networking, comparing its performance against software MPI over RDMA. The results demonstrate ACCL+'s significant advantages for FPGA-based distributed applications and highly competitive performance for CPU applications. We showcase ACCL+'s dual role with two use cases: seamlessly integrating as a collective offload engine to distribute CPU-based vector-matrix multiplication, and serving as a crucial and efficient component in designing fully FPGA-based distributed deep-learning recommendation inference.
Authors: Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo
Counterfactual Explanation (CE) techniques have garnered attention as a means to provide insights to the users engaging with AI systems. While extensively researched in domains such as medical imaging and autonomous vehicles, Graph Counterfactual Explanation (GCE) methods have been comparatively under-explored. GCEs generate a new graph similar to the original one, with a different outcome grounded on the underlying predictive model. Among these GCE techniques, those rooted in generative mechanisms have received relatively limited investigation despite demonstrating impressive accomplishments in other domains, such as artistic styles and natural language modelling. The preference for generative explainers stems from their capacity to generate counterfactual instances during inference, leveraging autonomously acquired perturbations of the input graph. Motivated by the rationales above, our study introduces RSGG-CE, a novel Robust Stochastic Graph Generator for Counterfactual Explanations able to produce counterfactual examples from the learned latent space considering a partially ordered generation sequence. Furthermore, we undertake quantitative and qualitative analyses to compare RSGG-CE's performance against SoA generative explainers, highlighting its increased ability to engendering plausible counterfactual candidates.
Authors: Michael Psenka, Alejandro Escontrela, Pieter Abbeel, Yi Ma
Diffusion models have become a popular choice for representing actor policies in behavior cloning and offline reinforcement learning. This is due to their natural ability to optimize an expressive class of distributions over a continuous space. However, previous works fail to exploit the score-based structure of diffusion models, and instead utilize a simple behavior cloning term to train the actor, limiting their ability in the actor-critic setting. In this paper, we focus on off-policy reinforcement learning and propose a new method for learning a diffusion model policy that exploits the linked structure between the score of the policy and the action gradient of the Q-function. We denote this method Q-score matching and provide theoretical justification for this approach. We conduct experiments in simulated environments to demonstrate the effectiveness of our proposed method and compare to popular baselines.
Authors: Gabriel Agostini, Emma Pierson, Nikhil Garg
Decision-makers often observe the occurrence of events through a reporting process. City governments, for example, rely on resident reports to find and then resolve urban infrastructural problems such as fallen street trees, flooded basements, or rat infestations. Without additional assumptions, there is no way to distinguish events that occur but are not reported from events that truly did not occur--a fundamental problem in settings with positive-unlabeled data. Because disparities in reporting rates correlate with resident demographics, addressing incidents only on the basis of reports leads to systematic neglect in neighborhoods that are less likely to report events. We show how to overcome this challenge by leveraging the fact that events are spatially correlated. Our framework uses a Bayesian spatial latent variable model to infer event occurrence probabilities and applies it to storm-induced flooding reports in New York City, further pooling results across multiple storms. We show that a model accounting for under-reporting and spatial correlation predicts future reports more accurately than other models, and further induces a more equitable set of inspections: its allocations better reflect the population and provide equitable service to non-white, less traditionally educated, and lower-income residents. This finding reflects heterogeneous reporting behavior learned by the model: reporting rates are higher in Census tracts with higher populations, proportions of white residents, and proportions of owner-occupied households. Our work lays the groundwork for more equitable proactive government services, even with disparate reporting behavior.
Authors: Rupali Bhati, Sai Krishna Gottipati, Clodéric Mars, Matthew E. Taylor
While there has been significant progress in curriculum learning and continuous learning for training agents to generalize across a wide variety of environments in the context of single-agent reinforcement learning, it is unclear if these algorithms would still be valid in a multi-agent setting. In a competitive setting, a learning agent can be trained by making it compete with a curriculum of increasingly skilled opponents. However, a general intelligent agent should also be able to learn to act around other agents and cooperate with them to achieve common goals. When cooperating with other agents, the learning agent must (a) learn how to perform the task (or subtask), and (b) increase the overall team reward. In this paper, we aim to answer the question of what kind of cooperative teammate, and a curriculum of teammates should a learning agent be trained with to achieve these two objectives. Our results on the game Overcooked show that a pre-trained teammate who is less skilled is the best teammate for overall team reward but the worst for the learning of the agent. Moreover, somewhat surprisingly, a curriculum of teammates with decreasing skill levels performs better than other types of curricula.
Authors: Ilias Diakonikolas, Daniel M. Kane, Jasper C. H. Lee, Thanasis Pittas
We study the clustering problem for mixtures of bounded covariance distributions, under a fine-grained separation assumption. Specifically, given samples from a $k$-component mixture distribution $D = \sum_{i =1}^k w_i P_i$, where each $w_i \ge \alpha$ for some known parameter $\alpha$, and each $P_i$ has unknown covariance $\Sigma_i \preceq \sigma^2_i \cdot I_d$ for some unknown $\sigma_i$, the goal is to cluster the samples assuming a pairwise mean separation in the order of $(\sigma_i+\sigma_j)/\sqrt{\alpha}$ between every pair of components $P_i$ and $P_j$. Our contributions are as follows:
For the special case of nearly uniform mixtures, we give the first poly-time algorithm for this clustering task. Prior work either required separation scaling with the maximum cluster standard deviation (i.e. $\max_i \sigma_i$) [DKK+22b] or required both additional structural assumptions and mean separation scaling as a large degree polynomial in $1/\alpha$ [BKK22].
For general-weight mixtures, we point out that accurate clustering is information-theoretically impossible under our fine-grained mean separation assumptions. We introduce the notion of a clustering refinement -- a list of not-too-small subsets satisfying a similar separation, and which can be merged into a clustering approximating the ground truth -- and show that it is possible to efficiently compute an accurate clustering refinement of the samples. Furthermore, under a variant of the "no large sub-cluster'' condition from in prior work [BKK22], we show that our algorithm outputs an accurate clustering, not just a refinement, even for general-weight mixtures. As a corollary, we obtain efficient clustering algorithms for mixtures of well-conditioned high-dimensional log-concave distributions.
Moreover, our algorithm is robust to $\Omega(\alpha)$-fraction of adversarial outliers.
Authors: Anaelia Ovalle, Ninareh Mehrabi, Palash Goyal, Jwala Dhamala, Kai-Wei Chang, Richard Zemel, Aram Galstyan, Yuval Pinter, Rahul Gupta
A large body of NLP research has documented the ways gender biases manifest and amplify within large language models (LLMs), though this research has predominantly operated within a gender binary-centric context. A growing body of work has identified the harmful limitations of this gender-exclusive framing; many LLMs cannot correctly and consistently refer to persons outside the gender binary, especially if they use neopronouns. While data scarcity has been identified as a possible culprit, the precise mechanisms through which it influences LLM misgendering remain underexplored. Our work addresses this gap by studying data scarcity's role in subword tokenization and, consequently, the formation of LLM word representations. We uncover how the Byte-Pair Encoding (BPE) tokenizer, a backbone for many popular LLMs, contributes to neopronoun misgendering through out-of-vocabulary behavior. We introduce pronoun tokenization parity (PTP), a novel approach to reduce LLM neopronoun misgendering by preserving a token's functional structure. We evaluate PTP's efficacy using pronoun consistency-based metrics and a novel syntax-based metric. Through several controlled experiments, finetuning LLMs with PTP improves neopronoun consistency from 14.5% to 58.4%, highlighting the significant role tokenization plays in LLM pronoun consistency.
Authors: Aadirupa Saha, Vitaly Feldman, Tomer Koren, Yishay Mansour
We address the problem of convex optimization with preference feedback, where the goal is to minimize a convex function given a weaker form of comparison queries. Each query consists of two points and the dueling feedback returns a (noisy) single-bit binary comparison of the function values of the two queried points. Here we consider the sign-function-based comparison feedback model and analyze the convergence rates with batched and multiway (argmin of a set queried points) comparisons. Our main goal is to understand the improved convergence rates owing to parallelization in sign-feedback-based optimization problems. Our work is the first to study the problem of convex optimization with multiway preferences and analyze the optimal convergence rates. Our first contribution lies in designing efficient algorithms with a convergence rate of $\smash{\widetilde O}(\frac{d}{\min\{m,d\} \epsilon})$ for $m$-batched preference feedback where the learner can query $m$-pairs in parallel. We next study a $m$-multiway comparison (`battling') feedback, where the learner can get to see the argmin feedback of $m$-subset of queried points and show a convergence rate of $\smash{\widetilde O}(\frac{d}{ \min\{\log m,d\}\epsilon })$. We show further improved convergence rates with an additional assumption of strong convexity. Finally, we also study the convergence lower bounds for batched preferences and multiway feedback optimization showing the optimality of our convergence rates w.r.t. $m$.
Authors: Min Dai, Yuchao Dong, Yanwei Jia, Xun Yu Zhou
We study Merton's expected utility maximization problem in an incomplete market, characterized by a factor process in addition to the stock price process, where all the model primitives are unknown. We take the reinforcement learning (RL) approach to learn optimal portfolio policies directly by exploring the unknown market, without attempting to estimate the model parameters. Based on the entropy-regularization framework for general continuous-time RL formulated in Wang et al. (2020), we propose a recursive weighting scheme on exploration that endogenously discounts the current exploration reward by the past accumulative amount of exploration. Such a recursive regularization restores the optimality of Gaussian exploration. However, contrary to the existing results, the optimal Gaussian policy turns out to be biased in general, due to the interwinding needs for hedging and for exploration. We present an asymptotic analysis of the resulting errors to show how the level of exploration affects the learned policies. Furthermore, we establish a policy improvement theorem and design several RL algorithms to learn Merton's optimal strategies. At last, we carry out both simulation and empirical studies with a stochastic volatility environment to demonstrate the efficiency and robustness of the RL algorithms in comparison to the conventional plug-in method.
Authors: Rico Angell, Andrew McCallum
While semidefinite programming (SDP) has traditionally been limited to moderate-sized problems, recent algorithms augmented with matrix sketching techniques have enabled solving larger SDPs. However, these methods achieve scalability at the cost of an increase in the number of necessary iterations, resulting in slower convergence as the problem size grows. Furthermore, they require iteration-dependent parameter schedules that prohibit effective utilization of warm-start initializations important in practical applications with incrementally-arriving data or mixed-integer programming. We present SpecBM, a provably correct, fast and scalable algorithm for solving massive SDPs that can leverage a warm-start initialization to further accelerate convergence. Our proposed algorithm is a spectral bundle method for solving general SDPs containing both equality and inequality constraints. Moveover, when augmented with an optional matrix sketching technique, our algorithm achieves the dramatically improved scalability of previous work while sustaining convergence speed. We empirically demonstrate the effectiveness of our method, both with and without warm-starting, across multiple applications with large instances. For example, on a problem with 600 million decision variables, SpecBM achieved a solution of standard accuracy in less than 7 minutes, where the previous state-of-the-art scalable SDP solver requires more than 16 hours. Our method solves an SDP with more than 10^13 decision variables on a single machine with 16 cores and no more than 128GB RAM; the previous state-of-the-art method had not achieved an accurate solution after 72 hours on the same instance. We make our implementation in pure JAX publicly available.
Authors: Phuoc Nguyen, Truyen Tran, Sunil Gupta, Thin Nguyen, Svetha Venkatesh
Identifying root causes of anomalies in causal processes is vital across disciplines. Once identified, one can isolate the root causes and implement necessary measures to restore the normal operation. Causal processes are often modelled as graphs with entities being nodes and their paths/interconnections as edge. Existing work only consider the contribution of nodes in the generative process, thus can not attribute the outlier score to the edges of the mechanism if the anomaly occurs in the connections. In this paper, we consider both individual edge and node of each mechanism when identifying the root causes. We introduce a noisy functional causal model to account for this purpose. Then, we employ Bayesian learning and inference methods to infer the noises of the nodes and edges. We then represent the functional form of a target outlier leaf as a function of the node and edge noises. Finally, we propose an efficient gradient-based attribution method to compute the anomaly attribution scores which scales linearly with the number of nodes and edges. Experiments on simulated datasets and two real-world scenario datasets show better anomaly attribution performance of the proposed method compared to the baselines. Our method scales to larger graphs with more nodes and edges.
Authors: Youshao Xiao, Weichang Wu, Zhenglei Zhou, Fagui Mao, Shangchun Zhao, Lin Ju, Lei Liang, Xiaolu Zhang, Jun Zhou
Recently, ChatGPT or InstructGPT like large language models (LLM) has made a significant impact in the AI world. These models are incredibly versatile, capable of performing language tasks on par or even exceeding the capabilities of human experts. Many works have attempted to reproduce the complex InstructGPT's RLHF (Reinforcement Learning with Human Feedback) training pipeline. However, the mainstream distributed RLHF training methods typically adopt a fixed model placement strategy, referred to as the Flattening strategy. This strategy treats all four models involved in RLHF as a single entity and places them on all devices, regardless of their differences. Unfortunately, this strategy exacerbates the generation bottlenecks in the RLHF training and degrades the overall training efficiency. To address these issues, we propose an adaptive model placement framework that offers two flexible model placement strategies. These strategies allow for the agile allocation of models across devices in a fine-grained manner. The Interleaving strategy helps reduce memory redundancy and communication costs during RLHF training. On the other hand, the Separation strategy improves the throughput of model training by separating the training and generation stages of the RLHF pipeline. Notably, this framework seamlessly integrates with other mainstream techniques for acceleration and enables automatic hyperparameter search. Extensive experiments have demonstrated that our Interleaving and Separation strategies can achieve notable improvements up to 11x, compared to the current state-of-the-art (SOTA) approaches. These experiments encompassed a wide range of training scenarios, involving models of varying sizes and devices of different scales. The results highlight the effectiveness and superiority of our approaches in accelerating the training of distributed RLHF.
Authors: Shih-Kuang (Alex)Lee, Sun-Ting Tsai, Sharon Glotzer
Detecting and analyzing the local environment is crucial for investigating the dynamical processes of crystal nucleation and shape colloidal particle self-assembly. Recent developments in machine learning provide a promising avenue for better order parameters in complex systems that are challenging to study using traditional approaches. However, the application of machine learning to self-assembly on systems of particle shapes is still underexplored. To address this gap, we propose a simple, physics-agnostic, yet powerful approach that involves training a multilayer perceptron (MLP) as a local environment classifier for systems of particle shapes, using input features such as particle distances and orientations. Our MLP classifier is trained in a supervised manner with a shape symmetry-encoded data augmentation technique without the need for any conventional roto-translations invariant symmetry functions. We evaluate the performance of our classifiers on four different scenarios involving self-assembly of cubic structures, 2-dimensional and 3-dimensional patchy particle shape systems, hexagonal bipyramids with varying aspect ratios, and truncated shapes with different degrees of truncation. The proposed training process and data augmentation technique are both straightforward and flexible, enabling easy application of the classifier to other processes involving particle orientations. Our work thus presents a valuable tool for investigating self-assembly processes on systems of particle shapes, with potential applications in structure identification of any particle-based or molecular system where orientations can be defined.
Authors: Yacine Izza, Kuldeep S. Meel, Joao Marques-Silva
Formal abductive explanations offer crucial guarantees of rigor and so are of interest in high-stakes uses of machine learning (ML). One drawback of abductive explanations is explanation size, justified by the cognitive limits of human decision-makers. Probabilistic abductive explanations (PAXps) address this limitation, but their theoretical and practical complexity makes their exact computation most often unrealistic. This paper proposes novel efficient algorithms for the computation of locally-minimal PXAps, which offer high-quality approximations of PXAps in practice. The experimental results demonstrate the practical efficiency of the proposed algorithms.
Authors: Zeinab Zakani, Hadi Moradi, Sogand Ghasemzadeh, Maryam Riazi, Fatemeh Mortazavi
Objective: Early identification of ADHD is necessary to provide the opportunity for timely treatment. However, screening the symptoms of ADHD on a large scale is not easy. This study aimed to validate a video game (FishFinder) for the screening of ADHD using objective measurement of the core symptoms of this disorder. Method: The FishFinder measures attention and impulsivity through in-game performance and evaluates the child's hyperactivity using smartphone motion sensors. This game was tested on 26 children with ADHD and 26 healthy children aged 5 to 12 years. A Support Vector Machine was employed to detect children with ADHD. results: This system showed 92.3% accuracy, 90% sensitivity, and 93.7% specificity using a combination of in-game and movement features. Conclusions: The FishFinder demonstrated a strong ability to identify ADHD in children. So, this game can be used as an affordable, accessible, and enjoyable method for the objective screening of ADHD.
Authors: Hisato Komatsu
In recent years, simulations of pedestrians using the multi-agent reinforcement learning (MARL) have been studied. This study considered the roads on a grid-world environment, and implemented pedestrians as MARL agents using an echo-state network and the least squares policy iteration method. Under this environment, the ability of these agents to learn to move forward by avoiding other agents was investigated. Specifically, we considered two types of tasks: the choice between a narrow direct route and a broad detour, and the bidirectional pedestrian flow in a corridor. The simulations results indicated that the learning was successful when the density of the agents was not that high.
Authors: Yang Jiao, Kai Yang, Tiancheng Wu, Chengtao Jian, Jianwei Huang
Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach; 2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes $\mu$-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed $\mu$-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the $\mu$-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain $\epsilon$-stationary point is upper bounded by $\mathcal{O}(\frac{1}{\epsilon^2})$. Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80$\%$.
Authors: Avinandan Bose, Mihaela Curmei, Daniel L. Jiang, Jamie Morgenstern, Sarah Dean, Lillian J.Ratliff, Maryam Fazel
This paper studies ML systems that interactively learn from users across multiple subpopulations with heterogeneous data distributions. The primary objective is to provide specialized services for different user groups while also predicting user preferences. Once the users select a service based on how well the service anticipated their preference, the services subsequently adapt and refine themselves based on the user data they accumulate, resulting in an iterative, alternating minimization process between users and services (learning dynamics). Employing such tailored approaches has two main challenges: (i) Unknown user preferences: Typically, data on user preferences are unavailable without interaction, and uniform data collection across a large and diverse user base can be prohibitively expensive. (ii) Suboptimal Local Solutions: The total loss (sum of loss functions across all users and all services) landscape is not convex even if the individual losses on a single service are convex, making it likely for the learning dynamics to get stuck in local minima. The final outcome of the aforementioned learning dynamics is thus strongly influenced by the initial set of services offered to users, and is not guaranteed to be close to the globally optimal outcome. In this work, we propose a randomized algorithm to adaptively select very few users to collect preference data from, while simultaneously initializing a set of services. We prove that under mild assumptions on the loss functions, the expected total loss achieved by the algorithm right after initialization is within a factor of the globally optimal total loss with complete user preference data, and this factor scales only logarithmically in the number of services. Our theory is complemented by experiments on real as well as semi-synthetic datasets.
Authors: Boshi Tang, Zhiyong Wu, Xixin Wu, Qiaochu Huang, Jun Chen, Shun Lei, Helen Meng
Graph neural networks (GNNs) have exhibited impressive performance in modeling graph data as exemplified in various applications. Recently, the GNN calibration problem has attracted increasing attention, especially in cost-sensitive scenarios. Previous work has gained empirical insights on the issue, and devised effective approaches for it, but theoretical supports still fall short. In this work, we shed light on the relationship between GNN calibration and nodewise similarity via theoretical analysis. A novel calibration framework, named SimCalib, is accordingly proposed to consider similarity between nodes at global and local levels. At the global level, the Mahalanobis distance between the current node and class prototypes is integrated to implicitly consider similarity between the current node and all nodes in the same class. At the local level, the similarity of node representation movement dynamics, quantified by nodewise homophily and relative degree, is considered. Informed about the application of nodewise movement patterns in analyzing nodewise behavior on the over-smoothing problem, we empirically present a possible relationship between over-smoothing and GNN calibration problem. Experimentally, we discover a correlation between nodewise similarity and model calibration improvement, in alignment with our theoretical results. Additionally, we conduct extensive experiments investigating different design factors and demonstrate the effectiveness of our proposed SimCalib framework for GNN calibration by achieving state-of-the-art performance on 14 out of 16 benchmarks.
Authors: Luyao Guo, Luqing Wang, Xinli Shi, Jinde Cao
Distributed optimization methods with probabilistic local updates have recently gained attention for their provable ability to communication acceleration. Nevertheless, this capability is effective only when the loss function is smooth and the network is sufficiently well-connected. In this paper, we propose the first linear convergent method MG-Skip with probabilistic local updates for nonsmooth distributed optimization. Without any extra condition for the network connectivity, MG-Skip allows for the multiple-round gossip communication to be skipped in most iterations, while its iteration complexity is $\mathcal{O}\left(\kappa \log \frac{1}{\epsilon}\right)$ and communication complexity is only $\mathcal{O}\left(\sqrt{\frac{\kappa}{(1-\rho)}} \log \frac{1}{\epsilon}\right)$, where $\kappa$ is the condition number of the loss function and $\rho$ reflects the connectivity of the network topology. To the best of our knowledge, MG-Skip achieves the best communication complexity when the loss function has the smooth (strongly convex)+nonsmooth (convex) composite form.
Authors: Karthikeyan Natesan Ramamurthy, Aldo Guzmán-Sáenz, Mustafa Hajij
Due to their ability to model meaningful higher order relations among a set of entities, higher order network models have emerged recently as a powerful alternative for graph-based network models which are only capable of modeling binary relationships. Message passing paradigm is still dominantly used to learn representations even for higher order network models. While powerful, message passing can have disadvantages during inference, particularly when the higher order connectivity information is missing or corrupted. To overcome such limitations, we propose Topo-MLP, a purely MLP-based simplicial neural network algorithm to learn the representation of elements in a simplicial complex without explicitly relying on message passing. Our framework utilizes a novel Higher Order Neighborhood Contrastive (HONC) loss which implicitly incorporates the simplicial structure into representation learning. Our proposed model's simplicity makes it faster during inference. Moreover, we show that our model is robust when faced with missing or corrupted connectivity structure.
Authors: Di Wu, Yuling Jiao, Li Shen, Haizhao Yang, Xiliang Lu
Deep reinforcement learning (RL) has shown remarkable success in specific offline decision-making scenarios, yet its theoretical guarantees are still under development. Existing works on offline RL theory primarily emphasize a few trivial settings, such as linear MDP or general function approximation with strong assumptions and independent data, which lack guidance for practical use. The coupling of deep learning and Bellman residuals makes this problem challenging, in addition to the difficulty of data dependence. In this paper, we establish a non-asymptotic estimation error of pessimistic offline RL using general neural network approximation with $\mathcal{C}$-mixing data regarding the structure of networks, the dimension of datasets, and the concentrability of data coverage, under mild assumptions. Our result shows that the estimation error consists of two parts: the first converges to zero at a desired rate on the sample size with partially controllable concentrability, and the second becomes negligible if the residual constraint is tight. This result demonstrates the explicit efficiency of deep adversarial offline RL frameworks. We utilize the empirical process tool for $\mathcal{C}$-mixing sequences and the neural network approximation theory for the H\"{o}lder class to achieve this. We also develop methods to bound the Bellman estimation error caused by function approximation with empirical Bellman constraint perturbations. Additionally, we present a result that lessens the curse of dimensionality using data with low intrinsic dimensionality and function classes with low complexity. Our estimation provides valuable insights into the development of deep offline RL and guidance for algorithm model design.
Authors: Weixi Song, Zuchao Li, Lefei Zhang, Hai Zhao, Bo Du
With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation, including Adapters, Bia-only, and the recently widely used Low-Rank Adaptation. Although these methods have demonstrated their effectiveness to some extent and have been widely applied, the underlying principles are still unclear. In this paper, we reveal the transition of loss landscape in the downstream domain from random initialization to pre-trained initialization, that is, from low-amplitude oscillation to high-amplitude oscillation. The parameter gradients exhibit a property akin to sparsity, where a small fraction of components dominate the total gradient norm, for instance, 1% of the components account for 99% of the gradient. This property ensures that the pre-trained model can easily find a flat minimizer which guarantees the model's ability to generalize even with a low number of trainable parameters. Based on this, we propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT), and validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning. The code is accessible at https://github.com/song-wx/SIFT/.
Authors: Alperen Enes Bayar, Ufuk Uyan, Elif Toprak, Cao Yuheng, Tang Juncheng, Ahmet Alp Kindiroglu
Urban environments are characterized by complex structures and diverse features, making accurate segmentation of point cloud data a challenging task. This paper presents a comprehensive study on the application of RandLA-Net, a state-of-the-art neural network architecture, for the 3D segmentation of large-scale point cloud data in urban areas. The study focuses on three major Chinese cities, namely Chengdu, Jiaoda, and Shenzhen, leveraging their unique characteristics to enhance segmentation performance.
To address the limited availability of labeled data for these specific urban areas, we employed transfer learning techniques. We transferred the learned weights from the Sensat Urban and Toronto 3D datasets to initialize our RandLA-Net model. Additionally, we performed class remapping to adapt the model to the target urban areas, ensuring accurate segmentation results.
The experimental results demonstrate the effectiveness of the proposed approach achieving over 80\% F1 score for each areas in 3D point cloud segmentation. The transfer learning strategy proves to be crucial in overcoming data scarcity issues, providing a robust solution for urban point cloud analysis. The findings contribute to the advancement of point cloud segmentation methods, especially in the context of rapidly evolving Chinese urban areas.
Authors: Ziqian Zeng, Yihuai Hong, Hongliang Dai, Huiping Zhuang, Cen Chen
Early Exiting is one of the most popular methods to achieve efficient inference. Current early exiting methods adopt the (weighted) sum of the cross entropy loss of all internal classifiers during training, imposing all these classifiers to predict all instances correctly. However, during inference, as long as one internal classifier predicts an instance correctly, it can accelerate without losing accuracy. Thus, there is a notable gap between training and inference. We propose ConsistentEE, an early exiting method that is consistent in training and inference. ConsistentEE formulates the early exiting process as a reinforcement learning problem. A policy network is added to decide whether an instance should exit or continue. The training objective of ConsistentEE only require each instance to be predicted correctly by one internal classifier. Additionally, we introduce the concept Memorize Layer to measure the hardness of an instance. We incorporate memorized layer into reward function design, which allows ``easy'' instances to focus more on acceleration while ``hard'' instances to focus more on accuracy. Experimental results show that our method outperforms other baselines on various natural language understanding and generation tasks.
Authors: Yuwei Cao, Hao Peng, Zhengtao Yu, Philip S. Yu
As a trending approach for social event detection, graph neural network (GNN)-based methods enable a fusion of natural language semantics and the complex social network structural information, thus showing SOTA performance. However, GNN-based methods can miss useful message correlations. Moreover, they require manual labeling for training and predetermining the number of events for prediction. In this work, we address social event detection via graph structural entropy (SE) minimization. While keeping the merits of the GNN-based methods, the proposed framework, HISEvent, constructs more informative message graphs, is unsupervised, and does not require the number of events given a priori. Specifically, we incrementally explore the graph neighborhoods using 1-dimensional (1D) SE minimization to supplement the existing message graph with edges between semantically related messages. We then detect events from the message graph by hierarchically minimizing 2-dimensional (2D) SE. Our proposed 1D and 2D SE minimization algorithms are customized for social event detection and effectively tackle the efficiency problem of the existing SE minimization algorithms. Extensive experiments show that HISEvent consistently outperforms GNN-based methods and achieves the new SOTA for social event detection under both closed- and open-set settings while being efficient and robust.
Authors: Mosam Dabhi, Laszlo A. Jeni, Simon Lucey
The lifting of 3D structure and camera from 2D landmarks is at the cornerstone of the entire discipline of computer vision. Traditional methods have been confined to specific rigid objects, such as those in Perspective-n-Point (PnP) problems, but deep learning has expanded our capability to reconstruct a wide range of object classes (e.g. C3PDO and PAUL) with resilience to noise, occlusions, and perspective distortions. All these techniques, however, have been limited by the fundamental need to establish correspondences across the 3D training data -- significantly limiting their utility to applications where one has an abundance of "in-correspondence" 3D data. Our approach harnesses the inherent permutation equivariance of transformers to manage varying number of points per 3D data instance, withstands occlusions, and generalizes to unseen categories. We demonstrate state of the art performance across 2D-3D lifting task benchmarks. Since our approach can be trained across such a broad class of structures we refer to it simply as a 3D Lifting Foundation Model (3D-LFM) -- the first of its kind.
Authors: Jie Liu, Yijia Cao, Yong Li, Yixiu Guo, Wei Deng
Accurately predicting line loss rates is vital for effective line loss management in distribution networks, especially over short-term multi-horizons ranging from one hour to one week. In this study, we propose Attention-GCN-LSTM, a novel method that combines Graph Convolutional Networks (GCN), Long Short-Term Memory (LSTM), and a three-level attention mechanism to address this challenge. By capturing spatial and temporal dependencies, our model enables accurate forecasting of line loss rates across multiple horizons. Through comprehensive evaluation using real-world data from 10KV feeders, our Attention-GCN-LSTM model consistently outperforms existing algorithms, exhibiting superior performance in terms of prediction accuracy and multi-horizon forecasting. This model holds significant promise for enhancing line loss management in distribution networks.
Authors: Basma Kalandar, Ziemowit Dworakowski
The count of people suffering from various levels of hearing loss reached 1.57 billion in 2019. This huge number tends to suffer on many personal and professional levels and strictly needs to be included with the rest of society healthily. This paper presents a proof of concept of an automatic sign language recognition system based on data obtained using a wearable device of 3 flex sensors. The system is designed to interpret a selected set of American Sign Language (ASL) dynamic words by collecting data in sequences of the performed signs and using machine learning methods. The built models achieved high-quality performances, such as Random Forest with 99% accuracy, Support Vector Machine (SVM) with 99%, and two K-Nearest Neighbor (KNN) models with 98%. This indicates many possible paths toward the development of a full-scale system.
Authors: Akihito Taya, Yuuki Nishiyama, Kaoru Sezaki
Federated learning (FL) achieves collaborative learning without the need for data sharing, thus preventing privacy leakage. To extend FL into a fully decentralized algorithm, researchers have applied distributed optimization algorithms to FL by considering machine learning (ML) tasks as parameter optimization problems. Conversely, the consensus-based multi-hop federated distillation (CMFD) proposed in the authors' previous work makes neural network (NN) models get close with others in a function space rather than in a parameter space. Hence, this study solves two unresolved challenges of CMFD: (1) communication cost reduction and (2) visualization of model convergence. Based on a proposed dynamic communication cost reduction method (DCCR), the amount of data transferred in a network is reduced; however, with a slight degradation in the prediction accuracy. In addition, a technique for visualizing the distance between the NN models in a function space is also proposed. The technique applies a dimensionality reduction technique by approximating infinite-dimensional functions as numerical vectors to visualize the trajectory of how the models change by the distributed learning algorithm.
Authors: Ganesh Bikshandi, Jay Shah
We provide an optimized implementation of the forward pass of FlashAttention-2, a popular memory-aware scaled dot-product attention algorithm, as a custom fused CUDA kernel targeting NVIDIA Hopper architecture and written using the open-source CUTLASS library. In doing so, we explain the challenges and techniques involved in fusing online-softmax with back-to-back GEMM kernels, utilizing the Hopper-specific Tensor Memory Accelerator (TMA) and Warpgroup Matrix-Multiply-Accumulate (WGMMA) instructions, defining and transforming CUTLASS Layouts and Tensors, overlapping copy and GEMM operations, and choosing optimal tile sizes for the Q, K and V attention matrices while balancing the register pressure and shared memory utilization. In head-to-head benchmarks on a single H100 PCIe GPU for some common choices of hyperparameters, we observe 20-50% higher FLOPs/s over a version of FlashAttention-2 optimized for last-generation NVIDIA Ampere architecture.
Authors: Yulai Cong, Sijia Li
Mixture models serve as one fundamental tool with versatile applications. However, their training techniques, like the popular Expectation Maximization (EM) algorithm, are notoriously sensitive to parameter initialization and often suffer from bad local optima that could be arbitrarily worse than the optimal. To address the long-lasting bad-local-optima challenge, we draw inspiration from the recent ground-breaking foundation models and propose to leverage their underlying big learning principle to upgrade the EM. Specifically, we present the Big Learning EM (BigLearn-EM), an EM upgrade that simultaneously performs joint, marginal, and orthogonally transformed marginal matchings between data and model distributions. Through simulated experiments, we empirically show that the BigLearn-EM is capable of delivering the optimal with high probability; comparisons on benchmark clustering datasets further demonstrate its effectiveness and advantages over existing techniques. The code is available at https://github.com/YulaiCong/Big-Learning-Expectation-Maximization.
Authors: Pengwei Yan, Kaisong Song, Zhuoren Jiang, Yangyang Kang, Tianqianjin Lin, Changlong Sun, Xiaozhong Liu
While self-supervised graph pretraining techniques have shown promising results in various domains, their application still experiences challenges of limited topology learning, human knowledge dependency, and incompetent multi-level interactions. To address these issues, we propose a novel solution, Dual-level Graph self-supervised Pretraining with Motif discovery (DGPM), which introduces a unique dual-level pretraining structure that orchestrates node-level and subgraph-level pretext tasks. Unlike prior approaches, DGPM autonomously uncovers significant graph motifs through an edge pooling module, aligning learned motif similarities with graph kernel-based similarities. A cross-matching task enables sophisticated node-motif interactions and novel representation learning. Extensive experiments on 15 datasets validate DGPM's effectiveness and generalizability, outperforming state-of-the-art methods in unsupervised representation learning and transfer learning settings. The autonomously discovered motifs demonstrate the potential of DGPM to enhance robustness and interpretability.
Authors: Hamza Mukhtar, Muhammad Usman Ghani Khan
Multi-object tracking (MOT) has profound applications in a variety of fields, including surveillance, sports analytics, self-driving, and cooperative robotics. Despite considerable advancements, existing MOT methodologies tend to falter when faced with non-uniform movements, occlusions, and appearance-reappearance scenarios of the objects. Recognizing this inadequacy, we put forward an integrated MOT method that not only marries object detection and identity linkage within a singular, end-to-end trainable framework but also equips the model with the ability to maintain object identity links over long periods of time. Our proposed model, named STMMOT, is built around four key modules: 1) candidate proposal generation, which generates object proposals via a vision-transformer encoder-decoder architecture that detects the object from each frame in the video; 2) scale variant pyramid, a progressive pyramid structure to learn the self-scale and cross-scale similarities in multi-scale feature maps; 3) spatio-temporal memory encoder, extracting the essential information from the memory associated with each object under tracking; and 4) spatio-temporal memory decoder, simultaneously resolving the tasks of object detection and identity association for MOT. Our system leverages a robust spatio-temporal memory module that retains extensive historical observations and effectively encodes them using an attention-based aggregator. The uniqueness of STMMOT lies in representing objects as dynamic query embeddings that are updated continuously, which enables the prediction of object states with attention mechanisms and eradicates the need for post-processing.
Authors: Yujie Li, Zezhi Shao, Yongjun Xu, Qiang Qiu, Zhaogang Cao, Fei Wang
Complex spatial dependencies in transportation networks make traffic prediction extremely challenging. Much existing work is devoted to learning dynamic graph structures among sensors, and the strategy of mining spatial dependencies from traffic data, known as data-driven, tends to be an intuitive and effective approach. However, Time-Shift of traffic patterns and noise induced by random factors hinder data-driven spatial dependence modeling. In this paper, we propose a novel dynamic frequency domain graph convolution network (DFDGCN) to capture spatial dependencies. Specifically, we mitigate the effects of time-shift by Fourier transform, and introduce the identity embedding of sensors and time embedding when capturing data for graph learning since traffic data with noise is not entirely reliable. The graph is combined with static predefined and self-adaptive graphs during graph convolution to predict future traffic data through classical causal convolutions. Extensive experiments on four real-world datasets demonstrate that our model is effective and outperforms the baselines.
Authors: Wei Chen, Zhiyi Huang, Ruichu Cai, Zhifeng Hao, Kun Zhang
Causal discovery with latent variables is a crucial but challenging task. Despite the emergence of numerous methods aimed at addressing this challenge, they are not fully identified to the structure that two observed variables are influenced by one latent variable and there might be a directed edge in between. Interestingly, we notice that this structure can be identified through the utilization of higher-order cumulants. By leveraging the higher-order cumulants of non-Gaussian data, we provide an analytical solution for estimating the causal coefficients or their ratios. With the estimated (ratios of) causal coefficients, we propose a novel approach to identify the existence of a causal edge between two observed variables subject to latent variable influence. In case when such a causal edge exits, we introduce an asymmetry criterion to determine the causal direction. The experimental results demonstrate the effectiveness of our proposed method.
Authors: Xiyuan Jin, Jing Wang, Lei Liu, Youfang Lin
As an exemplary self-supervised approach for representation learning, time-series contrastive learning has exhibited remarkable advancements in contemporary research. While recent contrastive learning strategies have focused on how to construct appropriate positives and negatives, in this study, we conduct theoretical analysis and find they have overlooked the fundamental issues: false negatives and class imbalance inherent in the InfoNCE loss-based framework. Therefore, we introduce a straightforward modification grounded in the SimCLR framework, universally adaptable to models engaged in the instance discrimination task. By constructing instance graphs to facilitate interactive learning among instances, we emulate supervised contrastive learning via the multiple-instances discrimination task, mitigating the harmful impact of false negatives. Moreover, leveraging the graph structure and few-labeled data, we perform semi-supervised consistency classification and enhance the representative ability of minority classes. We compared our method with the most popular time-series contrastive learning methods on four real-world time-series datasets and demonstrated our significant advantages in overall performance.
Authors: Collin Leiber, Dominik Mautz, Claudia Plant, Christian Böhm
High-dimensional datasets often contain multiple meaningful clusterings in different subspaces. For example, objects can be clustered either by color, weight, or size, revealing different interpretations of the given dataset. A variety of approaches are able to identify such non-redundant clusterings. However, most of these methods require the user to specify the expected number of subspaces and clusters for each subspace. Stating these values is a non-trivial problem and usually requires detailed knowledge of the input dataset. In this paper, we propose a framework that utilizes the Minimum Description Length Principle (MDL) to detect the number of subspaces and clusters per subspace automatically. We describe an efficient procedure that greedily searches the parameter space by splitting and merging subspaces and clusters within subspaces. Additionally, an encoding strategy is introduced that allows us to detect outliers in each subspace. Extensive experiments show that our approach is highly competitive to state-of-the-art methods.
Authors: Anubha Pandey, Aditi Rai, Maneet Singh, Deepak Bhatt, Tanmoy Bhowmik
Recent research has identified discriminatory behavior of automated prediction algorithms towards groups identified on specific protected attributes (e.g., gender, ethnicity, age group, etc.). When deployed in real-world scenarios, such techniques may demonstrate biased predictions resulting in unfair outcomes. Recent literature has witnessed algorithms for mitigating such biased behavior mostly by adding convex surrogates of fairness metrics such as demographic parity or equalized odds in the loss function, which are often not easy to estimate. This research proposes a novel in-processing based GroupMixNorm layer for mitigating bias from deep learning models. The GroupMixNorm layer probabilistically mixes group-level feature statistics of samples across different groups based on the protected attribute. The proposed method improves upon several fairness metrics with minimal impact on overall accuracy. Analysis on benchmark tabular and image datasets demonstrates the efficacy of the proposed method in achieving state-of-the-art performance. Further, the experimental analysis also suggests the robustness of the GroupMixNorm layer against new protected attributes during inference and its utility in eliminating bias from a pre-trained network.
Authors: Haeyong Kang, Jaehong Yoon, Sung Ju Hwang, Chang D. Yoo
Inspired by the Regularized Lottery Ticket Hypothesis (RLTH), which highlights the presence of competitive subnetworks within dense networks for continual learning tasks, we introduce Winning Subnetworks (WSN). This approach utilizes reused weights in dense networks to enhance learning in Task Incremental Learning (TIL) scenarios. To mitigate overfitting in Few-Shot Class Incremental Learning (FSCIL), we have developed WSN variants referred to as the Soft subnetwork (SoftNet). Furthermore, addressing WSN's limitation of sparse reused weights in Video Incremental Learning (VIL), we propose the Fourier Subneural Operator (FSO). The FSO, operating in Fourier space, adaptively and compactly encodes videos, discovering reusable subnetworks with diverse bandwidths. We have applied FSO's Fourier representations to various continual learning contexts, including VIL, TIL, and FSCIL. Our extensive experiments across these scenarios demonstrate FSO's remarkable efficacy in continual learning, significantly enhancing task performance at various convolutional representational levels: it boosts performance in the higher layers for TIL and FSCIL and the lower layers for VIL.
Authors: Dongmin Kim, Sunghyun Park, Jaegul Choo
Time-series anomaly detection deals with the problem of detecting anomalous timesteps by learning normality from the sequence of observations. However, the concept of normality evolves over time, leading to a "new normal problem", where the distribution of normality can be changed due to the distribution shifts between training and test data. This paper highlights the prevalence of the new normal problem in unsupervised time-series anomaly detection studies. To tackle this issue, we propose a simple yet effective test-time adaptation strategy based on trend estimation and a self-supervised approach to learning new normalities during inference. Extensive experiments on real-world benchmarks demonstrate that incorporating the proposed strategy into the anomaly detector consistently improves the model's performance compared to the baselines, leading to robustness to the distribution shifts.
Authors: Egide Ndamuzi, Rachel Akimana, Paterne Gahungu, Elie Bimenyimana
Air pollution is a result of multiple sources including both natural and anthropogenic activities. The rapid urbanization of the cities such as Bujumbura economic capital of Burundi, is one of these factors. The very first characterization of the spatio-temporal variability of PM2.5 in Bujumbura and the forecasting of PM2.5 concentration have been conducted in this paper using data collected during a year, from august 2022 to august 2023, by low cost sensors installed in Bujumbura city. For each commune, an hourly, daily and seasonal analysis were carried out and the results showed that the mass concentrations of PM2.5 in the three municipalities differ from one commune to another. The average hourly and annual PM2.5 concentrations exceed the World Health Organization standards. The range is between 28.3 and 35.0 microgram/m3 . In order to make prediction of PM2.5 concentration, an investigation of RNN with Long Short Term Memory (LSTM) has been undertaken.
Authors: Top Piriyakulkij, Volodymyr Kuleshov, Kevin Ellis
Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences. To enable this ability for instruction-tuned large language models (LLMs), one may prompt them to ask users questions to infer their preferences, transforming the language models into more robust, interactive systems. However, out of the box, these models are not efficient at extracting preferences: the questions they generate are not informative, requiring a high number of user interactions and impeding the usability of the downstream system. In this work, we introduce an inference-time algorithm that helps LLMs quickly infer preferences by using more informative questions. Our algorithm uses a probabilistic model whose conditional distributions are defined by prompting an LLM, and returns questions that optimize expected entropy and expected model change. Results in a simplified interactive web shopping setting with real product items show that an LLM equipped with our entropy reduction algorithm outperforms baselines with the same underlying LLM on task performance while using fewer user interactions.
Authors: Jing Nan, Yan Qin, Wei Dai, Chau Yuen
Data-driven soft sensors provide a potentially cost-effective and more accurate modeling approach to measure difficult-to-measure indices in industrial processes compared to mechanistic approaches. Artificial intelligence (AI) techniques, such as deep learning, have become a popular soft sensors modeling approach in the area of machine learning and big data. However, soft sensors models based deep learning potentially lead to complex model structures and excessive training time. In addition, industrial processes often rely on distributed control systems (DCS) characterized by resource constraints. Herein, guided by spatial geometric, a lightweight geometric constructive neural network, namely LightGCNet, is proposed, which utilizes compact angle constraint to assign the hidden parameters from dynamic intervals. At the same time, a node pool strategy and spatial geometric relationships are used to visualize and optimize the process of assigning hidden parameters, enhancing interpretability. In addition, the universal approximation property of LightGCNet is proved by spatial geometric analysis. Two versions algorithmic implementations of LightGCNet are presented in this article. Simulation results concerning both benchmark datasets and the ore grinding process indicate remarkable merits of LightGCNet in terms of small network size, fast learning speed, and sound generalization.
Authors: Siamul Karim Khan, Patrick Tinsley, Mahsa Mitcheff, Patrick Flynn, Kevin W. Bowyer, Adam Czajka
Synthesis of same-identity biometric iris images, both for existing and non-existing identities while preserving the identity across a wide range of pupil sizes, is complex due to intricate iris muscle constriction mechanism, requiring a precise model of iris non-linear texture deformations to be embedded into the synthesis pipeline. This paper presents the first method of fully data-driven, identity-preserving, pupil size-varying s ynthesis of iris images. This approach is capable of synthesizing images of irises with different pupil sizes representing non-existing identities as well as non-linearly deforming the texture of iris images of existing subjects given the segmentation mask of the target iris image. Iris recognition experiments suggest that the proposed deformation model not only preserves the identity when changing the pupil size but offers better similarity between same-identity iris samples with significant differences in pupil size, compared to state-of-the-art linear and non-linear (bio-mechanical-based) iris deformation models. Two immediate applications of the proposed approach are: (a) synthesis of, or enhancement of the existing biometric datasets for iris recognition, mimicking those acquired with iris sensors, and (b) helping forensic human experts in examining iris image pairs with significant differences in pupil dilation. Source codes and weights of the models are made available with the paper.
Authors: Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Artem Agarkov, Viacheslav Sinii, Sergey Kolesnikov
We present XLand-MiniGrid, a suite of tools and grid-world environments for meta-reinforcement learning research inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid. XLand-Minigrid is written in JAX, designed to be highly scalable, and can potentially run on GPU or TPU accelerators, democratizing large-scale experimentation with limited resources. To demonstrate the generality of our library, we have implemented some well-known single-task environments as well as new meta-learning environments capable of generating $10^8$ distinct tasks. We have empirically shown that the proposed environments can scale up to $2^{13}$ parallel instances on the GPU, reaching tens of millions of steps per second.
Authors: Xin Mu, Yu Wang, Zhengan Huang, Junzuo Lai, Yehong Zhang, Hui Wang, Yue Yu
In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important. Within this context, machine learning (ML) models, being highly valuable digital assets, have gained significant attention for IP protection. This paper introduces a practical encryption-based framework called \textit{EncryIP}, which seamlessly integrates a public-key encryption scheme into the model learning process. This approach enables the protected model to generate randomized and confused labels, ensuring that only individuals with accurate secret keys, signifying authorized users, can decrypt and reveal authentic labels. Importantly, the proposed framework not only facilitates the protected model to multiple authorized users without requiring repetitive training of the original ML model with IP protection methods but also maintains the model's performance without compromising its accuracy. Compared to existing methods like watermark-based, trigger-based, and passport-based approaches, \textit{EncryIP} demonstrates superior effectiveness in both training protected models and efficiently detecting the unauthorized spread of ML models.
Authors: Lena G. M. Bauer, Collin Leiber, Christian Böhm, Claudia Plant
Over the last decade, the Dip-test of unimodality has gained increasing interest in the data mining community as it is a parameter-free statistical test that reliably rates the modality in one-dimensional samples. It returns a so called Dip-value and a corresponding probability for the sample's unimodality (Dip-p-value). These two values share a sigmoidal relationship. However, the specific transformation is dependent on the sample size. Many Dip-based clustering algorithms use bootstrapped look-up tables translating Dip- to Dip-p-values for a certain limited amount of sample sizes. We propose a specifically designed sigmoid function as a substitute for these state-of-the-art look-up tables. This accelerates computation and provides an approximation of the Dip- to Dip-p-value transformation for every single sample size. Further, it is differentiable and can therefore easily be integrated in learning schemes using gradient descent. We showcase this by exploiting our function in a novel subspace clustering algorithm called Dip'n'Sub. We highlight in extensive experiments the various benefits of our proposal.
Authors: Abhishek Jana, Md Kamruzzaman Sarker, Monireh Ebrahimi, Pascal Hitzler, George T Amariucai
Powered by new advances in sensor development and artificial intelligence, the decreasing cost of computation, and the pervasiveness of handheld computation devices, biometric user authentication (and identification) is rapidly becoming ubiquitous. Modern approaches to biometric authentication, based on sophisticated machine learning techniques, cannot avoid storing either trained-classifier details or explicit user biometric data, thus exposing users' credentials to falsification. In this paper, we introduce a secure way to handle user-specific information involved with the use of vector-space classifiers or artificial neural networks for biometric authentication. Our proposed architecture, called a Neural Fuzzy Extractor (NFE), allows the coupling of pre-existing classifiers with fuzzy extractors, through a artificial-neural-network-based buffer called an expander, with minimal or no performance degradation. The NFE thus offers all the performance advantages of modern deep-learning-based classifiers, and all the security of standard fuzzy extractors. We demonstrate the NFE retrofit to a classic artificial neural network for a simple scenario of fingerprint-based user authentication.
Authors: Mengyue Yang, Furui Liu, Zhitang Chen, Xinwei Shen, Jianye Hao, Jun Wang
Learning disentanglement aims at finding a low dimensional representation which consists of multiple explanatory and generative factors of the observational data. The framework of variational autoencoder (VAE) is commonly used to disentangle independent factors from observations. However, in real scenarios, factors with semantics are not necessarily independent. Instead, there might be an underlying causal structure which renders these factors dependent. We thus propose a new VAE based framework named CausalVAE, which includes a Causal Layer to transform independent exogenous factors into causal endogenous ones that correspond to causally related concepts in data. We further analyze the model identifiabitily, showing that the proposed model learned from observations recovers the true one up to a certain degree by providing supervision signals (e.g. feature labels). Experiments are conducted on various datasets, including synthetic and real word benchmark CelebA. Results show that the causal representations learned by CausalVAE are semantically interpretable, and their causal relationship as a Directed Acyclic Graph (DAG) is identified with good accuracy. Furthermore, we demonstrate that the proposed CausalVAE model is able to generate counterfactual data through "do-operation" to the causal factors.
Authors: Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall, Sahir, Raviteja Chunduru, Ahmed Touati, Sriram Ganapathi Subramanian, Matthew E. Taylor, Sarath Chandar
Reinforcement learning (RL) algorithms typically deal with maximizing the expected cumulative return (discounted or undiscounted, finite or infinite horizon). However, several crucial applications in the real world, such as drug discovery, do not fit within this framework because an RL agent only needs to identify states (molecules) that achieve the highest reward within a trajectory and does not need to optimize for the expected cumulative return. In this work, we formulate an objective function to maximize the expected maximum reward along a trajectory, derive a novel functional form of the Bellman equation, introduce the corresponding Bellman operators, and provide a proof of convergence. Using this formulation, we achieve state-of-the-art results on the task of molecule generation that mimics a real-world drug discovery pipeline.
Authors: Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt
Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models. We draw a connection between such autoregressive generative models and the task of lossy video compression. Specifically, we view recent neural video compression methods (Lu et al., 2019; Yang et al., 2020b; Agustssonet al., 2020) as instances of a generalized stochastic temporal autoregressive transform, and propose avenues for enhancement based on this insight. Comprehensive evaluations on large-scale video data show improved rate-distortion performance over both state-of-the-art neural and conventional video compression methods.
Authors: Partha P Mitra, Clément Sire
Contemporary Artificial Intelligence (AI) stands on two legs: large training data corpora and many-parameter artificial neural networks (ANNs). The data corpora are needed to represent the complexity and heterogeneity of the world. The role of the networks is less transparent due to the obscure dependence of the network parameters and outputs on the training data and inputs. This raises problems, ranging from technical-scientific to legal-ethical. We hypothesize that a transparent approach to machine learning is possible without using networks at all. By generalizing a parameter-free, statistically consistent data interpolation method, which we analyze theoretically in detail, we develop a framework for generative modeling. Given the growing usage of machine learning techniques in science, we demonstrate this framework with an example from the field of animal behavior. We applied this generative Hilbert framework to the trajectories of small groups of swimming fish. The framework outperforms previously developed state-of-the-art traditional mathematical behavioral models and contemporary ANN-based models in reproducing naturalistic behaviors. We do not suggest that the proposed framework will outperform networks in all applications, as over-parameterized networks can interpolate. However, our framework is theoretically sound, transparent, deterministic and parameter free: it does not require any compute-expensive training, does not involve optimization, has no model selection, and is easily reproduced and ported. We also propose an easily computed method of credit assignment based on this framework that could help address ethical-legal challenges raised by generative AI.
Authors: Ziang Li, Kailun Wu, Yiwen Guo, Changshui Zhang
Drawing on theoretical insights, we advocate an error-based thresholding (EBT) mechanism for learned ISTA (LISTA), which utilizes a function of the layer-wise reconstruction error to suggest a specific threshold for each observation in the shrinkage function of each layer. We show that the proposed EBT mechanism well disentangles the learnable parameters in the shrinkage functions from the reconstruction errors, endowing the obtained models with improved adaptivity to possible data variations. With rigorous analyses, we further show that the proposed EBT also leads to a faster convergence on the basis of LISTA or its variants, in addition to its higher adaptivity. Extensive experimental results confirm our theoretical analyses and verify the effectiveness of our methods.
Authors: Liang Hou, Qi Cao, Yige Yuan, Songtao Zhao, Chongyang Ma, Siyuan Pan, Pengfei Wan, Zhongyuan Wang, Huawei Shen, Xueqi Cheng
Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic $-$ harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs.
Authors: Jiawei Xu, Cheng Zhou, Yizheng Zhang, Baoxiang Wang, Lei Han
We consider the problem of policy transfer between two Markov Decision Processes (MDPs). We introduce a lemma based on existing theoretical results in reinforcement learning to measure the relativity gap between two arbitrary MDPs, that is the difference between any two cumulative expected returns defined on different policies and environment dynamics. Based on this lemma, we propose two new algorithms referred to as Relative Policy Optimization (RPO) and Relative Transition Optimization (RTO), which offer fast policy transfer and dynamics modelling, respectively. RPO transfers the policy evaluated in one environment to maximize the return in another, while RTO updates the parameterized dynamics model to reduce the gap between the dynamics of the two environments. Integrating the two algorithms results in the complete Relative Policy-Transition Optimization (RPTO) algorithm, in which the policy interacts with the two environments simultaneously, such that data collections from two environments, policy and transition updates are completed in one closed loop to form a principled learning framework for policy transfer. We demonstrate the effectiveness of RPTO on a set of MuJoCo continuous control tasks by creating policy transfer problems via variant dynamics.
Authors: Kevin Denamganaï, Sondess Missaoui, James Alfred Walker
Human beings use compositionality to generalise from past experiences to novel experiences. We assume a separation of our experiences into fundamental atomic components that can be recombined in novel ways to support our ability to engage with novel experiences. We frame this as the ability to learn to generalise compositionally, and we will refer to behaviours making use of this ability as compositional learning behaviours (CLBs). A central problem to learning CLBs is the resolution of a binding problem (BP). While it is another feat of intelligence that human beings perform with ease, it is not the case for state-of-the-art artificial agents. Thus, in order to build artificial agents able to collaborate with human beings, we propose to develop a novel benchmark to investigate agents' abilities to exhibit CLBs by solving a domain-agnostic version of the BP. We take inspiration from the language emergence and grounding framework of referential games and propose a meta-learning extension of referential games, entitled Meta-Referential Games, and use this framework to build our benchmark, the Symbolic Behaviour Benchmark (S2B). We provide baseline results and error analysis showing that our benchmark is a compelling challenge that we hope will spur the research community towards developing more capable artificial agents.
Authors: Arjun Ramachandra, Karthik Natarajan
In this paper, we provide a characterization of the expected value of monotone submodular set functions with $n$ pairwise independent random inputs. Inspired by the notion of ``correlation gap'', we study the ratio of the maximum expected value of a function with arbitrary dependence among the random inputs with given marginal probabilities to the maximum expected value of the function with pairwise independent random inputs and the same marginal probabilities. Our results show that the ratio is upper bounded by: (a) $4/3$ for $n = 3$ with general marginal probabilities and any monotone submodular set function (b) $4/3$ for general $n$ with small and large marginal probabilities and any monotone submodular set function and (c) $4k/(4k-1)$ for general $n$, general identical probabilities and rank functions of $k$-uniform matroids. The bound is tight in all three cases. This contrasts with the $e/(e-1)$ bound on the correlation gap ratio for monotone submodular set functions with mutually independent random inputs (which is known to be tight in case (b)), and illustrates a fundamental difference in the behavior of submodular functions with weaker notions of independence. These results can be immediately extended beyond pairwise independence to correlated random inputs. We discuss applications in distributionally robust optimization and mechanism design and end the paper with a conjecture.
Authors: Ricky Fajri, Akrati Saxena, Yulong Pei, Mykola Pechenizkiy
Active Learning (AL) techniques have proven to be highly effective in reducing data labeling costs across a range of machine learning tasks. Nevertheless, one known challenge of these methods is their potential to introduce unfairness towards sensitive attributes. Although recent approaches have focused on enhancing fairness in AL, they tend to reduce the model's accuracy. To address this issue, we propose a novel strategy, named Fair Active Learning using fair Clustering, Uncertainty, and Representativeness (FAL-CUR), to improve fairness in AL. FAL-CUR tackles the fairness problem in AL by combining fair clustering with an acquisition function that determines which samples to query based on their uncertainty and representativeness scores. We evaluate the performance of FAL-CUR on four real-world datasets, and the results demonstrate that FAL-CUR achieves a 15% - 20% improvement in fairness compared to the best state-of-the-art method in terms of equalized odds while maintaining stable accuracy scores. Furthermore, an ablation study highlights the crucial roles of fair clustering in preserving fairness and the acquisition function in stabilizing the accuracy performance.
Authors: Oliver Urs Lenz, Daniel Peralta, Chris Cornelis
We propose polar encoding, a representation of categorical and numerical $[0,1]$-valued attributes with missing values to be used in a classification context. We argue that this is a good baseline approach, because it can be used with any classification algorithm, preserves missingness information, is very simple to apply and offers good performance. In particular, unlike the existing missing-indicator approach, it does not require imputation, ensures that missing values are equidistant from non-missing values, and lets decision tree algorithms choose how to split missing values, thereby providing a practical realisation of the "missingness incorporated in attributes" (MIA) proposal. Furthermore, we show that categorical and $[0,1]$-valued attributes can be viewed as special cases of a single attribute type, corresponding to the classical concept of barycentric coordinates, and that this offers a natural interpretation of polar encoding as a fuzzified form of one-hot encoding. With an experiment based on twenty real-life datasets with missing values, we show that, in terms of the resulting classification performance, polar encoding performs better than the state-of-the-art strategies \e{multiple imputation by chained equations} (MICE) and \e{multiple imputation with denoising autoencoders} (MIDAS) and -- depending on the classifier -- about as well or better than mean/mode imputation with missing-indicators.
Authors: Zhirui Chen, P. N. Karthik, Vincent Y. F. Tan, Yeow Meng Chee
We study best arm identification in a federated multi-armed bandit setting with a central server and multiple clients, when each client has access to a {\em subset} of arms and each arm yields independent Gaussian observations. The goal is to identify the best arm of each client subject to an upper bound on the error probability; here, the best arm is one that has the largest {\em average} value of the means averaged across all clients having access to the arm. Our interest is in the asymptotics as the error probability vanishes. We provide an asymptotic lower bound on the growth rate of the expected stopping time of any algorithm. Furthermore, we show that for any algorithm whose upper bound on the expected stopping time matches with the lower bound up to a multiplicative constant ({\em almost-optimal} algorithm), the ratio of any two consecutive communication time instants must be {\em bounded}, a result that is of independent interest. We thereby infer that an algorithm can communicate no more sparsely than at exponential time instants in order to be almost-optimal. For the class of almost-optimal algorithms, we present the first-of-its-kind asymptotic lower bound on the expected number of {\em communication rounds} until stoppage. We propose a novel algorithm that communicates at exponential time instants, and demonstrate that it is asymptotically almost-optimal.
Authors: Jinus Bordbar, Mohammadreza Mohammadrezaie, Saman Ardalan, Mohammad Ebrahim Shiri
Online social media is integral to human life, facilitating messaging, information sharing, and confidential communication while preserving privacy. Platforms like Twitter, Instagram, and Facebook exemplify this phenomenon. However, users face challenges due to network anomalies, often stemming from malicious activities such as identity theft for financial gain or harm. This paper proposes a novel method using user similarity measures and the Generative Adversarial Network (GAN) algorithm to identify fake user accounts in the Twitter dataset. Despite the problem's complexity, the method achieves an AUC rate of 80\% in classifying and detecting fake accounts. Notably, the study builds on previous research, highlighting advancements and insights into the evolving landscape of anomaly detection in online social networks.
Authors: Lisheng Wu, Ke Chen
Reinforcement learning (RL) often struggles to accomplish a sparse-reward long-horizon task in a complex environment. Goal-conditioned reinforcement learning (GCRL) has been employed to tackle this difficult problem via a curriculum of easy-to-reach sub-goals. In GCRL, exploring novel sub-goals is essential for the agent to ultimately find the pathway to the desired goal. How to explore novel sub-goals efficiently is one of the most challenging issues in GCRL. Several goal exploration methods have been proposed to address this issue but still struggle to find the desired goals efficiently. In this paper, we propose a novel learning objective by optimizing the entropy of both achieved and new goals to be explored for more efficient goal exploration in sub-goal selection based GCRL. To optimize this objective, we first explore and exploit the frequently occurring goal-transition patterns mined in the environments similar to the current task to compose skills via skill learning. Then, the pretrained skills are applied in goal exploration. Evaluation on a variety of spare-reward long-horizon benchmark tasks suggests that incorporating our method into several state-of-the-art GCRL baselines significantly boosts their exploration efficiency while improving or maintaining their performance. The source code is available at: https://github.com/GEAPS/GEAPS.
Authors: Stanislas Ducotterd, Alexis Goujon, Pakshal Bohra, Dimitris Perdios, Sebastian Neumayer, Michael Unser
Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep learning community. Unfortunately, it has been shown both theoretically and empirically that they perform poorly when equipped with ReLU activation functions. By contrast, neural networks with learnable 1-Lipschitz linear splines are known to be more expressive. In this paper, we show that such networks correspond to global optima of a constrained functional optimization problem that consists of the training of a neural network composed of 1-Lipschitz linear layers and 1-Lipschitz freeform activation functions with second-order total-variation regularization. Further, we propose an efficient method to train these neural networks. Our numerical experiments show that our trained networks compare favorably with existing 1-Lipschitz neural architectures.
Authors: Ben Abramowitz, Omer Lev, Nicholas Mattei
We consider the problem of determining a binary ground truth using advice from a group of independent reviewers (experts) who express their guess about a ground truth correctly with some independent probability (competence). In this setting, when all reviewers are competent (competence greater than one-half), the Condorcet Jury Theorem tells us that adding more reviewers increases the overall accuracy, and if all competences are known, then there exists an optimal weighting of the reviewers. However, in practical settings, reviewers may be noisy or incompetent, i.e., competence below half, and the number of experts may be small, so the asymptotic Condorcet Jury Theorem is not practically relevant. In such cases we explore appointing one or more chairs (judges) who determine the weight of each reviewer for aggregation, creating multiple levels. However, these chairs may be unable to correctly identify the competence of the reviewers they oversee, and therefore unable to compute the optimal weighting. We give conditions when a set of chairs is able to weight the reviewers optimally, and depending on the competence distribution of the agents, give results about when it is better to have more chairs or more reviewers. Through numerical simulations we show that in some cases it is better to have more chairs, but in many cases it is better to have more reviewers.
Authors: Brian Testa, Yi Xiao, Harshit Sharma, Avery Gump, Asif Salekin
Smart speaker voice assistants (VAs) such as Amazon Echo and Google Home have been widely adopted due to their seamless integration with smart home devices and the Internet of Things (IoT) technologies. These VA services raise privacy concerns, especially due to their access to our speech. This work considers one such use case: the unaccountable and unauthorized surveillance of a user's emotion via speech emotion recognition (SER). This paper presents DARE-GP, a solution that creates additive noise to mask users' emotional information while preserving the transcription-relevant portions of their speech. DARE-GP does this by using a constrained genetic programming approach to learn the spectral frequency traits that depict target users' emotional content, and then generating a universal adversarial audio perturbation that provides this privacy protection. Unlike existing works, DARE-GP provides: a) real-time protection of previously unheard utterances, b) against previously unseen black-box SER classifiers, c) while protecting speech transcription, and d) does so in a realistic, acoustic environment. Further, this evasion is robust against defenses employed by a knowledgeable adversary. The evaluations in this work culminate with acoustic evaluations against two off-the-shelf commercial smart speakers using a small-form-factor (raspberry pi) integrated with a wake-word system to evaluate the efficacy of its real-world, real-time deployment.
Authors: Jinus Bordbar, Saman Ardalan, Mohammadreza Mohammadrezaie, Zahra Ghasemi
As social media continues to grow rapidly, the prevalence of harassment on these platforms has also increased. This has piqued the interest of researchers in the field of fake detection. Social media data, often forms complex graphs with numerous nodes, posing several challenges. These challenges and limitations include dealing with a significant amount of irrelevant features in matrices and addressing issues such as high data dispersion and an imbalanced class distribution within the dataset. To overcome these challenges and limitations, researchers have employed auto-encoders and a combination of semi-supervised learning with a GAN algorithm, referred to as SGAN. Our proposed method utilizes auto-encoders for feature extraction and incorporates SGAN. By leveraging an unlabeled dataset, the unsupervised layer of SGAN compensates for the limited availability of labeled data, making efficient use of the limited number of labeled instances. Multiple evaluation metrics were employed, including the Confusion Matrix and the ROC curve. The dataset was divided into training and testing sets, with 100 labeled samples for training and 1,000 samples for testing. The novelty of our research lies in applying SGAN to address the issue of imbalanced datasets in fake account detection. By optimizing the use of a smaller number of labeled instances and reducing the need for extensive computational power, our method offers a more efficient solution. Additionally, our study contributes to the field by achieving an 81% accuracy in detecting fake accounts using only 100 labeled samples. This demonstrates the potential of SGAN as a powerful tool for handling minority classes and addressing big data challenges in fake account detection.
Authors: Roman Pogodin, Namrata Deka, Yazhe Li, Danica J. Sutherland, Victor Veitch, Arthur Gretton
We introduce the Conditional Independence Regression CovariancE (CIRCE), a measure of conditional independence for multivariate continuous-valued variables. CIRCE applies as a regularizer in settings where we wish to learn neural features $\varphi(X)$ of data $X$ to estimate a target $Y$, while being conditionally independent of a distractor $Z$ given $Y$. Both $Z$ and $Y$ are assumed to be continuous-valued but relatively low dimensional, whereas $X$ and its features may be complex and high dimensional. Relevant settings include domain-invariant learning, fairness, and causal learning. The procedure requires just a single ridge regression from $Y$ to kernelized features of $Z$, which can be done in advance. It is then only necessary to enforce independence of $\varphi(X)$ from residuals of this regression, which is possible with attractive estimation properties and consistency guarantees. By contrast, earlier measures of conditional feature dependence require multiple regressions for each step of feature learning, resulting in more severe bias and variance, and greater computational cost. When sufficiently rich features are used, we establish that CIRCE is zero if and only if $\varphi(X) \perp \!\!\! \perp Z \mid Y$. In experiments, we show superior performance to previous methods on challenging benchmarks, including learning conditionally invariant image features.
Authors: Erfaun Noorani, Christos Mavridis, John Baras
While reinforcement learning has shown experimental success in a number of applications, it is known to be sensitive to noise and perturbations in the parameters of the system, leading to high variance in the total reward amongst different episodes in slightly different environments. To introduce robustness, as well as sample efficiency, risk-sensitive reinforcement learning methods are being thoroughly studied. In this work, we provide a definition of robust reinforcement learning policies and formulate a risk-sensitive reinforcement learning problem to approximate them, by solving an optimization problem with respect to a modified objective based on exponential criteria. In particular, we study a model-free risk-sensitive variation of the widely-used Monte Carlo Policy Gradient algorithm and introduce a novel risk-sensitive online Actor-Critic algorithm based on solving a multiplicative Bellman equation using stochastic approximation updates. Analytical results suggest that the use of exponential criteria generalizes commonly used ad-hoc regularization approaches, improves sample efficiency, and introduces robustness with respect to perturbations in the model parameters and the environment. The implementation, performance, and robustness properties of the proposed methods are evaluated in simulated experiments.
Authors: Carlos Martin, Tuomas Sandholm
There has been substantial progress on finding game-theoretic equilibria. Most of that work has focused on games with finite, discrete action spaces. However, many games involving space, time, money, and other fine-grained quantities have continuous action spaces (or are best modeled as such). We study the problem of finding an approximate Nash equilibrium of games with continuous action sets. The standard measure of closeness to Nash equilibrium is exploitability, which measures how much players can benefit from unilaterally changing their strategy. We propose two new methods that minimize an approximation of the exploitability with respect to the strategy profile. The first method uses a learned best-response function, which takes the current strategy profile as input and returns candidate best responses for each player. The strategy profile and best-response functions are trained simultaneously, with the former trying to minimize exploitability while the latter tries to maximize it. The second method maintains an ensemble of candidate best responses for each player. In each iteration, the best-performing elements of each ensemble are used to update the current strategy profile. The strategy profile and best-response ensembles are simultaneously trained to minimize and maximize the approximate exploitability, respectively. We evaluate our methods on various continuous games, showing that they outperform prior methods.
Authors: Marlon Tobaben, Aliaksandra Shysheya, John Bronskill, Andrew Paverd, Shruti Tople, Santiago Zanella-Beguelin, Richard E Turner, Antti Honkela
There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models. These DP models are typically pretrained on large public datasets and then fine-tuned on private downstream datasets that are relatively large and similar in distribution to the pretraining data. However, in many applications including personalization and federated learning, it is crucial to perform well (i) in the few-shot setting, as obtaining large amounts of labeled data may be problematic; and (ii) on datasets from a wide variety of domains for use in various specialist settings. To understand under which conditions few-shot DP can be effective, we perform an exhaustive set of experiments that reveals how the accuracy and vulnerability to attack of few-shot DP image classification models are affected as the number of shots per class, privacy level, model architecture, downstream dataset, and subset of learnable parameters in the model vary. We show that to achieve DP accuracy on par with non-private models, the shots per class must be increased as the privacy level increases. We also show that learning parameter-efficient FiLM adapters under DP is competitive with learning just the final classifier layer or learning all of the network parameters. Finally, we evaluate DP federated learning systems and establish state-of-the-art performance on the challenging FLAIR benchmark.
Authors: Emanuele Marconato, Gianpaolo Bontempo, Elisa Ficarra, Simone Calderara, Andrea Passerini, Stefano Teso
We introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence of neuro-symbolic tasks, that is, it has to map sub-symbolic inputs to high-level concepts and compute predictions by reasoning consistently with prior knowledge. Our key observation is that neuro-symbolic tasks, although different, often share concepts whose semantics remains stable over time. Traditional approaches fall short: existing continual strategies ignore knowledge altogether, while stock neuro-symbolic architectures suffer from catastrophic forgetting. We show that leveraging prior knowledge by combining neuro-symbolic architectures with continual strategies does help avoid catastrophic forgetting, but also that doing so can yield models affected by reasoning shortcuts. These undermine the semantics of the acquired concepts, even when detailed prior knowledge is provided upfront and inference is exact, and in turn continual performance. To overcome these issues, we introduce COOL, a COncept-level cOntinual Learning strategy tailored for neuro-symbolic continual problems that acquires high-quality concepts and remembers them over time. Our experiments on three novel benchmarks highlights how COOL attains sustained high performance on neuro-symbolic continual learning tasks in which other strategies fail.
Authors: Eugene Bagdasaryan, Vitaly Shmatikov
Machine learning (ML) models trained on data from potentially untrusted sources are vulnerable to poisoning. A small, maliciously crafted subset of the training inputs can cause the model to learn a "backdoor" task (e.g., misclassify inputs with a certain feature) in addition to its main task. Recent research proposed many hypothetical backdoor attacks whose efficacy heavily depends on the configuration and training hyperparameters of the target model.
Given the variety of potential backdoor attacks, ML engineers who are not security experts have no way to measure how vulnerable their current training pipelines are, nor do they have a practical way to compare training configurations so as to pick the more resistant ones. Deploying a defense requires evaluating and choosing from among dozens of research papers and re-engineering the training pipeline.
In this paper, we aim to provide ML engineers with pragmatic tools to audit the backdoor resistance of their training pipelines and to compare different training configurations, to help choose one that best balances accuracy and security.
First, we propose a universal, attack-agnostic resistance metric based on the minimum number of training inputs that must be compromised before the model learns any backdoor.
Second, we design, implement, and evaluate Mithridates a multi-stage approach that integrates backdoor resistance into the training-configuration search. ML developers already rely on hyperparameter search to find configurations that maximize the model's accuracy. Mithridates extends this standard tool to balance accuracy and resistance without disruptive changes to the training pipeline. We show that hyperparameters found by Mithridates increase resistance to multiple types of backdoor attacks by 3-5x with only a slight impact on accuracy. We also discuss extensions to AutoML and federated learning.
Authors: Baoyu Jing, Yuchen Yan, Kaize Ding, Chanyoung Park, Yada Zhu, Huan Liu, Hanghang Tong
A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are based on contrastive learning which learns embeddings by discriminating positive and negative node pairs. Contrastive learning usually requires a large number of negative node pairs, which could lead to computational burden and semantic errors. In this paper, we introduce a novel synergistic representation learning model (STERLING) to learn node embeddings without negative node pairs. STERLING preserves the unique local and global synergies in bipartite graphs. The local synergies are captured by maximizing the similarity of the inter-type and intra-type positive node pairs, and the global synergies are captured by maximizing the mutual information of co-clusters. Theoretical analysis demonstrates that STERLING could improve the connectivity between different node types in the embedding space. Extensive empirical evaluation on various benchmark datasets and tasks demonstrates the effectiveness of STERLING for extracting node embeddings.
Authors: Weigang Lu, Ziyu Guan, Wei Zhao, Yaming Yang, Yuanhai Lv, Lining Xing, Baosheng Yu, Dacheng Tao
Pseudo Labeling is a technique used to improve the performance of semi-supervised Graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions. However, the quality of generated pseudo-labels has been a longstanding concern due to the sensitivity of the classification objective with respect to the given labels. To avoid the untrustworthy classification supervision indicating ``a node belongs to a specific class,'' we favor the fault-tolerant contrasting supervision demonstrating ``two nodes do not belong to the same class.'' Thus, the problem of generating high-quality pseudo-labels is then transformed into a relaxed version, i.e., identifying reliable negative pairs. To achieve this, we propose a general framework for GNNs, termed Pseudo Contrastive Learning (PCL). It separates two nodes whose positive and negative pseudo-labels target the same class. To incorporate topological knowledge into learning, we devise a topologically weighted contrastive loss that spends more effort separating negative pairs with smaller topological distances. Experimentally, we apply PCL to various GNNs, which consistently outperform their counterparts using other popular general techniques on five real-world graphs.
Authors: Marius Schubert, Tobias Riedlinger, Karsten Kahl, Daniel Kröll, Sebastian Schoenen, Siniša Šegvić, Matthias Rottmann
Labeling datasets for supervised object detection is a dull and time-consuming task. Errors can be easily introduced during annotation and overlooked during review, yielding inaccurate benchmarks and performance degradation of deep neural networks trained on noisy labels. In this work, we for the first time introduce a benchmark for label error detection methods on object detection datasets as well as a label error detection method and a number of baselines. We simulate four different types of randomly introduced label errors on train and test sets of well-labeled object detection datasets. For our label error detection method we assume a two-stage object detector to be given and consider the sum of both stages' classification and regression losses. The losses are computed with respect to the predictions and the noisy labels including simulated label errors, aiming at detecting the latter. We compare our method to three baselines: a naive one without deep learning, the object detector's score and the entropy of the classification softmax distribution. We outperform all baselines and demonstrate that among the considered methods, ours is the only one that detects label errors of all four types efficiently. Furthermore, we detect real label errors a) on commonly used test datasets in object detection and b) on a proprietary dataset. In both cases we achieve low false positives rates, i.e., we detect label errors with a precision for a) of up to 71.5% and for b) with 97%.
Authors: Thanh Vu, Baochen Sun, Bodi Yuan, Alex Ngai, Yueqi Li, Jan-Michael Frahm
The success of data mixing augmentations in image classification tasks has been well-received. However, these techniques cannot be readily applied to object detection due to challenges such as spatial misalignment, foreground/background distinction, and plurality of instances. To tackle these issues, we first introduce a novel conceptual framework called Supervision Interpolation (SI), which offers a fresh perspective on interpolation-based augmentations by relaxing and generalizing Mixup. Based on SI, we propose LossMix, a simple yet versatile and effective regularization that enhances the performance and robustness of object detectors and more. Our key insight is that we can effectively regularize the training on mixed data by interpolating their loss errors instead of ground truth labels. Empirical results on the PASCAL VOC and MS COCO datasets demonstrate that LossMix can consistently outperform state-of-the-art methods widely adopted for detection. Furthermore, by jointly leveraging LossMix with unsupervised domain adaptation, we successfully improve existing approaches and set a new state of the art for cross-domain object detection.
Authors: Bangti Jin, Xiyao Li, Qimeng Quan, Zhi Zhou
In this work we develop a novel approach using deep neural networks to reconstruct the conductivity distribution in elliptic problems from one measurement of the solution over the whole domain. The approach is based on a mixed reformulation of the governing equation and utilizes the standard least-squares objective, with deep neural networks as ansatz functions to approximate the conductivity and flux simultaneously. We provide a thorough analysis of the deep neural network approximations of the conductivity for both continuous and empirical losses, including rigorous error estimates that are explicit in terms of the noise level, various penalty parameters and neural network architectural parameters (depth, width and parameter bound). We also provide multiple numerical experiments in two- and multi-dimensions to illustrate distinct features of the approach, e.g., excellent stability with respect to data noise and capability of solving high-dimensional problems.
Authors: Min Hu, Zhizhong Tan, Bin Liu, Guosheng Yin
This study aims to address the challenges of futures price prediction in high-frequency trading (HFT) by proposing a continuous learning factor predictor based on graph neural networks. The model integrates multi-factor pricing theories with real-time market dynamics, effectively bypassing the limitations of existing methods that lack financial theory guidance and ignore various trend signals and their interactions. We propose three heterogeneous tasks, including price moving average regression, price gap regression and change-point detection to trace the short-, intermediate-, and long-term trend factors present in the data. In addition, this study also considers the cross-sectional correlation characteristics of future contracts, where prices of different futures often show strong dynamic correlations. Each variable (future contract) depends not only on its historical values (temporal) but also on the observation of other variables (cross-sectional). To capture these dynamic relationships more accurately, we resort to the spatio-temporal graph neural network (STGNN) to enhance the predictive power of the model. The model employs a continuous learning strategy to simultaneously consider these tasks (factors). Additionally, due to the heterogeneity of the tasks, we propose to calculate parameter importance with mutual information between original observations and the extracted features to mitigate the catastrophic forgetting (CF) problem. Empirical tests on 49 commodity futures in China's futures market demonstrate that the proposed model outperforms other state-of-the-art models in terms of prediction accuracy. Not only does this research promote the integration of financial theory and deep learning, but it also provides a scientific basis for actual trading decisions.
Authors: Danish Rizvi, David Boyle
Unmanned Aerial Vehicles (UAVs) are increasingly used as aerial base stations to provide ad hoc communications infrastructure. Building upon prior research efforts which consider either static nodes, 2D trajectories or single UAV systems, this paper focuses on the use of multiple UAVs for providing wireless communication to mobile users in the absence of terrestrial communications infrastructure. In particular, we jointly optimize UAV 3D trajectory and NOMA power allocation to maximize system throughput. Firstly, a weighted K-means-based clustering algorithm establishes UAV-user associations at regular intervals. The efficacy of training a novel Shared Deep Q-Network (SDQN) with action masking is then explored. Unlike training each UAV separately using DQN, the SDQN reduces training time by using the experiences of multiple UAVs instead of a single agent. We also show that SDQN can be used to train a multi-agent system with differing action spaces. Simulation results confirm that: 1) training a shared DQN outperforms a conventional DQN in terms of maximum system throughput (+20%) and training time (-10%); 2) it can converge for agents with different action spaces, yielding a 9% increase in throughput compared to mutual learning algorithms; and 3) combining NOMA with an SDQN architecture enables the network to achieve a better sum rate compared with existing baseline schemes.
Authors: Kristóf Németh, Dániel Hadházi
In our study, we apply artificial neural networks (ANNs) to nowcast quarterly GDP growth for the U.S. economy. Using the monthly FRED-MD database, we compare the nowcasting performance of five different ANN architectures: the multilayer perceptron (MLP), the one-dimensional convolutional neural network (1D CNN), the Elman recurrent neural network (RNN), the long short-term memory network (LSTM), and the gated recurrent unit (GRU). The empirical analysis presents the results from two distinctively different evaluation periods. The first (2012:Q1 -- 2019:Q4) is characterized by balanced economic growth, while the second (2012:Q1 -- 2022:Q4) also includes periods of the COVID-19 recession. According to our results, longer input sequences result in more accurate nowcasts in periods of balanced economic growth. However, this effect ceases above a relatively low threshold value of around six quarters (eighteen months). During periods of economic turbulence (e.g., during the COVID-19 recession), longer input sequences do not help the models' predictive performance; instead, they seem to weaken their generalization capability. Combined results from the two evaluation periods indicate that architectural features enabling for long-term memory do not result in more accurate nowcasts. On the other hand, the 1D CNN has proved to be a highly suitable model for GDP nowcasting. The network has shown good nowcasting performance among the competitors during the first evaluation period and achieved the overall best accuracy during the second evaluation period. Consequently, first in the literature, we propose the application of the 1D CNN for economic nowcasting.
Authors: Joo Hyung Lee, Wonpyo Park, Nicole Mitchell, Jonathan Pilault, Johan Obando-Ceron, Han-Byul Kim, Namhoon Lee, Elias Frantar, Yun Long, Amir Yazdanbakhsh, Shivani Agrawal, Suvinay Subramanian, Xin Wang, Sheng-Chun Kao, Xingyao Zhang, Trevor Gale, Aart Bik, Woohyun Han, Milen Ferev, Zhonglin Han, Hong-Seok Kim, Yann Dauphin, Gintare Karolina Dziugaite, Pablo Samuel Castro, Utku Evci
This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research. JaxPruner aims to accelerate research on sparse neural networks by providing concise implementations of popular pruning and sparse training algorithms with minimal memory and latency overhead. Algorithms implemented in JaxPruner use a common API and work seamlessly with the popular optimization library Optax, which, in turn, enables easy integration with existing JAX based libraries. We demonstrate this ease of integration by providing examples in four different codebases: Scenic, t5x, Dopamine and FedJAX and provide baseline experiments on popular benchmarks.
Authors: Hans W. A. Hanley, Zakir Durumeric
As large language models (LLMs) like ChatGPT have gained traction, an increasing number of news websites have begun utilizing them to generate articles. However, not only can these language models produce factually inaccurate articles on reputable websites but disreputable news sites can utilize LLMs to mass produce misinformation. To begin to understand this phenomenon, we present one of the first large-scale studies of the prevalence of synthetic articles within online news media. To do this, we train a DeBERTa-based synthetic news detector and classify over 15.90 million articles from 3,074 misinformation and mainstream news websites. We find that between January 1, 2022, and May 1, 2023, the relative number of synthetic news articles increased by 55.4% on mainstream websites while increasing by 457% on misinformation sites. We find that this increase is largely driven by smaller less popular websites. Analyzing the impact of the release of ChatGPT using an interrupted-time-series, we show that while its release resulted in a marked increase in synthetic articles on small sites as well as misinformation news websites, there was not a corresponding increase on large mainstream news websites.
Authors: Keisuke Fujii, Kazushi Tsutsui, Atom Scott, Hiroshi Nakahara, Naoya Takeishi, Yoshinobu Kawahara
Modeling of real-world biological multi-agents is a fundamental problem in various scientific and engineering fields. Reinforcement learning (RL) is a powerful framework to generate flexible and diverse behaviors in cyberspace; however, when modeling real-world biological multi-agents, there is a domain gap between behaviors in the source (i.e., real-world data) and the target (i.e., cyberspace for RL), and the source environment parameters are usually unknown. In this paper, we propose a method for adaptive action supervision in RL from real-world demonstrations in multi-agent scenarios. We adopt an approach that combines RL and supervised learning by selecting actions of demonstrations in RL based on the minimum distance of dynamic time warping for utilizing the information of the unknown source dynamics. This approach can be easily applied to many existing neural network architectures and provide us with an RL model balanced between reproducibility as imitation and generalization ability to obtain rewards in cyberspace. In the experiments, using chase-and-escape and football tasks with the different dynamics between the unknown source and target environments, we show that our approach achieved a balance between the reproducibility and the generalization ability compared with the baselines. In particular, we used the tracking data of professional football players as expert demonstrations in football and show successful performances despite the larger gap between behaviors in the source and target environments than the chase-and-escape task.
Authors: Lean Wang, Lei Li, Damai Dai, Deli Chen, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun
In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks. However, the underlying mechanism of how LLMs learn from the provided context remains under-explored. In this paper, we investigate the working mechanism of ICL through an information flow lens. Our findings reveal that label words in the demonstration examples function as anchors: (1) semantic information aggregates into label word representations during the shallow computation layers' processing; (2) the consolidated information in label words serves as a reference for LLMs' final predictions. Based on these insights, we introduce an anchor re-weighting method to improve ICL performance, a demonstration compression technique to expedite inference, and an analysis framework for diagnosing ICL errors in GPT2-XL. The promising applications of our findings again validate the uncovered ICL working mechanism and pave the way for future studies.
Authors: Wang Zhu, Jesse Thomason, Robin Jia
We train a language model (LM) to robustly answer multistep questions by generating and answering sub-questions. We propose Chain-of-Questions, a framework that trains a model to generate sub-questions and sub-answers one at a time by leveraging human annotated question decomposition meaning representation (QDMR). The key technical challenge is that QDMR only contains sub-questions but not answers to those sub-questions, so we treat sub-answers as latent variables and optimize them using a novel dynamic mixture of Hard-EM and MAPO. Chain-of-Questions greatly outperforms strong neuro-symbolic methods by 9.0 F1 on DROP contrast set, and outperforms GPT-3.5 by 24.3 F1 on HOTPOTQA adversarial set, thus demonstrating the effectiveness and robustness of our framework.
Authors: Nathanael Bosch, Philipp Hennig, Filip Tronarp
Probabilistic solvers provide a flexible and efficient framework for simulation, uncertainty quantification, and inference in dynamical systems. However, like standard solvers, they suffer performance penalties for certain stiff systems, where small steps are required not for reasons of numerical accuracy but for the sake of stability. This issue is greatly alleviated in semi-linear problems by the probabilistic exponential integrators developed in this paper. By including the fast, linear dynamics in the prior, we arrive at a class of probabilistic integrators with favorable properties. Namely, they are proven to be L-stable, and in a certain case reduce to a classic exponential integrator -- with the added benefit of providing a probabilistic account of the numerical error. The method is also generalized to arbitrary non-linear systems by imposing piece-wise semi-linearity on the prior via Jacobians of the vector field at the previous estimates, resulting in probabilistic exponential Rosenbrock methods. We evaluate the proposed methods on multiple stiff differential equations and demonstrate their improved stability and efficiency over established probabilistic solvers. The present contribution thus expands the range of problems that can be effectively tackled within probabilistic numerics.
Authors: Benedikt Brantner
One of the primary reasons behind the success of neural networks has been the emergence of an array of new, highly-successful optimizers, perhaps most importantly the Adam optimizer. It is wiedely used for training neural networks, yet notoriously hard to interpret. Lacking a clear physical intuition, Adam is difficult to generalize to manifolds. Some attempts have been made to directly apply parts of the Adam algorithm to manifolds or to find an underlying structure, but a full generalization has remained elusive. In this work a new approach is presented that leverages the special structure of the manifolds which are relevant for optimization of neural networks, such as the Stiefel manifold, the symplectic Stiefel manifold, the Grassmann manifold and the symplectic Grassmann manifold: all of these are homogeneous spaces and as such admit a global tangent space representation. This global tangent space representation is used to perform all of the steps in the Adam optimizer. The resulting algorithm is then applied to train a transformer for which orthogonality constraints are enforced up to machine precision and we observe significant speed-ups in the training process. Optimization of neural networks where they weights do not lie on a manifold is identified as a special case of the presented framkework. This allows for a flexible implementation in which the learning rate is adapted simultaneously for all parameters, irrespective of whether they are an element of a general manifold or a vector space.
Authors: Atli Kosson, Dongyang Fan, Martin Jaggi
Batch Normalization (BN) is widely used to stabilize the optimization process and improve the test performance of deep neural networks. The regularization effect of BN depends on the batch size and explicitly using smaller batch sizes with Batch Normalization, a method known as Ghost Batch Normalization (GBN), has been found to improve generalization in many settings. We investigate the effectiveness of GBN by disentangling the induced ``Ghost Noise'' from normalization and quantitatively analyzing the distribution of noise as well as its impact on model performance. Inspired by our analysis, we propose a new regularization technique called Ghost Noise Injection (GNI) that imitates the noise in GBN without incurring the detrimental train-test discrepancy effects of small batch training. We experimentally show that GNI can provide a greater generalization benefit than GBN. Ghost Noise Injection can also be beneficial in otherwise non-noisy settings such as layer-normalized networks, providing additional evidence of the usefulness of Ghost Noise in Batch Normalization as a regularizer.
Authors: Peter Sorrenson, Felix Draxler, Armand Rousselot, Sander Hummerich, Lea Zimmermann, Ullrich Köthe
Normalizing Flows explicitly maximize a full-dimensional likelihood on the training data. However, real data is typically only supported on a lower-dimensional manifold leading the model to expend significant compute on modeling noise. Injective Flows fix this by jointly learning a manifold and the distribution on it. So far, they have been limited by restrictive architectures and/or high computational cost. We lift both constraints by a new efficient estimator for the maximum likelihood loss, compatible with free-form bottleneck architectures. We further show that naively learning both the data manifold and the distribution on it can lead to divergent solutions, and use this insight to motivate a stable maximum likelihood training objective. We perform extensive experiments on toy, tabular and image data, demonstrating the competitive performance of the resulting model.
Authors: Max van Spengler, Philipp Wirth, Pascal Mettes
Deep learning in hyperbolic space is quickly gaining traction in the fields of machine learning, multimedia, and computer vision. Deep networks commonly operate in Euclidean space, implicitly assuming that data lies on regular grids. Recent advances have shown that hyperbolic geometry provides a viable alternative foundation for deep learning, especially when data is hierarchical in nature and when working with few embedding dimensions. Currently however, no accessible open-source library exists to build hyperbolic network modules akin to well-known deep learning libraries. We present HypLL, the Hyperbolic Learning Library to bring the progress on hyperbolic deep learning together. HypLL is built on top of PyTorch, with an emphasis in its design for ease-of-use, in order to attract a broad audience towards this new and open-ended research direction. The code is available at: https://github.com/maxvanspengler/hyperbolic_learning_library.
Authors: Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher Ré, Clark Barrett, Zhangyang Wang, Beidi Chen
Large Language Models (LLMs), despite their recent impressive accomplishments, are notably cost-prohibitive to deploy, particularly for applications involving long-content generation, such as dialogue systems and story writing. Often, a large amount of transient state information, referred to as the KV cache, is stored in GPU memory in addition to model parameters, scaling linearly with the sequence length and batch size. In this paper, we introduce a novel approach for implementing the KV cache which significantly reduces its memory footprint. Our approach is based on the noteworthy observation that a small portion of tokens contributes most of the value when computing attention scores. We call these tokens Heavy Hitters (H$_2$). Through a comprehensive investigation, we find that (i) the emergence of H$_2$ is natural and strongly correlates with the frequent co-occurrence of tokens in the text, and (ii) removing them results in significant performance degradation. Based on these insights, we propose Heavy Hitter Oracle (H$_2$O), a KV cache eviction policy that dynamically retains a balance of recent and H$_2$ tokens. We formulate the KV cache eviction as a dynamic submodular problem and prove (under mild assumptions) a theoretical guarantee for our novel eviction algorithm which could help guide future work. We validate the accuracy of our algorithm with OPT, LLaMA, and GPT-NeoX across a wide range of tasks. Our implementation of H$_2$O with 20% heavy hitters improves the throughput over three leading inference systems DeepSpeed Zero-Inference, Hugging Face Accelerate, and FlexGen by up to 29$\times$, 29$\times$, and 3$\times$ on OPT-6.7B and OPT-30B. With the same batch size, H2O can reduce the latency by up to 1.9$\times$. The code is available at https://github.com/FMInference/H2O.
Authors: Andrea Coccaro, Francesco Armando Di Bello, Stefano Giagu, Lucrezia Rambelli, Nicola Stocchetti
Experimental particle physics demands a sophisticated trigger and acquisition system capable to efficiently retain the collisions of interest for further investigation. Heterogeneous computing with the employment of FPGA cards may emerge as a trending technology for the triggering strategy of the upcoming high-luminosity program of the Large Hadron Collider at CERN. In this context, we present two machine-learning algorithms for selecting events where neutral long-lived particles decay within the detector volume studying their accuracy and inference time when accelerated on commercially available Xilinx FPGA accelerator cards. The inference time is also confronted with a CPU- and GPU-based hardware setup. The proposed new algorithms are proven efficient for the considered benchmark physics scenario and their accuracy is found to not degrade when accelerated on the FPGA cards. The results indicate that all tested architectures fit within the latency requirements of a second-level trigger farm and that exploiting accelerator technologies for real-time processing of particle-physics collisions is a promising research field that deserves additional investigations, in particular with machine-learning models with a large number of trainable parameters.
Authors: Raghav Soni, Daniel Harnack, Hauke Isermann, Sotaro Fushimi, Shivesh Kumar, Frank Kirchner
Legged locomotion is arguably the most suited and versatile mode to deal with natural or unstructured terrains. Intensive research into dynamic walking and running controllers has recently yielded great advances, both in the optimal control and reinforcement learning (RL) literature. Hopping is a challenging dynamic task involving a flight phase and has the potential to increase the traversability of legged robots. Model based control for hopping typically relies on accurate detection of different jump phases, such as lift-off or touch down, and using different controllers for each phase. In this paper, we present a end-to-end RL based torque controller that learns to implicitly detect the relevant jump phases, removing the need to provide manual heuristics for state detection. We also extend a method for simulation to reality transfer of the learned controller to contact rich dynamic tasks, resulting in successful deployment on the robot after training without parameter tuning.
Authors: Hans W. A. Hanley, Deepak Kumar, Zakir Durumeric
Misinformation, propaganda, and outright lies proliferate on the web, with some narratives having dangerous real-world consequences on public health, elections, and individual safety. However, despite the impact of misinformation, the research community largely lacks automated and programmatic approaches for tracking news narratives across online platforms. In this work, utilizing daily scrapes of 1,334 unreliable news websites, the large-language model MPNet, and DP-Means clustering, we introduce a system to automatically identify and track the narratives spread within online ecosystems. Identifying 52,036 narratives on these 1,334 websites, we describe the most prevalent narratives spread in 2022 and identify the most influential websites that originate and amplify narratives. Finally, we show how our system can be utilized to detect new narratives originating from unreliable news websites and to aid fact-checkers in more quickly addressing misinformation. We release code and data at https://github.com/hanshanley/specious-sites.
Authors: Jae Yong Lee, Seungchan Ko, Youngjoon Hong
Partial differential equations (PDEs) underlie our understanding and prediction of natural phenomena across numerous fields, including physics, engineering, and finance. However, solving parametric PDEs is a complex task that necessitates efficient numerical methods. In this paper, we propose a novel approach for solving parametric PDEs using a Finite Element Operator Network (FEONet). Our proposed method leverages the power of deep learning in conjunction with traditional numerical methods, specifically the finite element method, to solve parametric PDEs in the absence of any paired input-output training data. We performed various experiments on several benchmark problems and confirmed that our approach has demonstrated excellent performance across various settings and environments, proving its versatility in terms of accuracy, generalization, and computational flexibility. Our FEONet framework shows potential for application in various fields where PDEs play a crucial role in modeling complex domains with diverse boundary conditions and singular behavior. Furthermore, we provide theoretical convergence analysis to support our approach, utilizing finite element approximation in numerical analysis.
Authors: Yanci Zhang, Han Yu
Federated learning (FL) is an emerging approach for training machine learning models collaboratively while preserving data privacy. The need for privacy protection makes it difficult for FL models to achieve global transparency and explainability. To address this limitation, we incorporate logic-based explanations into FL by proposing the Logical Reasoning-based eXplainable Federated Learning (LR-XFL) approach. Under LR-XFL, FL clients create local logic rules based on their local data and send them, along with model updates, to the FL server. The FL server connects the local logic rules through a proper logical connector that is derived based on properties of client data, without requiring access to the raw data. In addition, the server also aggregates the local model updates with weight values determined by the quality of the clients' local data as reflected by their uploaded logic rules. The results show that LR-XFL outperforms the most relevant baseline by 1.19%, 5.81% and 5.41% in terms of classification accuracy, rule accuracy and rule fidelity, respectively. The explicit rule evaluation and expression under LR-XFL enable human experts to validate and correct the rules on the server side, hence improving the global FL model's robustness to errors. It has the potential to enhance the transparency of FL models for areas like healthcare and finance where both data privacy and explainability are important.
Authors: B. A. Schreiber, J. Denholm, F. Jaeckle, M. J. Arends, K. M. Branson, C.-B. Schönlieb, E. J. Soilleux
We present an innovative method for rapidly segmenting hematoxylin and eosin (H&E)-stained tissue in whole-slide images (WSIs) that eliminates a wide range of undesirable artefacts such as pen marks and scanning artefacts. Our method involves taking a single-channel representation of a lowmagnification RGB overview of the WSI in which the pixel values are bimodally distributed such that H&E-stained tissue is easily distinguished from both background and a wide variety of artefacts. We demonstrate our method on 30 WSIs prepared from a wide range of institutions and WSI digital scanners, each containing substantial artefacts, and compare it to segmentations provided by Otsu thresholding and Histolab tissue segmentation and pen filtering tools. We found that our method segmented the tissue and fully removed all artefacts in 29 out of 30 WSIs, whereas Otsu thresholding failed to remove any artefacts, and the Histolab pen filtering tools only partially removed the pen marks. The beauty of our approach lies in its simplicity: manipulating RGB colour space and using Otsu thresholding allows for the segmentation of H&E-stained tissue and the rapid removal of artefacts without the need for machine learning or parameter tuning.
Authors: Yu Wang, Xin Xin, Zaiqiao Meng, Joemon Jose, Fuli Feng
Learning from corrupted labels is very common in real-world machine-learning applications. Memorizing such noisy labels could affect the learning of the model, leading to sub-optimal performances. In this work, we propose a novel framework to learn robust machine-learning models from noisy labels. Through an empirical study, we find that different models make relatively similar predictions on clean examples, while the predictions on noisy examples vary much more across different models. Motivated by this observation, we propose \em denoising with cross-model agreement \em (DeCA) which aims to minimize the KL-divergence between the true label distributions parameterized by two machine learning models while maximizing the likelihood of data observation. We employ the proposed DeCA on both the binary label scenario and the multiple label scenario. For the binary label scenario, we select implicit feedback recommendation as the downstream task and conduct experiments with four state-of-the-art recommendation models on four datasets. For the multiple-label scenario, the downstream application is image classification on two benchmark datasets. Experimental results demonstrate that the proposed methods significantly improve the model performance compared with normal training and other denoising methods on both binary and multiple-label scenarios.
Authors: Mingxin Li, Richong Zhang, Zhijie Nie, Yongyi Mao
Sentence Representation Learning (SRL) is a fundamental task in Natural Language Processing (NLP), with the Contrastive Learning of Sentence Embeddings (CSE) being the mainstream technique due to its superior performance. An intriguing phenomenon in CSE is the significant performance gap between supervised and unsupervised methods, with their only difference lying in the training data. Previous works attribute this performance gap to differences in two representation properties (alignment and uniformity). However, since alignment and uniformity only measure the results, they fail to answer "What aspects of the training data contribute to the performance gap?" and "How can the performance gap be narrowed?", In this paper, we conduct empirical experiments to answer these "What" and "How" questions. We first answer the "What" question by thoroughly comparing the behavior of supervised and unsupervised CSE during their respective training processes. From the comparison, we identify the similarity pattern as a key factor to the performance gap, and introduce a metric, called Relative Fitting Difficulty (RFD), to measure the complexity of the similarity pattern. Then, based on the insights gained from the "What" question, we tackle the "How" question by increasing the pattern complexity of the training data. We achieve this by leveraging the In-Context Learning (ICL) capability of the Large Language Model (LLM) to generate data that simulates complex patterns. By utilizing the hierarchical patterns in the LLM-generated data, we effectively narrow the gap between supervised and unsupervised CSE. We release our codes and appendix at https://github.com/BDBC-KG-NLP/NGCSE.
Authors: Clayton W. Kosonocky, Claus O. Wilke, Edward M. Marcotte, Andrew D. Ellington
The fundamental goal of small molecule discovery is to generate chemicals with target functionality. While this often proceeds through structure-based methods, we set out to investigate the practicality of orthogonal methods that leverage the extensive corpus of chemical literature. We hypothesize that a sufficiently large text-derived chemical function dataset would mirror the actual landscape of chemical functionality. Such a landscape would implicitly capture complex physical and biological interactions given that chemical function arises from both a molecule's structure and its interacting partners. To evaluate this hypothesis, we built a Chemical Function (CheF) dataset of patent-derived functional labels. This dataset, comprising 631K molecule-function pairs, was created using an LLM- and embedding-based method to obtain functional labels for approximately 100K molecules from their corresponding 188K unique patents. We carry out a series of analyses demonstrating that the CheF dataset contains a semantically coherent textual representation of the functional landscape congruent with chemical structural relationships, thus approximating the actual chemical function landscape. We then demonstrate that this text-based functional landscape can be leveraged to identify drugs with target functionality using a model able to predict functional profiles from structure alone. We believe that functional label-guided molecular discovery may serve as an orthogonal approach to traditional structure-based methods in the pursuit of designing novel functional molecules.
Authors: Hitesh Sagtani, Madan Jhawar, Rishabh Mehrotra, Olivier Jeunen
Ad-load balancing is a critical challenge in online advertising systems, particularly in the context of social media platforms, where the goal is to maximize user engagement and revenue while maintaining a satisfactory user experience. This requires the optimization of conflicting objectives, such as user satisfaction and ads revenue. Traditional approaches to ad-load balancing rely on static allocation policies, which fail to adapt to changing user preferences and contextual factors. In this paper, we present an approach that leverages off-policy learning and evaluation from logged bandit feedback. We start by presenting a motivating analysis of the ad-load balancing problem, highlighting the conflicting objectives between user satisfaction and ads revenue. We emphasize the nuances that arise due to user heterogeneity and the dependence on the user's position within a session. Based on this analysis, we define the problem as determining the optimal ad-load for a particular feed fetch. To tackle this problem, we propose an off-policy learning framework that leverages unbiased estimators such as Inverse Propensity Scoring (IPS) and Doubly Robust (DR) to learn and estimate the policy values using offline collected stochastic data. We present insights from online A/B experiments deployed at scale across over 80 million users generating over 200 million sessions, where we find statistically significant improvements in both user satisfaction metrics and ads revenue for the platform.
Authors: Baris Ata, J. Michael Harrison, Nian Si
Motivated by applications in queueing theory, we consider a stochastic control problem whose state space is the $d$-dimensional positive orthant. The controlled process $Z$ evolves as a reflected Brownian motion whose covariance matrix is exogenously specified, as are its directions of reflection from the orthant's boundary surfaces. A system manager chooses a drift vector $\theta(t)$ at each time $t$ based on the history of $Z$, and the cost rate at time $t$ depends on both $Z(t)$ and $\theta(t)$. In our initial problem formulation, the objective is to minimize expected discounted cost over an infinite planning horizon, after which we treat the corresponding ergodic control problem. Extending earlier work by Han et al. (Proceedings of the National Academy of Sciences, 2018, 8505-8510), we develop and illustrate a simulation-based computational method that relies heavily on deep neural network technology. For test problems studied thus far, our method is accurate to within a fraction of one percent, and is computationally feasible in dimensions up to at least $d=30$.
Authors: Akshay J. Dave, Richard B. Vilim
This work introduces Physics-informed State-space neural network Models (PSMs), a novel solution to achieving real-time optimization, flexibility, and fault tolerance in autonomous systems, particularly in transport-dominated systems such as chemical, biomedical, and power plants. Traditional data-driven methods fall short due to a lack of physical constraints like mass conservation; PSMs address this issue by training deep neural networks with sensor data and physics-informing using components' Partial Differential Equations (PDEs), resulting in a physics-constrained, end-to-end differentiable forward dynamics model. Through two in silico experiments -- a heated channel and a cooling system loop -- we demonstrate that PSMs offer a more accurate approach than a purely data-driven model. In the former experiment, PSMs demonstrated significantly lower average root-mean-square errors across test datasets compared to a purely data-driven neural network, with reductions of 44 %, 48 %, and 94 % in predicting pressure, velocity, and temperature, respectively.
Beyond accuracy, PSMs demonstrate a compelling multitask capability, making them highly versatile. In this work, we showcase two: supervisory control of a nonlinear system through a sequentially updated state-space representation and the proposal of a diagnostic algorithm using residuals from each of the PDEs. The former demonstrates PSMs' ability to handle constant and time-dependent constraints, while the latter illustrates their value in system diagnostics and fault detection. We further posit that PSMs could serve as a foundation for Digital Twins, constantly updated digital representations of physical systems.
Authors: Mathilde Papillon, Mustafa Hajij, Helen Jenne, Johan Mathe, Audun Myers, Theodore Papamarkou, Ghada Zamzmi, Tolga Birdal, Tamal Dey, Tim Doster, Tegan Emerson, Gurusankar Gopalakrishnan, Devendra Govil, Aldo Guzmán-Sáenz, Henry Kvinge, Neal Livesay, Soham Mukherjee, Shreyas N. Samaga, Karthikeyan Natesan Ramamurthy, Maneel Reddy Karri, Paul Rosen, Sophia Sanborn, Robin Walters, Jens Agerberg, Sadrodin Barikbin, Claudio Battiloro, Gleb Bazhenov, Guillermo Bernardez, Aiden Brent, Sergio Escalera, Simone Fiorellino, Dmitrii Gavrilev, Mohammed Hassanin, Paul Häusner, Odin Hoff Gardaa, Abdelwahed Khamis, Manuel Lecha, German Magai, Tatiana Malygina, Rubén Ballester, Kalyan Nadimpalli, Alexander Nikitin, Abraham Rabinowitz, Alessandro Salatiello, Simone Scardapane, Luca Scofano, et al. (11 additional authors not shown)
This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning. The competition asked participants to provide open-source implementations of topological neural networks from the literature by contributing to the python packages TopoNetX (data processing) and TopoModelX (deep learning). The challenge attracted twenty-eight qualifying submissions in its two-month duration. This paper describes the design of the challenge and summarizes its main findings.
Authors: Zhiqian Lan, Yuxuan Jiang, Yao Mu, Chen Chen, Shengbo Eben Li
Motion prediction is crucial for autonomous vehicles to operate safely in complex traffic environments. Extracting effective spatiotemporal relationships among traffic elements is key to accurate forecasting. Inspired by the successful practice of pretrained large language models, this paper presents SEPT, a modeling framework that leverages self-supervised learning to develop powerful spatiotemporal understanding for complex traffic scenes. Specifically, our approach involves three masking-reconstruction modeling tasks on scene inputs including agents' trajectories and road network, pretraining the scene encoder to capture kinematics within trajectory, spatial structure of road network, and interactions among roads and agents. The pretrained encoder is then finetuned on the downstream forecasting task. Extensive experiments demonstrate that SEPT, without elaborate architectural design or manual feature engineering, achieves state-of-the-art performance on the Argoverse 1 and Argoverse 2 motion forecasting benchmarks, outperforming previous methods on all main metrics by a large margin.
Authors: Hao Liu, Jiarui Feng, Lecheng Kong, Ningyue Liang, Dacheng Tao, Yixin Chen, Muhan Zhang
Designing a single model to address multiple tasks has been a long-standing objective in artificial intelligence. Recently, large language models have demonstrated exceptional capability in solving different tasks within the language domain. However, a unified model for various graph tasks remains underexplored, primarily due to the challenges unique to the graph learning domain. First, graph data from different areas carry distinct attributes and follow different distributions. Such discrepancy makes it hard to represent graphs in a single representation space. Second, tasks on graphs diversify into node, link, and graph tasks, requiring distinct embedding strategies. Finally, an appropriate graph prompting paradigm for in-context learning is unclear. We propose \textbf{One for All (OFA)}, the first general framework that can use a single graph model to address the above challenges. Specifically, OFA proposes text-attributed graphs to unify different graph data by describing nodes and edges with natural language and uses language models to encode the diverse and possibly cross-domain text attributes to feature vectors in the same embedding space. Furthermore, OFA introduces the concept of nodes-of-interest to standardize different tasks with a single task representation. For in-context learning on graphs, OFA introduces a novel graph prompting paradigm that appends prompting substructures to the input graph, which enables it to address varied tasks without fine-tuning. We train the OFA model using graph data from multiple domains (including citation networks, molecular graphs, knowledge graphs, etc.) simultaneously and evaluate its ability in supervised, few-shot, and zero-shot learning scenarios. OFA performs well across different tasks, making it the first general-purpose across-domains classification model on graphs.
Authors: Soroosh Tayebi Arasteh, Christiane Kuhl, Marwin-Jonathan Saehn, Peter Isfort, Daniel Truhn, Sven Nebelung
Developing robust artificial intelligence (AI) models that generalize well to unseen datasets is challenging and usually requires large and variable datasets, preferably from multiple institutions. In federated learning (FL), a model is trained collaboratively at numerous sites that hold local datasets without exchanging them. So far, the impact of training strategy, i.e., local versus collaborative, on the diagnostic on-domain and off-domain performance of AI models interpreting chest radiographs has not been assessed. Consequently, using 610,000 chest radiographs from five institutions across the globe, we assessed diagnostic performance as a function of training strategy (i.e., local vs. collaborative), network architecture (i.e., convolutional vs. transformer-based), generalization performance (i.e., on-domain vs. off-domain), imaging finding (i.e., cardiomegaly, pleural effusion, pneumonia, atelectasis, consolidation, pneumothorax, and no abnormality), dataset size (i.e., from n=18,000 to 213,921 radiographs), and dataset diversity. Large datasets not only showed minimal performance gains with FL but, in some instances, even exhibited decreases. In contrast, smaller datasets revealed marked improvements. Thus, on-domain performance was mainly driven by training data size. However, off-domain performance leaned more on training diversity. When trained collaboratively across diverse external institutions, AI models consistently surpassed models trained locally for off-domain tasks, emphasizing FL's potential in leveraging data diversity. In conclusion, FL can bolster diagnostic privacy, reproducibility, and off-domain reliability of AI models and, potentially, optimize healthcare outcomes.
Authors: Xavier Tan, Han Yu
The success of Federated Learning (FL) depends on the quantity and quality of the data owners (DOs) as well as their motivation to join FL model training. Reputation-based FL participant selection methods have been proposed. However, they still face the challenges of the cold start problem and potential selection bias towards highly reputable DOs. Such a bias can result in lower reputation DOs being prematurely excluded from future FL training rounds, thereby reducing the diversity of training data and the generalizability of the resulting models. To address these challenges, we propose the Gradual Participant Selection scheme for Auction-based Federated Learning (GPS-AFL). Unlike existing AFL incentive mechanisms which generally assume that all DOs required for an FL task must be selected in one go, GPS-AFL gradually selects the required DOs over multiple rounds of training as more information is revealed through repeated interactions. It is designed to strike a balance between cost saving and performance enhancement, while mitigating the drawbacks of selection bias in reputation-based FL. Extensive experiments based on real-world datasets demonstrate the significant advantages of GPS-AFL, which reduces costs by 33.65% and improved total utility by 2.91%, on average compared to the best-performing state-of-the-art approach.
Authors: Anej Svete, Ryan Cotterell
Studying language models (LMs) in terms of well-understood formalisms allows us to precisely characterize their abilities and limitations. Previous work has investigated the representational capacity of recurrent neural network (RNN) LMs in terms of their capacity to recognize unweighted formal languages. However, LMs do not describe unweighted formal languages -- rather, they define \emph{probability distributions} over strings. In this work, we study what classes of such probability distributions RNN LMs can represent, which allows us to make more direct statements about their capabilities. We show that simple RNNs are equivalent to a subclass of probabilistic finite-state automata, and can thus model a strict subset of probability distributions expressible by finite-state models. Furthermore, we study the space complexity of representing finite-state LMs with RNNs. We show that, to represent an arbitrary deterministic finite-state LM with $N$ states over an alphabet $\alphabet$, an RNN requires $\Omega\left(N |\Sigma|\right)$ neurons. These results present a first step towards characterizing the classes of distributions RNN LMs can represent and thus help us understand their capabilities and limitations.
Authors: Peter S. Park, Max Tegmark
AI companies are attempting to create AI systems that outperform humans at most economically valuable work. Current AI models are already automating away the livelihoods of some artists, actors, and writers. But there is infighting between those who prioritize current harms and future harms. We construct a game-theoretic model of conflict to study the causes and consequences of this disunity. Our model also helps explain why throughout history, stakeholders sharing a common threat have found it advantageous to unite against it, and why the common threat has in turn found it advantageous to divide and conquer.
Under realistic parameter assumptions, our model makes several predictions that find preliminary corroboration in the historical-empirical record. First, current victims of AI-driven disempowerment need the future victims to realize that their interests are also under serious and imminent threat, so that future victims are incentivized to support current victims in solidarity. Second, the movement against AI-driven disempowerment can become more united, and thereby more likely to prevail, if members believe that their efforts will be successful as opposed to futile. Finally, the movement can better unite and prevail if its members are less myopic. Myopic members prioritize their future well-being less than their present well-being, and are thus disinclined to solidarily support current victims today at personal cost, even if this is necessary to counter the shared threat of AI-driven disempowerment.
Authors: Cong Dao Tran, Truong Son Hy
Recently, Deep reinforcement learning (DRL) models have shown promising results in solving routing problems. However, most DRL solvers are commonly proposed to solve node routing problems, such as the Traveling Salesman Problem (TSP). Meanwhile, there has been limited research on applying neural methods to arc routing problems, such as the Chinese Postman Problem (CPP), since they often feature irregular and complex solution spaces compared to TSP. To fill these gaps, this paper proposes a novel DRL framework to address the CPP with load-dependent costs (CPP-LC) (Corberan et al., 2018), which is a complex arc routing problem with load constraints. The novelty of our method is two-fold. First, we formulate the CPP-LC as a Markov Decision Process (MDP) sequential model. Subsequently, we introduce an autoregressive model based on DRL, namely Arc-DRL, consisting of an encoder and decoder to address the CPP-LC challenge effectively. Such a framework allows the DRL model to work efficiently and scalably to arc routing problems. Furthermore, we propose a new bio-inspired meta-heuristic solution based on Evolutionary Algorithm (EA) for CPP-LC. Extensive experiments show that Arc-DRL outperforms existing meta-heuristic methods such as Iterative Local Search (ILS) and Variable Neighborhood Search (VNS) proposed by (Corberan et al., 2018) on large benchmark datasets for CPP-LC regarding both solution quality and running time; while the EA gives the best solution quality with much more running time. We release our C++ implementations for metaheuristics such as EA, ILS and VNS along with the code for data generation and our generated data at https://github.com/HySonLab/Chinese_Postman_Problem
Authors: Yuan Peiwen, Zhu Changsheng
There has been an emergence of various models for long-term time series forecasting. Recent studies have demonstrated that a single linear layer, using Channel Dependent (CD) or Channel Independent (CI) modeling, can even outperform a large number of sophisticated models. However, current research primarily considers CD and CI as two complementary yet mutually exclusive approaches, unable to harness these two extremes simultaneously. And it is also a challenging issue that both CD and CI are static strategies that cannot be determined to be optimal for a specific dataset without extensive experiments. In this paper, we reconsider whether the current CI strategy is the best solution for time series forecasting. First, we propose a simple yet effective strategy called CSC, which stands for $\mathbf{C}$hannel $\mathbf{S}$elf-$\mathbf{C}$lustering strategy, for linear models. Our Channel Self-Clustering (CSC) enhances CI strategy's performance improvements while reducing parameter size, for exmpale by over 10 times on electricity dataset, and significantly cutting training time. Second, we further propose Channel Rearrangement (CR), a method for deep models inspired by the self-clustering. CR attains competitive performance against baselines. Finally, we also discuss whether it is best to forecast the future values using the historical values of the same channel as inputs. We hope our findings and methods could inspire new solutions beyond CD/CI.
Authors: Houwen Peng, Kan Wu, Yixuan Wei, Guoshuai Zhao, Yuxiang Yang, Ze Liu, Yifan Xiong, Ziyue Yang, Bolin Ni, Jingcheng Hu, Ruihang Li, Miaosen Zhang, Chen Li, Jia Ning, Ruizhe Wang, Zheng Zhang, Shuguang Liu, Joe Chau, Han Hu, Peng Cheng
In this paper, we explore FP8 low-bit data formats for efficient training of large language models (LLMs). Our key insight is that most variables, such as gradients and optimizer states, in LLM training can employ low-precision data formats without compromising model accuracy and requiring no changes to hyper-parameters. Specifically, we propose a new FP8 automatic mixed-precision framework for training LLMs. This framework offers three levels of FP8 utilization to streamline mixed-precision and distributed parallel training for LLMs. It gradually incorporates 8-bit gradients, optimizer states, and distributed learning in an incremental manner. Experiment results show that, during the training of GPT-175B model on H100 GPU platform, our FP8 mixed-precision training framework not only achieved a remarkable 39% reduction in real memory usage but also ran 75% faster than the widely adopted BF16 framework (i.e., Megatron-LM), surpassing the speed of Nvidia Transformer Engine by 37%. This largely reduces the training costs for large foundation models. Furthermore, our FP8 mixed-precision training methodology is generic. It can be seamlessly applied to other tasks such as LLM instruction tuning and reinforcement learning with human feedback, offering savings in fine-tuning expenses. Our FP8 low-precision training framework is open-sourced at {https://github.com/Azure/MS-AMP}{aka.ms/MS.AMP}.
Authors: Yann Hicke, Anmol Agarwal, Qianou Ma, Paul Denny
Responding to the thousands of student questions on online QA platforms each semester has a considerable human cost, particularly in computing courses with rapidly growing enrollments. To address the challenges of scalable and intelligent question-answering (QA), we introduce an innovative solution that leverages open-source Large Language Models (LLMs) from the LLaMA-2 family to ensure data privacy. Our approach combines augmentation techniques such as retrieval augmented generation (RAG), supervised fine-tuning (SFT), and learning from human preferences data using Direct Preference Optimization (DPO). Through extensive experimentation on a Piazza dataset from an introductory CS course, comprising 10,000 QA pairs and 1,500 pairs of preference data, we demonstrate a significant 30% improvement in the quality of answers, with RAG being a particularly impactful addition. Our contributions include the development of a novel architecture for educational QA, extensive evaluations of LLM performance utilizing both human assessments and LLM-based metrics, and insights into the challenges and future directions of educational data processing. This work paves the way for the development of AI-TA, an intelligent QA assistant customizable for courses with an online QA platform
Authors: Jiachen Zhao
Recently, large language models (LLMs) have made remarkable progress in natural language processing. The most representative ability of LLMs is in-context learning (ICL), which enables LLMs to learn patterns from in-context exemplars without training. The performance of ICL greatly depends on the exemplars used. However, how to choose exemplars remains unclear due to the lack of understanding of how in-context learning works. In this paper, we present a novel perspective on ICL by conceptualizing it as contextual retrieval from a model of associative memory. We establish a theoretical framework of ICL based on Hopfield Networks. Based on our framework, we look into how in-context exemplars influence the performance of ICL and propose more efficient active exemplar selection. Our study sheds new light on the mechanism of ICL by connecting it to memory retrieval, with potential implications for advancing the understanding of LLMs.
Authors: Xiangguo Sun, Hong Cheng, Hang Dong, Bo Qiao, Si Qin, Qingwei Lin
Scoring systems are commonly seen for platforms in the era of big data. From credit scoring systems in financial services to membership scores in E-commerce shopping platforms, platform managers use such systems to guide users towards the encouraged activity pattern, and manage resources more effectively and more efficiently thereby. To establish such scoring systems, several "empirical criteria" are firstly determined, followed by dedicated top-down design for each factor of the score, which usually requires enormous effort to adjust and tune the scoring function in the new application scenario. What's worse, many fresh projects usually have no ground-truth or any experience to evaluate a reasonable scoring system, making the designing even harder. To reduce the effort of manual adjustment of the scoring function in every new scoring system, we innovatively study the scoring system from the preset empirical criteria without any ground truth, and propose a novel framework to improve the system from scratch. In this paper, we propose a "counter-empirical attacking" mechanism that can generate "attacking" behavior traces and try to break the empirical rules of the scoring system. Then an adversarial "enhancer" is applied to evaluate the scoring system and find the improvement strategy. By training the adversarial learning problem, a proper scoring function can be learned to be robust to the attacking activity traces that are trying to violate the empirical criteria. Extensive experiments have been conducted on two scoring systems including a shared computing resource platform and a financial credit system. The experimental results have validated the effectiveness of our proposed framework.
Authors: Javier Marin
In recent years, significant progress in generative AI has highlighted the important role of physics-inspired models that utilize advanced mathematical concepts based on fundamental physics principles to enhance artificial intelligence capabilities. Among these models, those based on diffusion equations have greatly improved image quality. This study aims to explore the potential uses of Maxwell-Boltzmann equation, which forms the basis of the kinetic theory of gases, and the Michaelis-Menten model in Marketing Mix Modelling (MMM) applications. We propose incorporating these equations into Hierarchical Bayesian models to analyse consumer behaviour in the context of advertising. These equation sets excel in accurately describing the random dynamics in complex systems like social interactions and consumer-advertising interactions.
Authors: Franz A. Heinsen
We find a succinct expression for computing the sequence $x_t = a_t x_{t-1} + b_t$ in parallel with two prefix sums, given $t = (1, 2, \dots, n)$, $a_t \in \mathbb{R}^n$, $b_t \in \mathbb{R}^n$, and initial value $x_0 \in \mathbb{R}$. On $n$ parallel processors, the computation of $n$ elements incurs $\mathcal{O}(\log n)$ time and $\mathcal{O}(n)$ space. Sequences of this form are ubiquitous in science and engineering, making efficient parallelization useful for a vast number of applications. We implement our expression in software, test it on parallel hardware, and verify that it executes faster than sequential computation by a factor of $\frac{n}{\log n}$.
Authors: Josh Andle, Ali Payani, Salimeh Yasaei-Sekeh
Continual Learning (CL) has generated attention as a method of avoiding Catastrophic Forgetting (CF) in the sequential training of neural networks, improving network efficiency and adaptability to different tasks. Additionally, CL serves as an ideal setting for studying network behavior and Forward Knowledge Transfer (FKT) between tasks. Pruning methods for CL train subnetworks to handle the sequential tasks which allows us to take a structured approach to investigating FKT. Sharing prior subnetworks' weights leverages past knowledge for the current task through FKT. Understanding which weights to share is important as sharing all weights can yield sub-optimal accuracy. This paper investigates how different sharing decisions affect the FKT between tasks. Through this lens we demonstrate how task complexity and similarity influence the optimal weight sharing decisions, giving insights into the relationships between tasks and helping inform decision making in similar CL methods. We implement three sequential datasets designed to emphasize variation in task complexity and similarity, reporting results for both ResNet-18 and VGG-16. By sharing in accordance with the decisions supported by our findings, we show that we can improve task accuracy compared to other sharing decisions.
Authors: Alexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook, Andrei Lupu, Gardar Ingvarsson, Timon Willi, Akbir Khan, Christian Schroeder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert Tjarko Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktaschel, Chris Lu, Jakob Nicolaus Foerster
Benchmarks play an important role in the development of machine learning algorithms. For example, research in reinforcement learning (RL) has been heavily influenced by available environments and benchmarks. However, RL environments are traditionally run on the CPU, limiting their scalability with typical academic compute. Recent advancements in JAX have enabled the wider use of hardware acceleration to overcome these computational hurdles, enabling massively parallel RL training pipelines and environments. This is particularly useful for multi-agent reinforcement learning (MARL) research. First of all, multiple agents must be considered at each environment step, adding computational burden, and secondly, the sample complexity is increased due to non-stationarity, decentralised partial observability, or other MARL challenges. In this paper, we present JaxMARL, the first open-source code base that combines ease-of-use with GPU enabled efficiency, and supports a large number of commonly used MARL environments as well as popular baseline algorithms. When considering wall clock time, our experiments show that per-run our JAX-based training pipeline is up to 12500x faster than existing approaches. This enables efficient and thorough evaluations, with the potential to alleviate the evaluation crisis of the field. We also introduce and benchmark SMAX, a vectorised, simplified version of the popular StarCraft Multi-Agent Challenge, which removes the need to run the StarCraft II game engine. This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL. We provide code at https://github.com/flairox/jaxmarl.
Authors: Will LeVine, Ben Pikus, Tony Chen, Sean Hendryx
Foundation models, specifically Large Language Models (LLM's), have lately gained wide-spread attention and adoption. Reinforcement Learning with Human Feedback (RLHF) involves training a reward model to capture desired behaviors, which is then used to align LLM's. These reward models are additionally used at inference-time to estimate LLM responses' adherence to those desired behaviors. However, there is little work measuring how robust these reward models are to distribution shifts. In this work, we evaluate how reward model performance - measured via accuracy and calibration (i.e. alignment between accuracy and confidence) - is affected by distribution shift. We show novel calibration patterns and accuracy drops due to OOD prompts and responses, and that the reward model is more sensitive to shifts in responses than prompts. Additionally, we adapt an OOD detection technique commonly used in classification to the reward model setting to detect these distribution shifts in prompts and responses.
Authors: Xinhui Liu, Zhenghao Chen, Luping Zhou, Dong Xu, Wei Xi, Gairui Bai, Yihan Zhao, Jizhong Zhao
Conventional Federated Domain Adaptation (FDA) approaches usually demand an abundance of assumptions, which makes them significantly less feasible for real-world situations and introduces security hazards. This paper relaxes the assumptions from previous FDAs and studies a more practical scenario named Universal Federated Domain Adaptation (UFDA). It only requires the black-box model and the label set information of each source domain, while the label sets of different source domains could be inconsistent, and the target-domain label set is totally blind. Towards a more effective solution for our newly proposed UFDA scenario, we propose a corresponding methodology called Hot-Learning with Contrastive Label Disambiguation (HCLD). It particularly tackles UFDA's domain shifts and category gaps problems by using one-hot outputs from the black-box models of various source domains. Moreover, to better distinguish the shared and unknown classes, we further present a cluster-level strategy named Mutual-Voting Decision (MVD) to extract robust consensus knowledge across peer classes from both source and target domains. Extensive experiments on three benchmark datasets demonstrate that our method achieves comparable performance for our UFDA scenario with much fewer assumptions, compared to previous methodologies with comprehensive additional assumptions.
Authors: Kaiwen Hou
This manuscript enriches the framework of continuous normalizing flows (CNFs) within causal inference, primarily to augment the geometric properties of parametric submodels used in targeted maximum likelihood estimation (TMLE). By introducing an innovative application of CNFs, we construct a refined series of parametric submodels that enable a directed interpolation between the prior distribution $p_0$ and the empirical distribution $p_1$. This proposed methodology serves to optimize the semiparametric efficiency bound in causal inference by orchestrating CNFs to align with Wasserstein gradient flows. Our approach not only endeavors to minimize the mean squared error in the estimation but also imbues the estimators with geometric sophistication, thereby enhancing robustness against misspecification. This robustness is crucial, as it alleviates the dependence on the standard $n^{\frac{1}{4}}$ rate for a doubly-robust perturbation direction in TMLE. By incorporating robust optimization principles and differential geometry into the estimators, the developed geometry-aware CNFs represent a significant advancement in the pursuit of doubly robust causal inference.
Authors: Tadbhagya Kumar, Anuj Kumar, Pinaki Pal
The high computational cost associated with solving for detailed chemistry poses a significant challenge for predictive computational fluid dynamics (CFD) simulations of turbulent reacting flows. These models often require solving a system of coupled stiff ordinary differential equations (ODEs). While deep learning techniques have been experimented with to develop faster surrogate models, they often fail to integrate reliably with CFD solvers. This instability arises because deep learning methods optimize for training error without ensuring compatibility with ODE solvers, leading to accumulation of errors over time. Recently, NeuralODE-based techniques have offered a promising solution by effectively modeling chemical kinetics. In this study, we extend the NeuralODE framework for stiff chemical kinetics by incorporating mass conservation constraints directly into the loss function during training. This ensures that the total mass and the elemental mass are conserved, a critical requirement for reliable downstream integration with CFD solvers. Proof-of-concept studies are performed with physics-constrained neuralODE (PC-NODE) approach for homogeneous autoignition of hydrogen-air mixture over a range of composition and thermodynamic conditions. Our results demonstrate that this enhancement not only improves the physical consistency with respect to mass conservation criteria but also ensures better robustness. Lastly, a posteriori studies are performed wherein the trained PC-NODE model is coupled with a 3D CFD solver for computing the chemical source terms. PC-NODE is shown to be more accurate relative to the purely data-driven neuralODE approach. Moreover, PC-NODE also exhibits robustness and generalizability to unseen initial conditions from within (interpolative capability) as well as outside (extrapolative capability) the training regime.
Authors: Yixuan Wang, Ruochen Jiao, Chengtian Lang, Sinong Simon Zhan, Chao Huang, Zhaoran Wang, Zhuoran Yang, Qi Zhu
Autonomous Driving (AD) faces crucial hurdles for commercial launch, notably in the form of diminished public trust and safety concerns from long-tail unforeseen driving scenarios. This predicament is due to the limitation of deep neural networks in AD software, which struggle with interpretability and exhibit poor generalization capabilities in out-of-distribution and uncertain scenarios. To this end, this paper advocates for the integration of Large Language Models (LLMs) into the AD system, leveraging their robust common-sense knowledge, reasoning abilities, and human-interaction capabilities. The proposed approach deploys the LLM as an intelligent decision-maker in planning, incorporating safety verifiers for contextual safety learning to enhance overall AD performance and safety. We present results from two case studies that affirm the efficacy of our approach. We further discuss the potential integration of LLM for other AD software components including perception, prediction, and simulation. Despite the observed challenges in the case studies, the integration of LLMs is promising and beneficial for reinforcing both safety and performance in AD.
Authors: Subhabrata Dutta, Joykirat Singh, Ishan Pandey, Sunny Manchanda, Soumen Chakrabarti, Tanmoy Chakraborty
Large Language Models (LLM) exhibit zero-shot mathematical reasoning capacity as a behavior emergent with scale, commonly manifesting as chain-of-thoughts (CoT) reasoning. However, multiple empirical findings suggest that this prowess is exclusive to LLMs with exorbitant sizes (beyond 50 billion parameters). Meanwhile, educational neuroscientists suggest that symbolic algebraic manipulation be introduced around the same time as arithmetic word problems to modularize language-to-formulation, symbolic manipulation of the formulation, and endgame arithmetic. In this paper, we start with the hypothesis that much smaller LMs, which are weak at multi-step reasoning, can achieve reasonable arithmetic reasoning if arithmetic word problems are posed as a formalize-then-solve task. In our architecture, which we call SYRELM, the LM serves the role of a translator to map natural language arithmetic questions into a formal language (FL) description. A symbolic solver then evaluates the FL expression to obtain the answer. A small frozen LM, equipped with an efficient low-rank adapter, is capable of generating FL expressions that incorporate natural language descriptions of the arithmetic problem (e.g., variable names and their purposes, formal expressions combining variables, etc.). We adopt policy-gradient reinforcement learning to train the adapted LM, informed by the non-differentiable symbolic solver. This marks a sharp departure from the recent development in tool-augmented LLMs, in which the external tools (e.g., calculator, Web search, etc.) are essentially detached from the learning phase of the LM. SYRELM shows massive improvements (e.g., +30.65 absolute point improvement in accuracy on the SVAMP dataset using GPT-J 6B model) over base LMs, while keeping our testbed easy to diagnose, interpret and within reach of most researchers.
Authors: Marc-André Zöller, Marius Lindauer, Marco F. Huber
In today's data-driven landscape, time series forecasting is pivotal in decision-making across various sectors. Yet, the proliferation of more diverse time series data, coupled with the expanding landscape of available forecasting methods, poses significant challenges for forecasters. To meet the growing demand for efficient forecasting, we introduce auto-sktime, a novel framework for automated time series forecasting. The proposed framework uses the power of automated machine learning (AutoML) techniques to automate the creation of the entire forecasting pipeline. The framework employs Bayesian optimization, to automatically construct pipelines from statistical, machine learning (ML) and deep neural network (DNN) models. Furthermore, we propose three essential improvements to adapt AutoML to time series data: First, pipeline templates to account for the different supported forecasting models. Second, a novel warm-starting technique to start the optimization from prior optimization runs. Third, we adapt multi-fidelity optimizations to make them applicable to a search space containing statistical, ML and DNN models. Experimental results on 64 diverse real-world time series datasets demonstrate the effectiveness and efficiency of the framework, outperforming traditional methods while requiring minimal human involvement.
Authors: Tao Hu, Honglong Zhang, Fan Zeng, Min Du, XiangKun Du, Yue Zheng, Quanqi Li, Mengran Zhang, Dan Yang, Jihao Wu
In the field of intracity freight transportation, changes in order volume are significantly influenced by temporal and spatial factors. When building subsidy and pricing strategies, predicting the causal effects of these strategies on order volume is crucial. In the process of calculating causal effects, confounding variables can have an impact. Traditional methods to control confounding variables handle data from a holistic perspective, which cannot ensure the precision of causal effects in specific temporal and spatial dimensions. However, temporal and spatial dimensions are extremely critical in the logistics field, and this limitation may directly affect the precision of subsidy and pricing strategies. To address these issues, this study proposes a technique based on flexible temporal-spatial grid partitioning. Furthermore, based on the flexible grid partitioning technique, we further propose a continuous entropy balancing method in the temporal-spatial domain, which named TS-EBCT (Temporal-Spatial Entropy Balancing for Causal Continue Treatments). The method proposed in this paper has been tested on two simulation datasets and two real datasets, all of which have achieved excellent performance. In fact, after applying the TS-EBCT method to the intracity freight transportation field, the prediction accuracy of the causal effect has been significantly improved. It brings good business benefits to the company's subsidy and pricing strategies.
Authors: Jun Liu, Yiming Meng, Maxwell Fitzsimmons, Ruikun Zhou
We provide a systematic investigation of using physics-informed neural networks to compute Lyapunov functions. We encode Lyapunov conditions as a partial differential equation (PDE) and use this for training neural network Lyapunov functions. We analyze the analytical properties of the solutions to the Lyapunov and Zubov PDEs. In particular, we show that employing the Zubov equation in training neural Lyapunov functions can lead to approximate regions of attraction close to the true domain of attraction. We also examine approximation errors and the convergence of neural approximations to the unique solution of Zubov's equation. We then provide sufficient conditions for the learned neural Lyapunov functions that can be readily verified by satisfiability modulo theories (SMT) solvers, enabling formal verification of both local stability analysis and region-of-attraction estimates in the large. Through a number of nonlinear examples, ranging from low to high dimensions, we demonstrate that the proposed framework can outperform traditional sums-of-squares (SOS) Lyapunov functions obtained using semidefinite programming (SDP).
Authors: José Chelotti, Luciano Martinez-Rau, Mariano Ferrero, Leandro Vignolo, Julio Galli, Alejandra Planisich, H. Leonardo Rufiner, Leonardo Giovanini
Livestock feeding behavior is an influential research area for those involved in animal husbandry and agriculture. In recent years, there has been a growing interest in automated systems for monitoring the behavior of ruminants. Despite the developments accomplished in the last decade, there is still much to do and learn about the methods for measuring and analyzing livestock feeding behavior. Automated monitoring systems mainly use motion, acoustic, and image sensors to collect animal behavioral data. The performance evaluation of existing methods is a complex task and direct comparisons between studies are difficult. Several factors prevent a direct comparison, starting from the diversity of data and performance metrics used in the experiments. To the best of our knowledge, this work represents the first tutorial-style review on the analysis of the feeding behavior of ruminants, emphasizing the relationship between sensing methodologies, signal processing and computational intelligence methods. It assesses the main sensing methodologies (i.e. based on movement, sound, images/videos and pressure) and the main techniques to measure and analyze the signals associated with feeding behavior, evaluating their use in different settings and situations. It also highlights the potentiality of automated monitoring systems to provide valuable information that improves our understanding of livestock feeding behavior. The relevance of these systems is increasingly important due to their impact on production systems and research. Finally, the paper closes by discussing future challenges and opportunities in livestock feeding behavior monitoring.
Authors: Micah Goldblum, Anima Anandkumar, Richard Baraniuk, Tom Goldstein, Kyunghyun Cho, Zachary C Lipton, Melanie Mitchell, Preetum Nakkiran, Max Welling, Andrew Gordon Wilson
The goal of this series is to chronicle opinions and issues in the field of machine learning as they stand today and as they change over time. The plan is to host this survey periodically until the AI singularity paperclip-frenzy-driven doomsday, keeping an updated list of topical questions and interviewing new community members for each edition. In this issue, we probed people's opinions on interpretable AI, the value of benchmarking in modern NLP, the state of progress towards understanding deep learning, and the future of academia.
Authors: Zi-Yu Khoo, Jonathan Sze Choong Low, Stéphane Bressan
Many functions characterising physical systems are additively separable. This is the case, for instance, of mechanical Hamiltonian functions in physics, population growth equations in biology, and consumer preference and utility functions in economics. We consider the scenario in which a surrogate of a function is to be tested for additive separability. The detection that the surrogate is additively separable can be leveraged to improve further learning. Hence, it is beneficial to have the ability to test for such separability in surrogates. The mathematical approach is to test if the mixed partial derivative of the surrogate is zero; or empirically, lower than a threshold. We present and comparatively and empirically evaluate the eight methods to compute the mixed partial derivative of a surrogate function.
Authors: Tom Nuno Wolf, Fabian Bongratz, Anne-Marie Rickmann, Sebastian Pölsterl, Christian Wachinger
Explaining predictions of black-box neural networks is crucial when applied to decision-critical tasks. Thus, attribution maps are commonly used to identify important image regions, despite prior work showing that humans prefer explanations based on similar examples. To this end, ProtoPNet learns a set of class-representative feature vectors (prototypes) for case-based reasoning. During inference, similarities of latent features to prototypes are linearly classified to form predictions and attribution maps are provided to explain the similarity. In this work, we evaluate whether architectures for case-based reasoning fulfill established axioms required for faithful explanations using the example of ProtoPNet. We show that such architectures allow the extraction of faithful explanations. However, we prove that the attribution maps used to explain the similarities violate the axioms. We propose a new procedure to extract explanations for trained ProtoPNets, named ProtoPFaith. Conceptually, these explanations are Shapley values, calculated on the similarity scores of each prototype. They allow to faithfully answer which prototypes are present in an unseen image and quantify each pixel's contribution to that presence, thereby complying with all axioms. The theoretical violations of ProtoPNet manifest in our experiments on three datasets (CUB-200-2011, Stanford Dogs, RSNA) and five architectures (ConvNet, ResNet, ResNet50, WideResNet50, ResNeXt50). Our experiments show a qualitative difference between the explanations given by ProtoPNet and ProtoPFaith. Additionally, we quantify the explanations with the Area Over the Perturbation Curve, on which ProtoPFaith outperforms ProtoPNet on all experiments by a factor $>10^3$.
Authors: Girolamo Macaluso, Alessandro Sestini, Andrew D. Bagdanov
Offline reinforcement learning leverages pre-collected datasets of transitions to train policies. It can serve as effective initialization for online algorithms, enhancing sample efficiency and speeding up convergence. However, when such datasets are limited in size and quality, offline pre-training can produce sub-optimal policies and lead to degraded online reinforcement learning performance. In this paper we propose a model-based data augmentation strategy to maximize the benefits of offline reinforcement learning pre-training and reduce the scale of data needed to be effective. Our approach leverages a world model of the environment trained on the offline dataset to augment states during offline pre-training. We evaluate our approach on a variety of MuJoCo robotic tasks and our results show it can jump-start online fine-tuning and substantially reduce - in some cases by an order of magnitude - the required number of environment interactions.
Authors: Oscar Chang, Dongseong Hwang, Olivier Siohan
In streaming settings, speech recognition models have to map sub-sequences of speech to text before the full audio stream becomes available. However, since alignment information between speech and text is rarely available during training, models need to learn it in a completely self-supervised way. In practice, the exponential number of possible alignments makes this extremely challenging, with models often learning peaky or sub-optimal alignments. Prima facie, the exponential nature of the alignment space makes it difficult to even quantify the uncertainty of a model's alignment distribution. Fortunately, it has been known for decades that the entropy of a probabilistic finite state transducer can be computed in time linear to the size of the transducer via a dynamic programming reduction based on semirings. In this work, we revisit the entropy semiring for neural speech recognition models, and show how alignment entropy can be used to supervise models through regularization or distillation. We also contribute an open-source implementation of CTC and RNN-T in the semiring framework that includes numerically stable and highly parallel variants of the entropy semiring. Empirically, we observe that the addition of alignment distillation improves the accuracy and latency of an already well-optimized teacher-student distillation model, achieving state-of-the-art performance on the Librispeech dataset in the streaming scenario.
Authors: Oscar Chang, Otavio Braga, Hank Liao, Dmitriy Serdyuk, Olivier Siohan
It has been shown that learning audiovisual features can lead to improved speech recognition performance over audio-only features, especially for noisy speech. However, in many common applications, the visual features are partially or entirely missing, e.g.~the speaker might move off screen. Multi-modal models need to be robust: missing video frames should not degrade the performance of an audiovisual model to be worse than that of a single-modality audio-only model. While there have been many attempts at building robust models, there is little consensus on how robustness should be evaluated. To address this, we introduce a framework that allows claims about robustness to be evaluated in a precise and testable way. We also conduct a systematic empirical study of the robustness of common audiovisual speech recognition architectures on a range of acoustic noise conditions and test suites. Finally, we show that an architecture-agnostic solution based on cascades can consistently achieve robustness to missing video, even in settings where existing techniques for robustness like dropout fall short.
Authors: Debajyoti Sengupta, Matthew Leigh, John Andrew Raine, Samuel Klein, Tobias Golling
We introduce a new technique called Drapes to enhance the sensitivity in searches for new physics at the LHC. By training diffusion models on side-band data, we show how background templates for the signal region can be generated either directly from noise, or by partially applying the diffusion process to existing data. In the partial diffusion case, data can be drawn from side-band regions, with the inverse diffusion performed for new target conditional values, or from the signal region, preserving the distribution over the conditional property that defines the signal region. We apply this technique to the hunt for resonances using the LHCO di-jet dataset, and achieve state-of-the-art performance for background template generation using high level input features. We also show how Drapes can be applied to low level inputs with jet constituents, reducing the model dependence on the choice of input observables. Using jet constituents we can further improve sensitivity to the signal process, but observe a loss in performance where the signal significance before applying any selection is below 4$\sigma$.
Authors: Paul Seurin, Koroush Shirvan
A novel method, the Pareto Envelope Augmented with Reinforcement Learning (PEARL), has been developed to address the challenges posed by multi-objective problems, particularly in the field of engineering where the evaluation of candidate solutions can be time-consuming. PEARL distinguishes itself from traditional policy-based multi-objective Reinforcement Learning methods by learning a single policy, eliminating the need for multiple neural networks to independently solve simpler sub-problems. Several versions inspired from deep learning and evolutionary techniques have been crafted, catering to both unconstrained and constrained problem domains. Curriculum Learning is harnessed to effectively manage constraints in these versions. PEARL's performance is first evaluated on classical multi-objective benchmarks. Additionally, it is tested on two practical PWR core Loading Pattern optimization problems to showcase its real-world applicability. The first problem involves optimizing the Cycle length and the rod-integrated peaking factor as the primary objectives, while the second problem incorporates the mean average enrichment as an additional objective. Furthermore, PEARL addresses three types of constraints related to boron concentration, peak pin burnup, and peak pin power. The results are systematically compared against a conventional approach, the Non-dominated Sorting Genetic Algorithm. Notably, PEARL, specifically the PEARL-NdS variant, efficiently uncovers a Pareto front without necessitating additional efforts from the algorithm designer, as opposed to a single optimization with scaled objectives. It also outperforms the classical approach across multiple performance metrics, including the Hyper-volume.
Authors: Paul K. Mandal
In the era of rapidly advancing medical technologies, the segmentation of medical data has become inevitable, necessitating the development of privacy preserving machine learning algorithms that can train on distributed data. Consolidating sensitive medical data is not always an option particularly due to the stringent privacy regulations imposed by the Health Insurance Portability and Accountability Act (HIPAA). In this paper, we introduce a HIPAA compliant framework that can train from distributed data. We then propose a multimodal vertical federated model for Alzheimer's Disease (AD) detection, a serious neurodegenerative condition that can cause dementia, severely impairing brain function and hindering simple tasks, especially without preventative care. This vertical federated model offers a distributed architecture that enables collaborative learning across diverse sources of medical data while respecting privacy constraints imposed by HIPAA. It is also able to leverage multiple modalities of data, enhancing the robustness and accuracy of AD detection. Our proposed model not only contributes to the advancement of federated learning techniques but also holds promise for overcoming the hurdles posed by data segmentation in medical research. By using vertical federated learning, this research strives to provide a framework that enables healthcare institutions to harness the collective intelligence embedded in their distributed datasets without compromising patient privacy.
Authors: Lorenzo Steccanella, Anders Jonsson
This paper presents a state representation for reward-free Markov decision processes. The idea is to learn, in a self-supervised manner, an embedding space where distances between pairs of embedded states correspond to the minimum number of actions needed to transition between them. Unlike previous methods, our approach incorporates an asymmetric norm parametrization, enabling accurate approximations of minimum action distances in environments with inherent asymmetry. We show how this representation can be leveraged to learn goal-conditioned policies, providing a notion of similarity between states and goals and a useful heuristic distance to guide planning. To validate our approach, we conduct empirical experiments on both symmetric and asymmetric environments. Our results show that our asymmetric norm parametrization performs comparably to symmetric norms in symmetric environments and surpasses symmetric norms in asymmetric environments.
Authors: Lyudong Jin, Ming Tang, Meng Zhang, Hao Wang
Mobile edge computing (MEC) is a promising paradigm for real-time applications with intensive computational needs (e.g., autonomous driving), as it can reduce the processing delay. In this work, we focus on the timeliness of computational-intensive updates, measured by Age-ofInformation (AoI), and study how to jointly optimize the task updating and offloading policies for AoI with fractional form. Specifically, we consider edge load dynamics and formulate a task scheduling problem to minimize the expected time-average AoI. The uncertain edge load dynamics, the nature of the fractional objective, and hybrid continuous-discrete action space (due to the joint optimization) make this problem challenging and existing approaches not directly applicable. To this end, we propose a fractional reinforcement learning(RL) framework and prove its convergence. We further design a model-free fractional deep RL (DRL) algorithm, where each device makes scheduling decisions with the hybrid action space without knowing the system dynamics and decisions of other devices. Experimental results show that our proposed algorithms reduce the average AoI by up to 57.6% compared with several non-fractional benchmarks.
Authors: Wei Wan, Yuxuan Ning, Shengshan Hu, Lulu Xue, Minghui Li, Leo Yu Zhang, Hai Jin
\textit{Federated learning} (FL) and \textit{split learning} (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users' devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. \textit{Split federated learning} (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of robustness.
In this paper, we present a novel poisoning attack known as MISA. It poisons both the top and bottom models, causing a \textbf{\underline{misa}}lignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention.
Authors: Franz Thaler, Matthias A.F. Gsell, Gernot Plank, Martin Urschler
Late gadolinium enhanced (LGE) magnetic resonance (MR) imaging is widely established to assess the viability of myocardial tissue of patients after acute myocardial infarction (MI). We propose the Cascading Refinement CNN (CaRe-CNN), which is a fully 3D, end-to-end trained, 3-stage CNN cascade that exploits the hierarchical structure of such labeled cardiac data. Throughout the three stages of the cascade, the label definition changes and CaRe-CNN learns to gradually refine its intermediate predictions accordingly. Furthermore, to obtain more consistent qualitative predictions, we propose a series of post-processing steps that take anatomical constraints into account. Our CaRe-CNN was submitted to the FIMH 2023 MYOSAIQ challenge, where it ranked second out of 18 participating teams. CaRe-CNN showed great improvements most notably when segmenting the difficult but clinically most relevant myocardial infarct tissue (MIT) as well as microvascular obstructions (MVO). When computing the average scores over all labels, our method obtained the best score in eight out of ten metrics. Thus, accurate cardiac segmentation after acute MI via our CaRe-CNN allows generating patient-specific models of the heart serving as an important step towards personalized medicine.
Authors: Bao Nguyen, Viet Anh Nguyen
Given a (machine learning) classifier and a collection of unlabeled data, how can we efficiently identify misclassification patterns presented in this dataset? To address this problem, we propose a human-machine collaborative framework that consists of a team of human annotators and a sequential recommendation algorithm. The recommendation algorithm is conceptualized as a stochastic sampler that, in each round, queries the annotators a subset of samples for their true labels and obtains the feedback information on whether the samples are misclassified. The sampling mechanism needs to balance between discovering new patterns of misclassification (exploration) and confirming the potential patterns of classification (exploitation). We construct a determinantal point process, whose intensity balances the exploration-exploitation trade-off through the weighted update of the posterior at each round to form the generator of the stochastic sampler. The numerical results empirically demonstrate the competitive performance of our framework on multiple datasets at various signal-to-noise ratios.