Authors: Pingping Dong, Xiao-Lin Wang, Indranil Bose, Kam K. H. Ng, Xiaoning Zhang, Xiaoge Zhang
Abstract: Accurate and reliable prediction has profound implications to a wide range of applications. In this study, we focus on an instance of spatio-temporal learning problem--traffic prediction--to demonstrate an advanced deep learning model developed for making accurate and reliable forecast. Despite the significant progress in traffic prediction, limited studies have incorporated both explicit and implicit traffic patterns simultaneously to improve prediction performance. Meanwhile, the variability nature of traffic states necessitates quantifying the uncertainty of model predictions in a statistically principled way; however, extant studies offer no provable guarantee on the statistical validity of confidence intervals in reflecting its actual likelihood of containing the ground truth. In this paper, we propose an end-to-end traffic prediction framework that leverages three primary components to generate accurate and reliable traffic predictions: dynamic causal structure learning for discovering implicit traffic patterns from massive traffic data, causally-aware spatio-temporal multi-graph convolution network (CASTMGCN) for learning spatio-temporal dependencies, and conformal prediction for uncertainty quantification. CASTMGCN fuses several graphs that characterize different important aspects of traffic networks and an auxiliary graph that captures the effect of exogenous factors on the road network. On this basis, a conformal prediction approach tailored to spatio-temporal data is further developed for quantifying the uncertainty in node-wise traffic predictions over varying prediction horizons. Experimental results on two real-world traffic datasets demonstrate that the proposed method outperforms several state-of-the-art models in prediction accuracy; moreover, it generates more efficient prediction regions than other methods while strictly satisfying the statistical validity in coverage.
Authors: Shaina Raza, Arash Shaban-Nejad, Elham Dolatabadi, Hiroshi Mamiya
Abstract: Background: The rapid advancement of Machine Learning (ML) represents novel opportunities to enhance public health research, surveillance, and decision-making. However, there is a lack of comprehensive understanding of algorithmic bias -- systematic errors in predicted population health outcomes -- resulting from the public health application of ML. The objective of this narrative review is to explore the types of bias generated by ML and quantitative metrics to assess these biases. Methods: We performed search on PubMed, MEDLINE, IEEE (Institute of Electrical and Electronics Engineers), ACM (Association for Computing Machinery) Digital Library, Science Direct, and Springer Nature. We used keywords to identify studies describing types of bias and metrics to measure these in the domain of ML and public and population health published in English between 2008 and 2023, inclusive. Results: A total of 72 articles met the inclusion criteria. Our review identified the commonly described types of bias and quantitative metrics to assess these biases from an equity perspective. Conclusion: The review will help formalize the evaluation framework for ML on public health from an equity perspective.
Authors: Venkatesh Balavadhani Parthasarathy, Ahtsham Zafar, Aafaq Khan, Arsalan Shahid
Abstract: This report examines the fine-tuning of Large Language Models (LLMs), integrating theoretical insights with practical applications. It outlines the historical evolution of LLMs from traditional Natural Language Processing (NLP) models to their pivotal role in AI. A comparison of fine-tuning methodologies, including supervised, unsupervised, and instruction-based approaches, highlights their applicability to different tasks. The report introduces a structured seven-stage pipeline for fine-tuning LLMs, spanning data preparation, model initialization, hyperparameter tuning, and model deployment. Emphasis is placed on managing imbalanced datasets and optimization techniques. Parameter-efficient methods like Low-Rank Adaptation (LoRA) and Half Fine-Tuning are explored for balancing computational efficiency with performance. Advanced techniques such as memory fine-tuning, Mixture of Experts (MoE), and Mixture of Agents (MoA) are discussed for leveraging specialized networks and multi-agent collaboration. The report also examines novel approaches like Proximal Policy Optimization (PPO) and Direct Preference Optimization (DPO), which align LLMs with human preferences, alongside pruning and routing optimizations to improve efficiency. Further sections cover validation frameworks, post-deployment monitoring, and inference optimization, with attention to deploying LLMs on distributed and cloud-based platforms. Emerging areas such as multimodal LLMs, fine-tuning for audio and speech, and challenges related to scalability, privacy, and accountability are also addressed. This report offers actionable insights for researchers and practitioners navigating LLM fine-tuning in an evolving landscape.
Authors: Scotty Black, Christian Darken
Abstract: In the domain of combat simulations, the training and deployment of deep reinforcement learning (RL) agents still face substantial challenges due to the dynamic and intricate nature of such environments. Unfortunately, as the complexity of the scenarios and available information increases, the training time required to achieve a certain threshold of performance does not just increase, but often does so exponentially. This relationship underscores the profound impact of complexity in training RL agents. This paper introduces a novel approach that addresses this limitation in training artificial intelligence (AI) agents using RL. Traditional RL methods have been shown to struggle in these high-dimensional, dynamic environments due to real-world computational constraints and the known sample inefficiency challenges of RL. To overcome these limitations, we propose a method of localized observation abstraction using piecewise linear spatial decay. This technique simplifies the state space, reducing computational demands while still preserving essential information, thereby enhancing AI training efficiency in dynamic environments where spatial relationships are often critical. Our analysis reveals that this localized observation approach consistently outperforms the more traditional global observation approach across increasing scenario complexity levels. This paper advances the research on observation abstractions for RL, illustrating how localized observation with piecewise linear spatial decay can provide an effective solution to large state representation challenges in dynamic environments.
Authors: Scotty Black
Abstract: In today's rapidly evolving military landscape, advancing artificial intelligence (AI) in support of wargaming becomes essential. Despite reinforcement learning (RL) showing promise for developing intelligent agents, conventional RL faces limitations in handling the complexity inherent in combat simulations. This dissertation proposes a comprehensive approach, including targeted observation abstractions, multi-model integration, a hybrid AI framework, and an overarching hierarchical reinforcement learning (HRL) framework. Our localized observation abstraction using piecewise linear spatial decay simplifies the RL problem, enhancing computational efficiency and demonstrating superior efficacy over traditional global observation methods. Our multi-model framework combines various AI methodologies, optimizing performance while still enabling the use of diverse, specialized individual behavior models. Our hybrid AI framework synergizes RL with scripted agents, leveraging RL for high-level decisions and scripted agents for lower-level tasks, enhancing adaptability, reliability, and performance. Our HRL architecture and training framework decomposes complex problems into manageable subproblems, aligning with military decision-making structures. Although initial tests did not show improved performance, insights were gained to improve future iterations. This study underscores AI's potential to revolutionize wargaming, emphasizing the need for continued research in this domain.
Authors: Nakul Upadhya, Eldan Cohen
Abstract: Interpretable clustering algorithms aim to group similar data points while explaining the obtained groups to support knowledge discovery and pattern recognition tasks. While most approaches to interpretable clustering construct clusters using decision trees, the interpretability of trees often deteriorates on complex problems where large trees are required. In this work, we introduce the Neural Clustering Additive Model (NeurCAM), a novel approach to the interpretable clustering problem that leverages neural generalized additive models to provide fuzzy cluster membership with additive explanations of the obtained clusters. To promote sparsity in our model's explanations, we introduce selection gates that explicitly limit the number of features and pairwise interactions leveraged. Additionally, we demonstrate the capacity of our model to perform text clustering that considers the contextual representation of the texts while providing explanations for the obtained clusters based on uni- or bi-word terms. Extensive experiments show that NeurCAM achieves performance comparable to black-box methods on tabular datasets while remaining interpretable. Additionally, our approach significantly outperforms other interpretable clustering approaches when clustering on text data.
Authors: Jainaveen Sundaram, Ravishankar Iyer
Abstract: Multimodal Large Language Models (MM-LLMs) have seen significant advancements in the last year, demonstrating impressive performance across tasks. However, to truly democratize AI, models must exhibit strong capabilities and be able to run efficiently on small compute footprints accessible by most. Part of this quest, we introduce LLaVaOLMoBitnet1B - the first Ternary Multimodal LLM capable of accepting Image(s)+Text inputs to produce coherent textual responses. The model is fully open-sourced along with training scripts to encourage further research in this space. This accompanying technical report highlights the training process, evaluation details, challenges associated with ternary models and future opportunities. Link to the model: https://huggingface.co/IntelLabs/LlavaOLMoBitnet1B
Authors: Tomoumi Takase, Ryo Karakida
Abstract: While data augmentation (DA) is generally applied to input data, several studies have reported that applying DA to hidden layers in neural networks, i.e., feature augmentation, can improve performance. However, in previous studies, the layers to which DA is applied have not been carefully considered, often being applied randomly and uniformly or only to a specific layer, leaving room for arbitrariness. Thus, in this study, we investigated the trends of suitable layers for applying DA in various experimental configurations, e.g., training from scratch, transfer learning, various dataset settings, and different models. In addition, to adjust the suitable layers for DA automatically, we propose the adaptive layer selection (AdaLASE) method, which updates the ratio to perform DA for each layer based on the gradient descent method during training. The experimental results obtained on several image classification datasets indicate that the proposed AdaLASE method altered the ratio as expected and achieved high overall test accuracy.
Authors: Hangfeng He, Weijie J. Su
Abstract: Large language models (LLMs) have been widely employed across various application domains, yet their black-box nature poses significant challenges to understanding how these models process input data internally to make predictions. In this paper, we introduce a precise and quantitative law that governs the learning of contextualized token embeddings through intermediate layers in pre-trained LLMs for next-token prediction. Our findings reveal that each layer contributes equally to enhancing prediction accuracy, from the lowest to the highest layer -- a universal phenomenon observed across a diverse array of open-source LLMs, built on architectures such as Transformer, RWKV, and Mamba. We demonstrate that this law offers new perspectives and insights to inform and guide practices in LLM development and applications, including model scaling, pre-training tasks, and information flow. Overall, our law enables more fine-grained approaches to the design, training, and interpretation of LLMs through scrutinizing their internal data processing mechanisms.
Authors: Bao Duong, Hung Le, Thin Nguyen
Abstract: Unraveling cause-effect structures embedded in mere observational data is of great scientific interest, owning to the wealth of knowledge that can benefit from such structures. Recently, reinforcement learning (RL) has emerged as the enhancement for classical techniques to search for the most probable causal explanation in the form of a directed acyclic graph (DAG). Yet, effectively exploring the DAG space is challenging due to the vast number of candidates and the intricate constraint of acyclicity. In this study, we present REACT (REinforced DAG learning without acyclicity ConstrainTs)-a novel causal discovery approach fueled by the RL machinery with an efficient DAG generation policy. Through a novel parametrization of DAGs, which allows for directly mapping a real-valued vector to an adjacency matrix representing a valid DAG in a single step without enforcing any acyclicity constraint, we are able to navigate the search space much more effectively with policy gradient methods. In addition, our comprehensive numerical evaluations on a diverse set of both synthetic and real data confirm the effectiveness of our method compared with state-of-the-art baselines.
Authors: Sihao Wu, Xingyu Zhao, Xiaowei Huang
Abstract: Data efficiency of learning, which plays a key role in the Reinforcement Learning (RL) training process, becomes even more important in continual RL with sequential environments. In continual RL, the learner interacts with non-stationary, sequential tasks and is required to learn new tasks without forgetting previous knowledge. However, there is little work on implementing data augmentation for continual RL. In this paper, we investigate the efficacy of data augmentation for continual RL. Specifically, we provide benchmarking data augmentations for continual RL, by (1) summarising existing data augmentation methods and (2) including a new augmentation method for continual RL: Adversarial Augmentation with Gradient Episodic Memory (Adv-GEM). Extensive experiments show that data augmentations, such as random amplitude scaling, state-switch, mixup, adversarial augmentation, and Adv-GEM, can improve existing continual RL algorithms in terms of their average performance, catastrophic forgetting, and forward transfer, on robot control tasks. All data augmentation methods are implemented as plug-in modules for trivial integration into continual RL methods.
Authors: Xinwei Zhang, Zhiqi Bu, Mingyi Hong, Meisam Razaviyayn
Abstract: Privacy is a growing concern in modern deep-learning systems and applications. Differentially private (DP) training prevents the leakage of sensitive information in the collected training data from the trained machine learning models. DP optimizers, including DP stochastic gradient descent (DPSGD) and its variants, privatize the training procedure by gradient clipping and DP noise injection. However, in practice, DP models trained using DPSGD and its variants often suffer from significant model performance degradation. Such degradation prevents the application of DP optimization in many key tasks, such as foundation model pretraining. In this paper, we provide a novel signal processing perspective to the design and analysis of DP optimizers. We show that a ``frequency domain'' operation called low-pass filtering can be used to effectively reduce the impact of DP noise. More specifically, by defining the ``frequency domain'' for both the gradient and differential privacy (DP) noise, we have developed a new component, called DOPPLER. This component is designed for DP algorithms and works by effectively amplifying the gradient while suppressing DP noise within this frequency domain. As a result, it maintains privacy guarantees and enhances the quality of the DP-protected model. Our experiments show that the proposed DP optimizers with a low-pass filter outperform their counterparts without the filter by 3%-10% in test accuracy on various models and datasets. Both theoretical and practical evidence suggest that the DOPPLER is effective in closing the gap between DP and non-DP training.
Authors: Chansung Park, Juyong Jiang, Fan Wang, Sayak Paul, Jing Tang, Sunghun Kim
Abstract: The widespread adoption of cloud-based proprietary large language models (LLMs) has introduced significant challenges, including operational dependencies, privacy concerns, and the necessity of continuous internet connectivity. In this work, we introduce an LLMOps pipeline, "LlamaDuo", for the seamless migration of knowledge and abilities from service-oriented LLMs to smaller, locally manageable models. This pipeline is crucial for ensuring service continuity in the presence of operational failures, strict privacy policies, or offline requirements. Our LlamaDuo involves fine-tuning a small language model against the service LLM using a synthetic dataset generated by the latter. If the performance of the fine-tuned model falls short of expectations, it is enhanced by further fine-tuning with additional similar data created by the service LLM. This iterative process guarantees that the smaller model can eventually match or even surpass the service LLM's capabilities in specific downstream tasks, offering a practical and scalable solution for managing AI deployments in constrained environments. Extensive experiments with leading edge LLMs are conducted to demonstrate the effectiveness, adaptability, and affordability of LlamaDuo across various downstream tasks. Our pipeline implementation is available at https://github.com/deep-diver/llamaduo.
Authors: Xinyue Hu, Zhibin Duan, Xinyang Liu, Yuxin Li, Bo Chen, Mingyuan Zhou
Abstract: Recently, generative graph models have shown promising results in learning graph representations through self-supervised methods. However, most existing generative graph representation learning (GRL) approaches rely on random masking across the entire graph, which overlooks the entanglement of learned representations. This oversight results in non-robustness and a lack of explainability. Furthermore, disentangling the learned representations remains a significant challenge and has not been sufficiently explored in GRL research. Based on these insights, this paper introduces DiGGR (Disentangled Generative Graph Representation Learning), a self-supervised learning framework. DiGGR aims to learn latent disentangled factors and utilizes them to guide graph mask modeling, thereby enhancing the disentanglement of learned representations and enabling end-to-end joint learning. Extensive experiments on 11 public datasets for two different graph learning tasks demonstrate that DiGGR consistently outperforms many previous self-supervised methods, verifying the effectiveness of the proposed approach.
Authors: Seungbeom Hu, ChanJun Park, Andrew Ferraiuolo, Sang-Ki Ko, Jinwoo Kim, Haein Song, Jieung Kim
Abstract: Determining the optimal size of a neural network is critical, as it directly impacts runtime performance and memory usage. Pruning is a well-established model compression technique that reduces the size of neural networks while mathematically guaranteeing accuracy preservation. However, many recent pruning methods overlook the global contributions of individual model components, making it difficult to ensure that a pruned model meets the desired dataset and performance requirements. To address these challenges, we developed a new pruning algorithm, MPruner, that leverages mutual information through vector similarity. MPruner utilizes layer clustering with the Centered Kernel Alignment (CKA) similarity metric, allowing us to incorporate global information from the neural network for more precise and efficient layer-wise pruning. We evaluated MPruner across various architectures and configurations, demonstrating its versatility and providing practical guidelines. MPruner achieved up to a 50% reduction in parameters and memory usage for CNN and transformer-based models, with minimal to no loss in accuracy.
Authors: Yuqi Bai, Ziyu Zhao, Minqin Zhu, Kun Kuang
Abstract: Off-Policy Evaluation (OPE) is employed to assess the potential impact of a hypothetical policy using logged contextual bandit feedback, which is crucial in areas such as personalized medicine and recommender systems, where online interactions are associated with significant risks and costs. Traditionally, OPE methods rely on the Stable Unit Treatment Value Assumption (SUTVA), which assumes that the reward for any given individual is unaffected by the actions of others. However, this assumption often fails in real-world scenarios due to the presence of interference, where an individual's reward is affected not just by their own actions but also by the actions of their peers. This realization reveals significant limitations of existing OPE methods in real-world applications. To address this limitation, we propose IntIPW, an IPW-style estimator that extends the Inverse Probability Weighting (IPW) framework by integrating marginalized importance weights to account for both individual actions and the influence of adjacent entities. Extensive experiments are conducted on both synthetic and real-world data to demonstrate the effectiveness of the proposed IntIPW method.
Authors: Alperen Tercan, Vinayak S. Prabhu
Abstract: Lexicographic multi-objective problems, which impose a lexicographic importance order over the objectives, arise in many real-life scenarios. Existing Reinforcement Learning work directly addressing lexicographic tasks has been scarce. The few proposed approaches were all noted to be heuristics without theoretical guarantees as the Bellman equation is not applicable to them. Additionally, the practical applicability of these prior approaches also suffers from various issues such as not being able to reach the goal state. While some of these issues have been known before, in this work we investigate further shortcomings, and propose fixes for improving practical performance in many cases. We also present a policy optimization approach using our Lexicographic Projection Optimization (LPO) algorithm that has the potential to address these theoretical and practical concerns. Finally, we demonstrate our proposed algorithms on benchmark problems.
Authors: Haiyao Cao, Zhen Zhang, Panpan Cai, Yuhang Liu, Jinan Zou, Ehsan Abbasnejad, Biwei Huang, Mingming Gong, Anton van den Hengel, Javen Qinfeng Shi
Abstract: One of the significant challenges in reinforcement learning (RL) when dealing with noise is estimating latent states from observations. Causality provides rigorous theoretical support for ensuring that the underlying states can be uniquely recovered through identifiability. Consequently, some existing work focuses on establishing identifiability from a causal perspective to aid in the design of algorithms. However, these results are often derived from a purely causal viewpoint, which may overlook the specific RL context. We revisit this research line and find that incorporating RL-specific context can reduce unnecessary assumptions in previous identifiability analyses for latent states. More importantly, removing these assumptions allows algorithm design to go beyond the earlier boundaries constrained by them. Leveraging these insights, we propose a novel approach for general partially observable Markov Decision Processes (POMDPs) by replacing the complicated structural constraints in previous methods with two simple constraints for transition and reward preservation. With the two constraints, the proposed algorithm is guaranteed to disentangle state and noise that is faithful to the underlying dynamics. Empirical evidence from extensive benchmark control tasks demonstrates the superiority of our approach over existing counterparts in effectively disentangling state belief from noise.
Authors: Mateusz Wyrembek, George Baryannis, Alexandra Brintrup
Abstract: The penultimate goal for developing machine learning models in supply chain management is to make optimal interventions. However, most machine learning models identify correlations in data rather than inferring causation, making it difficult to systematically plan for better outcomes. In this article, we propose and evaluate the use of causal machine learning for developing supply chain risk intervention models, and demonstrate its use with a case study in supply chain risk management in the maritime engineering sector. Our findings highlight that causal machine learning enhances decision-making processes by identifying changes that can be achieved under different supply chain interventions, allowing "what-if" scenario planning. We therefore propose different machine learning developmental pathways for for predicting risk, and planning for interventions to minimise risk and outline key steps for supply chain researchers to explore causal machine learning.
Authors: Mingliang Zhang, Sichang Su, Chengyang He, Guillaume Sartoretti
Abstract: In multi-agent reinforcement learning (MARL), achieving multi-task generalization to diverse agents and objectives presents significant challenges. Existing online MARL algorithms primarily focus on single-task performance, but their lack of multi-task generalization capabilities typically results in substantial computational waste and limited real-life applicability. Meanwhile, existing offline multi-task MARL approaches are heavily dependent on data quality, often resulting in poor performance on unseen tasks. In this paper, we introduce HyGen, a novel hybrid MARL framework, Hybrid Training for Enhanced Multi-Task Generalization, which integrates online and offline learning to ensure both multi-task generalization and training efficiency. Specifically, our framework extracts potential general skills from offline multi-task datasets. We then train policies to select the optimal skills under the centralized training and decentralized execution paradigm (CTDE). During this stage, we utilize a replay buffer that integrates both offline data and online interactions. We empirically demonstrate that our framework effectively extracts and refines general skills, yielding impressive generalization to unseen tasks. Comparative analyses on the StarCraft multi-agent challenge show that HyGen outperforms a wide range of existing solely online and offline methods.
Authors: Alberto Pepe, Sven Buchholz, Joan Lasenby
Abstract: We introduce STAResNet, a ResNet architecture in Spacetime Algebra (STA) to solve Maxwell's partial differential equations (PDEs). Recently, networks in Geometric Algebra (GA) have been demonstrated to be an asset for truly geometric machine learning. In \cite{brandstetter2022clifford}, GA networks have been employed for the first time to solve partial differential equations (PDEs), demonstrating an increased accuracy over real-valued networks. In this work we solve Maxwell's PDEs both in GA and STA employing the same ResNet architecture and dataset, to discuss the impact that the choice of the right algebra has on the accuracy of GA networks. Our study on STAResNet shows how the correct geometric embedding in Clifford Networks gives a mean square error (MSE), between ground truth and estimated fields, up to 2.6 times lower than than obtained with a standard Clifford ResNet with 6 times fewer trainable parameters. STAREsNet demonstrates consistently lower MSE and higher correlation regardless of scenario. The scenarios tested are: sampling period of the dataset; presence of obstacles with either seen or unseen configurations; the number of channels in the ResNet architecture; the number of rollout steps; whether the field is in 2D or 3D space. This demonstrates how choosing the right algebra in Clifford networks is a crucial factor for more compact, accurate, descriptive and better generalising pipelines.
Authors: Sagar Srinivas Sakhinana, Geethan Sannidhi, Chidaksh Ravuru, Venkataramana Runkana
Abstract: Spatio-temporal forecasting is crucial in transportation, logistics, and supply chain management. However, current methods struggle with large, complex datasets. We propose a dynamic, multi-modal approach that integrates the strengths of traditional forecasting methods and instruction tuning of small language models for time series trend analysis. This approach utilizes a mixture of experts (MoE) architecture with parameter-efficient fine-tuning (PEFT) methods, tailored for consumer hardware to scale up AI solutions in low resource settings while balancing performance and latency tradeoffs. Additionally, our approach leverages related past experiences for similar input time series to efficiently handle both intra-series and inter-series dependencies of non-stationary data with a time-then-space modeling approach, using grouped-query attention, while mitigating the limitations of traditional forecasting techniques in handling distributional shifts. Our approach models predictive uncertainty to improve decision-making. Our framework enables on-premises customization with reduced computational and memory demands, while maintaining inference speed and data privacy/security. Extensive experiments on various real-world datasets demonstrate that our framework provides robust and accurate forecasts, significantly outperforming existing methods.
Authors: Laura Latorre, Liliana Petrychenko, Regina Beets-Tan, Taisiya Kopytova, Wilson Silva
Abstract: We explore deep generative models to generate case-based explanations in a medical federated learning setting. Explaining AI model decisions through case-based interpretability is paramount to increasing trust and allowing widespread adoption of AI in clinical practice. However, medical AI training paradigms are shifting towards federated learning settings in order to comply with data protection regulations. In a federated scenario, past data is inaccessible to the current user. Thus, we use a deep generative model to generate synthetic examples that protect privacy and explain decisions. Our proof-of-concept focuses on pleural effusion diagnosis and uses publicly available Chest X-ray data.
Authors: Thomas Decker, Alexander Koebler, Michael Lebacher, Ingo Thon, Volker Tresp, Florian Buettner
Abstract: Monitoring and maintaining machine learning models are among the most critical challenges in translating recent advances in the field into real-world applications. However, current monitoring methods lack the capability of provide actionable insights answering the question of why the performance of a particular model really degraded. In this work, we propose a novel approach to explain the behavior of a black-box model under feature shifts by attributing an estimated performance change to interpretable input characteristics. We refer to our method that combines concepts from Optimal Transport and Shapley Values as Explanatory Performance Estimation (XPE). We analyze the underlying assumptions and demonstrate the superiority of our approach over several baselines on different data sets across various data modalities such as images, audio, and tabular data. We also indicate how the generated results can lead to valuable insights, enabling explanatory model monitoring by revealing potential root causes for model deterioration and guiding toward actionable countermeasures.
Authors: Yifei He, Yuzheng Hu, Yong Lin, Tong Zhang, Han Zhao
Abstract: Model merging offers an effective strategy to combine the strengths of multiple finetuned models into a unified model that preserves the specialized capabilities of each. Existing methods merge models in a global manner, performing arithmetic operations across all model parameters. However, such global merging often leads to task interference, degrading the performance of the merged model. In this work, we introduce Localize-and-Stitch, a novel approach that merges models in a localized way. Our algorithm works in two steps: i) Localization: identify tiny ($1\%$ of the total parameters) localized regions in the finetuned models containing essential skills for the downstream tasks, and ii) Stitching: reintegrate only these essential regions back into the pretrained model for task synergy. We demonstrate that our approach effectively locates sparse regions responsible for finetuned performance, and the localized regions could be treated as compact and interpretable representations of the finetuned models (tasks). Empirically, we evaluate our method on various vision and language benchmarks, showing that it outperforms existing model merging methods under different data availability scenarios. Beyond strong empirical performance, our algorithm also facilitates model compression and preserves pretrained knowledge, enabling flexible and continual skill composition from multiple finetuned models with minimal storage and computational overhead. Our code is available at https://github.com/yifei-he/Localize-and-Stitch.
Authors: Chenqing Hua, Bozitao Zhong, Sitao Luan, Liang Hong, Guy Wolf, Doina Precup, Shuangjia Zheng
Abstract: Enzymes, with their specific catalyzed reactions, are necessary for all aspects of life, enabling diverse biological processes and adaptations. Predicting enzyme functions is essential for understanding biological pathways, guiding drug development, enhancing bioproduct yields, and facilitating evolutionary studies. Addressing the inherent complexities, we introduce a new approach to annotating enzymes based on their catalyzed reactions. This method provides detailed insights into specific reactions and is adaptable to newly discovered reactions, diverging from traditional classifications by protein family or expert-derived reaction classes. We employ machine learning algorithms to analyze enzyme reaction datasets, delivering a much more refined view on the functionality of enzymes. Our evaluation leverages the largest enzyme-reaction dataset to date, derived from the SwissProt and Rhea databases with entries up to January 8, 2024. We frame the enzyme-reaction prediction as a retrieval problem, aiming to rank enzymes by their catalytic ability for specific reactions. With our model, we can recruit proteins for novel reactions and predict reactions in novel proteins, facilitating enzyme discovery and function annotation.
Authors: Xueying Ding, Rui Xi, Leman Akoglu
Abstract: The astonishing successes of ML have raised growing concern for the fairness of modern methods when deployed in real world settings. However, studies on fairness have mostly focused on supervised ML, while unsupervised outlier detection (OD), with numerous applications in finance, security, etc., have attracted little attention. While a few studies proposed fairness-enhanced OD algorithms, they remain agnostic to the underlying driving mechanisms or sources of unfairness. Even within the supervised ML literature, there exists debate on whether unfairness stems solely from algorithmic biases (i.e. design choices) or from the biases encoded in the data on which they are trained. To close this gap, this work aims to shed light on the possible sources of unfairness in OD by auditing detection models under different data-centric factors. By injecting various known biases into the input data -- as pertain to sample size disparity, under-representation, feature measurement noise, and group membership obfuscation -- we find that the OD algorithms under the study all exhibit fairness pitfalls, although differing in which types of data bias they are more susceptible to. Most notable of our study is to demonstrate that OD algorithm bias is not merely a data bias problem. A key realization is that the data properties that emerge from bias injection could as well be organic -- as pertain to natural group differences w.r.t. sparsity, base rate, variance, and multi-modality. Either natural or biased, such data properties can give rise to unfairness as they interact with certain algorithmic design choices.
Authors: Andr\'es Catalino Castillo Jim\'enez, Ege C. Kaya, Lintao Ye, Abolfazl Hashemi
Abstract: In a conventional Federated Learning framework, client selection for training typically involves the random sampling of a subset of clients in each iteration. However, this random selection often leads to disparate performance among clients, raising concerns regarding fairness, particularly in applications where equitable outcomes are crucial, such as in medical or financial machine learning tasks. This disparity typically becomes more pronounced with the advent of performance-centric client sampling techniques. This paper introduces two novel methods, namely SUBTRUNC and UNIONFL, designed to address the limitations of random client selection. Both approaches utilize submodular function maximization to achieve more balanced models. By modifying the facility location problem, they aim to mitigate the fairness concerns associated with random selection. SUBTRUNC leverages client loss information to diversify solutions, while UNIONFL relies on historical client selection data to ensure a more equitable performance of the final model. Moreover, these algorithms are accompanied by robust theoretical guarantees regarding convergence under reasonable assumptions. The efficacy of these methods is demonstrated through extensive evaluations across heterogeneous scenarios, revealing significant improvements in fairness as measured by a client dissimilarity metric.
Authors: Qing Li, Runze Gan, Simon Godsill
Abstract: This paper investigates the task of tracking multiple objects in clutter under a distributed multi-sensor network with time-varying connectivity. Designed with the same objective as the centralised variational multi-object tracker, the proposed method achieves optimal decentralised fusion in performance with local processing and communication with only neighboring sensors. A key innovation is the decentralised construction of a locally maximised evidence lower bound, which greatly reduces the information required for communication. Our decentralised natural gradient descent variational multi-object tracker, enhanced with the gradient tracking strategy and natural gradients that adjusts the direction of traditional gradients to the steepest, shows rapid convergence. Our results verify that the proposed method is empirically equivalent to the centralised fusion in tracking accuracy, surpasses suboptimal fusion techniques with comparable costs, and achieves much lower communication overhead than the consensus-based variational multi-object tracker.
Authors: Amir Hossein Rahmati, Mingzhou Fan, Ruida Zhou, Nathan M. Urban, Byung-Jun Yoon, Xiaoning Qian
Abstract: Instead of randomly acquiring training data points, Uncertainty-based Active Learning (UAL) operates by querying the label(s) of pivotal samples from an unlabeled pool selected based on the prediction uncertainty, thereby aiming at minimizing the labeling cost for model training. The efficacy of UAL critically depends on the model capacity as well as the adopted uncertainty-based acquisition function. Within the context of this study, our analytical focus is directed toward comprehending how the capacity of the machine learning model may affect UAL efficacy. Through theoretical analysis, comprehensive simulations, and empirical studies, we conclusively demonstrate that UAL can lead to worse performance in comparison with random sampling when the machine learning model class has low capacity and is unable to cover the underlying ground truth. In such situations, adopting acquisition functions that directly target estimating the prediction performance may be beneficial for improving the performance of UAL.
Authors: Cyan Subhra Mishra, Deeksha Chaudhary, Jack Sampson, Mahmut Taylan Knademir, Chita Das
Abstract: The deployment of Deep Neural Networks in energy-constrained environments, such as Energy Harvesting Wireless Sensor Networks, presents unique challenges, primarily due to the intermittent nature of power availability. To address these challenges, this study introduces and evaluates a novel training methodology tailored for DNNs operating within such contexts. In particular, we propose a dynamic dropout technique that adapts to both the architecture of the device and the variability in energy availability inherent in energy harvesting scenarios. Our proposed approach leverages a device model that incorporates specific parameters of the network architecture and the energy harvesting profile to optimize dropout rates dynamically during the training phase. By modulating the network's training process based on predicted energy availability, our method not only conserves energy but also ensures sustained learning and inference capabilities under power constraints. Our preliminary results demonstrate that this strategy provides 6 to 22 percent accuracy improvements compared to the state of the art with less than 5 percent additional compute. This paper details the development of the device model, describes the integration of energy profiles with intermittency aware dropout and quantization algorithms, and presents a comprehensive evaluation of the proposed approach using real-world energy harvesting data.
Authors: Mohammad Mohammadi, Sreejita Ghosh
Abstract: Classification of sets of inputs (e.g., images and texts) is an active area of research within both computer vision (CV) and natural language processing (NLP). A common way to represent a set of vectors is to model them as linear subspaces. In this contribution, we present a prototype-based approach for learning on the manifold formed from such linear subspaces, the Grassmann manifold. Our proposed method learns a set of subspace prototypes capturing the representative characteristics of classes and a set of relevance factors automating the selection of the dimensionality of the subspaces. This leads to a transparent classifier model which presents the computed impact of each input vector on its decision. Through experiments on benchmark image and text datasets, we have demonstrated the efficiency of our proposed classifier, compared to the transformer-based models in terms of not only performance and explainability but also computational resource requirements.
Authors: Nadav Cohen, Noam Razin
Abstract: These notes are based on a lecture delivered by NC on March 2021, as part of an advanced course in Princeton University on the mathematical understanding of deep learning. They present a theory (developed by NC, NR and collaborators) of linear neural networks -- a fundamental model in the study of optimization and generalization in deep learning. Practical applications born from the presented theory are also discussed. The theory is based on mathematical tools that are dynamical in nature. It showcases the potential of such tools to push the envelope of our understanding of optimization and generalization in deep learning. The text assumes familiarity with the basics of statistical learning theory. Exercises (without solutions) are included.
Authors: Wenxuan Zhou, Zhihao Qu, Shen-Huan Lyu, Miao Cai, Baoliu Ye
Abstract: This paper introduces a novel framework designed to achieve a high compression ratio in Split Learning (SL) scenarios where resource-constrained devices are involved in large-scale model training. Our investigations demonstrate that compressing feature maps within SL leads to biased gradients that can negatively impact the convergence rates and diminish the generalization capabilities of the resulting models. Our theoretical analysis provides insights into how compression errors critically hinder SL performance, which previous methodologies underestimate. To address these challenges, we employ a narrow bit-width encoded mask to compensate for the sparsification error without increasing the order of time complexity. Supported by rigorous theoretical analysis, our framework significantly reduces compression errors and accelerates the convergence. Extensive experiments also verify that our method outperforms existing solutions regarding training efficiency and communication complexity.
Authors: Ioannis Athanasiadis, Shashi Nagarajan, Fredrik Lindsten, Michael Felsberg
Abstract: Variational Autoencoders (VAEs) are a popular framework for unsupervised learning and data generation. A plethora of methods have been proposed focusing on improving VAEs, with the incorporation of adversarial objectives and the integration of prior learning mechanisms being prominent directions. When it comes to the former, an indicative instance is the recently introduced family of Introspective VAEs aiming at ensuring that a low likelihood is assigned to unrealistic samples. In this study, we focus on the Soft-IntroVAE (S-IntroVAE) and investigate the implication of incorporating a multimodal and learnable prior into this framework. Namely, we formulate the prior as a third player and show that when trained in cooperation with the decoder constitutes an effective way for prior learning, which shares the Nash Equilibrium with the vanilla S-IntroVAE. Furthermore, based on a modified formulation of the optimal ELBO in S-IntroVAE, we develop theoretically motivated regularizations, that is (i) adaptive variance clipping to stabilize training when learning the prior and (ii) responsibility regularization to discourage the formation of inactive prior mode. Finally, we perform a series of targeted experiments on a 2D density estimation benchmark and in an image generation setting comprised of the (F)-MNIST and CIFAR-10 datasets demonstrating the benefit of prior learning in S-IntroVAE in generation and representation learning.
Authors: S. Akansha
Abstract: Graph Neural Networks (GNNs) have emerged as powerful tools for predicting outcomes in graph-structured data. However, a notable limitation of GNNs is their inability to provide robust uncertainty estimates, which undermines their reliability in contexts where errors are costly. One way to address this issue is by providing prediction sets that contain the true label with a predefined probability margin. Our approach builds upon conformal prediction (CP), a framework that promises to construct statistically robust prediction sets or intervals. There are two primary challenges: first, given dependent data like graphs, it is unclear whether the critical assumption in CP - exchangeability - still holds when applied to node classification. Second, even if the exchangeability assumption is valid for conformalized link prediction, we need to ensure high efficiency, i.e., the resulting prediction set or the interval length is small enough to provide useful information. In this article, we propose a novel approach termed Robust Conformal Prediction for GNNs (RoCP-GNN), which integrates conformal prediction (CP) directly into the GNN training process. This method generates prediction sets, instead of just point predictions, that are valid at a user-defined confidence level, assuming only exchangeability. Our approach robustly predicts outcomes with any predictive GNN model while quantifying the uncertainty in predictions within the realm of graph-based semi-supervised learning (SSL). Experimental results demonstrate that GNN models with size loss provide a statistically significant increase in performance. We validate our approach on standard graph benchmark datasets by coupling it with various state-of-the-art GNNs in node classification. The code will be made available after publication.
Authors: Kuluhan Binici, Shivam Aggarwal, Cihan Acar, Nam Trung Pham, Karianto Leman, Gim Hee Lee, Tulika Mitra
Abstract: Knowledge distillation (KD) is a key element in neural network compression that allows knowledge transfer from a pre-trained teacher model to a more compact student model. KD relies on access to the training dataset, which may not always be fully available due to privacy concerns or logistical issues related to the size of the data. To address this, "data-free" KD methods use synthetic data, generated through model inversion, to mimic the target data distribution. However, conventional model inversion methods are not designed to utilize supplementary information from the target dataset, and thus, cannot leverage it to improve performance, even when it is available. In this paper, we consider condensed samples, as a form of supplementary information, and introduce a method for using them to better approximate the target data distribution, thereby enhancing the KD performance. Our approach is versatile, evidenced by improvements of up to 11.4% in KD accuracy across various datasets and model inversion-based methods. Importantly, it remains effective even when using as few as one condensed sample per class, and can also enhance performance in few-shot scenarios where only limited real data samples are available.
Authors: Kazuhisa Fujita
Abstract: This paper presents novel game AI agents based on the AlphaZero framework, enhanced with Vision Transformers (ViT): AlphaViT, AlphaViD, and AlphaVDA. These agents are designed to play various board games of different sizes using a single model, overcoming AlphaZero's limitation of being restricted to a fixed board size. AlphaViT uses only a transformer encoder, while AlphaViD and AlphaVDA contain both an encoder and a decoder. AlphaViD's decoder receives input from the encoder output, while AlphaVDA uses a learnable matrix as decoder input. Using the AlphaZero framework, the three proposed methods demonstrate their versatility in different game environments, including Connect4, Gomoku, and Othello. Experimental results show that these agents, whether trained on a single game or on multiple games simultaneously, consistently outperform traditional algorithms such as Minimax and Monte Carlo tree search using a single DNN with shared weights, while approaching the performance of AlphaZero. In particular, AlphaViT and AlphaViD show strong performance across games, with AlphaViD benefiting from an additional decoder layer that enhances its ability to adapt to different action spaces and board sizes. These results may suggest the potential of transformer-based architectures to develop more flexible and robust game AI agents capable of excelling in multiple games and dynamic environments.
Authors: Zhiyang Wang, Juan Cervino, Alejandro Ribeiro
Abstract: Graph neural networks (GNNs) have demonstrated their effectiveness in various tasks supported by their generalization capabilities. However, the current analysis of GNN generalization relies on the assumption that training and testing data are independent and identically distributed (i.i.d). This imposes limitations on the cases where a model mismatch exists when generating testing data. In this paper, we examine GNNs that operate on geometric graphs generated from manifold models, explicitly focusing on scenarios where there is a mismatch between manifold models generating training and testing data. Our analysis reveals the robustness of the GNN generalization in the presence of such model mismatch. This indicates that GNNs trained on graphs generated from a manifold can still generalize well to unseen nodes and graphs generated from a mismatched manifold. We attribute this mismatch to both node feature perturbations and edge perturbations within the generated graph. Our findings indicate that the generalization gap decreases as the number of nodes grows in the training graph while increasing with larger manifold dimension as well as larger mismatch. Importantly, we observe a trade-off between the generalization of GNNs and the capability to discriminate high-frequency components when facing a model mismatch. The most important practical consequence of this analysis is to shed light on the filter design of generalizable GNNs robust to model mismatch. We verify our theoretical findings with experiments on multiple real-world datasets.
Authors: Haitz S\'aez de Oc\'ariz Borde, Anastasis Kratsios, Marc T. Law, Xiaowen Dong, Michael Bronstein
Abstract: We propose a class of trainable deep learning-based geometries called Neural Spacetimes (NSTs), which can universally represent nodes in weighted directed acyclic graphs (DAGs) as events in a spacetime manifold. While most works in the literature focus on undirected graph representation learning or causality embedding separately, our differentiable geometry can encode both graph edge weights in its spatial dimensions and causality in the form of edge directionality in its temporal dimensions. We use a product manifold that combines a quasi-metric (for space) and a partial order (for time). NSTs are implemented as three neural networks trained in an end-to-end manner: an embedding network, which learns to optimize the location of nodes as events in the spacetime manifold, and two other networks that optimize the space and time geometries in parallel, which we call a neural (quasi-)metric and a neural partial order, respectively. The latter two networks leverage recent ideas at the intersection of fractal geometry and deep learning to shape the geometry of the representation space in a data-driven fashion, unlike other works in the literature that use fixed spacetime manifolds such as Minkowski space or De Sitter space to embed DAGs. Our main theoretical guarantee is a universal embedding theorem, showing that any $k$-point DAG can be embedded into an NST with $1+\mathcal{O}(\log(k))$ distortion while exactly preserving its causal structure. The total number of parameters defining the NST is sub-cubic in $k$ and linear in the width of the DAG. If the DAG has a planar Hasse diagram, this is improved to $\mathcal{O}(\log(k)) + 2)$ spatial and 2 temporal dimensions. We validate our framework computationally with synthetic weighted DAGs and real-world network embeddings; in both cases, the NSTs achieve lower embedding distortions than their counterparts using fixed spacetime geometries.
Authors: Darpit Dave, Kathan Vyas, Jagadish Kumaran Jayagopal, Alfredo Garcia, Madhav Erraguntla, Mark Lawley
Abstract: Continuous glucose monitoring (CGM) devices provide real-time glucose monitoring and timely alerts for glycemic excursions, improving glycemic control among patients with diabetes. However, identifying rare events like hypoglycemia and hyperglycemia remain challenging due to their infrequency. Moreover, limited access to sensitive patient data hampers the development of robust machine learning models. Our objective is to accurately predict glycemic excursions while addressing data privacy concerns. To tackle excursion prediction, we propose a novel Hypo-Hyper (HH) loss function, which significantly improves performance in the glycemic excursion regions. The HH loss function demonstrates a 46% improvement over mean-squared error (MSE) loss across 125 patients. To address privacy concerns, we propose FedGlu, a machine learning model trained in a federated learning (FL) framework. FL allows collaborative learning without sharing sensitive data by training models locally and sharing only model parameters across other patients. FedGlu achieves a 35% superior glycemic excursion detection rate compared to local models. This improvement translates to enhanced performance in predicting both, hypoglycemia and hyperglycemia, for 105 out of 125 patients. These results underscore the effectiveness of the proposed HH loss function in augmenting the predictive capabilities of glucose predictions. Moreover, implementing models within a federated learning framework not only ensures better predictive capabilities but also safeguards sensitive data concurrently.
Authors: David Durst, Feng Xie, Vishnu Sarukkai, Brennan Shacklett, Iuri Frosio, Chen Tessler, Joohwan Kim, Carly Taylor, Gilbert Bernstein, Sanjiban Choudhury, Pat Hanrahan, Kayvon Fatahalian
Abstract: In multiplayer, first-person shooter games like Counter-Strike: Global Offensive (CS:GO), coordinated movement is a critical component of high-level strategic play. However, the complexity of team coordination and the variety of conditions present in popular game maps make it impractical to author hand-crafted movement policies for every scenario. We show that it is possible to take a data-driven approach to creating human-like movement controllers for CS:GO. We curate a team movement dataset comprising 123 hours of professional game play traces, and use this dataset to train a transformer-based movement model that generates human-like team movement for all players in a "Retakes" round of the game. Importantly, the movement prediction model is efficient. Performing inference for all players takes less than 0.5 ms per game step (amortized cost) on a single CPU core, making it plausible for use in commercial games today. Human evaluators assess that our model behaves more like humans than both commercially-available bots and procedural movement controllers scripted by experts (16% to 59% higher by TrueSkill rating of "human-like"). Using experiments involving in-game bot vs. bot self-play, we demonstrate that our model performs simple forms of teamwork, makes fewer common movement mistakes, and yields movement distributions, player lifetimes, and kill locations similar to those observed in professional CS:GO match play.
Authors: Negar Orangi-Fard
Abstract: Chronic obstructive pulmonary disease (COPD) is a chronic inflammatory lung disease that causes obstructed airflow from the lungs. In the United States, more than 15.7 million Americans have been diagnosed with COPD, with 96% of individuals living with at least one other chronic health condition. It is the 4th leading cause of death in the country. Over 2.2 million patients are admitted to hospitals annually due to COPD exacerbations. Monitoring and predicting patient exacerbations on-time could save their life. This paper presents two different predictive models to predict COPD exacerbation using AI and natural language processing (NLP) approaches. These models use respiration summary notes, symptoms, and vital signs. To train and test these models, data records containing physiologic signals and vital signs time series were used. These records were captured from patient monitors and comprehensive clinical data obtained from hospital medical information systems for tens of thousands of Intensive Care Unit (ICU) patients. We achieved an area under the Receiver operating characteristic (ROC) curve of 0.82 in detection and prediction of COPD exacerbation.
Authors: Shengzhong Mao, Chaoli Zhang, Yichi Song, Jindong Wang, Xiao-Jun Zeng, Zenglin Xu, Qingsong Wen
Abstract: Recent advancements in the collection and analysis of sequential educational data have brought time series analysis to a pivotal position in educational research, highlighting its essential role in facilitating data-driven decision-making. However, there is a lack of comprehensive summaries that consolidate these advancements. To the best of our knowledge, this paper is the first to provide a comprehensive review of time series analysis techniques specifically within the educational context. We begin by exploring the landscape of educational data analytics, categorizing various data sources and types relevant to education. We then review four prominent time series methods-forecasting, classification, clustering, and anomaly detection-illustrating their specific application points in educational settings. Subsequently, we present a range of educational scenarios and applications, focusing on how these methods are employed to address diverse educational tasks, which highlights the practical integration of multiple time series methods to solve complex educational problems. Finally, we conclude with a discussion on future directions, including personalized learning analytics, multimodal data fusion, and the role of large language models (LLMs) in educational time series. The contributions of this paper include a detailed taxonomy of educational data, a synthesis of time series techniques with specific educational applications, and a forward-looking perspective on emerging trends and future research opportunities in educational analysis. The related papers and resources are available and regularly updated at the project page.
Authors: Luca Silvano Carocci, Qiwei Han
Abstract: This study presents a novel application of Graph Neural Networks (GNNs) to optimize dealership network planning for a luxury car manufacturer in the U.S. By conducting a comprehensive literature review on dealership location determinants, the study identifies 65 county-level explanatory variables, augmented by two additional measures of regional interconnectedness derived from social and mobility data. An ablation study involving 34 variable combinations and ten state-of-the-art GNN operators reveals key insights into the predictive power of various variables, particularly highlighting the significance of competition, demographic factors, and mobility patterns in influencing dealership location decisions. The analysis pinpoints seven specific counties as promising targets for network expansion. This research not only illustrates the effectiveness of GNNs in solving complex geospatial decision-making problems but also provides actionable recommendations and valuable methodological insights for industry practitioners.
Authors: Jie Feng, Yuwei Du, Jie Zhao, Yong Li
Abstract: Human mobility prediction plays a crucial role in various real-world applications. Although deep learning based models have shown promising results over the past decade, their reliance on extensive private mobility data for training and their inability to perform zero-shot predictions, have hindered further advancements. Recently, attempts have been made to apply large language models (LLMs) to mobility prediction task. However, their performance has been constrained by the absence of a systematic design of workflow. They directly generate the final output using LLMs, which limits the potential of LLMs to uncover complex mobility patterns and underestimates their extensive reserve of global geospatial knowledge. In this paper, we introduce AgentMove, a systematic agentic prediction framework to achieve generalized mobility prediction for any cities worldwide. In AgentMove, we first decompose the mobility prediction task into three sub-tasks and then design corresponding modules to complete these subtasks, including spatial-temporal memory for individual mobility pattern mining, world knowledge generator for modeling the effects of urban structure and collective knowledge extractor for capturing the shared patterns among population. Finally, we combine the results of three modules and conduct a reasoning step to generate the final predictions. Extensive experiments on mobility data from two sources in 12 cities demonstrate that AgentMove outperforms the best baseline more than 8% in various metrics and it shows robust predictions with various LLMs as base and also less geographical bias across cities. Codes and data can be found in https://github.com/tsinghua-fib-lab/AgentMove.
Authors: Quanziang Wang, Renzhen Wang, Yichen Wu, Xixi Jia, Minghao Zhou, Deyu Meng
Abstract: In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA), a bi-level framework that augments the classification network to adapt to catastrophic distribution shifts during training, enabling the network to achieve a stable consolidation of all seen tasks. However, the CBA module adjusts distribution shifts in a class-specific manner, exacerbating the stability gap issue and, to some extent, fails to meet the need for continual testing in online CL. To mitigate this challenge, we further propose a novel class-agnostic CBA module that separately aggregates the posterior probabilities of classes from new and old tasks, and applies a stable adjustment to the resulting posterior probabilities. We combine the two kinds of CBA modules into a unified Dual-CBA module, which thus is capable of adapting to catastrophic distribution shifts and simultaneously meets the real-time testing requirements of online CL. Besides, we propose Incremental Batch Normalization (IBN), a tailored BN module to re-estimate its population statistics for alleviating the feature bias arising from the inner loop optimization problem of our bi-level framework. To validate the effectiveness of the proposed method, we theoretically provide some insights into how it mitigates catastrophic distribution shifts, and empirically demonstrate its superiority through extensive experiments based on four rehearsal-based baselines and three public continual learning benchmarks.
Authors: Xiaoyu Wang, Guojun Xiong, Houwei Cao, Jian Li, Yong Liu
Abstract: Federated Learning (FL) aims to train a shared model using data and computation power on distributed agents coordinated by a central server. Decentralized FL (DFL) utilizes local model exchange and aggregation between agents to reduce the communication and computation overheads on the central server. However, when agents are mobile, the communication opportunity between agents can be sporadic, largely hindering the convergence and accuracy of DFL. In this paper, we study delay-tolerant model spreading and aggregation enabled by model caching on mobile agents. Each agent stores not only its own model, but also models of agents encountered in the recent past. When two agents meet, they exchange their own models as well as the cached models. Local model aggregation works on all models in the cache. We theoretically analyze the convergence of DFL with cached models, explicitly taking into account the model staleness introduced by caching. We design and compare different model caching algorithms for different DFL and mobility scenarios. We conduct detailed case studies in a vehicular network to systematically investigate the interplay between agent mobility, cache staleness, and model convergence. In our experiments, cached DFL converges quickly, and significantly outperforms DFL without caching.
Authors: Rohin Sood, Kevin Zhu
Abstract: Effective water quality monitoring in coastal regions is crucial due to the progressive deterioration caused by pollution and human activities. To address this, this study develops time-series models to predict chlorophyll-a (Chl-a), suspended solids (SS), and turbidity using Sentinel-2 satellite data and Google Earth Engine (GEE) in the coastal regions of Hong Kong. Leveraging Long Short-Term Memory (LSTM) Recurrent Neural Networks, the study incorporates extensive temporal datasets to enhance prediction accuracy. The models utilize spectral data from Sentinel-2, focusing on optically active components, and demonstrate that selected variables closely align with the spectral characteristics of Chl-a and SS. The results indicate improved predictive performance over previous methods, highlighting the potential for remote sensing technology in continuous and comprehensive water quality assessment.
Authors: Yiyang Jia, Guohong Peng, Zheng Yang, Tianhao Chen
Abstract: In this survey, we provide an overview of category theory-derived machine learning from four mainstream perspectives: gradient-based learning, probability-based learning, invariance and equivalence-based learning, and topos-based learning. For the first three topics, we primarily review research in the past five years, updating and expanding on the previous survey by Shiebler et al.. The fourth topic, which delves into higher category theory, particularly topos theory, is surveyed for the first time in this paper. In certain machine learning methods, the compositionality of functors plays a vital role, prompting the development of specific categorical frameworks. However, when considering how the global properties of a network reflect in local structures and how geometric properties are expressed with logic, the topos structure becomes particularly significant and profound.
Authors: Brodie Oldfield, Sevvandi Kandanaarachchi, Ziqi Xu, Mario Andr\'es Mu\~noz
Abstract: Experimental evaluation is crucial in AI research, especially for assessing algorithms across diverse tasks. Many studies often evaluate a limited set of algorithms, failing to fully understand their strengths and weaknesses within a comprehensive portfolio. This paper introduces an Item Response Theory (IRT) based analysis tool for algorithm portfolio evaluation called AIRT-Module. Traditionally used in educational psychometrics, IRT models test question difficulty and student ability using responses to test questions. Adapting IRT to algorithm evaluation, the AIRT-Module contains a Shiny web application and the R package airt. AIRT-Module uses algorithm performance measures to compute anomalousness, consistency, and difficulty limits for an algorithm and the difficulty of test instances. The strengths and weaknesses of algorithms are visualised using the difficulty spectrum of the test instances. AIRT-Module offers a detailed understanding of algorithm capabilities across varied test instances, thus enhancing comprehensive AI method assessment. It is available at https://sevvandi.shinyapps.io/AIRT/ .
Authors: Yang Qiu, Wei Liu, Jun Wang, Ruixuan Li
Abstract: This article introduces PAGE, a parameterized generative interpretive framework. PAGE is capable of providing faithful explanations for any graph neural network without necessitating prior knowledge or internal details. Specifically, we train the auto-encoder to generate explanatory substructures by designing appropriate training strategy. Due to the dimensionality reduction of features in the latent space of the auto-encoder, it becomes easier to extract causal features leading to the model's output, which can be easily employed to generate explanations. To accomplish this, we introduce an additional discriminator to capture the causality between latent causal features and the model's output. By designing appropriate optimization objectives, the well-trained discriminator can be employed to constrain the encoder in generating enhanced causal features. Finally, these features are mapped to substructures of the input graph through the decoder to serve as explanations. Compared to existing methods, PAGE operates at the sample scale rather than nodes or edges, eliminating the need for perturbation or encoding processes as seen in previous methods. Experimental results on both artificially synthesized and real-world datasets demonstrate that our approach not only exhibits the highest faithfulness and accuracy but also significantly outperforms baseline models in terms of efficiency.
Authors: Anna Markovich, Nikita Puchkin
Abstract: We suggest a novel algorithm for online change point detection based on sequential score function estimation and tracking the best expert approach. The core of the procedure is a version of the fixed share forecaster for the case of infinite number of experts and quadratic loss functions. The algorithm shows a promising performance in numerical experiments on artificial and real-world data sets. We also derive new upper bounds on the dynamic regret of the fixed share forecaster with varying parameter, which are of independent interest.
Authors: Jingyang Zhu, Yuanming Shi, Yong Zhou, Chunxiao Jiang, Linling Kuang
Abstract: Space-ground integrated networks hold great promise for providing global connectivity, particularly in remote areas where large amounts of valuable data are generated by Internet of Things (IoT) devices, but lacking terrestrial communication infrastructure. The massive data is conventionally transferred to the cloud server for centralized artificial intelligence (AI) models training, raising huge communication overhead and privacy concerns. To address this, we propose a hierarchical learning and computing framework, which leverages the lowlatency characteristic of low-earth-orbit (LEO) satellites and the global coverage of geostationary-earth-orbit (GEO) satellites, to provide global aggregation services for locally trained models on ground IoT devices. Due to the time-varying nature of satellite network topology and the energy constraints of LEO satellites, efficiently aggregating the received local models from ground devices on LEO satellites is highly challenging. By leveraging the predictability of inter-satellite connectivity, modeling the space network as a directed graph, we formulate a network energy minimization problem for model aggregation, which turns out to be a Directed Steiner Tree (DST) problem. We propose a topologyaware energy-efficient routing (TAEER) algorithm to solve the DST problem by finding a minimum spanning arborescence on a substitute directed graph. Extensive simulations under realworld space-ground integrated network settings demonstrate that the proposed TAEER algorithm significantly reduces energy consumption and outperforms benchmarks.
Authors: Miguel Alves Gomes, Philipp Meisen, Tobias Meisen
Abstract: The rapid evolution of technology has transformed business operations and customer interactions worldwide, with personalization emerging as a key opportunity for e-commerce companies to engage customers more effectively. The application of machine learning, particularly that of deep learning models, has gained significant traction due to its ability to rapidly recognize patterns in large datasets, thereby offering numerous possibilities for personalization. These models use embeddings to map discrete information, such as product IDs, into a latent vector space, a method increasingly popular in recent years. However, e-commerce's dynamic nature, characterized by frequent new product introductions, poses challenges for these embeddings, which typically require fixed dimensions and inputs, leading to the need for periodic retraining from scratch. This paper introduces a modular algorithm that extends embedding input size while preserving learned knowledge, addressing the challenges posed by e-commerce's dynamism. The proposed algorithm also incorporates strategies to mitigate the cold start problem associated with new products. The results of initial experiments suggest that this method outperforms traditional embeddings.
Authors: Xuan Zhao, Klaus Broelemann, Salvatore Ruggieri, Gjergji Kasneci
Abstract: We introduce an innovative approach to enhancing the empirical risk minimization (ERM) process in model training through a refined reweighting scheme of the training data to enhance fairness. This scheme aims to uphold the sufficiency rule in fairness by ensuring that optimal predictors maintain consistency across diverse sub-groups. We employ a bilevel formulation to address this challenge, wherein we explore sample reweighting strategies. Unlike conventional methods that hinge on model size, our formulation bases generalization complexity on the space of sample weights. We discretize the weights to improve training speed. Empirical validation of our method showcases its effectiveness and robustness, revealing a consistent improvement in the balance between prediction performance and fairness metrics across various experiments.
Authors: Shunsuke Kubo, Shinnosuke Matsuo, Daiki Suehiro, Kazuhiro Terada, Hiroaki Ito, Akihiko Yoshizawa, Ryoma Bise
Abstract: Learning from label proportions (LLP) is a kind of weakly supervised learning that trains an instance-level classifier from label proportions of bags, which consist of sets of instances without using instance labels. A challenge in LLP arises when the number of instances in a bag (bag size) is numerous, making the traditional LLP methods difficult due to GPU memory limitations. This study aims to develop an LLP method capable of learning from bags with large sizes. In our method, smaller bags (mini-bags) are generated by sampling instances from large-sized bags (original bags), and these mini-bags are used in place of the original bags. However, the proportion of a mini-bag is unknown and differs from that of the original bag, leading to overfitting. To address this issue, we propose a perturbation method for the proportion labels of sampled mini-bags to mitigate overfitting to noisy label proportions. This perturbation is added based on the multivariate hypergeometric distribution, which is statistically modeled. Additionally, loss weighting is implemented to reduce the negative impact of proportions sampled from the tail of the distribution. Experimental results demonstrate that the proportion label perturbation and loss weighting achieve classification accuracy comparable to that obtained without sampling. Our codes are available at https://github.com/stainlessnight/LLP-LargeBags.
Authors: Yuxia Wu, Shujie Li, Yuan Fang, Chuan Shi
Abstract: Graph Neural Networks (GNNs) are essential for various graph-based learning tasks. Notably, classical GNN architectures operate under the assumption of homophily, which posits that connected nodes are likely to share similar features. However, this assumption limits the effectiveness of GNNs in handling heterophilic graphs where connected nodes often exhibit dissimilar characteristics. Existing approaches for homophily graphs such as non-local neighbor extension and architectural refinement overlook the rich textual data associated with nodes, which could unlock deeper insights into these heterophilic contexts. With advancements in Large Language Models (LLMs), there is significant promise to enhance GNNs by leveraging the extensive open-world knowledge within LLMs to more effectively interpret and utilize textual data for characterizing heterophilic graphs. In this work, we explore the potential of LLMs for modeling heterophilic graphs and propose a novel two-stage framework: LLM-enhanced edge discriminator and LLM-guided edge reweighting. Specifically, in the first stage, we fine-tune the LLM to better identify homophilic and heterophilic edges based on the textual information of their nodes. In the second stage, we adaptively manage message propagation in GNNs for different edge types based on node features, structures, and heterophilic or homophilic characteristics. To cope with the computational demands when deploying LLMs in practical scenarios, we further explore model distillation techniques to fine-tune smaller, more efficient models that maintain competitive performance. Extensive experiments validate the effectiveness of our framework, demonstrating the feasibility of using LLMs to enhance GNNs for node classification on heterophilic graphs.
Authors: Boyuan Li, Zihao Peng, Yafei Li, Mingliang Xu, Shengbo Chen, Baofeng Ji, Cong Shen
Abstract: Federated Learning (FL) can be coordinated under the orchestration of a central server to collaboratively build a privacy-preserving model without the need for data exchange. However, participant data heterogeneity leads to local optima divergence, subsequently affecting convergence outcomes. Recent research has focused on global sharpness-aware minimization (SAM) and dynamic regularization techniques to enhance consistency between global and local generalization and optimization objectives. Nonetheless, the estimation of global SAM introduces additional computational and memory overhead, while dynamic regularization suffers from bias in the local and global dual variables due to training isolation. In this paper, we propose a novel FL algorithm, FedTOGA, designed to consider optimization and generalization objectives while maintaining minimal uplink communication overhead. By linking local perturbations to global updates, global generalization consistency is improved. Additionally, global updates are used to correct local dynamic regularizers, reducing dual variables bias and enhancing optimization consistency. Global updates are passively received by clients, reducing overhead. We also propose neighborhood perturbation to approximate local perturbation, analyzing its strengths and limitations. Theoretical analysis shows FedTOGA achieves faster convergence $O(1/T)$ under non-convex functions. Empirical studies demonstrate that FedTOGA outperforms state-of-the-art algorithms, with a 1\% accuracy increase and 30\% faster convergence, achieving state-of-the-art.
Authors: Hymalai Bello, Daniel Gei{\ss}ler, Sungho Suh, Bo Zhou, Paul Lukowicz
Abstract: Smaller machine learning models, with less complex architectures and sensor inputs, can benefit wearable sensor-based human activity recognition (HAR) systems in many ways, from complexity and cost to battery life. In the specific case of smart factories, optimizing human-robot collaboration hinges on the implementation of cutting-edge, human-centric AI systems. To this end, workers' activity recognition enables accurate quantification of performance metrics, improving efficiency holistically. We present a two-stage semantic-aware knowledge distillation (KD) approach, TSAK, for efficient, privacy-aware, and wearable HAR in manufacturing lines, which reduces the input sensor modalities as well as the machine learning model size, while reaching similar recognition performance as a larger multi-modal and multi-positional teacher model. The first stage incorporates a teacher classifier model encoding attention, causal, and combined representations. The second stage encompasses a semantic classifier merging the three representations from the first stage. To evaluate TSAK, we recorded a multi-modal dataset at a smart factory testbed with wearable and privacy-aware sensors (IMU and capacitive) located on both workers' hands. In addition, we evaluated our approach on OpenPack, the only available open dataset mimicking the wearable sensor placements on both hands in the manufacturing HAR scenario. We compared several KD strategies with different representations to regulate the training process of a smaller student model. Compared to the larger teacher model, the student model takes fewer sensor channels from a single hand, has 79% fewer parameters, runs 8.88 times faster, and requires 96.6% less computing power (FLOPS).
Authors: Sarvesh Gharat, Aniket Yadav, Nikhil Karamchandani, Jayakrishnan Nair
Abstract: We study the representative arm identification (RAI) problem in the multi-armed bandits (MAB) framework, wherein we have a collection of arms, each associated with an unknown reward distribution. An underlying instance is defined by a partitioning of the arms into clusters of predefined sizes, such that for any $j > i$, all arms in cluster $i$ have a larger mean reward than those in cluster $j$. The goal in RAI is to reliably identify a certain prespecified number of arms from each cluster, while using as few arm pulls as possible. The RAI problem covers as special cases several well-studied MAB problems such as identifying the best arm or any $M$ out of the top $K$, as well as both full and coarse ranking. We start by providing an instance-dependent lower bound on the sample complexity of any feasible algorithm for this setting. We then propose two algorithms, based on the idea of confidence intervals, and provide high probability upper bounds on their sample complexity, which orderwise match the lower bound. Finally, we do an empirical comparison of both algorithms along with an LUCB-type alternative on both synthetic and real-world datasets, and demonstrate the superior performance of our proposed schemes in most cases.
Authors: Khandoker Nosiba Arifin, Sayma Akter Rupa, Md Musfique Anwar, Israt Jahan
Abstract: Lemons and oranges, both are the most economically significant citrus fruits globally. The production of lemons and oranges is severely affected due to diseases in its growth stages. Fruit quality has degraded due to the presence of flaws. Thus, it is necessary to diagnose the disease accurately so that we can avoid major loss of lemons and oranges. To improve citrus farming, we proposed a disease classification approach for lemons and oranges. This approach would enable early disease detection and intervention, reduce yield losses, and optimize resource allocation. For the initial modeling of disease classification, the research uses innovative deep learning architectures such as VGG16, VGG19 and ResNet50. In addition, for achieving better accuracy, the basic machine learning algorithms used for classification problems include Random Forest, Naive Bayes, K-Nearest Neighbors (KNN) and Logistic Regression. The lemon and orange fruits diseases are classified more accurately (95.0% for lemon and 99.69% for orange) by the model. The model's base features were extracted from the ResNet50 pre-trained model and the diseases are classified by the Logistic Regression which beats the performance given by VGG16 and VGG19 for other classifiers. Experimental outcomes show that the proposed model also outperforms existing models in which most of them classified the diseases using the Softmax classifier without using any individual classifiers.
Authors: David Denisov, Dan Feldman, Shlomi Dolev, Michael Segal
Abstract: We suggest efficient and provable methods to compute an approximation for imbalanced point clustering, that is, fitting $k$-centers to a set of points in $\mathbb{R}^d$, for any $d,k\geq 1$. To this end, we utilize \emph{coresets}, which, in the context of the paper, are essentially weighted sets of points in $\mathbb{R}^d$ that approximate the fitting loss for every model in a given set, up to a multiplicative factor of $1\pm\varepsilon$. We provide [Section 3 and Section E in the appendix] experiments that show the empirical contribution of our suggested methods for real images (novel and reference), synthetic data, and real-world data. We also propose choice clustering, which by combining clustering algorithms yields better performance than each one separately.
Authors: Muhammad Rajabinasab, Anton D. Lautrup, Tobias Hyrup, Arthur Zimek
Abstract: Expressive evaluation metrics are indispensable for informative experiments in all areas, and while several metrics are established in some areas, in others, such as feature selection, only indirect or otherwise limited evaluation metrics are found. In this paper, we propose a novel evaluation metric to address several problems of its predecessors and allow for flexible and reliable evaluation of feature selection algorithms. The proposed metric is a dynamic metric with two properties that can be used to evaluate both the performance and the stability of a feature selection algorithm. We conduct several empirical experiments to illustrate the use of the proposed metric in the successful evaluation of feature selection algorithms. We also provide a comparison and analysis to show the different aspects involved in the evaluation of the feature selection algorithms. The results indicate that the proposed metric is successful in carrying out the evaluation task for feature selection algorithms. This paper is an extended version of a paper accepted at SISAP 2024.
Authors: Loris Schoenegger, Yuxi Xia, Benjamin Roth
Abstract: The increasing difficulty to distinguish language-model-generated from human-written text has led to the development of detectors of machine-generated text (MGT). However, in many contexts, a black-box prediction is not sufficient, it is equally important to know on what grounds a detector made that prediction. Explanation methods that estimate feature importance promise to provide indications of which parts of an input are used by classifiers for prediction. However, the quality of different explanation methods has not previously been assessed for detectors of MGT. This study conducts the first systematic evaluation of explanation quality for this task. The dimensions of faithfulness and stability are assessed with five automated experiments, and usefulness is evaluated in a user study. We use a dataset of ChatGPT-generated and human-written documents, and pair predictions of three existing language-model-based detectors with the corresponding SHAP, LIME, and Anchor explanations. We find that SHAP performs best in terms of faithfulness, stability, and in helping users to predict the detector's behavior. In contrast, LIME, perceived as most useful by users, scores the worst in terms of user performance at predicting the detectors' behavior.
Authors: Chang Gao, Jianfei Chen, Kang Zhao, Jiaqi Wang, Liping Jing
Abstract: Fully quantized training (FQT) accelerates the training of deep neural networks by quantizing the activations, weights, and gradients into lower precision. To explore the ultimate limit of FQT (the lowest achievable precision), we make a first attempt to 1-bit FQT. We provide a theoretical analysis of FQT based on Adam and SGD, revealing that the gradient variance influences the convergence of FQT. Building on these theoretical results, we introduce an Activation Gradient Pruning (AGP) strategy. The strategy leverages the heterogeneity of gradients by pruning less informative gradients and enhancing the numerical precision of remaining gradients to mitigate gradient variance. Additionally, we propose Sample Channel joint Quantization (SCQ), which utilizes different quantization strategies in the computation of weight gradients and activation gradients to ensure that the method is friendly to low-bitwidth hardware. Finally, we present a framework to deploy our algorithm. For fine-tuning VGGNet-16 and ResNet-18 on multiple datasets, our algorithm achieves an average accuracy improvement of approximately 6%, compared to per-sample quantization. Moreover, our training speedup can reach a maximum of 5.13x compared to full precision training.
Authors: Michael Kirchhof
Abstract: Uncertainty quantification is a key pillar of trustworthy machine learning. It enables safe reactions under unsafe inputs, like predicting only when the machine learning model detects sufficient evidence, discarding anomalous data, or emitting warnings when an error is likely to be inbound. This is particularly crucial in safety-critical areas like medical image classification or self-driving cars. Despite the plethora of proposed uncertainty quantification methods achieving increasingly higher scores on performance benchmarks, uncertainty estimates are often shied away from in practice. Many machine learning projects start from pretrained latent representations that come without uncertainty estimates. Uncertainties would need to be trained by practitioners on their own, which is notoriously difficult and resource-intense. This thesis makes uncertainty estimates easily accessible by adding them to the latent representation vectors of pretrained computer vision models. Besides proposing approaches rooted in probability and decision theory, such as Monte-Carlo InfoNCE (MCInfoNCE) and loss prediction, we delve into both theoretical and empirical questions. We show that these unobservable uncertainties about unobservable latent representations are indeed provably correct. We also provide an uncertainty-aware representation learning (URL) benchmark to compare these unobservables against observable ground-truths. Finally, we compile our findings to pretrain lightweight representation uncertainties on large-scale computer vision models that transfer to unseen datasets in a zero-shot manner. Our findings do not only advance the current theoretical understanding of uncertainties over latent variables, but also facilitate the access to uncertainty quantification for future researchers inside and outside the field, enabling straightforward but trustworthy machine learning.
Authors: Monica Millunzi, Lorenzo Bonicelli, Angelo Porrello, Jacopo Credi, Petter N. Kolm, Simone Calderara
Abstract: Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data environments. To address this issue, most approaches in Continual Learning (CL) rely on the replay of a restricted buffer of past data. However, the presence of noise in real-world scenarios, where human annotation is constrained by time limitations or where data is automatically gathered from the web, frequently renders these strategies vulnerable. In this study, we address the problem of CL under Noisy Labels (CLN) by introducing Alternate Experience Replay (AER), which takes advantage of forgetting to maintain a clear distinction between clean, complex, and noisy samples in the memory buffer. The idea is that complex or mislabeled examples, which hardly fit the previously learned data distribution, are most likely to be forgotten. To grasp the benefits of such a separation, we equip AER with Asymmetric Balanced Sampling (ABS): a new sample selection strategy that prioritizes purity on the current task while retaining relevant samples from the past. Through extensive computational comparisons, we demonstrate the effectiveness of our approach in terms of both accuracy and purity of the obtained buffer, resulting in a remarkable average gain of 4.71% points in accuracy with respect to existing loss-based purification strategies. Code is available at https://github.com/aimagelab/mammoth.
Authors: Danil Provodin, Bram van den Akker, Christina Katsimerou, Maurits Kaptein, Mykola Pechenizkiy
Abstract: In supervised machine learning, privileged information (PI) is information that is unavailable at inference, but is accessible during training time. Research on learning using privileged information (LUPI) aims to transfer the knowledge captured in PI onto a model that can perform inference without PI. It seems that this extra bit of information ought to make the resulting model better. However, finding conclusive theoretical or empirical evidence that supports the ability to transfer knowledge using PI has been challenging. In this paper, we critically examine the assumptions underlying existing theoretical analyses and argue that there is little theoretical justification for when LUPI should work. We analyze LUPI methods and reveal that apparent improvements in empirical risk of existing research may not directly result from PI. Instead, these improvements often stem from dataset anomalies or modifications in model design misguidedly attributed to PI. Our experiments for a wide variety of application domains further demonstrate that state-of-the-art LUPI approaches fail to effectively transfer knowledge from PI. Thus, we advocate for practitioners to exercise caution when working with PI to avoid unintended inductive biases.
Authors: Lucia Pezzetti, Stefano Favaro, Stefano Pelucchetti
Abstract: Bayesian Neural Networks represent a fascinating confluence of deep learning and probabilistic reasoning, offering a compelling framework for understanding uncertainty in complex predictive models. In this paper, we investigate the use of the preconditioned Crank-Nicolson algorithm and its Langevin version to sample from the reparametrised posterior distribution of the weights as the widths of Bayesian Neural Networks grow larger. In addition to being robust in the infinite-dimensional setting, we prove that the acceptance probabilities of the proposed methods approach 1 as the width of the network increases, independently of any stepsize tuning. Moreover, we examine and compare how the mixing speeds of the underdamped Langevin Monte Carlo, the preconditioned Crank-Nicolson and the preconditioned Crank-Nicolson Langevin samplers are influenced by changes in the network width in some real-world cases. Our findings suggest that, in wide Bayesian Neural Networks configurations, the preconditioned Crank-Nicolson method allows for more efficient sampling of the reparametrised posterior distribution, as evidenced by a higher effective sample size and improved diagnostic results compared with the other analysed algorithms.
Authors: Panyi Dong, Zhiyu Quan
Abstract: Machine Learning (ML) has gained popularity in actuarial research and insurance industrial applications. However, the performance of most ML tasks heavily depends on data preprocessing, model selection, and hyperparameter optimization, which are considered to be intensive in terms of domain knowledge, experience, and manual labor. Automated Machine Learning (AutoML) aims to automatically complete the full life-cycle of ML tasks and provides state-of-the-art ML models without human intervention or supervision. This paper introduces an AutoML workflow that allows users without domain knowledge or prior experience to achieve robust and effortless ML deployment by writing only a few lines of code. This proposed AutoML is specifically tailored for the insurance application, with features like the balancing step in data preprocessing, ensemble pipelines, and customized loss functions. These features are designed to address the unique challenges of the insurance domain, including the imbalanced nature of common insurance datasets. The full code and documentation are available on the GitHub repository. (https://github.com/PanyiDong/InsurAutoML)
Authors: Clayton Sanford, Daniel Hsu, Matus Telgarsky
Abstract: A simple communication complexity argument proves that no one-layer transformer can solve the induction heads task unless its size is exponentially larger than the size sufficient for a two-layer transformer.
Authors: Wei Tang, Weijia Zhang, Min-Ling Zhang
Abstract: Multi-instance partial-label learning (MIPL) addresses scenarios where each training sample is represented as a multi-instance bag associated with a candidate label set containing one true label and several false positives. Existing MIPL algorithms have primarily focused on mapping multi-instance bags to candidate label sets for disambiguation, disregarding the intrinsic properties of the label space and the supervised information provided by non-candidate label sets. In this paper, we propose an algorithm named ELIMIPL, i.e., Exploiting conjugate Label Information for Multi-Instance Partial-Label learning, which exploits the conjugate label information to improve the disambiguation performance. To achieve this, we extract the label information embedded in both candidate and non-candidate label sets, incorporating the intrinsic properties of the label space. Experimental results obtained from benchmark and real-world datasets demonstrate the superiority of the proposed ELIMIPL over existing MIPL algorithms and other well-established partial-label learning algorithms.
Authors: Dongyue Li, Kailai Chen, Predrag Radivojac, Hongyang R. Zhang
Abstract: Data augmentation is widely used for training a neural network given little labeled data. A common practice of augmentation training is applying a composition of multiple transformations sequentially to the data. Existing augmentation methods such as RandAugment randomly sample from a list of pre-selected transformations, while methods such as AutoAugment apply advanced search to optimize over an augmentation set of size $k^d$, which is the number of transformation sequences of length $d$, given a list of $k$ transformations. In this paper, we design efficient algorithms whose running time complexity is much faster than the worst-case complexity of $O(k^d)$, provably. We propose a new algorithm to search for a binary tree-structured composition of $k$ transformations, where each tree node corresponds to one transformation. The binary tree generalizes sequential augmentations, such as the SimCLR augmentation scheme for contrastive learning. Using a top-down, recursive search procedure, our algorithm achieves a runtime complexity of $O(2^d k)$, which is much faster than $O(k^d)$ as $k$ increases above $2$. We apply our algorithm to tackle data distributions with heterogeneous subpopulations by searching for one tree in each subpopulation and then learning a weighted combination, resulting in a forest of trees. We validate our proposed algorithms on numerous graph and image datasets, including a multi-label graph classification dataset we collected. The dataset exhibits significant variations in the sizes of graphs and their average degrees, making it ideal for studying data augmentation. We show that our approach can reduce the computation cost by 43% over existing search methods while improving performance by 4.3%. The tree structures can be used to interpret the relative importance of each transformation, such as identifying the important transformations on small vs. large graphs.
Authors: Sakhinana Sagar Srinivas, Chidaksh Ravuru, Geethan Sannidhi, Venkataramana Runkana
Abstract: Spatio-temporal forecasting plays a crucial role in various sectors such as transportation systems, logistics, and supply chain management. However, existing methods are limited by their ability to handle large, complex datasets. To overcome this limitation, we introduce a hybrid approach that combines the strengths of open-source large and small-scale language models (LLMs and LMs) with traditional forecasting methods. We augment traditional methods with dynamic prompting and a grouped-query, multi-head attention mechanism to more effectively capture both intra-series and inter-series dependencies in evolving nonlinear time series data. In addition, we facilitate on-premises customization by fine-tuning smaller open-source LMs for time series trend analysis utilizing descriptions generated by open-source large LMs on consumer-grade hardware using Low-Rank Adaptation with Activation Memory Reduction (LoRA-AMR) technique to reduce computational overhead and activation storage memory demands while preserving inference latency. We combine language model processing for time series trend analysis with traditional time series representation learning method for cross-modal integration, achieving robust and accurate forecasts. The framework effectiveness is demonstrated through extensive experiments on various real-world datasets, outperforming existing methods by significant margins in terms of forecast accuracy.
Authors: Yahao Ding, Wen Shang, Minrui Xu, Zhaohui Yang, Ye Hu, Dusit Niyato, Mohammad Shikh-Bahaei
Abstract: The Metaverse, a burgeoning collective virtual space merging augmented reality and persistent virtual worlds, necessitates advanced artificial intelligence (AI) and communication technologies to support immersive and interactive experiences. Federated learning (FL) has emerged as a promising technique for collaboratively training AI models while preserving data privacy. However, FL faces challenges such as high communication overhead and substantial computational demands, particularly for neural network (NN) models. To address these issues, we propose an integrated federated split learning and hyperdimensional computing (FSL-HDC) framework for emerging foundation models. This novel approach reduces communication costs, computation load, and privacy risks, making it particularly suitable for resource-constrained edge devices in the Metaverse, ensuring real-time responsive interactions. Additionally, we introduce an optimization algorithm that concurrently optimizes transmission power and bandwidth to minimize the maximum transmission time among all users to the server. The simulation results based on the MNIST dataset indicate that FSL-HDC achieves an accuracy rate of approximately 87.5%, which is slightly lower than that of FL-HDC. However, FSL-HDC exhibits a significantly faster convergence speed, approximately 3.733x that of FSL-NN, and demonstrates robustness to non-IID data distributions. Moreover, our proposed optimization algorithm can reduce the maximum transmission time by up to 64% compared with the baseline.
Authors: Luyue Xu, Liming Wang, Hong Xie, Mingqiang Zhou
Abstract: Contextual bandits serve as a fundamental algorithmic framework for optimizing recommendation decisions online. Though extensive attention has been paid to tailoring contextual bandits for recommendation applications, the "herding effects" in user feedback have been ignored. These herding effects bias user feedback toward historical ratings, breaking down the assumption of unbiased feedback inherent in contextual bandits. This paper develops a novel variant of the contextual bandit that is tailored to address the feedback bias caused by the herding effects. A user feedback model is formulated to capture this feedback bias. We design the TS-Conf (Thompson Sampling under Conformity) algorithm, which employs posterior sampling to balance the exploration and exploitation tradeoff. We prove an upper bound for the regret of the algorithm, revealing the impact of herding effects on learning speed. Extensive experiments on datasets demonstrate that TS-Conf outperforms four benchmark algorithms. Analysis reveals that TS-Conf effectively mitigates the negative impact of herding effects, resulting in faster learning and improved recommendation accuracy.
Authors: Yossi Arjevani
Abstract: Critical points of an invariant function may or may not be symmetric. We prove, however, that if a symmetric critical point exists, those adjacent to it are generically symmetry breaking. This mathematical mechanism is shown to carry important implications for our ability to efficiently minimize invariant nonconvex functions, in particular those associated with neural networks.
Authors: Shiyu Wang, Ziyuan Xu, Yamin Li, Mara Mather, Roza G. Bayrak, Catie Chang
Abstract: Interactions between the brain and body are of fundamental importance for human behavior and health. Functional magnetic resonance imaging (fMRI) captures whole-brain activity noninvasively, and modeling how fMRI signals interact with physiological dynamics of the body can provide new insight into brain function and offer potential biomarkers of disease. However, physiological recordings are not always possible to acquire since they require extra equipment and setup, and even when they are, the recorded physiological signals may contain substantial artifacts. To overcome this limitation, machine learning models have been proposed to directly extract features of respiratory and cardiac activity from resting-state fMRI signals. To date, such work has been carried out only in healthy young adults and in a pediatric population, leaving open questions about the efficacy of these approaches on older adults. Here, we propose a novel framework that leverages Transformer-based architectures for reconstructing two key physiological signals - low-frequency respiratory volume (RV) and heart rate (HR) fluctuations - from fMRI data, and test these models on a dataset of individuals aged 36-89 years old. Our framework outperforms previously proposed approaches (attaining median correlations between predicted and measured signals of r ~ .698 for RV and r ~ .618 for HR), indicating the potential of leveraging attention mechanisms to model fMRI-physiological signal relationships. We also evaluate several model training and fine-tuning strategies, and find that incorporating young-adult data during training improves the performance when predicting physiological signals in the aging cohort. Overall, our approach successfully infers key physiological variables directly from fMRI data from individuals across a wide range of the adult lifespan.
Authors: Sheel Nidhan, Haoliang Jiang, Lalit Ghule, Clancy Umphrey, Rishikesh Ranade, Jay Pathak
Abstract: In this paper, we propose a domain-decomposition-based deep learning (DL) framework, named transient-CoMLSim, for accurately modeling unsteady and nonlinear partial differential equations (PDEs). The framework consists of two key components: (a) a convolutional neural network (CNN)-based autoencoder architecture and (b) an autoregressive model composed of fully connected layers. Unlike existing state-of-the-art methods that operate on the entire computational domain, our CNN-based autoencoder computes a lower-dimensional basis for solution and condition fields represented on subdomains. Timestepping is performed entirely in the latent space, generating embeddings of the solution variables from the time history of embeddings of solution and condition variables. This approach not only reduces computational complexity but also enhances scalability, making it well-suited for large-scale simulations. Furthermore, to improve the stability of our rollouts, we employ a curriculum learning (CL) approach during the training of the autoregressive model. The domain-decomposition strategy enables scaling to out-of-distribution domain sizes while maintaining the accuracy of predictions -- a feature not easily integrated into popular DL-based approaches for physics simulations. We benchmark our model against two widely-used DL architectures, Fourier Neural Operator (FNO) and U-Net, and demonstrate that our framework outperforms them in terms of accuracy, extrapolation to unseen timesteps, and stability for a wide range of use cases.
Authors: Zijian Ding, Atefeh Sohrabizadeh, Weikai Li, Zongyue Qin, Yizhou Sun, Jason Cong
Abstract: There have been several recent works proposed to utilize model-based optimization methods to improve the productivity of using high-level synthesis (HLS) to design domain-specific architectures. They would replace the time-consuming performance estimation or simulation of design with a proxy model, and automatically insert pragmas to guide hardware optimizations. In this work, we address the challenges associated with high-level synthesis (HLS) design space exploration (DSE) through the evolving landscape of HLS tools. As these tools develop, the quality of results (QoR) from synthesis can vary significantly, complicating the maintenance of optimal design strategies across different toolchains. We introduce Active-CEM, a task transfer learning scheme that leverages a model-based explorer designed to adapt efficiently to changes in toolchains. This approach optimizes sample efficiency by identifying high-quality design configurations under a new toolchain without requiring extensive re-evaluation. We further refine our methodology by incorporating toolchain-invariant modeling. This allows us to predict QoR changes more accurately despite shifts in the black-box implementation of the toolchains. Experiment results on the HLSyn benchmark transitioning to new toolchain show an average performance improvement of 1.58$\times$ compared to AutoDSE and a 1.2$\times$ improvement over HARP, while also increasing the sample efficiency by 5.26$\times$, and reducing the runtime by 2.7$\times$.
Authors: Geethan Sannidhi, Sagar Srinivas Sakhinana, Venkataramana Runkana
Abstract: Pre-trained large language models (PLLMs) like OpenAI ChatGPT and Google Gemini face challenges such as inaccurate factual recall, hallucinations, biases, and future data leakage for temporal Knowledge Graph (tKG) forecasting. To address these issues, we introduce sLA-tKGF (small-scale language assistant for tKG forecasting), which utilizes Retrieval-Augmented Generation (RAG) aided, custom-trained small-scale language models through a tabula rasa approach from scratch for effective tKG forecasting. Our framework constructs knowledge-infused prompts with relevant historical data from tKGs, web search results, and PLLMs-generated textual descriptions to understand historical entity relationships prior to the target time. It leverages these external knowledge-infused prompts for deeper understanding and reasoning of context-specific semantic and temporal information to zero-shot prompt small-scale language models for more accurate predictions of future events within tKGs. It reduces hallucinations and mitigates distributional shift challenges through comprehending changing trends over time. As a result, it enables more accurate and contextually grounded forecasts of future events while minimizing computational demands. Rigorous empirical studies demonstrate our framework robustness, scalability, and state-of-the-art (SOTA) performance on benchmark datasets with interpretable and trustworthy tKG forecasting.
Authors: Borja Rodr\'iguez-G\'alvez, Ragnar Thobaben, Mikael Skoglund
Abstract: We investigate the in-distribution generalization of machine learning algorithms. We depart from traditional complexity-based approaches by analyzing information-theoretic bounds that quantify the dependence between a learning algorithm and the training data. We consider two categories of generalization guarantees: 1) Guarantees in expectation: These bounds measure performance in the average case. Here, the dependence between the algorithm and the data is often captured by information measures. While these measures offer an intuitive interpretation, they overlook the geometry of the algorithm's hypothesis class. Here, we introduce bounds using the Wasserstein distance to incorporate geometry, and a structured, systematic method to derive bounds capturing the dependence between the algorithm and an individual datum, and between the algorithm and subsets of the training data. 2) PAC-Bayesian guarantees: These bounds measure the performance level with high probability. Here, the dependence between the algorithm and the data is often measured by the relative entropy. We establish connections between the Seeger--Langford and Catoni's bounds, revealing that the former is optimized by the Gibbs posterior. We introduce novel, tighter bounds for various types of loss functions. To achieve this, we introduce a new technique to optimize parameters in probabilistic statements. To study the limitations of these approaches, we present a counter-example where most of the information-theoretic bounds fail while traditional approaches do not. Finally, we explore the relationship between privacy and generalization. We show that algorithms with a bounded maximal leakage generalize. For discrete data, we derive new bounds for differentially private algorithms that guarantee generalization even with a constant privacy parameter, which is in contrast to previous bounds in the literature.
Authors: Dominik St\"oger, Yizhe Zhu
Abstract: For the problem of reconstructing a low-rank matrix from a few linear measurements, two classes of algorithms have been widely studied in the literature: convex approaches based on nuclear norm minimization, and non-convex approaches that use factorized gradient descent. Under certain statistical model assumptions, it is known that nuclear norm minimization recovers the ground truth as soon as the number of samples scales linearly with the number of degrees of freedom of the ground-truth. In contrast, while non-convex approaches are computationally less expensive, existing recovery guarantees assume that the number of samples scales at least quadratically with the rank $r$ of the ground-truth matrix. In this paper, we close this gap by showing that the non-convex approaches can be as efficient as nuclear norm minimization in terms of sample complexity. Namely, we consider the problem of reconstructing a positive semidefinite matrix from a few Gaussian measurements. We show that factorized gradient descent with spectral initialization converges to the ground truth with a linear rate as soon as the number of samples scales with $ \Omega (rd\kappa^2)$, where $d$ is the dimension, and $\kappa$ is the condition number of the ground truth matrix. This improves the previous rank-dependence from quadratic to linear. Our proof relies on a probabilistic decoupling argument, where we show that the gradient descent iterates are only weakly dependent on the individual entries of the measurement matrices. We expect that our proof technique is of independent interest for other non-convex problems.
Authors: Wei-Ning Chen, Peter Kairouz, Sewoong Oh, Zheng Xu
Abstract: In this paper, we investigate potential randomization approaches that can complement current practices of input-based methods (such as licensing data and prompt filtering) and output-based methods (such as recitation checker, license checker, and model-based similarity score) for copyright protection. This is motivated by the inherent ambiguity of the rules that determine substantial similarity in copyright precedents. Given that there is no quantifiable measure of substantial similarity that is agreed upon, complementary approaches can potentially further decrease liability. Similar randomized approaches, such as differential privacy, have been successful in mitigating privacy risks. This document focuses on the technical and research perspective on mitigating copyright violation and hence is not confidential. After investigating potential solutions and running numerical experiments, we concluded that using the notion of Near Access-Freeness (NAF) to measure the degree of substantial similarity is challenging, and the standard approach of training a Differentially Private (DP) model costs significantly when used to ensure NAF. Alternative approaches, such as retrieval models, might provide a more controllable scheme for mitigating substantial similarity.
Authors: Leye Zhang, Xiangxiang Tian, Hongjun Zhang
Abstract: This paper constructs question answering system for bridge design specification based on large language model. Three implementation schemes are tried: full fine-tuning of the Bert pretrained model, parameter-efficient fine-tuning of the Bert pretrained model, and self-built language model from scratch. Through the self-built question and answer task dataset, based on the tensorflow and keras deep learning platform framework, the model is constructed and trained to predict the start position and end position of the answer in the bridge design specification given by the user. The experimental results show that full fine-tuning of the Bert pretrained model achieves 100% accuracy in the training-dataset, validation-dataset and test-dataset, and the system can extract the answers from the bridge design specification given by the user to answer various questions of the user; While parameter-efficient fine-tuning of the Bert pretrained model and self-built language model from scratch perform well in the training-dataset, their generalization ability in the test-dataset needs to be improved. The research of this paper provides a useful reference for the development of question answering system in professional field.
Authors: Jakub Olczak, Max Gordon
Abstract: Background: Radiography (X-rays) is the dominant modality in orthopedics, and improving the interpretation of radiographs is clinically relevant. Machine learning (ML) has revolutionized data analysis and has been applied to medicine, with some success, in the form of natural language processing (NLP) and artificial neural networks (ANN). Latent Dirichlet allocation (LDA) is an NLP method that automatically categorizes documents into topics. Successfully applying ML to orthopedic radiography could enable the creation of computer-aided decision systems for use in the clinic. We studied how an automated ML pipeline could classify orthopedic trauma radiographs from radiologist reports. Methods: Wrist and ankle radiographs from Danderyd Hospital in Sweden taken between 2002 and 2015, with radiologist reports. LDA was used to create image labels for radiographs from the radiologist reports. Radiographs and labels were used to train an image recognition ANN. The ANN outcomes were manually reviewed to get an accurate estimate of the method's utility and accuracy. Results: Image Labels generated via LDA could successfully train the ANN. The ANN reached an accuracy between 91% and 60% compared to a gold standard, depending on the label. Conclusions: We found that LDA was unsuited to label orthopedic radiographs from reports with high accuracy. However, despite this, the ANN could learn to detect some features in radiographs with high accuracy. The study also illustrates how ML and ANN can be applied to medical research.
Authors: Rishabh Srivastava, Addrish Roy
Abstract: Our study delves into the fusion of abstract art interpretation and text-to-image synthesis, addressing the challenge of achieving precise spatial control over image composition solely through textual prompts. Leveraging the capabilities of ControlNet, we empower users with finer control over the synthesis process, enabling enhanced manipulation of synthesized imagery. Inspired by the minimalist forms found in abstract artworks, we introduce a novel condition crafted from geometric primitives such as triangles.
Authors: Aryan Morteza, Hosein K. Nazari, Peyman Pahlevani
Abstract: This study proposes a machine learning-based Model Predictive Control (MPC) approach for controlling Air Handling Unit (AHU) systems by employing an Internet of Things (IoT) framework. The proposed framework utilizes an Artificial Neural Network (ANN) to provide dynamic-linear thermal model parameters considering building information and disturbances in real time, thereby facilitating the practical MPC of the AHU system. The proposed framework allows users to establish new setpoints for a closed-loop control system, enabling customization of the thermal environment to meet individual needs with minimal use of the AHU. The experimental results demonstrate the cost benefits of the proposed machine-learning-based MPC-IoT framework, achieving a 57.59\% reduction in electricity consumption compared with a clock-based manual controller while maintaining a high level of user satisfaction. The proposed framework offers remarkable flexibility and effectiveness, even in legacy systems with limited building information, making it a pragmatic and valuable solution for enhancing the energy efficiency and user comfort in pre-existing structures.
Authors: Qi Qian, Juhua Hu
Abstract: Vision-language pre-training such as CLIP enables zero-shot transfer that can classify images according to the candidate class names. While CLIP demonstrates an impressive zero-shot performance on diverse downstream tasks, the distribution from the target data has not been leveraged sufficiently. In this work, we study a novel online zero-shot transfer scenario, where each image arrives in a random order for classification and is visited only once to obtain prediction immediately without storing its representation. Compared with the vanilla zero-shot classification, the proposed framework preserves its flexibility for online service while considering the statistics of the arrived images as the side information to capture the distribution of target data, which can help improve the performance of real-world applications. To tackle the challenge of effective online optimization, we first develop online label learning to model the target data distribution. Then, the proxy of each class in the vision space is further optimized with the proposed online proxy learning method to mitigate the modality gap between images and text. The convergence of both online strategies can be theoretically guaranteed. By combining the predicted label from the online label learning and proxy learning, our online zero-shot transfer method (OnZeta) achieves $78.94\%$ accuracy on ImageNet without accessing the entire data set. Moreover, extensive experiments on other 13 downstream tasks with different vision encoders show a more than $3\%$ improvement on average, which demonstrates the effectiveness of our proposal. Code is available at \url{https://github.com/idstcv/OnZeta}.
Authors: Johannes O. Royset
Abstract: Solutions of bilevel optimization problems tend to suffer from instability under changes to problem data. In the optimistic setting, we construct a lifted, alternative formulation that exhibits desirable stability properties under mild assumptions that neither invoke convexity nor smoothness. The upper- and lower-level problems might involve integer restrictions and disjunctive constraints. In a range of results, we at most invoke pointwise and local calmness for the lower-level problem in a sense that holds broadly. The alternative formulation is computationally attractive with structural properties being brought out and an outer approximation algorithm becoming available.
Authors: Qi Qian, Yuanhong Xu, Juhua Hu
Abstract: Deep features extracted from certain layers of a pre-trained deep model show superior performance over the conventional hand-crafted features. Compared with fine-tuning or linear probing that can explore diverse augmentations, \eg, random crop/flipping, in the original input space, the appropriate augmentations for learning with fixed deep features are more challenging and have been less investigated, which degenerates the performance. To unleash the potential of fixed deep features, we propose a novel semantic adversarial augmentation (SeA) in the feature space for optimization. Concretely, the adversarial direction implied by the gradient will be projected to a subspace spanned by other examples to preserve the semantic information. Then, deep features will be perturbed with the semantic direction, and augmented features will be applied to learn the classifier. Experiments are conducted on $11$ benchmark downstream classification tasks with $4$ popular pre-trained models. Our method is $2\%$ better than the deep features without SeA on average. Moreover, compared to the expensive fine-tuning that is expected to give good performance, SeA shows a comparable performance on $6$ out of $11$ tasks, demonstrating the effectiveness of our proposal in addition to its efficiency. Code is available at \url{https://github.com/idstcv/SeA}.
Authors: Ankit Kulshrestha, Xiaoyuan Liu, Hayato Ushijima-Mwesigwa, Bao Bach, Ilya Safro
Abstract: In the present noisy intermediate scale quantum computing era, there is a critical need to devise methods for the efficient implementation of gate-based variational quantum circuits. This ensures that a range of proposed applications can be deployed on real quantum hardware. The efficiency of quantum circuit is desired both in the number of trainable gates and the depth of the overall circuit. The major concern of barren plateaus has made this need for efficiency even more acute. The problem of efficient quantum circuit realization has been extensively studied in the literature to reduce gate complexity and circuit depth. Another important approach is to design a method to reduce the \emph{parameter complexity} in a variational quantum circuit. Existing methods include hyperparameter-based parameter pruning which introduces an additional challenge of finding the best hyperparameters for different applications. In this paper, we present \emph{QAdaPrune} - an adaptive parameter pruning algorithm that automatically determines the threshold and then intelligently prunes the redundant and non-performing parameters. We show that the resulting sparse parameter sets yield quantum circuits that perform comparably to the unpruned quantum circuits and in some cases may enhance trainability of the circuits even if the original quantum circuit gets stuck in a barren plateau.\\ \noindent{\bf Reproducibility}: The source code and data are available at \url{https://github.com/aicaffeinelife/QAdaPrune.git}
Authors: Yikang Shen, Matthew Stallone, Mayank Mishra, Gaoyuan Zhang, Shawn Tan, Aditya Prasad, Adriana Meza Soria, David D. Cox, Rameswar Panda
Abstract: Finding the optimal learning rate for language model pretraining is a challenging task. This is not only because there is a complicated correlation between learning rate, batch size, number of training tokens, model size, and other hyperparameters but also because it is prohibitively expensive to perform a hyperparameter search for large language models with Billions or Trillions of parameters. Recent studies propose using small proxy models and small corpus to perform hyperparameter searches and transposing the optimal parameters to large models and large corpus. While the zero-shot transferability is theoretically and empirically proven for model size related hyperparameters, like depth and width, the zero-shot transfer from small corpus to large corpus is underexplored. In this paper, we study the correlation between optimal learning rate, batch size, and number of training tokens for the recently proposed WSD scheduler. After thousands of small experiments, we found a power-law relationship between variables and demonstrated its transferability across model sizes. Based on the observation, we propose a new learning rate scheduler, Power scheduler, that is agnostic about the number of training tokens and batch size. The experiment shows that combining the Power scheduler with Maximum Update Parameterization (muP) can consistently achieve impressive performance with one set of hyperparameters regardless of the number of training tokens, batch size, model size, and even model architecture. Our 3B dense and MoE models trained with the Power scheduler achieve comparable performance as state-of-the-art small language models. We open-source these pretrained models at https://ibm.biz/BdKhLa.
URLs: https://ibm.biz/BdKhLa.
Authors: Ekaterina Trofimova, Emil Sataev, Abhijit Singh Jowhari
Abstract: This paper presents CodeRefine, a novel framework for automatically transforming research paper methodologies into functional code using Large Language Models (LLMs). Our multi-step approach first extracts and summarizes key text chunks from papers, analyzes their code relevance, and creates a knowledge graph using a predefined ontology. Code is then generated from this structured representation and enhanced through a proposed retrospective retrieval-augmented generation approach. CodeRefine addresses the challenge of bridging theoretical research and practical implementation, offering a more accurate alternative to LLM zero-shot prompting. Evaluations on diverse scientific papers demonstrate CodeRefine's ability to improve code implementation from the paper, potentially accelerating the adoption of cutting-edge algorithms in real-world applications.
Authors: Georgios Bakirtzis, Michail Savvas, Ruihan Zhao, Sandeep Chinchali, Ufuk Topcu
Abstract: In reinforcement learning, conducting task composition by forming cohesive, executable sequences from multiple tasks remains challenging. However, the ability to (de)compose tasks is a linchpin in developing robotic systems capable of learning complex behaviors. Yet, compositional reinforcement learning is beset with difficulties, including the high dimensionality of the problem space, scarcity of rewards, and absence of system robustness after task composition. To surmount these challenges, we view task composition through the prism of category theory -- a mathematical discipline exploring structures and their compositional relationships. The categorical properties of Markov decision processes untangle complex tasks into manageable sub-tasks, allowing for strategical reduction of dimensionality, facilitating more tractable reward structures, and bolstering system robustness. Experimental results support the categorical theory of reinforcement learning by enabling skill reduction, reuse, and recycling when learning complex robotic arm tasks.
Authors: Yoshitaka Inoue, Tianci Song, Tianfan Fu
Abstract: Drug repurposing offers a promising avenue for accelerating drug development by identifying new therapeutic potentials of existing drugs. In this paper, we propose a multi-agent framework to enhance the drug repurposing process using state-of-the-art machine learning techniques and knowledge integration. Our framework comprises several specialized agents: an AI Agent trains robust drug-target interaction (DTI) models; a Knowledge Graph Agent utilizes the drug-gene interaction database (DGIdb), DrugBank, Comparative Toxicogenomics Database (CTD), and Search Tool for Interactions of Chemicals (STITCH) to systematically extract DTIs; and a Search Agent interacts with biomedical literature to annotate and verify computational predictions. By integrating outputs from these agents, our system effectively harnesses diverse data sources, including external databases, to propose viable repurposing candidates. Preliminary results demonstrate the potential of our approach in not only predicting drug-disease interactions but also in reducing the time and cost associated with traditional drug discovery methods. This paper highlights the scalability of multi-agent systems in biomedical research and their role in driving innovation in drug repurposing. Our approach not only outperforms existing methods in predicting drug repurposing potential but also provides interpretable results, paving the way for more efficient and cost-effective drug discovery processes.
Authors: Xuran Hu, Mingzhe Zhu, Zhenpeng Feng, Milo\v{s} Dakovi\'c, Ljubi\v{s}a Stankovi\'c
Abstract: The inherent "black box" nature of deep neural networks (DNNs) compromises their transparency and reliability. Recently, explainable AI (XAI) has garnered increasing attention from researchers. Several perturbation-based interpretations have emerged. However, these methods often fail to adequately consider feature dependencies. To solve this problem, we introduce a perturbation-based interpretation guided by feature coalitions, which leverages deep information of network to extract correlated features. Then, we proposed a carefully-designed consistency loss to guide network interpretation. Both quantitative and qualitative experiments are conducted to validate the effectiveness of our proposed method. Code is available at github.com/Teriri1999/Perturebation-on-Feature-Coalition.
Authors: Buxin Su, Jiayao Zhang, Natalie Collina, Yuling Yan, Didong Li, Kyunghyun Cho, Jianqing Fan, Aaron Roth, Weijie J. Su
Abstract: We conducted an experiment during the review process of the 2023 International Conference on Machine Learning (ICML) that requested authors with multiple submissions to rank their own papers based on perceived quality. We received 1,342 rankings, each from a distinct author, pertaining to 2,592 submissions. In this paper, we present an empirical analysis of how author-provided rankings could be leveraged to improve peer review processes at machine learning conferences. We focus on the Isotonic Mechanism, which calibrates raw review scores using author-provided rankings. Our analysis demonstrates that the ranking-calibrated scores outperform raw scores in estimating the ground truth ``expected review scores'' in both squared and absolute error metrics. Moreover, we propose several cautious, low-risk approaches to using the Isotonic Mechanism and author-provided rankings in peer review processes, including assisting senior area chairs' oversight of area chairs' recommendations, supporting the selection of paper awards, and guiding the recruitment of emergency reviewers. We conclude the paper by addressing the study's limitations and proposing future research directions.
Authors: Aditya Taparia, Som Sagar, Ransalu Senanayake
Abstract: Concept-based explanations have become a popular choice for explaining deep neural networks post-hoc because, unlike most other explainable AI techniques, they can be used to test high-level visual "concepts" that are not directly related to feature attributes. For instance, the concept of "stripes" is important to classify an image as a zebra. Concept-based explanation methods, however, require practitioners to guess and collect multiple candidate concept image sets, which can often be imprecise and labor-intensive. Addressing this limitation, in this paper, we frame concept image set creation as an image generation problem. However, since naively using a generative model does not result in meaningful concepts, we devise a reinforcement learning-based preference optimization algorithm that fine-tunes the vision-language generative model from approximate textual descriptions of concepts. Through a series of experiments, we demonstrate the capability of our method to articulate complex, abstract concepts that are otherwise challenging to craft manually. In addition to showing the efficacy and reliability of our method, we show how our method can be used as a diagnostic tool for analyzing neural networks.
Authors: Enas Altarawneh, Ameeta Agrawal, Michael Jenkin, Manos Papagelis
Abstract: Online conversations are particularly susceptible to derailment, which can manifest itself in the form of toxic communication patterns including disrespectful comments and abuse. Forecasting conversation derailment predicts signs of derailment in advance enabling proactive moderation of conversations. State-of-the-art approaches to conversation derailment forecasting sequentially encode conversations and use graph neural networks to model dialogue user dynamics. However, existing graph models are not able to capture complex conversational characteristics such as context propagation and emotional shifts. The use of common sense knowledge enables a model to capture such characteristics, thus improving performance. Following this approach, here we derive commonsense statements from a knowledge base of dialogue contextual information to enrich a graph neural network classification architecture. We fuse the multi-source information on utterance into capsules, which are used by a transformer-based forecaster to predict conversation derailment. Our model captures conversation dynamics and context propagation, outperforming the state-of-the-art models on the CGA and CMV benchmark datasets
Authors: Yidong Zhou, Jintai Chen, Weikang Li, Jinglei Cheng, Gopal Karemore, Marinka Zitnik, Frederic Chong, Junyu Liu, Tianfan Fu, Zhiding Liang
Abstract: Drug discovery and development is a highly complex and costly endeavor, typically requiring over a decade and substantial financial investment to bring a new drug to market. Traditional computer-aided drug design (CADD) has made significant progress in accelerating this process, but the development of quantum computing offers potential due to its unique capabilities. This paper discusses the integration of quantum computing into drug discovery and development, focusing on how quantum technologies might accelerate and enhance various stages of the drug development cycle. Specifically, we explore the application of quantum computing in addressing challenges related to drug discovery, such as molecular simulation and the prediction of drug-target interactions, as well as the optimization of clinical trial outcomes. By leveraging the inherent capabilities of quantum computing, we might be able to reduce the time and cost associated with bringing new drugs to market, ultimately benefiting public health.
Authors: Kailai Yang, Zhiwei Liu, Qianqian Xie, Jimin Huang, Erxue Min, Sophia Ananiadou
Abstract: Recent advancements in large language model alignment leverage token-level supervisions to perform fine-grained preference optimization. However, existing token-level alignment methods either optimize on all available tokens, which can be noisy and inefficient, or perform selective training with complex and expensive key token selection strategies. In this work, we propose Selective Preference Optimization (SePO), a novel selective alignment strategy that centers on efficient key token selection. SePO proposes the first token selection method based on Direct Preference Optimization (DPO), which trains an oracle model to estimate a token-level reward function on the target data. This method applies to any existing alignment datasets with response-level annotations and enables cost-efficient token selection with small-scale oracle models and training data. The estimated reward function is then utilized to score all tokens within the target dataset, where only the key tokens are selected to supervise the target policy model with a reference model-free contrastive objective function. Extensive experiments on three public evaluation benchmarks show that SePO significantly outperforms competitive baseline methods by only optimizing 30% key tokens on the target dataset. SePO applications on weak-to-strong generalization show that weak oracle models effectively supervise strong policy models with up to 16.8x more parameters. SePO also effectively selects key tokens from out-of-distribution data to enhance strong policy models and alleviate the over-optimization problem.
Authors: Vahid MohammadZadeh Eivaghi, Mahdi Aliyari Shoorehdeli
Abstract: False and nuisance alarms in industrial fault detection systems are often triggered by uncertainty, causing normal process variable fluctuations to be erroneously identified as faults. This paper introduces a novel encoder-based residual design that effectively decouples the stochastic and deterministic components of process variables without imposing detection delay. The proposed model employs two distinct encoders to factorize the latent space into two orthogonal spaces: one for the deterministic part and the other for the stochastic part. To ensure the identifiability of the desired spaces, constraints are applied during training. The deterministic space is constrained to be smooth to guarantee determinism, while the stochastic space is required to resemble standard Gaussian noise. Additionally, a decorrelation term enforces the independence of the learned representations. The efficacy of this approach is demonstrated through numerical examples and its application to the Tennessee Eastman process, highlighting its potential for robust fault detection. By focusing decision logic solely on deterministic factors, the proposed model significantly enhances prediction quality while achieving nearly zero false alarms and missed detections, paving the way for improved operational safety and integrity in industrial environments.
Authors: Hooman Danesh, Daniele Di Lorenzo, Francisco Chinesta, Stefanie Reese, Tim Brepols
Abstract: Auxetic structures, known for their negative Poisson's ratio, exhibit effective elastic properties heavily influenced by their underlying structural geometry and base material properties. While periodic homogenization of auxetic unit cells can be used to investigate these properties, it is computationally expensive and limits design space exploration and inverse analysis. In this paper, surrogate models are developed for the real-time prediction of the effective elastic properties of auxetic unit cells with orthogonal voids of different shapes. The unit cells feature orthogonal voids in four distinct shapes, including rectangular, diamond, oval, and peanut-shaped voids, each characterized by specific void diameters. The generated surrogate models accept geometric parameters and the elastic properties of the base material as inputs to predict the effective elastic constants in real-time. This rapid evaluation enables a practical inverse analysis framework for obtaining the optimal design parameters that yield the desired effective response. The fast Fourier transform (FFT)-based homogenization approach is adopted to efficiently generate data for developing the surrogate models, bypassing concerns about periodic mesh generation and boundary conditions typically associated with the finite element method (FEM). The performance of the generated surrogate models is rigorously examined through a train/test split methodology, a parametric study, and an inverse problem. Finally, a graphical user interface (GUI) is developed, offering real-time prediction of the effective tangent stiffness and performing inverse analysis to determine optimal geometric parameters.
Authors: Caixing Wang, Xingdong Feng
Abstract: The random feature (RF) approach is a well-established and efficient tool for scalable kernel methods, but existing literature has primarily focused on kernel ridge regression with random features (KRR-RF), which has limitations in handling heterogeneous data with heavy-tailed noises. This paper presents a generalization study of kernel quantile regression with random features (KQR-RF), which accounts for the non-smoothness of the check loss in KQR-RF by introducing a refined error decomposition and establishing a novel connection between KQR-RF and KRR-RF. Our study establishes the capacity-dependent learning rates for KQR-RF under mild conditions on the number of RFs, which are minimax optimal up to some logarithmic factors. Importantly, our theoretical results, utilizing a data-dependent sampling strategy, can be extended to cover the agnostic setting where the target quantile function may not precisely align with the assumed kernel space. By slightly modifying our assumptions, the capacity-dependent error analysis can also be applied to cases with Lipschitz continuous losses, enabling broader applications in the machine learning community. To validate our theoretical findings, simulated experiments and a real data application are conducted.
Authors: Thomas Hoang
Abstract: Our algorithm GNN: Graph Neural Network and Large Language Model Based for Data Discovery inherits the benefits of \cite{hoang2024plod} (PLOD: Predictive Learning Optimal Data Discovery), \cite{Hoang2024BODBO} (BOD: Blindly Optimal Data Discovery) in terms of overcoming the challenges of having to predefine utility function and the human input for attribute ranking, which helps prevent the time-consuming loop process. In addition to these previous works, our algorithm GNN leverages the advantages of graph neural networks and large language models to understand text type values that cannot be understood by PLOD and MOD, thus making the task of predicting outcomes more reliable. GNN could be seen as an extension of PLOD in terms of understanding the text type value and the user's preferences based on not only numerical values but also text values, making the promise of data science and analytics purposes.
Authors: Sakhinana Sagar Srinivas, Geethan Sannidhi, Sreeja Gangasani, Chidaksh Ravuru, Venkataramana Runkana
Abstract: Characterizing materials using electron micrographs is crucial in areas such as semiconductors and quantum materials. Traditional classification methods falter due to the intricatestructures of these micrographs. This study introduces an innovative architecture that leverages the generative capabilities of zero-shot prompting in Large Language Models (LLMs) such as GPT-4(language only), the predictive ability of few-shot (in-context) learning in Large Multimodal Models (LMMs) such as GPT-4(V)ision, and fuses knowledge across image based and linguistic insights for accurate nanomaterial category prediction. This comprehensive approach aims to provide a robust solution for the automated nanomaterial identification task in semiconductor manufacturing, blending performance, efficiency, and interpretability. Our method surpasses conventional approaches, offering precise nanomaterial identification and facilitating high-throughput screening.
Authors: Yoon Tae Park, Ting Xu, Mohamed Anany
Abstract: Uplift modeling is essential for optimizing marketing strategies by selecting individuals likely to respond positively to specific marketing campaigns. This importance escalates in multi-treatment marketing campaigns, where diverse treatment is available and we may want to assign the customers to treatment that can make the most impact. While there are existing approaches with convenient frameworks like Causalml, there are potential spaces to enhance the effect of uplift modeling in multi treatment cases. This paper introduces a novel approach to uplift modeling in multi-treatment campaigns, leveraging score ranking and calibration techniques to improve overall performance of the marketing campaign. We review existing uplift models, including Meta Learner frameworks (S, T, X), and their application in real-world scenarios. Additionally, we delve into insights from multi-treatment studies to highlight the complexities and potential advancements in the field. Our methodology incorporates Meta-Learner calibration and a scoring rank-based offer selection strategy. Extensive experiment results with real-world datasets demonstrate the practical benefits and superior performance of our approach. The findings underscore the critical role of integrating score ranking and calibration techniques in refining the performance and reliability of uplift predictions, thereby advancing predictive modeling in marketing analytics and providing actionable insights for practitioners seeking to optimize their campaign strategies.
Authors: Leonardo Matone, Ben Abramowitz, Nicholas Mattei, Avinash Balakrishnan
Abstract: Aggregating the preferences of multiple agents into a collective decision is a common step in many important problems across areas of computer science including information retrieval, reinforcement learning, and recommender systems. As Social Choice Theory has shown, the problem of designing algorithms for aggregation rules with specific properties (axioms) can be difficult, or provably impossible in some cases. Instead of designing algorithms by hand, one can learn aggregation rules, particularly voting rules, from data. However, the prior work in this area has required extremely large models, or been limited by the choice of preference representation, i.e., embedding. We recast the problem of designing a good voting rule into one of learning probabilistic versions of voting rules that output distributions over a set of candidates. Specifically, we use neural networks to learn probabilistic social choice functions from the literature. We show that embeddings of preference profiles derived from the social choice literature allows us to learn existing voting rules more efficiently and scale to larger populations of voters more easily than other work if the embedding is tailored to the learning objective. Moreover, we show that rules learned using embeddings can be tweaked to create novel voting rules with improved axiomatic properties. Namely, we show that existing voting rules require only minor modification to combat a probabilistic version of the No Show Paradox.
Authors: Benjamin C\^ot\'e, H\'el\`ene Cossette, Etienne Marceau
Abstract: A new family of tree-structured Markov random fields for a vector of discrete counting random variables is introduced. According to the characteristics of the family, the marginal distributions of the Markov random fields are all Poisson with the same mean, and are untied from the strength or structure of their built-in dependence. This key feature is uncommon for Markov random fields and most convenient for applications purposes. The specific properties of this new family confer a straightforward sampling procedure and analytic expressions for the joint probability mass function and the joint probability generating function of the vector of counting random variables, thus granting computational methods that scale well to vectors of high dimension. We study the distribution of the sum of random variables constituting a Markov random field from the proposed family, analyze a random variable's individual contribution to that sum through expected allocations, and establish stochastic orderings to assess a wide understanding of their behavior.
Authors: Dexter Allen, Isaac Kante, Dorian Bohler
Abstract: Beam steering involves the calibration of the angle and position at which a particle accelerator's electron beam is incident upon the x-ray target with respect to the rotation axis of the collimator. Beam Steering is an essential task for light sources. The Linac To Undulator is very difficult to steer and aim due to the changes of each use of the accelerator there must be re-calibration of magnets. However with each use of the Beamline its current method of steering runs into issues when faced with calibrating angles and positions. Human operators spend a substantial amount of time and resources on the task. We developed multiple different feed-forward-neural networks with varying hyper-parameters, inputs, and outputs, seeking to compare their performance. Specifically, our smaller models with 33 inputs and 13 outputs outperformed the larger models with 73 inputs and 50 outputs. We propose the following explanations for this lack of performance in larger models. First, a lack of training time and computational power limited the ability of our models to mature. Given more time, our models would outperform SVD. Second, when the input size of the model increases the noise increases as well. In this case more inputs corresponded to a greater length upon the LINAC accelerator. Less specific and larger models that seek to make more predictions will inherently perform worse than SVD.
Authors: Sakhinana Sagar Srinivas, Geethan Sannidhi, Venkataramana Runkana
Abstract: Characterizing materials with electron micrographs is a crucial task in fields such as semiconductors and quantum materials. The complex hierarchical structure of micrographs often poses challenges for traditional classification methods. In this study, we propose an innovative backbone architecture for analyzing electron micrographs. We create multi-modal representations of the micrographs by tokenizing them into patch sequences and, additionally, representing them as vision graphs, commonly referred to as patch attributed graphs. We introduce the Hierarchical Network Fusion (HNF), a multi-layered network structure architecture that facilitates information exchange between the multi-modal representations and knowledge integration across different patch resolutions. Furthermore, we leverage large language models (LLMs) to generate detailed technical descriptions of nanomaterials as auxiliary information to assist in the downstream task. We utilize a cross-modal attention mechanism for knowledge fusion across cross-domain representations(both image-based and linguistic insights) to predict the nanomaterial category. This multi-faceted approach promises a more comprehensive and accurate representation and classification of micrographs for nanomaterial identification. Our framework outperforms traditional methods, overcoming challenges posed by distributional shifts, and facilitating high-throughput screening.
Authors: Orlenys L\'opez-Pintado, Serhii Murashko, Marlon Dumas
Abstract: Simulation is a common approach to predict the effect of business process changes on quantitative performance. The starting point of Business Process Simulation (BPS) is a process model enriched with simulation parameters. To cope with the typically large parameter spaces of BPS models, several methods have been proposed to automatically discover BPS models from event logs. Virtually all these approaches neglect the data perspective of business processes. Yet, the data attributes manipulated by a business process often determine which activities are performed, how many times, and when. This paper addresses this gap by introducing a data-aware BPS modeling approach and a method to discover data-aware BPS models from event logs. The BPS modeling approach supports three types of data attributes (global, case-level, and event-level) as well as deterministic and stochastic attribute update rules and data-aware branching conditions. An empirical evaluation shows that the proposed method accurately discovers the type of each data attribute and its associated update rules, and that the resulting BPS models more closely replicate the process execution control flow relative to data-unaware BPS models.
Authors: Cho-Ying Wu, Quankai Gao, Chin-Cheng Hsu, Te-Lin Wu, Jing-Wen Chen, Ulrich Neumann
Abstract: Indoor monocular depth estimation helps home automation, including robot navigation or AR/VR for surrounding perception. Most previous methods primarily experiment with the NYUv2 Dataset and concentrate on the overall performance in their evaluation. However, their robustness and generalization to diversely unseen types or categories for indoor spaces (spaces types) have yet to be discovered. Researchers may empirically find degraded performance in a released pretrained model on custom data or less-frequent types. This paper studies the common but easily overlooked factor-space type and realizes a model's performance variances across spaces. We present InSpaceType Dataset, a high-quality RGBD dataset for general indoor scenes, and benchmark 13 recent state-of-the-art methods on InSpaceType. Our examination shows that most of them suffer from performance imbalance between head and tailed types, and some top methods are even more severe. The work reveals and analyzes underlying bias in detail for transparency and robustness. We extend the analysis to a total of 4 datasets and discuss the best practice in synthetic data curation for training indoor monocular depth. Further, dataset ablation is conducted to find out the key factor in generalization. This work marks the first in-depth investigation of performance variances across space types and, more importantly, releases useful tools, including datasets and codes, to closely examine your pretrained depth models. Data and code: https://depthcomputation.github.io/DepthPublic/
Authors: Junhong Yang, Banghai Wang, Junyu Quan, Qin Li
Abstract: Variational quantum algorithms (VQAs) have shown potential for quantum advantage with noisy intermediate-scale quantum (NISQ) devices for quantum machine learning (QML). However, given the high cost and limited availability of quantum resources, delegating VQAs via cloud networks is a more practical solution for clients with limited quantum capabilities. Recently, Shingu et al.[Physical Review A, 105, 022603 (2022)] proposed a variational secure cloud quantum computing protocol, utilizing ancilla-driven quantum computation (ADQC) for cloud-based VQAs with minimal quantum resource consumption. However, their protocol lacks verifiability, which exposes it to potential malicious behaviors by the server. Additionally, channel loss requires frequent re-delegation as the size of the delegated variational circuit grows, complicating verification due to increased circuit complexity. This paper introduces a new protocol to address these challenges and enhance both verifiability and tolerance to channel loss in cloud-based VQAs.
Authors: M. Nanmalar, P. Vijayalakshmi, T. Nagarajan
Abstract: Culture and language evolve together. The old literary form of Tamil is used commonly for writing and the contemporary colloquial Tamil is used for speaking. Human-computer interaction applications require Colloquial Tamil (CT) to make it more accessible and easy for the everyday user and, it requires Literary Tamil (LT) when information is needed in a formal written format. Continuing the use of LT alongside CT in computer aided language learning applications will both preserve LT, and provide ease of use via CT, at the same time. Hence there is a need for the conversion between LT and CT dialects, which demands as a first step, dialect identification. Dialect Identification (DID) of LT and CT is an unexplored area of research. In the current work, keeping the nuances of both these dialects in mind, five methods are explored which include two implicit methods - Gaussian Mixture Model (GMM) and Convolutional Neural Network (CNN); two explicit methods - Parallel Phone Recognition (PPR) and Parallel Large Vocabulary Continuous Speech Recognition (P-LVCSR); two versions of the proposed explicit Unified Phone Recognition method (UPR-1 and UPR-2). These methods vary based on: the need for annotated data, the size of the unit, the way in which modelling is carried out, and the way in which the final decision is made. Even though the average duration of the test utterances is less - 4.9s for LT and 2.5s for CT - the systems performed well, offering the following identification accuracies: 87.72% (GMM), 93.97% (CNN), 89.24% (PPR), 94.21% (P-LVCSR), 88.57% (UPR-1), 93.53% (UPR-1 with P-LVCSR), 94.55% (UPR-2), and 95.61% (UPR-2 with P-LVCSR).
Authors: S. Johanan Joysingh, P. Vijayalakshmi, T. Nagarajan
Abstract: Whisper, as a form of speech, is not sufficiently addressed by mainstream speech applications. This is due to the fact that systems built for normal speech do not work as expected for whispered speech. A first step to building a speech application that is inclusive of whispered speech, is the successful classification of whispered speech and normal speech. Such a front-end classification system is expected to have high accuracy and low computational overhead, which is the scope of this paper. One of the characteristics of whispered speech is the absence of the fundamental frequency (or pitch), and hence the pitch harmonics as well. The presence of the pitch and pitch harmonics in normal speech, and its absence in whispered speech, is evident in the spectral envelope of the Fourier transform. We observe that this characteristic is predominant in the first quarter of the spectrum, and exploit the same as a feature. We propose the use of one dimensional convolutional neural networks (1D-CNN) to capture these features from the quartered spectral envelope (QSE). The system yields an accuracy of 99.31% when trained and tested on the wTIMIT dataset, and 100% on the CHAINS dataset. The proposed feature is compared with Mel frequency cepstral coefficients (MFCC), a staple in the speech domain. The proposed classification system is also compared with the state-of-the-art system based on log-filterbank energy (LFBE) features trained on long short-term memory (LSTM) network. The proposed system based on 1D-CNN performs better than, or as good as, the state-of-the-art across multiple experiments. It also converges sooner, with lesser computational overhead. Finally, the proposed system is evaluated under the presence of white noise at various signal-to-noise ratios and found to be robust.
Authors: Taehyeong Kim, Hyungu Lee, Hayoung Choi
Abstract: Identifying breakpoints in piecewise regression is critical in enhancing the reliability and interpretability of data fitting. In this paper, we propose novel algorithms based on the greedy algorithm to accurately and efficiently identify breakpoints in piecewise polynomial regression. The algorithm updates the breakpoints to minimize the error by exploring the neighborhood of each breakpoint. It has a fast convergence rate and stability to find optimal breakpoints. Moreover, it can determine the optimal number of breakpoints. The computational results for real and synthetic data show that its accuracy is better than any existing methods. The real-world datasets demonstrate that breakpoints through the proposed algorithm provide valuable data information.
Authors: Miguel Tjia, Artem Kim, Elaine Wynette Wijaya, Hanna Tefara, Kevin Zhu
Abstract: 7,651 cases of Search and Rescue Missions (SAR) were reported by the United States Coast Guard in 2024, with over 1322 SAR helicopters deployed in the 6 first months alone. Through the utilizations of YOLO, we were able to run different weather conditions and lighting from our augmented dataset for training. YOLO then utilizes CNNs to apply a series of convolutions and pooling layers to the input image, where the convolution layers are able to extract the main features of the image. Through this, our YOLO model is able to learn to differentiate different objects which may considerably improve its accuracy, possibly enhancing the efficiency of SAR operations through enhanced detection accuracy. This paper aims to improve the model's accuracy of human detection in maritime SAR by evaluating a robust datasets containing various elevations and geological locations, as well as through data augmentation which simulates different weather and lighting. We observed that models trained on augmented datasets outperformed their non-augmented counterparts in which the human recall scores ranged from 0.891 to 0.911 with an improvement rate of 3.4\% on the YOLOv5l model. Results showed that these models demonstrate greater robustness to real-world conditions in varying of weather, brightness, tint, and contrast.
Authors: Harikrishnan Vijayakumaran, Jonathan B. Russ, Glaucio H. Paulino, Miguel A. Bessa
Abstract: Additive manufacturing methods together with topology optimization have enabled the creation of multiscale structures with controlled spatially-varying material microstructure. However, topology optimization or inverse design of such structures in the presence of nonlinearities remains a challenge due to the expense of computational homogenization methods and the complexity of differentiably parameterizing the microstructural response. A solution to this challenge lies in machine learning techniques that offer efficient, differentiable mappings between the material response and its microstructural descriptors. This work presents a framework for designing multiscale heterogeneous structures with spatially varying microstructures by merging a homogenization-based topology optimization strategy with a consistent machine learning approach grounded in hyperelasticity theory. We leverage neural architectures that adhere to critical physical principles such as polyconvexity, objectivity, material symmetry, and thermodynamic consistency to supply the framework with a reliable constitutive model that is dependent on material microstructural descriptors. Our findings highlight the potential of integrating consistent machine learning models with density-based topology optimization for enhancing design optimization of heterogeneous hyperelastic structures under finite deformations.
Authors: Minghao Liu, Le Zhang, Yingjie Tian, Xiaochao Qu, Luoqi Liu, Ting Liu
Abstract: Recent advances in text-to-image diffusion models have demonstrated impressive capabilities in image quality. However, complex scene generation remains relatively unexplored, and even the definition of `complex scene' itself remains unclear. In this paper, we address this gap by providing a precise definition of complex scenes and introducing a set of Complex Decomposition Criteria (CDC) based on this definition. Inspired by the artists painting process, we propose a training-free diffusion framework called Complex Diffusion (CxD), which divides the process into three stages: composition, painting, and retouching. Our method leverages the powerful chain-of-thought capabilities of large language models (LLMs) to decompose complex prompts based on CDC and to manage composition and layout. We then develop an attention modulation method that guides simple prompts to specific regions to complete the complex scene painting. Finally, we inject the detailed output of the LLM into a retouching model to enhance the image details, thus implementing the retouching stage. Extensive experiments demonstrate that our method outperforms previous SOTA approaches, significantly improving the generation of high-quality, semantically consistent, and visually diverse images for complex scenes, even with intricate prompts.
Authors: Brian Angulo, Gregory Gorbov, Aleksandr Panov, Konstantin Yakovlev
Abstract: Reinforcement learning is a widely used approach to autonomous navigation, showing potential in various tasks and robotic setups. Still, it often struggles to reach distant goals when safety constraints are imposed (e.g., the wheeled robot is prohibited from moving close to the obstacles). One of the main reasons for poor performance in such setups, which is common in practice, is that the need to respect the safety constraints degrades the exploration capabilities of an RL agent. To this end, we introduce a novel learnable algorithm that is based on decomposing the initial problem into smaller sub-problems via intermediate goals, on the one hand, and respects the limit of the cumulative safety constraints, on the other hand -- SPEIS(Safe Policy Exploration Improvement via Subgoals). It comprises the two coupled policies trained end-to-end: subgoal and safe. The subgoal policy is trained to generate the subgoal based on the transitions from the buffer of the safe (main) policy that helps the safe policy to reach distant goals. Simultaneously, the safe policy maximizes its rewards while attempting not to violate the limit of the cumulative safety constraints, thus providing a certain level of safety. We evaluate SPEIS in a wide range of challenging (simulated) environments that involve different types of robots in two different environments: autonomous vehicles from the POLAMP environment and car, point, doggo, and sweep from the safety-gym environment. We demonstrate that our method consistently outperforms state-of-the-art competitors and can significantly reduce the collision rate while maintaining high success rates (higher by 80% compared to the best-performing methods).
Authors: Li Li, Tanqiu Qiao, Hubert P. H. Shum, Toby P. Breckon
Abstract: 3D point clouds are essential for perceiving outdoor scenes, especially within the realm of autonomous driving. Recent advances in 3D LiDAR Object Detection focus primarily on the spatial positioning and distribution of points to ensure accurate detection. However, despite their robust performance in variable conditions, these methods are hindered by their sole reliance on coordinates and point intensity, resulting in inadequate isometric invariance and suboptimal detection outcomes. To tackle this challenge, our work introduces Transformation-Invariant Local (TraIL) features and the associated TraIL-Det architecture. Our TraIL features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize the inherent isotropic radiation of LiDAR to enhance local representation, improve computational efficiency, and boost detection performance. To effectively process the geometric relations among points within each proposal, we propose a Multi-head self-Attention Encoder (MAE) with asymmetric geometric features to encode high-dimensional TraIL features into manageable representations. Our method outperforms contemporary self-supervised 3D object detection approaches in terms of mAP on KITTI (67.8, 20% label, moderate) and Waymo (68.9, 20% label, moderate) datasets under various label ratios (20%, 50%, and 100%).
Authors: Yeji Park, Deokyeong Lee, Junsuk Choe, Buru Chang
Abstract: Hallucinations in Multimodal Large Language Models (MLLMs) where generated responses fail to accurately reflect the given image pose a significant challenge to their reliability. To address this, we introduce ConVis, a novel training-free contrastive decoding method. ConVis leverages a text-to-image (T2I) generation model to semantically reconstruct the given image from hallucinated captions. By comparing the contrasting probability distributions produced by the original and reconstructed images, ConVis enables MLLMs to capture visual contrastive signals that penalize hallucination generation. Notably, this method operates purely within the decoding process, eliminating the need for additional data or model updates. Our extensive experiments on five popular benchmarks demonstrate that ConVis effectively reduces hallucinations across various MLLMs, highlighting its potential to enhance model reliability.
Authors: Brandon Smart, Chuanxia Zheng, Iro Laina, Victor Adrian Prisacariu
Abstract: In this paper, we introduce Splatt3R, a pose-free, feed-forward method for in-the-wild 3D reconstruction and novel view synthesis from stereo pairs. Given uncalibrated natural images, Splatt3R can predict 3D Gaussian Splats without requiring any camera parameters or depth information. For generalizability, we start from a 'foundation' 3D geometry reconstruction method, MASt3R, and extend it to be a full 3D structure and appearance reconstructor. Specifically, unlike the original MASt3R which reconstructs only 3D point clouds, we predict the additional Gaussian attributes required to construct a Gaussian primitive for each point. Hence, unlike other novel view synthesis methods, Splatt3R is first trained by optimizing the 3D point cloud's geometry loss, and then a novel view synthesis objective. By doing this, we avoid the local minima present in training 3D Gaussian Splats from stereo views. We also propose a novel loss masking strategy that we empirically find is critical for strong performance on extrapolated viewpoints. We train Splatt3R on the ScanNet++ dataset and demonstrate excellent generalisation to uncalibrated, in-the-wild images. Splatt3R can reconstruct scenes at 4FPS at 512 x 512 resolution, and the resultant splats can be rendered in real-time.
Authors: Shuai Fu, Xiequn Wang, Qiushi Huang, Yu Zhang
Abstract: With the prevalence of large-scale pretrained vision-language models (VLMs), such as CLIP, soft-prompt tuning has become a popular method for adapting these models to various downstream tasks. However, few works delve into the inherent properties of learnable soft-prompt vectors, specifically the impact of their norms to the performance of VLMs. This motivates us to pose an unexplored research question: ``Do we need to normalize the soft prompts in VLMs?'' To fill this research gap, we first uncover a phenomenon, called the \textbf{Low-Norm Effect} by performing extensive corruption experiments, suggesting that reducing the norms of certain learned prompts occasionally enhances the performance of VLMs, while increasing them often degrades it. To harness this effect, we propose a novel method named \textbf{N}ormalizing th\textbf{e} soft-pro\textbf{m}pt v\textbf{e}ctors of vi\textbf{si}on-language model\textbf{s} (\textbf{Nemesis}) to normalize soft-prompt vectors in VLMs. To the best of our knowledge, our work is the first to systematically investigate the role of norms of soft-prompt vector in VLMs, offering valuable insights for future research in soft-prompt tuning. The code is available at \texttt{\href{https://github.com/ShyFoo/Nemesis}{https://github.com/ShyFoo/Nemesis}}.
URLs: https://github.com/ShyFoo/Nemesis, https://github.com/ShyFoo/Nemesis
Authors: Joseph Cho, Samuel Schmidgall, Cyril Zakka, Mrudang Mathur, Rohan Shad, William Hiesinger
Abstract: Diffusion-based video generation models have made significant strides, producing outputs with improved visual fidelity, temporal coherence, and user control. These advancements hold great promise for improving surgical education by enabling more realistic, diverse, and interactive simulation environments. In this study, we introduce SurGen, a text-guided diffusion model tailored for surgical video synthesis, producing the highest resolution and longest duration videos among existing surgical video generation models. We validate the visual and temporal quality of the outputs using standard image and video generation metrics. Additionally, we assess their alignment to the corresponding text prompts through a deep learning classifier trained on surgical data. Our results demonstrate the potential of diffusion models to serve as valuable educational tools for surgical trainees.
Authors: Joey Hejna, Chethan Bhateja, Yichen Jian, Karl Pertsch, Dorsa Sadigh
Abstract: Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been of utmost importance in vision and natural language processing, little work in robotics has questioned what data such models should actually be trained on. In this work we investigate how to weigh different subsets or ``domains'' of robotics datasets for robot foundation model pre-training. Concrete, we use distributionally robust optimization (DRO) to maximize worst-case performance across all possible downstream domains. Our method, Re-Mix, addresses the wide range of challenges that arise when applying DRO to robotics datasets including variability in action spaces and dynamics across different datasets. Re-Mix employs early stopping, action normalization, and discretization to counteract these issues. Through extensive experimentation on the largest open-source robot manipulation dataset, the Open X-Embodiment dataset, we demonstrate that data curation can have an outsized impact on downstream performance. Specifically, domain weights learned by Re-Mix outperform uniform weights by 38\% on average and outperform human-selected weights by 32\% on datasets used to train existing generalist robot policies, specifically the RT-X models.
Authors: Piotr Kicki, Davide Tateo, Puze Liu, Jonas Guenster, Jan Peters, Krzysztof Walas
Abstract: Trajectory planning under kinodynamic constraints is fundamental for advanced robotics applications that require dexterous, reactive, and rapid skills in complex environments. These constraints, which may represent task, safety, or actuator limitations, are essential for ensuring the proper functioning of robotic platforms and preventing unexpected behaviors. Recent advances in kinodynamic planning demonstrate that learning-to-plan techniques can generate complex and reactive motions under intricate constraints. However, these techniques necessitate the analytical modeling of both the robot and the entire task, a limiting assumption when systems are extremely complex or when constructing accurate task models is prohibitive. This paper addresses this limitation by combining learning-to-plan methods with reinforcement learning, resulting in a novel integration of black-box learning of motion primitives and optimization. We evaluate our approach against state-of-the-art safe reinforcement learning methods, showing that our technique, particularly when exploiting task structure, outperforms baseline methods in challenging scenarios such as planning to hit in robot air hockey. This work demonstrates the potential of our integrated approach to enhance the performance and safety of robots operating under complex kinodynamic constraints.
Authors: Md Awsafur Rahman, Zaber Ibn Abdul Hakim, Najibul Haque Sarker, Bishmoy Paul, Shaikh Anowarul Fattah
Abstract: The recent surge in AI-generated songs presents exciting possibilities and challenges. While these tools democratize music creation, they also necessitate the ability to distinguish between human-composed and AI-generated songs for safeguarding artistic integrity and content curation. Existing research and datasets in fake song detection only focus on singing voice deepfake detection (SVDD), where the vocals are AI-generated but the instrumental music is sourced from real songs. However, this approach is inadequate for contemporary end-to-end AI-generated songs where all components (vocals, lyrics, music, and style) could be AI-generated. Additionally, existing datasets lack lyrics-music diversity, long-duration songs, and open fake songs. To address these gaps, we introduce SONICS, a novel dataset for end-to-end Synthetic Song Detection (SSD), comprising over 97k songs with over 49k synthetic songs from popular platforms like Suno and Udio. Furthermore, we highlight the importance of modeling long-range temporal dependencies in songs for effective authenticity detection, an aspect overlooked in existing methods. To capture these patterns, we propose a novel model, SpecTTTra, that is up to 3 times faster and 6 times more memory efficient compared to popular CNN and Transformer-based models while maintaining competitive performance. Finally, we offer both AI-based and Human evaluation benchmarks, addressing another deficiency in current research.
Authors: Xiangge Huang, Jingyuan Li, Jiaqing Xie
Abstract: With the constraint of a no regret follower, will the players in a two-player Stackelberg game still reach Stackelberg equilibrium? We first show when the follower strategy is either reward-average or transform-reward-average, the two players can always get the Stackelberg Equilibrium. Then, we extend that the players can achieve the Stackelberg equilibrium in the two-player game under the no regret constraint. Also, we show a strict upper bound of the follower's utility difference between with and without no regret constraint. Moreover, in constant-sum two-player Stackelberg games with non-regret action sequences, we ensure the total optimal utility of the game remains also bounded.
Authors: Chiara Galdi, Michele Panariello, Massimiliano Todisco, Nicholas Evans
Abstract: We introduce 2D-Malafide, a novel and lightweight adversarial attack designed to deceive face deepfake detection systems. Building upon the concept of 1D convolutional perturbations explored in the speech domain, our method leverages 2D convolutional filters to craft perturbations which significantly degrade the performance of state-of-the-art face deepfake detectors. Unlike traditional additive noise approaches, 2D-Malafide optimises a small number of filter coefficients to generate robust adversarial perturbations which are transferable across different face images. Experiments, conducted using the FaceForensics++ dataset, demonstrate that 2D-Malafide substantially degrades detection performance in both white-box and black-box settings, with larger filter sizes having the greatest impact. Additionally, we report an explainability analysis using GradCAM which illustrates how 2D-Malafide misleads detection systems by altering the image areas used most for classification. Our findings highlight the vulnerability of current deepfake detection systems to convolutional adversarial attacks as well as the need for future work to enhance detection robustness through improved image fidelity constraints.
Authors: Hae Jin Song, Patrycja Krawczuk, Po-Hsuan Huang
Abstract: Geospatial data come from various sources, such as satellites, aircraft, and LiDAR. The variability of the source is not limited to the types of data acquisition techniques, as we have maps from different time periods. To incorporate these data for a coherent analysis, it is essential to first align different "styles" of geospatial data to its matching images that point to the same location on the surface of the Earth. In this paper, we approach the image registration as a two-step process of (1) extracting geospatial contents invariant to visual (and any other non-content-related) information, and (2) matching the data based on such (purely) geospatial contents. We hypothesize that a combination of $\beta$-VAE-like architecture [2] and adversarial training will achieve both the disentanglement of the geographic information and artistic styles and generation of new map tiles by composing the encoded geographic information with any artistic style.
Authors: Yury Kolomeytsev, Dmitry Golembiovsky
Abstract: Efficient navigation in dynamic environments is crucial for autonomous robots interacting with various environmental entities, including both moving agents and static obstacles. In this study, we present a novel methodology that enhances the robot's interaction with different types of agents and obstacles based on specific safety requirements. This approach uses information about the entity types, improving collision avoidance and ensuring safer navigation. We introduce a new reward function that penalizes the robot for collisions with different entities such as adults, bicyclists, children, and static obstacles, and additionally encourages the robot's proximity to the goal. It also penalizes the robot for being close to entities, and the safe distance also depends on the entity type. Additionally, we propose an optimized algorithm for training and testing, which significantly accelerates train, validation, and test steps and enables training in complex environments. Comprehensive experiments conducted using simulation demonstrate that our approach consistently outperforms conventional navigation and collision avoidance methods, including state-of-the-art techniques. To sum up, this work contributes to enhancing the safety and efficiency of navigation systems for autonomous robots in dynamic, crowded environments.
Authors: Leonid Erlygin, Alexey Zaytsev
Abstract: Accurately estimating image quality and model robustness improvement are critical challenges in unconstrained face recognition, which can be addressed through uncertainty estimation via probabilistic face embeddings. Previous research mainly focused on uncertainty estimation in face verification, leaving the open-set face recognition task underexplored. In open-set face recognition, one seeks to classify an image, which could also be unknown. Here, the low variance of probabilistic embedding does not imply a low error probability: an image embedding could be close to several classes in a gallery, thus yielding high uncertainty. We propose a method aware of two sources of ambiguity in the open-set recognition system: (1) the gallery uncertainty caused by overlapping classes and (2) the uncertainty of the face embeddings. To detect both types, we use a Bayesian probabilistic model of embedding distribution, which provides a principled uncertainty estimate. Challenging open-set face recognition datasets, such as IJB-C, serve as a testbed for our method. We also propose a new open-set recognition protocol for whale and dolphin identification. The proposed approach better identifies recognition errors than uncertainty estimation methods based solely on image quality.
Authors: Hanna Abi Akl
Abstract: We introduce semantic towers, an extrinsic knowledge representation method, and compare it to intrinsic knowledge in large language models for ontology learning. Our experiments show a trade-off between performance and semantic grounding for extrinsic knowledge compared to a fine-tuned model intrinsic knowledge. We report our findings on the Large Language Models for Ontology Learning (LLMs4OL) 2024 challenge.
Authors: Gang Qu, Ziyu Zhou, Vince D. Calhoun, Aiying Zhang, Yu-Ping Wang
Abstract: Multimodal neuroimaging modeling has becomes a widely used approach but confronts considerable challenges due to heterogeneity, which encompasses variability in data types, scales, and formats across modalities. This variability necessitates the deployment of advanced computational methods to integrate and interpret these diverse datasets within a cohesive analytical framework. In our research, we amalgamate functional magnetic resonance imaging, diffusion tensor imaging, and structural MRI into a cohesive framework. This integration capitalizes on the unique strengths of each modality and their inherent interconnections, aiming for a comprehensive understanding of the brain's connectivity and anatomical characteristics. Utilizing the Glasser atlas for parcellation, we integrate imaging derived features from various modalities: functional connectivity from fMRI, structural connectivity from DTI, and anatomical features from sMRI within consistent regions. Our approach incorporates a masking strategy to differentially weight neural connections, thereby facilitating a holistic amalgamation of multimodal imaging data. This technique enhances interpretability at connectivity level, transcending traditional analyses centered on singular regional attributes. The model is applied to the Human Connectome Project's Development study to elucidate the associations between multimodal imaging and cognitive functions throughout youth. The analysis demonstrates improved predictive accuracy and uncovers crucial anatomical features and essential neural connections, deepening our understanding of brain structure and function.
Authors: Inass Soukarieh, Gerhard Hessler, Herv\'e Minoux, Marcel Mohr, Friedemann Schmidt, Jan Wenzel, Pierre Barbillon, Hugo Gangloff, Pierre Gloaguen
Abstract: Mathematical modeling in systems toxicology enables a comprehensive understanding of the effects of pharmaceutical substances on cardiac health. However, the complexity of these models limits their widespread application in early drug discovery. In this paper, we introduce a novel approach to solving parameterized models of cardiac action potentials by combining meta-learning techniques with Systems Biology-Informed Neural Networks (SBINNs). The proposed method, HyperSBINN, effectively addresses the challenge of predicting the effects of various compounds at different concentrations on cardiac action potentials, outperforming traditional differential equation solvers in speed. Our model efficiently handles scenarios with limited data and complex parameterized differential equations. The HyperSBINN model demonstrates robust performance in predicting APD90 values, indicating its potential as a reliable tool for modeling cardiac electrophysiology and aiding in preclinical drug development. This framework represents an advancement in computational modeling, offering a scalable and efficient solution for simulating and understanding complex biological systems.
Authors: Yayati Jadhav, Peter Pak, Amir Barati Farimani
Abstract: Industry 4.0 has revolutionized manufacturing by driving digitalization and shifting the paradigm toward additive manufacturing (AM). Fused Deposition Modeling (FDM), a key AM technology, enables the creation of highly customized, cost-effective products with minimal material waste through layer-by-layer extrusion, posing a significant challenge to traditional subtractive methods. However, the susceptibility of material extrusion techniques to errors often requires expert intervention to detect and mitigate defects that can severely compromise product quality. While automated error detection and machine learning models exist, their generalizability across diverse 3D printer setups, firmware, and sensors is limited, and deep learning methods require extensive labeled datasets, hindering scalability and adaptability. To address these challenges, we present a process monitoring and control framework that leverages pre-trained Large Language Models (LLMs) alongside 3D printers to detect and address printing defects. The LLM evaluates print quality by analyzing images captured after each layer or print segment, identifying failure modes and querying the printer for relevant parameters. It then generates and executes a corrective action plan. We validated the effectiveness of the proposed framework in identifying defects by comparing it against a control group of engineers with diverse AM expertise. Our evaluation demonstrated that LLM-based agents not only accurately identify common 3D printing errors, such as inconsistent extrusion, stringing, warping, and layer adhesion, but also effectively determine the parameters causing these failures and autonomously correct them without any need for human intervention.
Authors: Weide Liu, Camilo Calixto, Simon K. Warfield, Davood Karimi
Abstract: Diffusion-weighted magnetic resonance imaging (dMRI) is the only non-invasive tool for studying white matter tracts and structural connectivity of the brain. These assessments rely heavily on tractography techniques, which reconstruct virtual streamlines representing white matter fibers. Much effort has been devoted to improving tractography methodology for adult brains, while tractography of the fetal brain has been largely neglected. Fetal tractography faces unique difficulties due to low dMRI signal quality, immature and rapidly developing brain structures, and paucity of reference data. This work presents the first machine learning model for fetal tractography. The model input consists of five sources of information: (1) Fiber orientation, inferred from a diffusion tensor fit to the dMRI signal; (2) Directions of recent propagation steps; (3) Global spatial information, encoded as distances to keypoints in the brain cortex; (4) Tissue segmentation information; and (5) Prior information about the expected local fiber orientations supplied with an atlas. In order to mitigate the local tensor estimation error, a large spatial context around the current point in the diffusion tensor image is encoded using convolutional and attention neural network modules. Moreover, the diffusion tensor information at a hypothetical next point is included in the model input. Filtering rules based on anatomically constrained tractography are applied to prune implausible streamlines. We trained the model on manually-refined whole-brain fetal tractograms and validated the trained model on an independent set of 11 test scans with gestational ages between 23 and 36 weeks. Results show that our proposed method achieves superior performance across all evaluated tracts. The new method can significantly advance the capabilities of dMRI for studying normal and abnormal brain development in utero.
Authors: Jan Jakub\r{u}v, Mikol\'a\v{s} Janota, Jelle Piepenbrock, Josef Urban
Abstract: In this work we considerably improve the state-of-the-art SMT solving on first-order quantified problems by efficient machine learning guidance of quantifier selection. Quantifiers represent a significant challenge for SMT and are technically a source of undecidability. In our approach, we train an efficient machine learning model that informs the solver which quantifiers should be instantiated and which not. Each quantifier may be instantiated multiple times and the set of the active quantifiers changes as the solving progresses. Therefore, we invoke the ML predictor many times, during the whole run of the solver. To make this efficient, we use fast ML models based on gradient boosting decision trees. We integrate our approach into the state-of-the-art cvc5 SMT solver and show a considerable increase of the system's holdout-set performance after training it on a large set of first-order problems collected from the Mizar Mathematical Library.
Authors: Yinghao Ma, Anders {\O}land, Anton Ragni, Bleiz MacSen Del Sette, Charalampos Saitis, Chris Donahue, Chenghua Lin, Christos Plachouras, Emmanouil Benetos, Elio Quinton, Elona Shatri, Fabio Morreale, Ge Zhang, Gy\"orgy Fazekas, Gus Xia, Huan Zhang, Ilaria Manco, Jiawen Huang, Julien Guinot, Liwei Lin, Luca Marinelli, Max W. Y. Lam, Megha Sharma, Qiuqiang Kong, Roger B. Dannenberg, Ruibin Yuan, Shangda Wu, Shih-Lun Wu, Shuqi Dai, Shun Lei, Shiyin Kang, Simon Dixon, Wenhu Chen, Wehhao Huang, Xingjian Du, Xingwei Qu, Xu Tan, Yizhi Li, Zeyue Tian, Zhiyong Wu, Zhizheng Wu, Ziyang Ma, Ziyu Wang
Abstract: In recent years, foundation models (FMs) such as large language models (LLMs) and latent diffusion models (LDMs) have profoundly impacted diverse sectors, including music. This comprehensive review examines state-of-the-art (SOTA) pre-trained models and foundation models in music, spanning from representation learning, generative learning and multimodal learning. We first contextualise the significance of music in various industries and trace the evolution of AI in music. By delineating the modalities targeted by foundation models, we discover many of the music representations are underexplored in FM development. Then, emphasis is placed on the lack of versatility of previous methods on diverse music applications, along with the potential of FMs in music understanding, generation and medical application. By comprehensively exploring the details of the model pre-training paradigm, architectural choices, tokenisation, finetuning methodologies and controllability, we emphasise the important topics that should have been well explored, like instruction tuning and in-context learning, scaling law and emergent ability, as well as long-sequence modelling etc. A dedicated section presents insights into music agents, accompanied by a thorough analysis of datasets and evaluations essential for pre-training and downstream tasks. Finally, by underscoring the vital importance of ethical considerations, we advocate that following research on FM for music should focus more on such issues as interpretability, transparency, human responsibility, and copyright issues. The paper offers insights into future challenges and trends on FMs for music, aiming to shape the trajectory of human-AI collaboration in the music realm.
Authors: Nicolas Yax, Pierre-Yves Oudeyer, Stefano Palminteri
Abstract: In machine learning, contamination refers to situations where testing data leak into the training set. The issue is particularly relevant for the evaluation of the performance of Large Language Models (LLMs), which are generally trained on gargantuan, and generally opaque, corpora of text scraped from the world wide web. Developing tools to detect contamination is therefore crucial to be able to fairly and properly track the evolution of the performance of LLMs. Most recent works in the field are not tailored to quantify contamination on short sequences of text like we find in psychology questionnaires. In the present paper we introduce LogProber, a novel, efficient, algorithm that we show able to detect contamination using token probability in given sentences. In the second part we investigate the limitations of the method and discuss how different training methods can contaminate models without leaving traces in the token probabilities.
Authors: Francesco Di Salvo, Sebastian Doerrich, Ines Rieger, Christian Ledig
Abstract: The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address label noise exhibit severe limitations due to computational complexity and application dependency. In this work, we propose WANN, a Weighted Adaptive Nearest Neighbor approach that builds on self-supervised feature representations obtained from foundation models. To guide the weighted voting scheme, we introduce a reliability score, which measures the likelihood of a data label being correct. WANN outperforms reference methods, including a linear layer trained with robust loss functions, on diverse datasets of varying size and under various noise types and severities. WANN also exhibits superior generalization on imbalanced data compared to both Adaptive-NNs (ANN) and fixed k-NNs. Furthermore, the proposed weighting scheme enhances supervised dimensionality reduction under noisy labels. This yields a significant boost in classification performance with 10x and 100x smaller image embeddings, minimizing latency and storage requirements. Our approach, emphasizing efficiency and explainability, emerges as a simple, robust solution to overcome the inherent limitations of deep neural network training. The code is available at https://github.com/francescodisalvo05/wann-noisy-labels .
URLs: https://github.com/francescodisalvo05/wann-noisy-labels
Authors: Sarah Rastegar, Mohammadreza Salehi, Yuki M. Asano, Hazel Doughty, Cees G. M. Snoek
Abstract: In this paper, we address Generalized Category Discovery, aiming to simultaneously uncover novel categories and accurately classify known ones. Traditional methods, which lean heavily on self-supervision and contrastive learning, often fall short when distinguishing between fine-grained categories. To address this, we introduce a novel concept called `self-expertise', which enhances the model's ability to recognize subtle differences and uncover unknown categories. Our approach combines unsupervised and supervised self-expertise strategies to refine the model's discernment and generalization. Initially, hierarchical pseudo-labeling is used to provide `soft supervision', improving the effectiveness of self-expertise. Our supervised technique differs from traditional methods by utilizing more abstract positive and negative samples, aiding in the formation of clusters that can generalize to novel categories. Meanwhile, our unsupervised strategy encourages the model to sharpen its category distinctions by considering within-category examples as `hard' negatives. Supported by theoretical insights, our empirical results showcase that our method outperforms existing state-of-the-art techniques in Generalized Category Discovery across several fine-grained datasets. Our code is available at: https://github.com/SarahRastegar/SelEx.
Authors: Chaochao Chen, Jiaming Zhang, Yizhao Zhang, Li Zhang, Lingjuan Lyu, Yuyuan Li, Biao Gong, Chenggang Yan
Abstract: With increasing privacy concerns in artificial intelligence, regulations have mandated the right to be forgotten, granting individuals the right to withdraw their data from models. Machine unlearning has emerged as a potential solution to enable selective forgetting in models, particularly in recommender systems where historical data contains sensitive user information. Despite recent advances in recommendation unlearning, evaluating unlearning methods comprehensively remains challenging due to the absence of a unified evaluation framework and overlooked aspects of deeper influence, e.g., fairness. To address these gaps, we propose CURE4Rec, the first comprehensive benchmark for recommendation unlearning evaluation. CURE4Rec covers four aspects, i.e., unlearning Completeness, recommendation Utility, unleaRning efficiency, and recommendation fairnEss, under three data selection strategies, i.e., core data, edge data, and random data. Specifically, we consider the deeper influence of unlearning on recommendation fairness and robustness towards data with varying impact levels. We construct multiple datasets with CURE4Rec evaluation and conduct extensive experiments on existing recommendation unlearning methods. Our code is released at https://github.com/xiye7lai/CURE4Rec.
Authors: Simon Kurz, Zhixue Zhao, Jian-Jia Chen, Lucie Flek
Abstract: Recent advances in large language model (LLM) pruning have shown state-of-the-art compression results in post-training and retraining-free settings while maintaining high predictive performance. However, such research mainly considers calibrating pruning using English text, despite the multilingual nature of modern LLMs and their frequent uses in non-English languages. In this paper, we set out to explore effective strategies for calibrating the pruning of multilingual language models. We present the first comprehensive empirical study, comparing different calibration languages for pruning multilingual models across diverse tasks, models, and state-of-the-art pruning techniques. Our results present practical suggestions, for example, calibrating in the target language can efficiently yield lower perplexity, but does not necessarily benefit downstream tasks. Our further analysis experiments unveil that calibration in the target language mainly contributes to preserving language-specific features related to fluency and coherence, but might not contribute to capturing language-agnostic features such as language understanding and reasoning. Last, we provide practical recommendations for future practitioners.
Authors: Zefang Liu, Weston M. Stacey
Abstract: The dynamics of burning plasmas in tokamaks are crucial for advancing controlled thermonuclear fusion. This study introduces the NeuralPlasmaODE, a multi-region multi-timescale transport model to simulate the complex energy transfer processes in ITER deuterium-tritium (D-T) plasmas. Our model captures the interactions between energetic alpha particles, electrons, and ions, which are vital for understanding phenomena such as thermal runaway instability. We employ neural ordinary differential equations (Neural ODEs) for the numerical derivation of diffusivity parameters, enabling precise modeling of energy interactions between different plasma regions. By leveraging transfer learning, we utilize model parameters derived from DIII-D experimental data, enhancing the efficiency and accuracy of our simulations without training from scratch. Applying this model to ITER's inductive and non-inductive operational scenarios, our results demonstrate that radiation and transport processes effectively remove excess heat from the core plasma, preventing thermal runaway instability. This study underscores the potential of machine learning in advancing our understanding and control of burning plasma dynamics in fusion reactors.
Authors: Benjamin D. Shaffer, Jeremy R. Vorenberg, M. Ani Hsieh
Abstract: Accurate and efficient fluid flow models are essential for applications relating to many physical phenomena including geophysical, aerodynamic, and biological systems. While these flows may exhibit rich and multiscale dynamics, in many cases underlying low-rank structures exist which describe the bulk of the motion. These structures tend to be spatially large and temporally slow, and may contain most of the energy in a given flow. The extraction and parsimonious representation of these low-rank dynamics from high-dimensional data is a key challenge. Inspired by the success of physics-informed machine learning methods, we propose a spectrally-informed approach to extract low-rank models of fluid flows by leveraging known spectral properties in the learning process. We incorporate this knowledge by imposing regularizations on the learned dynamics, which bias the training process towards learning low-frequency structures with corresponding higher power. We demonstrate the effectiveness of this method to improve prediction and produce learned models which better match the underlying spectral properties of prototypical fluid flows.
Authors: Trung Dinh Quoc Dang, Huy Hoang Nguyen, Aleksei Tiulpin
Abstract: Mamba, a State Space Model (SSM), has recently shown competitive performance to Convolutional Neural Networks (CNNs) and Transformers in Natural Language Processing and general sequence modeling. Various attempts have been made to adapt Mamba to Computer Vision tasks, including medical image segmentation (MIS). Vision Mamba (VM)-based networks are particularly attractive due to their ability to achieve global receptive fields, similar to Vision Transformers, while also maintaining linear complexity in the number of tokens. However, the existing VM models still struggle to maintain both spatially local and global dependencies of tokens in high dimensional arrays due to their sequential nature. Employing multiple and/or complicated scanning strategies is computationally costly, which hinders applications of SSMs to high-dimensional 2D and 3D images that are common in MIS problems. In this work, we propose Local-Global Vision Mamba, LoG-VMamba, that explicitly enforces spatially adjacent tokens to remain nearby on the channel axis, and retains the global context in a compressed form. Our method allows the SSMs to access the local and global contexts even before reaching the last token while requiring only a simple scanning strategy. Our segmentation models are computationally efficient and substantially outperform both CNN and Transformers-based baselines on a diverse set of 2D and 3D MIS tasks. The implementation of LoG-VMamba is available at \url{https://github.com/Oulu-IMEDS/LoG-VMamba}.
Authors: Reuma Arav, Dennis Wittich, Franz Rottensteiner
Abstract: In recent years, three-dimensional point clouds are used increasingly to document natural environments. Each dataset contains a diverse set of objects, at varying shapes and sizes, distributed throughout the data and intricately intertwined with the topography. Therefore, regions of interest are difficult to find and consequent analyses become a challenge. Inspired from visual perception principles, we propose to differentiate objects of interest from the cluttered environment by evaluating how much they stand out from their surroundings, i.e., their geometric salience. Previous saliency detection approaches suggested mostly handcrafted attributes for the task. However, such methods fail when the data are too noisy or have high levels of texture. Here we propose a learning-based mechanism that accommodates noise and textured surfaces. We assume that within the natural environment any change from the prevalent surface would suggest a salient object. Thus, we first learn the underlying surface and then search for anomalies within it. Initially, a deep neural network is trained to reconstruct the surface. Regions where the reconstructed part deviates significantly from the original point cloud yield a substantial reconstruction error, signifying an anomaly, i.e., saliency. We demonstrate the effectiveness of the proposed approach by searching for salient features in various natural scenarios, which were acquired by different acquisition platforms. We show the strong correlation between the reconstruction error and salient objects.
Authors: Logan Ward, J. Gregory Pauloski, Valerie Hayot-Sasson, Yadu Babuji, Alexander Brace, Ryan Chard, Kyle Chard, Rajeev Thakur, Ian Foster
Abstract: Computational workflows are a common class of application on supercomputers, yet the loosely coupled and heterogeneous nature of workflows often fails to take full advantage of their capabilities. We created Colmena to leverage the massive parallelism of a supercomputer by using Artificial Intelligence (AI) to learn from and adapt a workflow as it executes. Colmena allows scientists to define how their application should respond to events (e.g., task completion) as a series of cooperative agents. In this paper, we describe the design of Colmena, the challenges we overcame while deploying applications on exascale systems, and the science workflows we have enhanced through interweaving AI. The scaling challenges we discuss include developing steering strategies that maximize node utilization, introducing data fabrics that reduce communication overhead of data-intensive tasks, and implementing workflow tasks that cache costly operations between invocations. These innovations coupled with a variety of application patterns accessible through our agent-based steering model have enabled science advances in chemistry, biophysics, and materials science using different types of AI. Our vision is that Colmena will spur creative solutions that harness AI across many domains of scientific computing.
Authors: Carina I. Hausladen, Manuel Knott, Colin F. Camerer, Pietro Perona
Abstract: We explore social perception of human faces in CLIP, a widely used open-source vision-language model. To this end, we compare the similarity in CLIP embeddings between different textual prompts and a set of face images. Our textual prompts are constructed from well-validated social psychology terms denoting social perception. The face images are synthetic and are systematically and independently varied along six dimensions: the legally protected attributes of age, gender, and race, as well as facial expression, lighting, and pose. Independently and systematically manipulating face attributes allows us to study the effect of each on social perception and avoids confounds that can occur in wild-collected data due to uncontrolled systematic correlations between attributes. Thus, our findings are experimental rather than observational. Our main findings are three. First, while CLIP is trained on the widest variety of images and texts, it is able to make fine-grained human-like social judgments on face images. Second, age, gender, and race do systematically impact CLIP's social perception of faces, suggesting an undesirable bias in CLIP vis-a-vis legally protected attributes. Most strikingly, we find a strong pattern of bias concerning the faces of Black women, where CLIP produces extreme values of social perception across different ages and facial expressions. Third, facial expression impacts social perception more than age and lighting as much as age. The last finding predicts that studies that do not control for unprotected visual attributes may reach the wrong conclusions on bias. Our novel method of investigation, which is founded on the social psychology literature and on the experiments involving the manipulation of individual attributes, yields sharper and more reliable observations than previous observational methods and may be applied to study biases in any vision-language model.
Authors: Axel Klawonn, Martin Lanser, Janine Weber
Abstract: Deep convolutional neural networks (CNNs) have been shown to be very successful in a wide range of image processing applications. However, due to their increasing number of model parameters and an increasing availability of large amounts of training data, parallelization strategies to efficiently train complex CNNs are necessary. In previous work by the authors, a novel model parallel CNN architecture was proposed which is loosely inspired by domain decomposition. In particular, the novel network architecture is based on a decomposition of the input data into smaller subimages. For each of these subimages, local CNNs with a proportionally smaller number of parameters are trained in parallel and the resulting local classifications are then aggregated in a second step by a dense feedforward neural network (DNN). In the present work, we compare the resulting CNN-DNN architecture to less costly alternatives to combine the local classifications into a final, global decision. Additionally, we investigate the performance of the CNN-DNN trained as one coherent model as well as using a transfer learning strategy, where the parameters of the pre-trained local CNNs are used as initial values for a subsequently trained global coherent CNN-DNN model.
Authors: Karsten Roth, Vishaal Udandarao, Sebastian Dziadzio, Ameya Prabhu, Mehdi Cherti, Oriol Vinyals, Olivier H\'enaff, Samuel Albanie, Matthias Bethge, Zeynep Akata
Abstract: Multimodal foundation models serve numerous applications at the intersection of vision and language. Still, despite being pretrained on extensive data, they become outdated over time. To keep models updated, research into continual pretraining mainly explores scenarios with either (1) infrequent, indiscriminate updates on large-scale new data, or (2) frequent, sample-level updates. However, practical model deployment often operates in the gap between these two limit cases, as real-world applications often demand adaptation to specific subdomains, tasks or concepts -- spread over the entire, varying life cycle of a model. In this work, we complement current perspectives on continual pretraining through a research test bed as well as provide comprehensive guidance for effective continual model updates in such scenarios. We first introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements, constructed over 63 datasets with diverse visual and semantic coverage. Using FoMo-in-Flux, we explore the complex landscape of practical continual pretraining through multiple perspectives: (1) A data-centric investigation of data mixtures and stream orderings that emulate real-world deployment situations, (2) a method-centric investigation ranging from simple fine-tuning and traditional continual learning strategies to parameter-efficient updates and model merging, (3) meta learning rate schedules and mechanistic design choices, and (4) the influence of model and compute scaling. Together, our insights provide a practitioner's guide to continual multimodal pretraining for real-world deployment. Our benchmark and code is here: https://github.com/ExplainableML/fomo_in_flux.
Authors: Shivam Garg, Vatsal Sharan, Brian Hu Zhang, Gregory Valiant
Abstract: Given the apparent difficulty of learning models that are robust to adversarial perturbations, we propose tackling the simpler problem of developing adversarially robust features. Specifically, given a dataset and metric of interest, the goal is to return a function (or multiple functions) that 1) is robust to adversarial perturbations, and 2) has significant variation across the datapoints. We establish strong connections between adversarially robust features and a natural spectral property of the geometry of the dataset and metric of interest. This connection can be leveraged to provide both robust features, and a lower bound on the robustness of any function that has significant variance across the dataset. Finally, we provide empirical evidence that the adversarially robust features given by this spectral approach can be fruitfully leveraged to learn a robust (and accurate) model.
Authors: Brian Axelrod, Shivam Garg, Vatsal Sharan, Gregory Valiant
Abstract: Given data drawn from an unknown distribution, $D$, to what extent is it possible to ``amplify'' this dataset and output an even larger set of samples that appear to have been drawn from $D$? We formalize this question as follows: an $(n,m)$ $\text{amplification procedure}$ takes as input $n$ independent draws from an unknown distribution $D$, and outputs a set of $m > n$ ``samples''. An amplification procedure is valid if no algorithm can distinguish the set of $m$ samples produced by the amplifier from a set of $m$ independent draws from $D$, with probability greater than $2/3$. Perhaps surprisingly, in many settings, a valid amplification procedure exists, even when the size of the input dataset, $n$, is significantly less than what would be necessary to learn $D$ to non-trivial accuracy. Specifically we consider two fundamental settings: the case where $D$ is an arbitrary discrete distribution supported on $\le k$ elements, and the case where $D$ is a $d$-dimensional Gaussian with unknown mean, and fixed covariance. In the first case, we show that an $\left(n, n + \Theta(\frac{n}{\sqrt{k}})\right)$ amplifier exists. In particular, given $n=O(\sqrt{k})$ samples from $D$, one can output a set of $m=n+1$ datapoints, whose total variation distance from the distribution of $m$ i.i.d. draws from $D$ is a small constant, despite the fact that one would need quadratically more data, $n=\Theta(k)$, to learn $D$ up to small constant total variation distance. In the Gaussian case, we show that an $\left(n,n+\Theta(\frac{n}{\sqrt{d}} )\right)$ amplifier exists, even though learning the distribution to small constant total variation distance requires $\Theta(d)$ samples. In both the discrete and Gaussian settings, we show that these results are tight, to constant factors. Beyond these results, we formalize a number of curious directions for future research along this vein.
Authors: Prashant Rajaram, Puneet Manchanda
Abstract: Influencer marketing videos have surged in popularity, yet significant gaps remain in understanding the relationship between video features and engagement. This challenge is intensified by the complexities of interpreting unstructured data. While deep learning models effectively leverage unstructured data to predict business outcomes, they often function as black boxes with limited interpretability, particularly when human validation is hindered by the absence of a known ground truth. To address this issue, the authors develop an "interpretable deep learning framework" that not only makes good out-of-sample predictions using unstructured data but also provides insights into the captured relationships. Inspired by visual attention in print advertising, the interpretation approach uses measures of model attention to video features, eliminating spurious associations through a two-step process and shortlisting relationships for formal causal testing. This method is applicable across well-known attention mechanisms - additive attention, scaled dot-product attention, and gradient-based attention - when analyzing text, audio, or video image data. Validated using simulations, this approach outperforms benchmark feature selection methods. This framework is applied to YouTube influencer videos, linking video features to measures of shallow and deep engagement developed based on the dual-system framework of thinking. The findings guide influencers and brands in prioritizing video features associated with deep engagement.
Authors: Binchi Zhang, Minnan Luo, Shangbin Feng, Ziqi Liu, Jun Zhou, Qinghua Zheng
Abstract: Federated graph learning (FGL) has become an important research topic in response to the increasing scale and the distributed nature of graph-structured data in the real world. In FGL, a global graph is distributed across different clients, where each client holds a subgraph. Existing FGL methods often fail to effectively utilize cross-client edges, losing structural information during the training; additionally, local graphs often exhibit significant distribution divergence. These two issues make local models in FGL less desirable than in centralized graph learning, namely the local bias problem in this paper. To solve this problem, we propose a novel FGL framework to make the local models similar to the model trained in a centralized setting. Specifically, we design a distributed learning scheme, fully leveraging cross-client edges to aggregate information from other clients. In addition, we propose a label-guided sampling approach to alleviate the imbalanced local data and meanwhile, distinctly reduce the training overhead. Extensive experiments demonstrate that local bias can compromise the model performance and slow down the convergence during training. Experimental results also verify that our framework successfully mitigates local bias, achieving better performance than other baselines with lower time and memory overhead.
Authors: Tianya Terry Zhang
Abstract: Traffic state data, such as speed, volume and travel time collected from ubiquitous traffic monitoring sensors require advanced network level analytics for forecasting and identifying significant traffic patterns. This paper leverages diverse traffic state datasets from the Caltrans Performance Measurement System (PeMS) hosted on the open benchmark and achieved promising performance compared to well recognized spatial-temporal models. Drawing inspiration from the success of hierarchical architectures in various Artificial Intelligence (AI) tasks, we integrate cell and hidden states from low-level to high-level Long Short-Term Memory (LSTM) networks with an attention pooling mechanism, similar to human perception systems. The developed hierarchical structure is designed to account for dependencies across different time scales, capturing the spatial-temporal correlations of network-level traffic states, enabling the prediction of traffic states for all corridors rather than a single link or route. The efficiency of designed attention-based LSTM is analyzed by ablation study. Comparative results with baseline LSTM models demonstrate that the Hierarchical Attention LSTM (HierAttnLSTM) model not only provides higher prediction accuracy but also effectively forecasts unusual congestion patterns. Data and code are made publicly available to support reproducible scientific research.
Authors: Risto Vuorio, Pim de Haan, Johann Brehmer, Hanno Ackermann, Daniel Dijkman, Taco Cohen
Abstract: Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidden confounders in the causal graph. In previous work, to work around the confounding problem, policies have been trained using query access to the expert's policy or inverse reinforcement learning (IRL). However, both approaches have drawbacks as the expert's policy may not be available and IRL can be unstable in practice. Instead, we propose to train a variational inference model to infer the expert's latent information and use it to train a latent-conditional policy. We prove that using this method, under strong assumptions, the identification of the correct imitation learning policy is theoretically possible from expert demonstrations alone. In practice, we focus on a setting with less strong assumptions where we use exploration data for learning the inference model. We show in theory and practice that this algorithm converges to the correct interventional policy, solves the confounding issue, and can under certain assumptions achieve an asymptotically optimal imitation performance.
Authors: Ali Muzaffar, Hani Ragab Hassen, Hind Zantout, Michael A Lones
Abstract: The popularity of Android means it is a common target for malware. Over the years, various studies have found that machine learning models can effectively discriminate malware from benign applications. However, as the operating system evolves, so does malware, bringing into question the findings of these previous studies, many of which report very high accuracies using small, outdated, and often imbalanced datasets. In this paper, we reimplement 18 representative past works and reevaluate them using a balanced, relevant, and up-to-date dataset comprising 124,000 applications. We also carry out new experiments designed to fill holes in existing knowledge, and use our findings to identify the most effective features and models to use for Android malware detection within a contemporary environment. We show that high detection accuracies (up to 96.8%) can be achieved using features extracted through static analysis alone, yielding a modest benefit (1%) from using far more expensive dynamic analysis. API calls and opcodes are the most productive static and TCP network traffic provide the most predictive dynamic features. Random forests are generally the most effective model, outperforming more complex deep learning approaches. Whilst directly combining static and dynamic features is generally ineffective, ensembling models separately leads to performances comparable to the best models but using less brittle features.
Authors: Mauricio Tec, Kevin Josey, Oladimeji Mudele, Francesca Dominici
Abstract: A fundamental task in causal inference is estimating the effect of distribution shift in the treatment variable. We refer to this problem as shift-response function (SRF) estimation. Existing neural network methods for causal inference lack theoretical guarantees and practical implementations for SRF estimation. In this paper, we introduce Targeted Regularization for Exposure Shifts with Neural Networks (TRESNET), a method to estimate SRFs with robustness and efficiency guarantees. Our contributions are twofold. First, we propose a targeted regularization loss for neural networks with theoretical properties that ensure double robustness and asymptotic efficiency specific to SRF estimation. Second, we extend targeted regularization to support loss functions from the exponential family to accommodate non-continuous outcome distributions (e.g., discrete counts). We conduct benchmark experiments demonstrating TRESNET's broad applicability and competitiveness. We then apply our method to a key policy question in public health to estimate the causal effect of revising the US National Ambient Air Quality Standards (NAAQS) for PM 2.5 from 12 ${\mu}g/m^3$ to 9 ${\mu}g/m^3$. This change has been recently proposed by the US Environmental Protection Agency (EPA). Our goal is to estimate the reduction in deaths that would result from this anticipated revision using data consisting of 68 million individuals across the U.S.
Authors: Mehrnaz Mofakhami, Ioannis Mitliagkas, Gauthier Gidel
Abstract: Performative prediction is a framework for learning models that influence the data they intend to predict. We focus on finding classifiers that are performatively stable, i.e. optimal for the data distribution they induce. Standard convergence results for finding a performatively stable classifier with the method of repeated risk minimization assume that the data distribution is Lipschitz continuous to the model's parameters. Under this assumption, the loss must be strongly convex and smooth in these parameters; otherwise, the method will diverge for some problems. In this work, we instead assume that the data distribution is Lipschitz continuous with respect to the model's predictions, a more natural assumption for performative systems. As a result, we are able to significantly relax the assumptions on the loss function. In particular, we do not need to assume convexity with respect to the model's parameters. As an illustration, we introduce a resampling procedure that models realistic distribution shifts and show that it satisfies our assumptions. We support our theory by showing that one can learn performatively stable classifiers with neural networks making predictions about real data that shift according to our proposed procedure.
Authors: Zhi-Hua Zhou
Abstract: Conventional theoretical machine learning studies generally assume explicitly or implicitly that there are enough or even infinitely supplied computational resources. In real practice, however, computational resources are usually limited, and the performance of machine learning depends not only on how many data have been received, but also on how many data can be handled subject to computational resources available. Note that most current ``intelligent supercomputing'' facilities work like exclusive operating systems, where a fixed amount of resources are allocated to a machine learning task without adaptive scheduling strategies considering important factors such as the learning performance demands and learning process status. In this article, we introduce the notion of machine learning throughput, define Computational Resource Efficient Learning (CoRE-Learning), and present a theoretical framework that takes into account the influence of computational resources in learning theory. This framework can be naturally applied to stream learning where the incoming data streams can be potentially endless with overwhelming size and it is impractical to assume that all received data can be handled in time. It may also provide a theoretical perspective for the design of intelligent supercomputing operating systems.
Authors: Xiongxiao Xu, Kaize Ding, Canyu Chen, Kai Shu
Abstract: Graph anomaly detection has long been an important problem in various domains pertaining to information security such as financial fraud, social spam and network intrusion. The majority of existing methods are performed in an unsupervised manner, as labeled anomalies in a large scale are often too expensive to acquire. However, the identified anomalies may turn out to be uninteresting data instances due to the lack of prior knowledge. In real-world scenarios, it is often feasible to obtain limited labeled anomalies, which have great potential to advance graph anomaly detection. However, the work exploring limited labeled anomalies and a large amount of unlabeled nodes in graphs to detect anomalies is relatively limited. Therefore, in this paper, we study an important problem of few-shot graph anomaly detection. Nonetheless, it is challenging to fully leverage the information of few-shot anomalous nodes due to the irregularity of anomalies and the overfitting issue in the few-shot learning. To tackle the above challenges, we propose a novel meta-learning based framework, MetaGAD, that learns to adapt the knowledge from self-supervised learning to few-shot supervised learning for graph anomaly detection. In specific, we formulate the problem as a bi-level optimization, ensuring MetaGAD converging to minimizing the validation loss, thus enhancing the generalization capacity. The comprehensive experiments on six real-world datasets with synthetic anomalies and "organic" anomalies (available in the datasets) demonstrate the effectiveness of MetaGAD in detecting anomalies with few-shot anomalies. The code is available at https://github.com/XiongxiaoXu/MetaGAD.
Authors: Aneesh Komanduri, Yongkai Wu, Feng Chen, Xintao Wu
Abstract: Learning disentangled causal representations is a challenging problem that has gained significant attention recently due to its implications for extracting meaningful information for downstream tasks. In this work, we define a new notion of causal disentanglement from the perspective of independent causal mechanisms. We propose ICM-VAE, a framework for learning causally disentangled representations supervised by causally related observed labels. We model causal mechanisms using nonlinear learnable flow-based diffeomorphic functions to map noise variables to latent causal variables. Further, to promote the disentanglement of causal factors, we propose a causal disentanglement prior learned from auxiliary labels and the latent causal structure. We theoretically show the identifiability of causal factors and mechanisms up to permutation and elementwise reparameterization. We empirically demonstrate that our framework induces highly disentangled causal factors, improves interventional robustness, and is compatible with counterfactual generation.
Authors: Ziqin Chen, Yongqiang Wang
Abstract: Distributed online learning is gaining increased traction due to its unique ability to process large-scale datasets and streaming data. To address the growing public awareness and concern on privacy protection, plenty of algorithms have been proposed to enable differential privacy in distributed online optimization and learning. However, these algorithms often face the dilemma of trading learning accuracy for privacy. By exploiting the unique characteristics of online learning, this paper proposes an approach that tackles the dilemma and ensures both differential privacy and learning accuracy in distributed online learning. More specifically, while ensuring a diminishing expected instantaneous regret, the approach can simultaneously ensure a finite cumulative privacy budget, even in the infinite time horizon. To cater for the fully distributed setting, we adopt the local differential-privacy framework, which avoids the reliance on a trusted data curator that is required in the classic "centralized" (global) differential-privacy framework. To the best of our knowledge, this is the first algorithm that successfully ensures both rigorous local differential privacy and learning accuracy. The effectiveness of the proposed algorithm is evaluated using machine learning tasks, including logistic regression on the the "mushrooms" datasets and CNN-based image classification on the "MNIST" and "CIFAR-10" datasets.
Authors: Zhiyi Zhang, Pengfei Zhang, Zhuopin Xu, Qi Wang
Abstract: Convolutional neural networks necessitate good algorithms to reduce complexity, and sufficient utilization of parallel processors for acceleration. Within convolutional layers, there are three types of operators: convolution used in forward propagation, deconvolution and dilated-convolution utilized in backward propagation. During the execution of these operators, zeros are typically added to tensors, leading to redundant calculations and unnecessary strain on hardware. To circumvent these inefficiencies, we propose the C-K-S algorithm, accompanied by efficient GPU implementations. C-K-S trims filters to exclude zero-padding. For deconvolution and dilated-convolution, C-K-S transforms sparse tensors into dense tensors, and standardizes the local computational rules to simplify the hardware control. The experimental results demonstrate that C-K-S offers good performance in terms of speed and convergence, surpassing the capabilities of PyTorch and cuDNN in certain scenarios.
Authors: Xueying Ding, Yue Zhao, Leman Akoglu
Abstract: Outlier detection (OD) finds many applications with a rich literature of numerous techniques. Deep neural network based OD (DOD) has seen a recent surge of attention thanks to the many advances in deep learning. In this paper, we consider a critical-yet-understudied challenge with unsupervised DOD, that is, effective hyperparameter (HP) tuning/model selection. While several prior work report the sensitivity of OD models to HPs, it becomes ever so critical for the modern DOD models that exhibit a long list of HPs. We introduce HYPER for tuning DOD models, tackling two fundamental challenges: (1) validation without supervision (due to lack of labeled anomalies), and (2) efficient search of the HP/model space (due to exponential growth in the number of HPs). A key idea is to design and train a novel hypernetwork (HN) that maps HPs onto optimal weights of the main DOD model. In turn, HYPER capitalizes on a single HN that can dynamically generate weights for many DOD models (corresponding to varying HPs), which offers significant speed-up. In addition, it employs meta-learning on historical OD tasks with labels to train a proxy validation function, likewise trained with our proposed HN efficiently. Extensive experiments on 35 OD tasks show that HYPER achieves high performance against 8 baselines with significant efficiency gains.
Authors: Daniel Jiwoong Im, Alexander Kondratskiy, Vincent Harvey, Hsuan-Wei Fu
Abstract: Automated market makers (AMMs) are pricing mechanisms utilized by decentralized exchanges (DEX). Traditional AMM approaches are constrained by pricing solely based on their own liquidity pool, without consideration of external markets or risk management for liquidity providers. In this paper, we propose a new approach known as UBET AMM (UAMM), which calculates prices by considering external market prices and the impermanent loss of the liquidity pool. Despite relying on external market prices, our method maintains the desired properties of a constant product curve when computing slippages. The key element of UAMM is determining the appropriate slippage amount based on the desired target balance, which encourages the liquidity pool to minimize impermanent loss. We demonstrate that our approach eliminates arbitrage opportunities when external market prices are efficient.
Authors: Alina Ermilova, Elizaveta Kovtun, Dmitry Berestnev, Alexey Zaytsev
Abstract: The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output during inference by performing an adversarial attack called poisoning via introducing a backdoor into the model during training. For sequences of financial transactions of a customer, insertion of a backdoor is harder to perform, as models operate over a more complex discrete space of sequences, and systematic checks for insecurities occur. We provide a method to introduce concealed backdoors, creating vulnerabilities without altering their functionality for uncontaminated data. To achieve this, we replace a clean model with a poisoned one that is aware of the availability of a backdoor and utilize this knowledge. Our most difficult for uncovering attacks include either additional supervised detection step of poisoned data activated during the test or well-hidden model weight modifications. The experimental study provides insights into how these effects vary across different datasets, architectures, and model components. Alternative methods and baselines, such as distillation-type regularization, are also explored but found to be less efficient. Conducted on three open transaction datasets and architectures, including LSTM, CNN, and Transformer, our findings not only illuminate the vulnerabilities in contemporary models but also can drive the construction of more robust systems.
Authors: Zohair Shafi, Benjamin A. Miller, Tina Eliassi-Rad, Rajmonda S. Caceres
Abstract: Machine learning (ML) approaches are increasingly being used to accelerate combinatorial optimization (CO) problems. We investigate the Set Cover Problem (SCP) and propose Graph-SCP, a graph neural network method that augments existing optimization solvers by learning to identify a much smaller sub-problem that contains the solution space. Graph-SCP uses both supervised learning from prior solved instances and unsupervised learning aimed at minimizing the SCP objective. We evaluate the performance of Graph-SCP on synthetically weighted and unweighted SCP instances with diverse problem characteristics and complexities, and on instances from the OR Library, a canonical benchmark for SCP. We show that Graph-SCP reduces the problem size by 60-80% and achieves runtime speedups of up to 10x on average when compared to Gurobi (a state-of-the-art commercial solver), while maintaining solution quality. This is in contrast to fast greedy solutions that significantly compromise solution quality to achieve guaranteed polynomial runtime. We showcase Graph-SCP's ability to generalize to larger problem sizes, training on SCP instances with up to 3,000 subsets and testing on SCP instances with up to 10,000 subsets.
Authors: Zijun Gao, Haibao Liu, Lingbo Li
Abstract: Data Augmentation (DA) has become a critical approach in Time Series Classification (TSC), primarily for its capacity to expand training datasets, enhance model robustness, introduce diversity, and reduce overfitting. However, the current landscape of DA in TSC is plagued with fragmented literature reviews, nebulous methodological taxonomies, inadequate evaluative measures, and a dearth of accessible and user-oriented tools. This study addresses these challenges through a comprehensive examination of DA methodologies within the TSC domain.Our research began with an extensive literature review spanning a decade, revealing significant gaps in existing surveys and necessitating a detailed analysis of over 100 scholarly articles to identify more than 60 distinct DA techniques. This rigorous review led to the development of a novel taxonomy tailored to the specific needs of DA in TSC, categorizing techniques into five primary categories: Transformation-Based, Pattern-Based, Generative, Decomposition-Based, and Automated Data Augmentation. This taxonomy is intended to guide researchers in selecting appropriate methods with greater clarity. In response to the lack of comprehensive evaluations of foundational DA techniques, we conducted a thorough empirical study, testing nearly 20 DA strategies across 15 diverse datasets representing all types within the UCR time-series repository. Using ResNet and LSTM architectures, we employed a multifaceted evaluation approach, including metrics such as Accuracy, Method Ranking, and Residual Analysis, resulting in a benchmark accuracy of 84.98 +- 16.41% in ResNet and 82.41 +- 18.71% in LSTM. Our investigation underscored the inconsistent efficacies of DA techniques, for instance, methods like RGWs and Random Permutation significantly improved model performance, whereas others, like EMD, were less effective.
Authors: David Salinas, Nick Erickson
Abstract: We introduce TabRepo, a new dataset of tabular model evaluations and predictions. TabRepo contains the predictions and metrics of 1310 models evaluated on 200 classification and regression datasets. We illustrate the benefit of our dataset in multiple ways. First, we show that it allows to perform analysis such as comparing Hyperparameter Optimization against current AutoML systems while also considering ensembling at marginal cost by using precomputed model predictions. Second, we show that our dataset can be readily leveraged to perform transfer-learning. In particular, we show that applying standard transfer-learning techniques allows to outperform current state-of-the-art tabular systems in accuracy, runtime and latency.
Authors: Minqi Jiang, Michael Dennis, Edward Grefenstette, Tim Rockt\"aschel
Abstract: Unsupervised environment design (UED) is a form of automatic curriculum learning for training robust decision-making agents to zero-shot transfer into unseen environments. Such autocurricula have received much interest from the RL community. However, UED experiments, based on CPU rollouts and GPU model updates, have often required several weeks of training. This compute requirement is a major obstacle to rapid innovation for the field. This work introduces the minimax library for UED training on accelerated hardware. Using JAX to implement fully-tensorized environments and autocurriculum algorithms, minimax allows the entire training loop to be compiled for hardware acceleration. To provide a petri dish for rapid experimentation, minimax includes a tensorized grid-world based on MiniGrid, in addition to reusable abstractions for conducting autocurricula in procedurally-generated environments. With these components, minimax provides strong UED baselines, including new parallelized variants, which achieve over 120$\times$ speedups in wall time compared to previous implementations when training with equal batch sizes. The minimax library is available under the Apache 2.0 license at https://github.com/facebookresearch/minimax.
Authors: Xingtong Yu, Zhenghao Liu, Yuan Fang, Zemin Liu, Sihong Chen, Xinming Zhang
Abstract: Graph neural networks have emerged as a powerful tool for graph representation learning, but their performance heavily relies on abundant task-specific supervision. To reduce labeling requirement, the "pre-train, prompt" paradigms have become increasingly common. However, existing study of prompting on graphs is limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. To further enhance GraphPrompt in these two stages, we extend it into GraphPrompt+ with two major enhancements. First, we generalize several popular graph pre-training tasks beyond simple link prediction to broaden the compatibility with our task template. Second, we propose a more generalized prompt design that incorporates a series of prompt vectors within every layer of the pre-trained graph encoder, in order to capitalize on the hierarchical information across different layers beyond just the readout layer. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt and GraphPrompt+.
Authors: Paul K. Mandal
Abstract: 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, I introduce a HIPAA compliant framework that can train from distributed data. I 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 learning (VFL) model offers a distributed architecture that enables collaborative learning across diverse sources of medical data while respecting privacy constraints imposed by HIPAA. The VFL architecture proposed herein offers a novel distributed architecture, enabling collaborative learning across diverse sources of medical data while respecting statutory privacy constraints. By leveraging multiple modalities of data, the robustness and accuracy of AD detection can be enhanced. This 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.
Authors: Xiyuan Jin, Jing Wang, Lei Liu, Youfang Lin
Abstract: 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: Yige Li, Jiabo He, Hanxun Huang, Jun Sun, Xingjun Ma
Abstract: Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor attacks have been proposed, most rely on identifying and eliminating the ``shortcut" created by the backdoor, which links a specific source class to a target class. However, these approaches can be easily circumvented by designing multiple backdoor triggers that create shortcuts everywhere and therefore nowhere specific. In this study, we explore the concept of Multi-Trigger Backdoor Attacks (MTBAs), where multiple adversaries leverage different types of triggers to poison the same dataset. By proposing and investigating three types of multi-trigger attacks including \textit{parallel}, \textit{sequential}, and \textit{hybrid} attacks, we demonstrate that 1) multiple triggers can coexist, overwrite, or cross-activate one another, and 2) MTBAs easily break the prevalent shortcut assumption underlying most existing backdoor detection/removal methods, rendering them ineffective. Given the security risk posed by MTBAs, we have created a multi-trigger backdoor poisoning dataset to facilitate future research on detecting and mitigating these attacks, and we also discuss potential defense strategies against MTBAs.
Authors: Yufan Zhuang, Liyuan Liu, Chandan Singh, Jingbo Shang, Jianfeng Gao
Abstract: Decision trees are renowned for their ability to achieve high predictive performance while remaining interpretable, especially on tabular data. Traditionally, they are constructed through recursive algorithms, where they partition the data at every node in a tree. However, identifying a good partition is challenging, as decision trees optimized for local segments may not yield global generalization. To address this, we introduce MetaTree, a transformer-based model trained via meta-learning to directly produce strong decision trees. Specifically, we fit both greedy decision trees and globally optimized decision trees on a large number of datasets, and train MetaTree to produce only the trees that achieve strong generalization performance. This training enables MetaTree to emulate these algorithms and intelligently adapt its strategy according to the context, thereby achieving superior generalization performance.
Authors: Jose Cribeiro-Ramallo, Vadim Arzamasov, Klemens B\"ohm
Abstract: Outlier generation is a popular technique used for solving important outlier detection tasks. Generating outliers with realistic behavior is challenging. Popular existing methods tend to disregard the 'multiple views' property of outliers in high-dimensional spaces. The only existing method accounting for this property falls short in efficiency and effectiveness. We propose BISECT, a new outlier generation method that creates realistic outliers mimicking said property. To do so, BISECT employs a novel proposition introduced in this article stating how to efficiently generate said realistic outliers. Our method has better guarantees and complexity than the current methodology for recreating 'multiple views'. We use the synthetic outliers generated by BISECT to effectively enhance outlier detection in diverse datasets, for multiple use cases. For instance, oversampling with BISECT reduced the error by up to 3 times when compared with the baselines.
Authors: Brett Daley, Martha White, Marlos C. Machado
Abstract: Multistep returns, such as $n$-step returns and $\lambda$-returns, are commonly used to improve the sample efficiency of reinforcement learning (RL) methods. The variance of the multistep returns becomes the limiting factor in their length; looking too far into the future increases variance and reverses the benefits of multistep learning. In our work, we demonstrate the ability of compound returns -- weighted averages of $n$-step returns -- to reduce variance. We prove for the first time that any compound return with the same contraction modulus as a given $n$-step return has strictly lower variance. We additionally prove that this variance-reduction property improves the finite-sample complexity of temporal-difference learning under linear function approximation. Because general compound returns can be expensive to implement, we introduce two-bootstrap returns which reduce variance while remaining efficient, even when using minibatched experience replay. We conduct experiments showing that compound returns often increase the sample efficiency of $n$-step deep RL agents like DQN and PPO.
Authors: Hadi M. Dolatabadi, Sarah M. Erfani, Christopher Leckie
Abstract: Deep neural networks (DNNs) are vulnerable to shortcut learning: rather than learning the intended task, they tend to draw inconclusive relationships between their inputs and outputs. Shortcut learning is ubiquitous among many failure cases of neural networks, and traces of this phenomenon can be seen in their generalizability issues, domain shift, adversarial vulnerability, and even bias towards majority groups. In this paper, we argue that this commonality in the cause of various DNN issues creates a significant opportunity that should be leveraged to find a unified solution for shortcut learning. To this end, we outline the recent advances in topological data analysis (TDA), and persistent homology (PH) in particular, to sketch a unified roadmap for detecting shortcuts in deep learning. We demonstrate our arguments by investigating the topological features of computational graphs in DNNs using two cases of unlearnable examples and bias in decision-making as our test studies. Our analysis of these two failure cases of DNNs reveals that finding a unified solution for shortcut learning in DNNs is not out of reach, and TDA can play a significant role in forming such a framework.
Authors: Yufei He, Yuan Sui, Xiaoxin He, Bryan Hooi
Abstract: Foundation models like ChatGPT and GPT-4 have revolutionized artificial intelligence, exhibiting remarkable abilities to generalize across a wide array of tasks and applications beyond their initial training objectives. However, graph learning has predominantly focused on single-graph models, tailored to specific tasks or datasets, lacking the ability to transfer learned knowledge to different domains. This limitation stems from the inherent complexity and diversity of graph structures, along with the different feature and label spaces specific to graph data. In this paper, we recognize text as an effective unifying medium and employ Text-Attributed Graphs (TAGs) to leverage this potential. We present our UniGraph framework, designed to learn a foundation model for TAGs, which is capable of generalizing to unseen graphs and tasks across diverse domains. Unlike single-graph models that use pre-computed node features of varying dimensions as input, our approach leverages textual features for unifying node representations, even for graphs such as molecular graphs that do not naturally have textual features. We propose a novel cascaded architecture of Language Models (LMs) and Graph Neural Networks (GNNs) as backbone networks. Additionally, we propose the first pre-training algorithm specifically designed for large-scale self-supervised learning on TAGs, based on Masked Graph Modeling. We introduce graph instruction tuning using Large Language Models (LLMs) to enable zero-shot prediction ability. Our comprehensive experiments across various graph learning tasks and domains demonstrate the model's effectiveness in self-supervised representation learning on unseen graphs, few-shot in-context transfer, and zero-shot transfer, even surpassing or matching the performance of GNNs that have undergone supervised training on target datasets.
Authors: GuanWen Qiu, Da Kuang, Surbhi Goel
Abstract: Existing research often posits spurious features as easier to learn than core features in neural network optimization, but the impact of their relative simplicity remains under-explored. Moreover, studies mainly focus on end performance rather than the learning dynamics of feature learning. In this paper, we propose a theoretical framework and an associated synthetic dataset grounded in boolean function analysis. This setup allows for fine-grained control over the relative complexity (compared to core features) and correlation strength (with respect to the label) of spurious features to study the dynamics of feature learning under spurious correlations. Our findings uncover several interesting phenomena: (1) stronger spurious correlations or simpler spurious features slow down the learning rate of the core features, (2) two distinct subnetworks are formed to learn core and spurious features separately, (3) learning phases of spurious and core features are not always separable, (4) spurious features are not forgotten even after core features are fully learned. We demonstrate that our findings justify the success of retraining the last layer to remove spurious correlation and also identifies limitations of popular debiasing algorithms that exploit early learning of spurious features. We support our empirical findings with theoretical analyses for the case of learning XOR features with a one-hidden-layer ReLU network.
Authors: Mirco Theile, Hongpeng Cao, Marco Caccamo, Alberto L. Sangiovanni-Vincentelli
Abstract: In reinforcement learning (RL), exploiting environmental symmetries can significantly enhance efficiency, robustness, and performance. However, ensuring that the deep RL policy and value networks are respectively equivariant and invariant to exploit these symmetries is a substantial challenge. Related works try to design networks that are equivariant and invariant by construction, limiting them to a very restricted library of components, which in turn hampers the expressiveness of the networks. This paper proposes a method to construct equivariant policies and invariant value functions without specialized neural network components, which we term equivariant ensembles. We further add a regularization term for adding inductive bias during training. In a map-based path planning case study, we show how equivariant ensembles and regularization benefit sample efficiency and performance.
Authors: Naram Mhaisen, George Iosifidis
Abstract: This paper brings the concept of ``optimism" to the new and promising framework of online Non-stochastic Control (NSC). Namely, we study how NSC can benefit from a prediction oracle of unknown quality responsible for forecasting future costs. The posed problem is first reduced to an optimistic learning with delayed feedback problem, which is handled through the Optimistic Follow the Regularized Leader (OFTRL) algorithmic family. This reduction enables the design of \texttt{OptFTRL-C}, the first Disturbance Action Controller (DAC) with optimistic policy regret bounds. These new bounds are commensurate with the oracle's accuracy, ranging from $\mathcal{O}(1)$ for perfect predictions to the order-optimal $\mathcal{O}(\sqrt{T})$ even when all predictions fail. By addressing the challenge of incorporating untrusted predictions into online control, this work contributes to the advancement of the NSC framework and paves the way toward effective and robust learning-based controllers.
Authors: Fin Amin, Jung-Eun Kim
Abstract: When neural networks are confronted with unfamiliar data that deviate from their training set, this signifies a domain shift. While these networks output predictions on their inputs, they typically fail to account for their level of familiarity with these novel observations. While prevailing works navigate unsupervised domain adaptation with the goal of curtailing model entropy, they unintentionally birth models that grapple with sub-optimal calibration - a dilemma we term the over-certainty phenomenon. In this paper, we uncover a concerning trend in unsupervised domain adaptation and propose a solution that not only maintains accuracy but also addresses calibration.
Authors: Aneesh Komanduri, Chen Zhao, Feng Chen, Xintao Wu
Abstract: Diffusion probabilistic models (DPMs) have become the state-of-the-art in high-quality image generation. However, DPMs have an arbitrary noisy latent space with no interpretable or controllable semantics. Although there has been significant research effort to improve image sample quality, there is little work on representation-controlled generation using diffusion models. Specifically, causal modeling and controllable counterfactual generation using DPMs is an underexplored area. In this work, we propose CausalDiffAE, a diffusion-based causal representation learning framework to enable counterfactual generation according to a specified causal model. Our key idea is to use an encoder to extract high-level semantically meaningful causal variables from high-dimensional data and model stochastic variation using reverse diffusion. We propose a causal encoding mechanism that maps high-dimensional data to causally related latent factors and parameterize the causal mechanisms among latent factors using neural networks. To enforce the disentanglement of causal variables, we formulate a variational objective and leverage auxiliary label information in a prior to regularize the latent space. We propose a DDIM-based counterfactual generation procedure subject to do-interventions. Finally, to address the limited label supervision scenario, we also study the application of CausalDiffAE when a part of the training data is unlabeled, which also enables granular control over the strength of interventions in generating counterfactuals during inference. We empirically show that CausalDiffAE learns a disentangled latent space and is capable of generating high-quality counterfactual images.
Authors: Gabriel Turinici
Abstract: Physics-informed neural networks (PINN) is a extremely powerful paradigm used to solve equations encountered in scientific computing applications. An important part of the procedure is the minimization of the equation residual which includes, when the equation is time-dependent, a time sampling. It was argued in the literature that the sampling need not be uniform but should overweight initial time instants, but no rigorous explanation was provided for this choice. In the present work we take some prototypical examples and, under standard hypothesis concerning the neural network convergence, we show that the optimal time sampling follows a (truncated) exponential distribution. In particular we explain when is best to use uniform time sampling and when one should not. The findings are illustrated with numerical examples on linear equation, Burgers' equation and the Lorenz system.
Authors: Aaron Klein, Jacek Golebiowski, Xingchen Ma, Valerio Perrone, Cedric Archambeau
Abstract: Pre-trained language models (PLM), for example BERT or RoBERTa, mark the state-of-the-art for natural language understanding task when fine-tuned on labeled data. However, their large size poses challenges in deploying them for inference in real-world applications, due to significant GPU memory requirements and high inference latency. This paper explores neural architecture search (NAS) for structural pruning to find sub-parts of the fine-tuned network that optimally trade-off efficiency, for example in terms of model size or latency, and generalization performance. We also show how we can utilize more recently developed two-stage weight-sharing NAS approaches in this setting to accelerate the search process. Unlike traditional pruning methods with fixed thresholds, we propose to adopt a multi-objective approach that identifies the Pareto optimal set of sub-networks, allowing for a more flexible and automated compression process.
Authors: Tianxiang Zhan, Yuanpeng He, Yong Deng, Zhen Li
Abstract: In practical scenarios, time series forecasting necessitates timeliness, especially when dealing with large datasets. Consequently, the exploration of model architectures remains a perennially trending topic in research. To meet these performance demands, we propose a novel backbone from the perspective of information fusion. Introducing the Basic Probability Assignment (BPA) Module and the Time Evidence Fusion Network (TEFN), based on evidence theory, allows us to achieve superior performance. On the other hand, the perspective of multi-source information fusion effectively improves the accuracy of forecasting. Due to the fact that BPA is generated by fuzzy theory, TEFN also has considerable interpretability. In real data experiments, the TEFN partially achieved state-of-the-art, with low errors comparable to PatchTST, and operating efficiency surpass performance models such as Dlinear. Meanwhile, TEFN has high robustness and small error fluctuations in the random hyperparameter selection. TEFN is not a model that achieves the ultimate in single aspect, but a model that balances performance, accuracy, stability, and interpretability.
Authors: Jiaqing Xie, Ziheng Chi
Abstract: Pretrained language models (LMs) showcase significant capabilities in processing molecular text, while concurrently, message passing neural networks (MPNNs) demonstrate resilience and versatility in the domain of molecular science. Despite these advancements, we find there are limited studies investigating the bidirectional interactions between molecular structures and their corresponding textual representations. Therefore, in this paper, we propose two strategies to evaluate whether an information integration can enhance the performance: contrast learning, which involves utilizing an MPNN to supervise the training of the LM, and fusion, which exploits information from both models. Our empirical analysis reveals that the integration approaches exhibit superior performance compared to baselines when applied to smaller molecular graphs, while these integration approaches do not yield performance enhancements on large scale graphs.
Authors: Yanlei Yin, Lihua Wang, Dinh Thai Hoang, Wenbo Wang, Dusit Niyato
Abstract: In the process industry, long-term and efficient optimization of production lines requires real-time monitoring and analysis of operational states to fine-tune production line parameters. However, complexity in operational logic and intricate coupling of production process parameters make it difficult to develop an accurate mathematical model for the entire process, thus hindering the deployment of efficient optimization mechanisms. In view of these difficulties, we propose to deploy a digital twin of the production line by encoding its operational logic in a data-driven approach. By iteratively mapping the real-world data reflecting equipment operation status and product quality indicators in the digital twin, we adopt a quality prediction model for production process based on self-attention-enabled temporal convolutional neural networks. This model enables the data-driven state evolution of the digital twin. The digital twin takes a role of aggregating the information of actual operating conditions and the results of quality-sensitive analysis, which facilitates the optimization of process production with virtual-reality evolution. Leveraging the digital twin as an information-flow carrier, we extract temporal features from key process indicators and establish a production process quality prediction model based on the proposed deep neural network. Our operation experiments on a specific tobacco shredding line demonstrate that the proposed digital twin-based production process optimization method fosters seamless integration between virtual and real production lines. This integration achieves an average operating status prediction accuracy of over 98% and a product quality acceptance rate of over 96%.
Authors: Marcin Podhajski, Jan Dubi\'nski, Franziska Boenisch, Adam Dziedzic, Agnieszka Pregowska And Tomasz Michalak
Abstract: Graph Neural Networks (GNNs) are recognized as potent tools for processing real-world data organized in graph structures. Especially inductive GNNs, which allow for the processing of graph-structured data without relying on predefined graph structures, are becoming increasingly important in a wide range of applications. As such these networks become attractive targets for model-stealing attacks where an adversary seeks to replicate the functionality of the targeted network. Significant efforts have been devoted to developing model-stealing attacks that extract models trained on images and texts. However, little attention has been given to stealing GNNs trained on graph data. This paper identifies a new method of performing unsupervised model-stealing attacks against inductive GNNs, utilizing graph contrastive learning and spectral graph augmentations to efficiently extract information from the targeted model. The new type of attack is thoroughly evaluated on six datasets and the results show that our approach outperforms the current state-of-the-art by Shen et al. (2021). In particular, our attack surpasses the baseline across all benchmarks, attaining superior fidelity and downstream accuracy of the stolen model while necessitating fewer queries directed toward the target model.
Authors: Chuqi Chen, Yahong Yang, Yang Xiang, Wenrui Hao
Abstract: Neural network-based approaches have recently shown significant promise in solving partial differential equations (PDEs) in science and engineering, especially in scenarios featuring complex domains or the incorporation of empirical data. One advantage of the neural network method for PDEs lies in its automatic differentiation (AD), which necessitates only the sample points themselves, unlike traditional finite difference (FD) approximations that require nearby local points to compute derivatives. In this paper, we quantitatively demonstrate the advantage of AD in training neural networks. The concept of truncated entropy is introduced to characterize the training property. Specifically, through comprehensive experimental and theoretical analyses conducted on random feature models and two-layer neural networks, we discover that the defined truncated entropy serves as a reliable metric for quantifying the residual loss of random feature models and the training speed of neural networks for both AD and FD methods. Our experimental and theoretical analyses demonstrate that, from a training perspective, AD outperforms FD in solving partial differential equations.
Authors: Sebastian Loeschcke, Mads Toftrup, Michael J. Kastoryano, Serge Belongie, V\'esteinn Sn{\ae}bjarnarson
Abstract: Training of large neural networks requires significant computational resources. Despite advances using low-rank adapters and quantization, pretraining of models such as LLMs on consumer hardware has not been possible without model sharding, offloading during training, or per-layer gradient updates. To address these limitations, we propose LoQT, a method for efficiently training quantized models. LoQT uses gradient-based tensor factorization to initialize low-rank trainable weight matrices that are periodically merged into quantized full-rank weight matrices. Our approach is suitable for both pretraining and fine-tuning of models, which we demonstrate experimentally for language modeling and downstream task adaptation. We find that LoQT enables efficient training of models up to 7B parameters on a consumer-grade 24GB GPU. We also demonstrate the feasibility of training a 13B parameter model using per-layer gradient updates on the same hardware.
Authors: Youlong Ding, Xueyang Wu, Yining Meng, Yonggang Luo, Hao Wang, Weike Pan
Abstract: Deep learning with differential privacy (DP) has garnered significant attention over the past years, leading to the development of numerous methods aimed at enhancing model accuracy and training efficiency. This paper delves into the problem of training Transformer models with differential privacy. Our treatment is modular: the logic is to `reduce' the problem of training DP Transformer to the more basic problem of training DP vanilla neural nets. The latter is better understood and amenable to many model-agnostic methods. Such `reduction' is done by first identifying the hardness unique to DP Transformer training: the attention distraction phenomenon and a lack of compatibility with existing techniques for efficient gradient clipping. To deal with these two issues, we propose the Re-Attention Mechanism and Phantom Clipping, respectively. We believe that our work not only casts new light on training DP Transformers but also promotes a modular treatment to advance research in the field of differentially private deep learning.
Authors: Andrea Napoli, Paul White
Abstract: This paper considers the problem of model selection under domain shift. Motivated by principles from distributionally robust optimisation (DRO) and domain adaptation theory, it is proposed that the training-validation split should maximise the distribution mismatch between the two sets. By adopting the maximum mean discrepancy (MMD) as the measure of mismatch, it is shown that the partitioning problem reduces to kernel k-means clustering. A constrained clustering algorithm, which leverages linear programming to control the size, label, and (optionally) group distributions of the splits, is presented. The algorithm does not require additional metadata, and comes with convergence guarantees. In experiments, the technique consistently outperforms alternative splitting strategies across a range of datasets and training algorithms, for both domain generalisation (DG) and unsupervised domain adaptation (UDA) tasks. Analysis also shows the MMD between the training and validation sets to be strongly rank-correlated ($\rho=0.63$) with test domain accuracy, further substantiating the validity of this approach.
Authors: Sungchul Hong, Seunghwan An, Jong-June Jeon
Abstract: Recent advances in a generative neural network model extend the development of data augmentation methods. However, the augmentation methods based on the modern generative models fail to achieve notable performance for class imbalance data compared to the conventional model, Synthetic Minority Oversampling Technique (SMOTE). We investigate the problem of the generative model for imbalanced classification and introduce a framework to enhance the SMOTE algorithm using Variational Autoencoders (VAE). Our approach systematically quantifies the density of data points in a low-dimensional latent space using the VAE, simultaneously incorporating information on class labels and classification difficulty. Then, the data points potentially degrading the augmentation are systematically excluded, and the neighboring observations are directly augmented on the data space. Empirical studies on several imbalanced datasets represent that this simple process innovatively improves the conventional SMOTE algorithm over the deep learning models. Consequently, we conclude that the selection of minority data and the interpolation in the data space are beneficial for imbalanced classification problems with a relatively small number of data points.
Authors: Hiroaki Chiba-Okabe, Weijie J. Su
Abstract: The rapid progress of generative AI technology has sparked significant copyright concerns, leading to numerous lawsuits filed against AI developers. While various techniques for mitigating copyright issues have been studied, significant risks remain. Here, we propose a genericization method that modifies the outputs of a generative model to make them more generic and less likely to infringe copyright. To achieve this, we introduce a metric for quantifying the level of originality of data in a manner that is consistent with the legal framework. This metric can be practically estimated by drawing samples from a generative model, which is then used for the genericization process. As a practical implementation, we introduce PREGen, which combines our genericization method with an existing mitigation technique. Experiments demonstrate that our genericization method successfully modifies the output of a text-to-image generative model so that it produces more generic, copyright-compliant images. Compared to the existing method, PREGen reduces the likelihood of generating copyrighted characters by more than half when the names of copyrighted characters are used as the prompt, dramatically improving the performance. Additionally, while generative models can produce copyrighted characters even when their names are not directly mentioned in the prompt, PREGen almost entirely prevents the generation of such characters in these cases.
Authors: Arun D. Kulkarni
Abstract: Recently, convolution neural networks (CNNs) have attracted a great deal of attention due to their remarkable performance in various domains, particularly in image and text classification tasks. However, their application to tabular data classification remains underexplored. There are many fields such as bioinformatics, finance, medicine where nonimage data are prevalent. Adaption of CNNs to classify nonimage data remains highly challenging. This paper investigates the efficacy of CNNs for tabular data classification, aiming to bridge the gap between traditional machine learning approaches and deep learning techniques. We propose a novel framework fuzzy convolution neural network (FCNN) tailored specifically for tabular data to capture local patterns within feature vectors. In our approach, we map feature values to fuzzy memberships. The fuzzy membership vectors are converted into images that are used to train the CNN model. The trained CNN model is used to classify unknown feature vectors. To validate our approach, we generated six complex noisy data sets. We used randomly selected seventy percent samples from each data set for training and thirty percent for testing. The data sets were also classified using the state-of-the-art machine learning algorithms such as the decision tree (DT), support vector machine (SVM), fuzzy neural network (FNN), Bayes classifier, and Random Forest (RF). Experimental results demonstrate that our proposed model can effectively learn meaningful representations from tabular data, achieving competitive or superior performance compared to existing methods. Overall, our finding suggests that the proposed FCNN model holds promise as a viable alternative for tabular data classification tasks, offering a fresh prospective and potentially unlocking new opportunities for leveraging deep learning in structured data analysis.
Authors: M. P. S. G\^olo, J. G. B. M. Junior, D. F. Silva, R. M. Marcacini
Abstract: One-class learning (OCL) comprises a set of techniques applied when real-world problems have a single class of interest. The usual procedure for OCL is learning a hypersphere that comprises instances of this class and, ideally, repels unseen instances from any other classes. Besides, several OCL algorithms for graphs have been proposed since graph representation learning has succeeded in various fields. These methods may use a two-step strategy, initially representing the graph and, in a second step, classifying its nodes. On the other hand, end-to-end methods learn the node representations while classifying the nodes in one learning process. We highlight three main gaps in the literature on OCL for graphs: (i) non-customized representations for OCL; (ii) the lack of constraints on hypersphere parameters learning; and (iii) the methods' lack of interpretability and visualization. We propose One-cLass Graph Autoencoder (OLGA). OLGA is end-to-end and learns the representations for the graph nodes while encapsulating the interest instances by combining two loss functions. We propose a new hypersphere loss function to encapsulate the interest instances. OLGA combines this new hypersphere loss with the graph autoencoder reconstruction loss to improve model learning. OLGA achieved state-of-the-art results and outperformed six other methods with a statistically significant difference from five methods. Moreover, OLGA learns low-dimensional representations maintaining the classification performance with an interpretable model representation learning and results.
Authors: Sumukh K Aithal, Pratyush Maini, Zachary C. Lipton, J. Zico Kolter
Abstract: Colloquially speaking, image generation models based upon diffusion processes are frequently said to exhibit "hallucinations," samples that could never occur in the training data. But where do such hallucinations come from? In this paper, we study a particular failure mode in diffusion models, which we term mode interpolation. Specifically, we find that diffusion models smoothly "interpolate" between nearby data modes in the training set, to generate samples that are completely outside the support of the original training distribution; this phenomenon leads diffusion models to generate artifacts that never existed in real data (i.e., hallucinations). We systematically study the reasons for, and the manifestation of this phenomenon. Through experiments on 1D and 2D Gaussians, we show how a discontinuous loss landscape in the diffusion model's decoder leads to a region where any smooth approximation will cause such hallucinations. Through experiments on artificial datasets with various shapes, we show how hallucination leads to the generation of combinations of shapes that never existed. Finally, we show that diffusion models in fact know when they go out of support and hallucinate. This is captured by the high variance in the trajectory of the generated sample towards the final few backward sampling process. Using a simple metric to capture this variance, we can remove over 95% of hallucinations at generation time while retaining 96% of in-support samples. We conclude our exploration by showing the implications of such hallucination (and its removal) on the collapse (and stabilization) of recursive training on synthetic data with experiments on MNIST and 2D Gaussians dataset. We release our code at https://github.com/locuslab/diffusion-model-hallucination.
URLs: https://github.com/locuslab/diffusion-model-hallucination.
Authors: Yunbei Zhang, Akshay Mehra, Jihun Hamm
Abstract: Continual Test-Time Adaptation (CTTA) seeks to adapt a source pre-trained model to continually changing, unlabeled target domains. Existing TTA methods are typically designed for environments where domain changes occur sequentially and can struggle in more dynamic scenarios, as illustrated in Figure \ref{fig:settings}. Inspired by the principles of online K-Means, we introduce a novel approach to CTTA through visual prompting. We propose a \emph{Dynamic Prompt Coreset} that not only preserves knowledge from previously visited domains but also accommodates learning from new potential domains. This is complemented by a distance-based \emph{Weight Updating Mechanism} that ensures the coreset remains current and relevant. Our approach employs a fixed model architecture alongside the coreset and an innovative updating system to effectively mitigate challenges such as catastrophic forgetting and error accumulation. Extensive testing on four widely-used benchmarks demonstrates that our method consistently outperforms state-of-the-art alternatives in both classification and segmentation CTTA tasks across the structured and dynamic CTTA settings, with $99\%$ fewer trainable parameters.
Authors: Brett Daley, Marlos C. Machado, Martha White
Abstract: The recency heuristic in reinforcement learning is the assumption that stimuli that occurred closer in time to an acquired reward should be more heavily reinforced. The recency heuristic is one of the key assumptions made by TD($\lambda$), which reinforces recent experiences according to an exponentially decaying weighting. In fact, all other widely used return estimators for TD learning, such as $n$-step returns, satisfy a weaker (i.e., non-monotonic) recency heuristic. Why is the recency heuristic effective for temporal credit assignment? What happens when credit is assigned in a way that violates this heuristic? In this paper, we analyze the specific mathematical implications of adopting the recency heuristic in TD learning. We prove that any return estimator satisfying this heuristic: 1) is guaranteed to converge to the correct value function, 2) has a relatively fast contraction rate, and 3) has a long window of effective credit assignment, yet bounded worst-case variance. We also give a counterexample where on-policy, tabular TD methods violating the recency heuristic diverge. Our results offer some of the first theoretical evidence that credit assignment based on the recency heuristic facilitates learning.
Authors: Andrej Tschalzev, Sascha Marton, Stefan L\"udtke, Christian Bartelt, Heiner Stuckenschmidt
Abstract: Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing the performance of models typically consist of model-centric evaluation setups with overly standardized data preprocessing. This paper demonstrates that such model-centric evaluations are biased, as real-world modeling pipelines often require dataset-specific preprocessing and feature engineering. Therefore, we propose a data-centric evaluation framework. We select 10 relevant datasets from Kaggle competitions and implement expert-level preprocessing pipelines for each dataset. We conduct experiments with different preprocessing pipelines and hyperparameter optimization (HPO) regimes to quantify the impact of model selection, HPO, feature engineering, and test-time adaptation. Our main findings are: 1. After dataset-specific feature engineering, model rankings change considerably, performance differences decrease, and the importance of model selection reduces. 2. Recent models, despite their measurable progress, still significantly benefit from manual feature engineering. This holds true for both tree-based models and neural networks. 3. While tabular data is typically considered static, samples are often collected over time, and adapting to distribution shifts can be important even in supposedly static data. These insights suggest that research efforts should be directed toward a data-centric perspective, acknowledging that tabular data requires feature engineering and often exhibits temporal characteristics. Our framework is available under: https://github.com/atschalz/dc_tabeval.
Authors: Jeremy Kedziora
Abstract: In machine learning ensembles predictions from multiple models are aggregated. Despite widespread use and strong performance of ensembles in applied problems little is known about the mathematical properties of aggregating models and associated consequences for safe, explainable use of such models. In this paper we prove a theorem that shows that any ensemble will exhibit at least one of the following forms of prediction instability. It will either ignore agreement among all underlying models, change its mind when none of the underlying models have done so, or be manipulable through inclusion or exclusion of options it would never actually predict. As a consequence, ensemble aggregation procedures will always need to balance the benefits of information use against the risk of these prediction instabilities. This analysis also sheds light on what specific forms of prediction instability to expect from particular ensemble algorithms; for example popular tree ensembles like random forest, or xgboost will violate basic, intuitive fairness properties. Finally, we show that this can be ameliorated by using consistent models in asymptotic conditions.
Authors: Hao Feng, Boyuan Zhang, Fanjiang Ye, Min Si, Ching-Hsiang Chu, Jiannan Tian, Chunxing Yin, Summer Deng, Yuchen Hao, Pavan Balaji, Tong Geng, Dingwen Tao
Abstract: DLRM is a state-of-the-art recommendation system model that has gained widespread adoption across various industry applications. The large size of DLRM models, however, necessitates the use of multiple devices/GPUs for efficient training. A significant bottleneck in this process is the time-consuming all-to-all communication required to collect embedding data from all devices. To mitigate this, we introduce a method that employs error-bounded lossy compression to reduce the communication data size and accelerate DLRM training. We develop a novel error-bounded lossy compression algorithm, informed by an in-depth analysis of embedding data features, to achieve high compression ratios. Moreover, we introduce a dual-level adaptive strategy for error-bound adjustment, spanning both table-wise and iteration-wise aspects, to balance the compression benefits with the potential impacts on accuracy. We further optimize our compressor for PyTorch tensors on GPUs, minimizing compression overhead. Evaluation shows that our method achieves a 1.38$\times$ training speedup with a minimal accuracy impact.
Authors: Mohamed Hassouna, Clara Holzh\"uter, Pawel Lytaev, Josephine Thomas, Bernhard Sick, Christoph Scholz
Abstract: The rise of renewable energy and distributed generation requires new approaches to overcome the limitations of traditional methods. In this context, Graph Neural Networks are promising due to their ability to learn from graph-structured data. Combined with Reinforcement Learning, they can serve as control approaches to determine remedial network actions. This review analyses how Graph Reinforcement Learning (GRL) can improve representation learning and decision making in power grid use cases. Although GRL has demonstrated adaptability to unpredictable events and noisy data, it is primarily at a proof-of-concept stage. We highlight open challenges and limitations with respect to real-world applications.
Authors: Changhun Kim, Taewon Kim, Seungyeon Woo, June Yong Yang, Eunho Yang
Abstract: In real-world scenarios, tabular data often suffer from distribution shifts that threaten the performance of machine learning models. Despite its prevalence and importance, handling distribution shifts in the tabular domain remains underexplored due to the inherent challenges within the tabular data itself. In this sense, test-time adaptation (TTA) offers a promising solution by adapting models to target data without accessing source data, crucial for privacy-sensitive tabular domains. However, existing TTA methods either 1) overlook the nature of tabular distribution shifts, often involving label distribution shifts, or 2) impose architectural constraints on the model, leading to a lack of applicability. To this end, we propose AdapTable, a novel TTA framework for tabular data. AdapTable operates in two stages: 1) calibrating model predictions using a shift-aware uncertainty calibrator, and 2) adjusting these predictions to match the target label distribution with a label distribution handler. We validate the effectiveness of AdapTable through theoretical analysis and extensive experiments on various distribution shift scenarios. Our results demonstrate AdapTable's ability to handle various real-world distribution shifts, achieving up to a 16% improvement on the HELOC dataset.
Authors: Joseph Musielewicz, Janice Lan, Matt Uyttendaele, John R. Kitchin
Abstract: Graph neural networks (GNNs) have been shown to be astonishingly capable models for molecular property prediction, particularly as surrogates for expensive density functional theory calculations of relaxed energy for novel material discovery. However, one limitation of GNNs in this context is the lack of useful uncertainty prediction methods, as this is critical to the material discovery pipeline. In this work, we show that uncertainty quantification for relaxed energy calculations is more complex than uncertainty quantification for other kinds of molecular property prediction, due to the effect that structure optimizations have on the error distribution. We propose that distribution-free techniques are more useful tools for assessing calibration, recalibrating, and developing uncertainty prediction methods for GNNs performing relaxed energy calculations. We also develop a relaxed energy task for evaluating uncertainty methods for equivariant GNNs, based on distribution-free recalibration and using the Open Catalyst Project dataset. We benchmark a set of popular uncertainty prediction methods on this task, and show that latent distance methods, with our novel improvements, are the most well-calibrated and economical approach for relaxed energy calculations. Finally, we demonstrate that our latent space distance method produces results which align with our expectations on a clustering example, and on specific equation of state and adsorbate coverage examples from outside the training dataset.
Authors: Yue Yao, Shengchao Yan, Daniel Goehring, Wolfram Burgard, Joerg Reichardt
Abstract: Robustness against Out-of-Distribution (OoD) samples is a key performance indicator of a trajectory prediction model. However, the development and ranking of state-of-the-art (SotA) models are driven by their In-Distribution (ID) performance on individual competition datasets. We present an OoD testing protocol that homogenizes datasets and prediction tasks across two large-scale motion datasets. We introduce a novel prediction algorithm based on polynomial representations for agent trajectory and road geometry on both the input and output sides of the model. With a much smaller model size, training effort, and inference time, we reach near SotA performance for ID testing and significantly improve robustness in OoD testing. Within our OoD testing protocol, we further study two augmentation strategies of SotA models and their effects on model generalization. Highlighting the contrast between ID and OoD performance, we suggest adding OoD testing to the evaluation criteria of trajectory prediction models.
Authors: Orson Mengara
Abstract: Since the advent of generative artificial intelligence, every company and researcher has been rushing to develop their own generative models, whether commercial or not. Given the large number of users of these powerful new tools, there is currently no intrinsically verifiable way to explain from the ground up what happens when LLMs (large language models) learn. For example, those based on automatic speech recognition systems, which have to rely on huge and astronomical amounts of data collected from all over the web to produce fast and efficient results, In this article, we develop a backdoor attack called MarketBackFinal 2.0, based on acoustic data poisoning, MarketBackFinal 2.0 is mainly based on modern stock market models. In order to show the possible vulnerabilities of speech-based transformers that may rely on LLMs.
Authors: Ahmad Saeed Khan, Erik Schaffernicht, Johannes Andreas Stork
Abstract: Estimating treatment effects from observational data is paramount in healthcare, education, and economics, but current deep disentanglement-based methods to address selection bias are insufficiently handling irrelevant variables. We demonstrate in experiments that this leads to prediction errors. We disentangle pre-treatment variables with a deep embedding method and explicitly identify and represent irrelevant variables, additionally to instrumental, confounding and adjustment latent factors. To this end, we introduce a reconstruction objective and create an embedding space for irrelevant variables using an attached autoencoder. Instead of relying on serendipitous suppression of irrelevant variables as in previous deep disentanglement approaches, we explicitly force irrelevant variables into this embedding space and employ orthogonalization to prevent irrelevant information from leaking into the latent space representations of the other factors. Our experiments with synthetic and real-world benchmark datasets show that we can better identify irrelevant variables and more precisely predict treatment effects than previous methods, while prediction quality degrades less when additional irrelevant variables are introduced.
Authors: Bao Gia Doan, Afshar Shamsi, Xiao-Yu Guo, Arash Mohammadi, Hamid Alinejad-Rokny, Dino Sejdinovic, Damith C. Ranasinghe, Ehsan Abbasnejad
Abstract: Computational complexity of Bayesian learning is impeding its adoption in practical, large-scale tasks. Despite demonstrations of significant merits such as improved robustness and resilience to unseen or out-of-distribution inputs over their non- Bayesian counterparts, their practical use has faded to near insignificance. In this study, we introduce an innovative framework to mitigate the computational burden of Bayesian neural networks (BNNs). Our approach follows the principle of Bayesian techniques based on deep ensembles, but significantly reduces their cost via multiple low-rank perturbations of parameters arising from a pre-trained neural network. Both vanilla version of ensembles as well as more sophisticated schemes such as Bayesian learning with Stein Variational Gradient Descent (SVGD), previously deemed impractical for large models, can be seamlessly implemented within the proposed framework, called Bayesian Low-Rank LeArning (Bella). In a nutshell, i) Bella achieves a dramatic reduction in the number of trainable parameters required to approximate a Bayesian posterior; and ii) it not only maintains, but in some instances, surpasses the performance of conventional Bayesian learning methods and non-Bayesian baselines. Our results with large-scale tasks such as ImageNet, CAMELYON17, DomainNet, VQA with CLIP, LLaVA demonstrate the effectiveness and versatility of Bella in building highly scalable and practical Bayesian deep models for real-world applications.
Authors: Mengjie Fan, Jinlu Yu, Daniel Weiskopf, Nan Cao, Huai-Yu Wang, Liang Zhou
Abstract: We introduce a visual analysis method for multiple causal graphs with different outcome variables, namely, multi-outcome causal graphs. Multi-outcome causal graphs are important in healthcare for understanding multimorbidity and comorbidity. To support the visual analysis, we collaborated with medical experts to devise two comparative visualization techniques at different stages of the analysis process. First, a progressive visualization method is proposed for comparing multiple state-of-the-art causal discovery algorithms. The method can handle mixed-type datasets comprising both continuous and categorical variables and assist in the creation of a fine-tuned causal graph of a single outcome. Second, a comparative graph layout technique and specialized visual encodings are devised for the quick comparison of multiple causal graphs. In our visual analysis approach, analysts start by building individual causal graphs for each outcome variable, and then, multi-outcome causal graphs are generated and visualized with our comparative technique for analyzing differences and commonalities of these causal graphs. Evaluation includes quantitative measurements on benchmark datasets, a case study with a medical expert, and expert user studies with real-world health research data.
Authors: Michael Staniek, Marius Fracarolli, Michael Hagmann, Stefan Riezler
Abstract: Machine learning for early syndrome diagnosis aims to solve the intricate task of predicting a ground truth label that most often is the outcome (effect) of a medical consensus definition applied to observed clinical measurements (causes), given clinical measurements observed several hours before. Instead of focusing on the prediction of the future effect, we propose to directly predict the causes via time series forecasting (TSF) of clinical variables and determine the effect by applying the gold standard consensus definition to the forecasted values. This method has the invaluable advantage of being straightforwardly interpretable to clinical practitioners, and because model training does not rely on a particular label anymore, the forecasted data can be used to predict any consensus-based label. We exemplify our method by means of long-term TSF with Transformer models, with a focus on accurate prediction of sparse clinical variables involved in the SOFA-based Sepsis-3 definition and the new Simplified Acute Physiology Score (SAPS-II) definition. Our experiments are conducted on two datasets and show that contrary to recent proposals which advocate set function encoders for time series and direct multi-step decoders, best results are achieved by a combination of standard dense encoders with iterative multi-step decoders. The key for success of iterative multi-step decoding can be attributed to its ability to capture cross-variate dependencies and to a student forcing training strategy that teaches the model to rely on its own previous time step predictions for the next time step prediction.
Authors: Yoonhyuk Choi, Jiho Choi, Taewook Ko, Chong-Kwon Kim
Abstract: Traditional Graph Neural Networks (GNNs) rely on network homophily, which can lead to performance degradation due to over-smoothing in many real-world heterophily scenarios. Recent studies analyze the smoothing effect (separability) after message-passing (MP), depending on the expectation of node features. Regarding separability gain, they provided theoretical backgrounds on over-smoothing caused by various propagation schemes, including positive, signed, and blocked MPs. More recently, by extending these theorems, some works have suggested improvements in signed propagation under multiple classes. However, prior works assume that the error ratio of all propagation schemes is fixed, failing to investigate this phenomenon correctly. To solve this problem, we propose a novel method for estimating homophily and edge error ratio, integrated with dynamic selection between blocked and signed propagation during training. Our theoretical analysis, supported by extensive experiments, demonstrates that blocking MP can be more effective than signed propagation under high edge error ratios, improving the performance in both homophilic and heterophilic graphs.
Authors: Karel D'Oosterlinck, Winnie Xu, Chris Develder, Thomas Demeester, Amanpreet Singh, Christopher Potts, Douwe Kiela, Shikib Mehri
Abstract: Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. The interaction between model, paired data, and objective makes alignment a complicated procedure, sometimes producing subpar results. We study this and find that (i) preference data gives a better learning signal when the underlying responses are contrastive, and (ii) alignment objectives lead to better performance when they specify more control over the model during training. Based on these insights, we introduce Contrastive Learning from AI Revisions (CLAIR), a data-creation method which leads to more contrastive preference pairs, and Anchored Preference Optimization (APO), a controllable and more stable alignment objective. We align Llama-3-8B-Instruct using various comparable datasets and alignment objectives and measure MixEval-Hard scores, which correlate highly with human judgments. The CLAIR preferences lead to the strongest performance out of all datasets, and APO consistently outperforms less controllable objectives. Our best model, trained on 32K CLAIR preferences with APO, improves Llama-3-8B-Instruct by 7.65%, closing the gap with GPT4-turbo by 45%. Our code is available at https://github.com/ContextualAI/CLAIR_and_APO.
Authors: Haniyeh Ehsani Oskouie, Lionel Levine, Majid Sarrafzadeh
Abstract: As Artificial Intelligence (AI) models are increasingly integrated into critical systems, the need for a robust framework to establish the trustworthiness of AI is increasingly paramount. While collaborative efforts have established conceptual foundations for such a framework, there remains a significant gap in developing concrete, technically robust methods for assessing AI model quality and performance. A critical drawback in the traditional methods for assessing the validity and generalizability of models is their dependence on internal developer datasets, rendering it challenging to independently assess and verify their performance claims. This paper introduces a novel approach for assessing a newly trained model's performance based on another known model by calculating correlation between neural networks. The proposed method evaluates correlations by determining if, for each neuron in one network, there exists a neuron in the other network that produces similar output. This approach has implications for memory efficiency, allowing for the use of smaller networks when high correlation exists between networks of different sizes. Additionally, the method provides insights into robustness, suggesting that if two highly correlated networks are compared and one demonstrates robustness when operating in production environments, the other is likely to exhibit similar robustness. This contribution advances the technical toolkit for responsible AI, supporting more comprehensive and nuanced evaluations of AI models to ensure their safe and effective deployment. Code is available at https://github.com/aheldis/Cross-model-correlation.git.
URLs: https://github.com/aheldis/Cross-model-correlation.git.
Authors: Yunxiao Shi, Wujiang Xu, Mingyu Jin, Haimin Zhang, Qiang Wu, Yongfeng Zhang, Min Xu
Abstract: Modeling feature interactions is crucial for click-through rate (CTR) prediction, particularly when it comes to high-order explicit interactions. Traditional methods struggle with this task because they often predefine a maximum interaction order, which relies heavily on prior knowledge and can limit the model's effectiveness. Additionally, modeling high-order interactions typically leads to increased computational costs. Therefore, the challenge lies in adaptively modeling high-order feature interactions while maintaining efficiency. To address this issue, we introduce Kolmogorov-Arnold Represented Sparse Efficient Interaction Network (KarSein), designed to optimize both predictive accuracy and computational efficiency. We firstly identify limitations of directly applying Kolmogorov-Arnold Networks (KAN) to CTR and then introduce KarSein to overcome these issues. It features a novel architecture that reduces the computational costs of KAN and supports embedding vectors as feature inputs. Additionally, KarSein employs guided symbolic regression to address the challenge of KAN in spontaneously learning multiplicative relationships. Extensive experiments demonstrate KarSein's superior performance, achieving significant predictive accuracy with minimal computational overhead. Furthermore, KarSein maintains strong global explainability while enabling the removal of redundant features, resulting in a sparse network structure. These advantages also position KarSein as a promising method for efficient inference.
Authors: Housen Wang, Yuxing Chen, Sirong Cao, Xiaoli Wang, Qiang Liu
Abstract: We propose a unified framework for delay differential equations (DDEs) based on deep neural networks (DNNs) - the neural delay differential equations (NDDEs), aimed at solving the forward and inverse problems of delay differential equations. This framework could embed delay differential equations into neural networks to accommodate the diverse requirements of DDEs in terms of initial conditions, control equations, and known data. NDDEs adjust the network parameters through automatic differentiation and optimization algorithms to minimize the loss function, thereby obtaining numerical solutions to the delay differential equations without the grid dependence and polynomial interpolation typical of traditional numerical methods. In addressing inverse problems, the NDDE framework can utilize observational data to perform precise estimation of single or multiple delay parameters, which is very important in practical mathematical modeling. The results of multiple numerical experiments have shown that NDDEs demonstrate high precision in both forward and inverse problems, proving their effectiveness and promising potential in dealing with delayed differential equation issues.
Authors: Anke Tang, Li Shen, Yong Luo, Shuai Xie, Han Hu, Lefei Zhang, Bo Du, Dacheng Tao
Abstract: Deep model training on extensive datasets is increasingly becoming cost-prohibitive, prompting the widespread adoption of deep model fusion techniques to leverage knowledge from pre-existing models. From simple weight averaging to more sophisticated methods like AdaMerging, model fusion effectively improves model performance and accelerates the development of new models. However, potential interference between parameters of individual models and the lack of interpretability in the fusion progress remain significant challenges. Existing methods often try to resolve the parameter interference issue by evaluating attributes of parameters, such as their magnitude or sign, or by parameter pruning. In this study, we begin by examining the fine-tuning of linear layers through the lens of subspace analysis and explicitly define parameter interference as an optimization problem to shed light on this subject. Subsequently, we introduce an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction, which allows for the upscaling of source models into an MoE model without extra data or further training. Our approach relies on the observation that fine-tuning mostly keeps the important parts from the pre-training, but it uses less significant or unused areas to adapt to new tasks. Also, the issue of parameter interference, which is intrinsically intractable in the original parameter space, can be managed by expanding the dimensions. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning, and we apply our method to large language models (CLIP models, Flan-T5 models, and Mistral-7B models), highlighting the adaptability and scalability of SMILE. Code is available at https://github.com/tanganke/fusion_bench
Authors: Jinxin Liu, Zao Yang
Abstract: The responses generated by Large Language Models (LLMs) can include sensitive information from individuals and organizations, leading to potential privacy leakage. This work implements Influence Functions (IFs) to trace privacy leakage back to the training data, thereby mitigating privacy concerns of Language Models (LMs). However, we notice that current IFs struggle to accurately estimate the influence of tokens with large gradient norms, potentially overestimating their influence. When tracing the most influential samples, this leads to frequently tracing back to samples with large gradient norm tokens, overshadowing the actual most influential samples even if their influences are well estimated. To address this issue, we propose Heuristically Adjusted IF (HAIF), which reduces the weight of tokens with large gradient norms, thereby significantly improving the accuracy of tracing the most influential samples. To establish easily obtained groundtruth for tracing privacy leakage, we construct two datasets, PII-E and PII-CR, representing two distinct scenarios: one with identical text in the model outputs and pre-training data, and the other where models leverage their reasoning abilities to generate text divergent from pre-training data. HAIF significantly improves tracing accuracy, enhancing it by 20.96% to 73.71% on the PII-E dataset and 3.21% to 45.93% on the PII-CR dataset, compared to the best SOTA IFs against various GPT-2 and QWen-1.5 models. HAIF also outperforms SOTA IFs on real-world pretraining data CLUECorpus2020, demonstrating strong robustness regardless prompt and response lengths.
Authors: Yuqing Zhao, Divya Saxena, Jiannong Cao, Xiaoyun Liu, Changlin Song
Abstract: In continual learning (CL), model growth enhances adaptability over new data, improving knowledge retention for more tasks. However, improper model growth can lead to severe degradation of previously learned knowledge, an issue we name as growth-induced forgetting (GIFt), especially in task-agnostic CL using entire grown model for inference. Existing works, despite adopting model growth and random initialization for better adaptability, often fail to recognize the presence of GIFt caused by improper model growth. This oversight limits comprehensive control of forgetting and hinders full utilization of model growth. We are the first in CL to identify this issue and conduct an in-depth study on root cause of GIFt, where layer expansion stands out among model growth strategies, widening layers without affecting model functionality. Yet, direct adoption of layer expansion presents challenges. It lacks data-driven control and initialization of expanded parameters to balance adaptability and knowledge retention. This paper presents a novel SparseGrow approach to overcome the issue of GIFt while enhancing adaptability over new data. SparseGrow employs data-driven sparse layer expansion to control efficient parameter usage during growth, reducing GIFt from excessive growth and functionality changes. It also combines sparse growth with on-data initialization at training late-stage to create partially 0-valued expansions that fit learned distribution, enhancing retention and adaptability. To further minimize forgetting, freezing is applied by calculating the sparse mask, allowing data-driven preservation of important parameters. Through experiments across datasets with various settings, cases and task numbers, we demonstrate the necessity of layer expansion and showcase the effectiveness of SparseGrow in overcoming GIFt, highlighting its adaptability and knowledge retention for incremental tasks.
Authors: Jianxiang Zhou, Erdong Liu, Wei Chen, Siru Zhong, Yuxuan Liang
Abstract: Traffic forecasting has emerged as a crucial research area in the development of smart cities. Although various neural networks with intricate architectures have been developed to address this problem, they still face two key challenges: i) Recent advancements in network designs for modeling spatio-temporal correlations are starting to see diminishing returns in performance enhancements. ii) Additionally, most models do not account for the spatio-temporal heterogeneity inherent in traffic data, i.e., traffic distribution varies significantly across different regions and traffic flow patterns fluctuate across various time slots. To tackle these challenges, we introduce the Spatio-Temporal Graph Transformer (STGormer), which effectively integrates attribute and structure information inherent in traffic data for learning spatio-temporal correlations, and a mixture-of-experts module for capturing heterogeneity along spaital and temporal axes. Specifically, we design two straightforward yet effective spatial encoding methods based on the graph structure and integrate time position encoding into the vanilla transformer to capture spatio-temporal traffic patterns. Additionally, a mixture-of-experts enhanced feedforward neural network (FNN) module adaptively assigns suitable expert layers to distinct patterns via a spatio-temporal gating network, further improving overall prediction accuracy. Experiments on real-world traffic datasets demonstrate that STGormer achieves state-of-the-art performance.
Authors: Kai-liang Lu, Yu-meng Su, Zhuo Bi, Cheng Qiu, Wen-jun Zhang
Abstract: This paper compared physics-informed neural network (PINN), conventional neural network (NN) and traditional numerical discretization methods on solving differential equations (DEs) through literature investigation and experimental validation. We focused on the soft-constrained PINN approach and formalized its mathematical framework and computational flow for solving Ordinary DEs and Partial DEs (ODEs/PDEs). The working mechanism and its accuracy and efficiency were experimentally verified by solving typical linear and non-linear (e.g., Primer, Van der Pol, Duffing) oscillator ODEs. We demonstrate that the DeepXDE-based implementation of PINN is not only light code and efficient in training, but also flexible across CPU/GPU platforms. PINN greatly reduces the need for labeled data: when the nonlinearity of the ODE is weak, a very small amount of supervised training data plus a few unsupervised collocation points are sufficient to predict the solution; in the minimalist case, only one or two training points (with initial values) are needed for first- or second-order ODEs, respectively. We also find that, with the aid of collocation points and the use of physical information, PINN has the ability to extrapolate data outside the time domain of the training set, and especially is robust to noisy data, thus with enhanced generalization capabilities. Training is accelerated when the gains obtained along with the reduction in the amount of data outweigh the delay caused by the increase in the loss function terms. The soft-constrained PINN can easily impose a physical law (e.g., conservation of energy) constraint by adding a regularization term to the total loss function, thus improving the solution performance to ODEs that obey this physical law. Furthermore, PINN can also be used for stiff ODEs, PDEs, and other types of DEs, and is becoming a favorable catalyst for the era of Digital Twins.
Authors: Arjun Shah, Varun Viswanath, Kashish Gandhi, Dr. Nilesh Madhukar Patil
Abstract: This paper addresses the pressing need for an accurate solar energy prediction model, which is crucial for efficient grid integration. We explore the influence of the Air Quality Index and weather features on solar energy generation, employing advanced Machine Learning and Deep Learning techniques. Our methodology uses time series modeling and makes novel use of power transform normalization and zero-inflated modeling. Various Machine Learning algorithms and Conv2D Long Short-Term Memory model based Deep Learning models are applied to these transformations for precise predictions. Results underscore the effectiveness of our approach, demonstrating enhanced prediction accuracy with Air Quality Index and weather features. We achieved a 0.9691 $R^2$ Score, 0.18 MAE, 0.10 RMSE with Conv2D Long Short-Term Memory model, showcasing the power transform technique's innovation in enhancing time series forecasting for solar energy generation. Such results help our research contribute valuable insights to the synergy between Air Quality Index, weather features, and Deep Learning techniques for solar energy prediction.
Authors: Deanna Needell, Aaron A. Nelson, Rayan Saab, Palina Salanevich, Olov Schavemaker
Abstract: The learning speed of feed-forward neural networks is notoriously slow and has presented a bottleneck in deep learning applications for several decades. For instance, gradient-based learning algorithms, which are used extensively to train neural networks, tend to work slowly when all of the network parameters must be iteratively tuned. To counter this, both researchers and practitioners have tried introducing randomness to reduce the learning requirement. Based on the original construction of Igelnik and Pao, single layer neural-networks with random input-to-hidden layer weights and biases have seen success in practice, but the necessary theoretical justification is lacking. In this paper, we begin to fill this theoretical gap. We provide a (corrected) rigorous proof that the Igelnik and Pao construction is a universal approximator for continuous functions on compact domains, with approximation error decaying asymptotically like $O(1/\sqrt{n})$ for the number $n$ of network nodes. We then extend this result to the non-asymptotic setting, proving that one can achieve any desired approximation error with high probability provided $n$ is sufficiently large. We further adapt this randomized neural network architecture to approximate functions on smooth, compact submanifolds of Euclidean space, providing theoretical guarantees in both the asymptotic and non-asymptotic forms. Finally, we illustrate our results on manifolds with numerical experiments.
Authors: Sihan Zeng, Thinh T. Doan, Justin Romberg
Abstract: We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying optimization variable. These time-varying samples make gradient directions in our update biased and dependent, which can potentially lead to the divergence of the iterates. In our two-time-scale approach, one scale is to estimate the true gradient from these samples, which is then used to update the estimate of the optimal solution. While these two iterates are implemented simultaneously, the former is updated "faster" than the latter. Our first contribution is to characterize the finite-time complexity of the proposed two-time-scale stochastic gradient method. In particular, we provide explicit formulas for the convergence rates of this method under different structural assumptions, namely, strong convexity, PL condition, and general non-convexity. We apply our framework to various policy optimization problems. First, we look at the infinite-horizon average-reward MDP with finite state and action spaces and derive a convergence rate of $O(k^{-2/5})$ for the online actor-critic algorithm under function approximation, which recovers the best known rate derived specifically for this problem. Second, we study the linear-quadratic regulator and show that an online actor-critic method converges with rate $O(k^{-2/3})$. Third, we use the actor-critic algorithm to solve the policy optimization problem in an entropy regularized Markov decision process, where we also establish a convergence of $O(k^{-2/3})$. The results we derive for both the second and third problem are novel and previously unknown in the literature. Finally, we briefly present the application of our framework to gradient-based policy evaluation algorithms in reinforcement learning.
Authors: Jingqi Li, Donggun Lee, Somayeh Sojoudi, Claire J. Tomlin
Abstract: In this paper, we consider the infinite-horizon reach-avoid zero-sum game problem, where the goal is to find a set in the state space, referred to as the reach-avoid set, such that the system starting at a state therein could be controlled to reach a given target set without violating constraints under the worst-case disturbance. We address this problem by designing a new value function with a contracting Bellman backup, where the super-zero level set, i.e., the set of states where the value function is evaluated to be non-negative, recovers the reach-avoid set. Building upon this, we prove that the proposed method can be adapted to compute the viability kernel, or the set of states which could be controlled to satisfy given constraints, and the backward reachable set, or the set of states that could be driven towards a given target set. Finally, we propose to alleviate the curse of dimensionality issue in high-dimensional problems by extending Conservative Q-Learning, a deep reinforcement learning technique, to learn a value function such that the super-zero level set of the learned value function serves as a (conservative) approximation to the reach-avoid set. Our theoretical and empirical results suggest that the proposed method could learn reliably the reach-avoid set and the optimal control policy even with neural network approximation.
Authors: Matthias Rottmann, Marco Reese
Abstract: In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and requires plenty of human labor. In particular, review processes are time consuming and label errors can easily be overlooked by humans. The consequences are biased benchmarks and in extreme cases also performance degradation of deep neural networks (DNNs) trained on such datasets. DNNs for semantic segmentation yield pixel-wise predictions, which makes detection of label errors via uncertainty quantification a complex task. Uncertainty is particularly pronounced at the transitions between connected components of the prediction. By lifting the consideration of uncertainty to the level of predicted components, we enable the usage of DNNs together with component-level uncertainty quantification for the detection of label errors. We present a principled approach to benchmarking the task of label error detection by dropping labels from the Cityscapes dataset as well from a dataset extracted from the CARLA driving simulator, where in the latter case we have the labels under control. Our experiments show that our approach is able to detect the vast majority of label errors while controlling the number of false label error detections. Furthermore, we apply our method to semantic segmentation datasets frequently used by the computer vision community and present a collection of label errors along with sample statistics.
Authors: Hugo Freeman
Abstract: This paper studies a linear and additively separable model for multidimensional panel data of three or more dimensions with unobserved interactive fixed effects. Two approaches are considered to account for these unobserved interactive fixed-effects when estimating coefficients on the observed covariates. First, the model is embedded within the standard two dimensional panel framework and restrictions are formed under which the factor structure methods in Bai (2009) lead to consistent estimation of model parameters, but at slow rates of convergence. The second approach develops a kernel weighted fixed-effects method that is more robust to the multidimensional nature of the problem and can achieve the parametric rate of consistency under certain conditions. Theoretical results and simulations show some benefits to standard two-dimensional panel methods when the structure of the interactive fixed-effect term is known, but also highlight how the kernel weighted method performs well without knowledge of this structure. The methods are implemented to estimate the demand elasticity for beer.
Authors: Michael Drolet, Joseph Campbell, Heni Ben Amor
Abstract: We introduce an imitation learning-based physical human-robot interaction algorithm capable of predicting appropriate robot responses in complex interactions involving a superposition of multiple interactions. Our proposed algorithm, Blending Bayesian Interaction Primitives (B-BIP) allows us to achieve responsive interactions in complex hugging scenarios, capable of reciprocating and adapting to a hugs motion and timing. We show that this algorithm is a generalization of prior work, for which the original formulation reduces to the particular case of a single interaction, and evaluate our method through both an extensive user study and empirical experiments. Our algorithm yields significantly better quantitative prediction error and more-favorable participant responses with respect to accuracy, responsiveness, and timing, when compared to existing state-of-the-art methods.
Authors: Lei Li, Jian-Guo Liu, Yuliang Wang
Abstract: We consider the geometric ergodicity of the Stochastic Gradient Langevin Dynamics (SGLD) algorithm under nonconvexity settings. Via the technique of reflection coupling, we prove the Wasserstein contraction of SGLD when the target distribution is log-concave only outside some compact set. The time discretization and the minibatch in SGLD introduce several difficulties when applying the reflection coupling, which are addressed by a series of careful estimates of conditional expectations. As a direct corollary, the SGLD with constant step size has an invariant distribution and we are able to obtain its geometric ergodicity in terms of $W_1$ distance. The generalization to non-gradient drifts is also included.
Authors: Xiaoyuan Ma, Jordan Rodu
Abstract: The Baum-Welch (B-W) algorithm is the most widely accepted method for inferring hidden Markov models (HMM). However, it is prone to getting stuck in local optima, and can be too slow for many real-time applications. Spectral learning of HMMs (SHMM), based on the method of moments (MOM) has been proposed in the literature to overcome these obstacles. Despite its promises, asymptotic theory for SHMM has been elusive, and the long-run performance of SHMM can degrade due to unchecked propagation of error. In this paper, we (1) provide an asymptotic distribution for the approximate error of the likelihood estimated by SHMM, (2) propose a novel algorithm called projected SHMM (PSHMM) that mitigates the problem of error propagation, and (3) develop online learning variants of both SHMM and PSHMM that accommodate potential nonstationarity. We compare the performance of SHMM with PSHMM and estimation through the B-W algorithm on both simulated data and data from real world applications, and find that PSHMM not only retains the computational advantages of SHMM, but also provides more robust estimation and forecasting.
Authors: Rohitash Chandra, Joshua Simmons
Abstract: Bayesian inference provides a methodology for parameter estimation and uncertainty quantification in machine learning and deep learning methods. Variational inference and Markov Chain Monte-Carlo (MCMC) sampling methods are used to implement Bayesian inference. In the past three decades, MCMC sampling methods have faced some challenges in being adapted to larger models (such as in deep learning) and big data problems. Advanced proposal distributions that incorporate gradients, such as a Langevin proposal distribution, provide a means to address some of the limitations of MCMC sampling for Bayesian neural networks. Furthermore, MCMC methods have typically been constrained to statisticians and currently not well-known among deep learning researchers. We present a tutorial for MCMC methods that covers simple Bayesian linear and logistic models, and Bayesian neural networks. The aim of this tutorial is to bridge the gap between theory and implementation via coding, given a general sparsity of libraries and tutorials to this end. This tutorial provides code in Python with data and instructions that enable their use and extension. We provide results for some benchmark problems showing the strengths and weaknesses of implementing the respective Bayesian models via MCMC. We highlight the challenges in sampling multi-modal posterior distributions for the case of Bayesian neural networks and the need for further improvement of convergence diagnosis methods.
Authors: Kirsten Fischer, David Dahmen, Moritz Helias
Abstract: Residual networks have significantly better trainability and thus performance than feed-forward networks at large depth. Introducing skip connections facilitates signal propagation to deeper layers. In addition, previous works found that adding a scaling parameter for the residual branch further improves generalization performance. While they empirically identified a particularly beneficial range of values for this scaling parameter, the associated performance improvement and its universality across network hyperparameters yet need to be understood. For feed-forward networks, finite-size theories have led to important insights with regard to signal propagation and hyperparameter tuning. We here derive a systematic finite-size field theory for residual networks to study signal propagation and its dependence on the scaling for the residual branch. We derive analytical expressions for the response function, a measure for the network's sensitivity to inputs, and show that for deep networks the empirically found values for the scaling parameter lie within the range of maximal sensitivity. Furthermore, we obtain an analytical expression for the optimal scaling parameter that depends only weakly on other network hyperparameters, such as the weight variance, thereby explaining its universality across hyperparameters. Overall, this work provides a theoretical framework to study ResNets at finite size.
Authors: Irewola Aaron Oludehinwa, Andrei Velichko, Maksim Belyaev, Olasunkanmi I. Olusola
Abstract: This study proposes an enhancement to the existing method for detecting Solar Active Regions (ARs). Our technique tracks ARs using images from the Atmospheric Imaging Assembly (AIA) of NASA's Solar Dynamics Observatory (SDO). It involves a 2D circular kernel time series transformation, combined with Statistical and Entropy measures, and a Machine Learning (ML) approach. The technique transforms the circular area around pixels in the SDO AIA images into one-dimensional time series (1-DTS). Statistical measures (Median Value, Xmed; 95th Percentile, X95) and Entropy measures (Distribution Entropy, DisEn; Fuzzy Entropy, FuzzyEn) are used as feature selection methods (FSM 1), alongside a method applying 1-DTS elements directly as features (FSM 2). The ML algorithm classifies these series into three categories: no Active Region (nARs type 1, class 1), non-flaring Regions outside active regions with brightness (nARs type 2, class 2), and flaring Active Regions (ARs, class 3). The ML model achieves a classification accuracy of 0.900 and 0.914 for Entropy and Statistical measures, respectively. Notably, Fuzzy Entropy shows the highest classification accuracy (AKF=0.895), surpassing DisEn (AKF=0.738), X95 (AKF=0.873), and Xmed (AKF=0.840). This indicates the high effectiveness of Entropy and Statistical measures for AR detection in SDO AIA images. FSM 2 captures a similar distribution of flaring AR activities as FSM 1. Additionally, we introduce a generalizing characteristic of AR activities (GSA), finding a direct agreement between increased AR activities and higher GSA values. The Python code implementation of the proposed method is available in supplementary material.
Authors: Brando Miranda, Alycia Lee, Sudharsan Sundar, Allison Casasola, Sanmi Koyejo
Abstract: Current trends in pre-training Large Language Models (LLMs) primarily focus on the scaling of model and dataset size. While the quality of pre-training data is considered an important factor for training powerful LLMs, it remains a nebulous concept that has not been rigorously characterized. To this end, we propose a formalization of one key aspect of data quality -- measuring the variability of natural language data -- specifically via a measure we call the diversity coefficient. Our empirical analysis shows that the proposed diversity coefficient aligns with the intuitive properties of diversity and variability, e.g., it increases as the number of latent concepts increases. Then, we measure the diversity coefficient of publicly available pre-training datasets and demonstrate that their formal diversity is high compared to theoretical lower and upper bounds. Finally, we conduct a comprehensive set of controlled interventional experiments with GPT-2 and LLaMAv2 that demonstrate the diversity coefficient of pre-training data characterizes useful aspects of downstream model evaluation performance -- totaling 44 models of various sizes (51M to 7B parameters). We conclude that our formal notion of diversity is an important aspect of data quality that captures variability and causally leads to improved evaluation performance.
Authors: Nicolas Garcia Trillos, Melanie Weber
Abstract: Let $M$ denote a low-dimensional manifold embedded in Euclidean space and let ${X}= \{ x_1, \dots, x_n \}$ be a collection of points uniformly sampled from it. We study the relationship between the curvature of a random geometric graph built from ${X}$ and the curvature of the manifold $M$ via continuum limits of Ollivier's discrete Ricci curvature. We prove pointwise, non-asymptotic consistency results and also show that if $M$ has Ricci curvature bounded from below by a positive constant, then the random geometric graph will inherit this global structural property with high probability. We discuss applications of the global discrete curvature bounds to contraction properties of heat kernels on graphs, as well as implications for manifold learning from data clouds. In particular, we show that our consistency results allow for estimating the intrinsic curvature of a manifold by first estimating concrete extrinsic quantities.
Authors: Shunit Truzman, Guy Revach, Nir Shlezinger, Itzik Klein
Abstract: State estimation of dynamical systems from noisy observations is a fundamental task in many applications. It is commonly addressed using the linear Kalman filter (KF), whose performance can significantly degrade in the presence of outliers in the observations, due to the sensitivity of its convex quadratic objective function. To mitigate such behavior, outlier detection algorithms can be applied. In this work, we propose a parameter-free algorithm which mitigates the harmful effect of outliers while requiring only a short iterative process of the standard update step of the KF. To that end, we model each potential outlier as a normal process with unknown variance and apply online estimation through either expectation maximization or alternating maximization algorithms. Simulations and field experiment evaluations demonstrate competitive performance of our method, showcasing its robustness to outliers in filtering scenarios compared to alternative algorithms.
Authors: Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Zhuoer Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, Jie Tang
Abstract: Alignment has become a critical step for instruction-tuned Large Language Models (LLMs) to become helpful assistants. However, the effective evaluation of alignment for emerging Chinese LLMs is still largely unexplored. To fill in this gap, we introduce AlignBench, a comprehensive multi-dimensional benchmark for evaluating LLMs' alignment in Chinese. We design a human-in-the-loop data curation pipeline, containing eight main categories, 683 real-scenario rooted queries and corresponding human verified references. To ensure the correctness of references, each knowledge-intensive query is accompanied with evidences collected from reliable web sources (including URLs and quotations) by our annotators. For automatic evaluation, our benchmark employs a rule-calibrated multi-dimensional LLM-as-Judge~\cite{zheng2023judging} approach with Chain-of-Thought to generate explanations and final ratings, ensuring high reliability and interpretability. All evaluation code, data, and LLM generations are available at \url{https://github.com/THUDM/AlignBench}. Since its release, AlignBench has been adopted by top (Chinese) LLMs for evaluating their alignment capabilities in Chinese, including ChatGLM, Qwen, DeepSeek, Yi, Baichuan, and Abab.
Authors: Wouter A. C. van Amsterdam, Nan van Geloven, Jesse H. Krijthe, Rajesh Ranganath, Giovanni Cin\'a
Abstract: Prediction models are popular in medical research and practice. By predicting an outcome of interest for specific patients, these models may help inform difficult treatment decisions, and are often hailed as the poster children for personalized, data-driven healthcare. We show however, that using prediction models for decision making can lead to harmful decisions, even when the predictions exhibit good discrimination after deployment. These models are harmful self-fulfilling prophecies: their deployment harms a group of patients but the worse outcome of these patients does not invalidate the predictive power of the model. Our main result is a formal characterization of a set of such prediction models. Next we show that models that are well calibrated before and after deployment are useless for decision making as they made no change in the data distribution. These results point to the need to revise standard practices for validation, deployment and evaluation of prediction models that are used in medical decisions.
Authors: Qian Wang, Yaoyao Liu, Hefei Ling, Yingwei Li, Qihao Liu, Ping Li, Jiazhong Chen, Alan Yuille, Ning Yu
Abstract: In response to the rapidly evolving nature of adversarial attacks against visual classifiers on a monthly basis, numerous defenses have been proposed to generalize against as many known attacks as possible. However, designing a defense method that generalizes to all types of attacks is not realistic because the environment in which defense systems operate is dynamic and comprises various unique attacks that emerge as time goes on. A well-matched approach to the dynamic environment lies in a defense system that continuously collects adversarial data online to quickly improve itself. Therefore, we put forward a practical defense deployment against a challenging threat model and propose, for the first time, the Continual Adversarial Defense (CAD) framework that adapts to attack sequences under four principles: (1) continual adaptation to new attacks without catastrophic forgetting, (2) few-shot adaptation, (3) memory-efficient adaptation, and (4) high accuracy on both clean and adversarial data. We explore and integrate cutting-edge continual learning, few-shot learning, and ensemble learning techniques to qualify the principles. Extensive experiments validate the effectiveness of our approach against multiple stages of modern adversarial attacks and demonstrate significant improvements over numerous baseline methods. In particular, CAD is capable of quickly adapting with minimal budget and a low cost of defense failure while maintaining good performance against previous attacks. Our research sheds light on a brand-new paradigm for continual defense adaptation against dynamic and evolving attacks.
Authors: Zhaoxi Mu, Xinyu Yang, Sining Sun, Qing Yang
Abstract: Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the reference speech, which are irrelevant to speaker identity, can lead to speaker confusion within the speech extraction network. To overcome this challenge, we propose a self-supervised disentangled representation learning method. Our approach tackles this issue through a two-phase process, utilizing a reference speech encoding network and a global information disentanglement network to gradually disentangle the speaker identity information from other irrelevant factors. We exclusively employ the disentangled speaker identity information to guide the speech extraction network. Moreover, we introduce the adaptive modulation Transformer to ensure that the acoustic representation of the mixed signal remains undisturbed by the speaker embeddings. This component incorporates speaker embeddings as conditional information, facilitating natural and efficient guidance for the speech extraction network. Experimental results substantiate the effectiveness of our meticulously crafted approach, showcasing a substantial reduction in the likelihood of speaker confusion.
Authors: Ziyun Li, Christoph Meinel, Haojin Yang
Abstract: Generalized Class Discovery (GCD) plays a pivotal role in discerning both known and unknown categories from unlabeled datasets by harnessing the insights derived from a labeled set comprising recognized classes. A significant limitation in prevailing GCD methods is their presumption of an equitably distributed category occurrence in unlabeled data. Contrary to this assumption, visual classes in natural environments typically exhibit a long-tailed distribution, with known or prevalent categories surfacing more frequently than their rarer counterparts. Our research endeavors to bridge this disconnect by focusing on the long-tailed Generalized Category Discovery (Long-tailed GCD) paradigm, which echoes the innate imbalances of real-world unlabeled datasets. In response to the unique challenges posed by Long-tailed GCD, we present a robust methodology anchored in two strategic regularizations: (i) a reweighting mechanism that bolsters the prominence of less-represented, tail-end categories, and (ii) a class prior constraint that aligns with the anticipated class distribution. Comprehensive experiments reveal that our proposed method surpasses previous state-of-the-art GCD methods by achieving an improvement of approximately 6 - 9% on ImageNet100 and competitive performance on CIFAR100.
Authors: Gil Goldshlager, Nilin Abrahamsen, Lin Lin
Abstract: Neural network wavefunctions optimized using the variational Monte Carlo method have been shown to produce highly accurate results for the electronic structure of atoms and small molecules, but the high cost of optimizing such wavefunctions prevents their application to larger systems. We propose the Subsampled Projected-Increment Natural Gradient Descent (SPRING) optimizer to reduce this bottleneck. SPRING combines ideas from the recently introduced minimum-step stochastic reconfiguration optimizer (MinSR) and the classical randomized Kaczmarz method for solving linear least-squares problems. We demonstrate that SPRING outperforms both MinSR and the popular Kronecker-Factored Approximate Curvature method (KFAC) across a number of small atoms and molecules, given that the learning rates of all methods are optimally tuned. For example, on the oxygen atom, SPRING attains chemical accuracy after forty thousand training iterations, whereas both MinSR and KFAC fail to do so even after one hundred thousand iterations.
Authors: Harsh Parikh, Rachael Ross, Elizabeth Stuart, Kara Rudolph
Abstract: Randomized controlled trials (RCTs) serve as the cornerstone for understanding causal effects, yet extending inferences to target populations presents challenges due to effect heterogeneity and underrepresentation. Our paper addresses the critical issue of identifying and characterizing underrepresented subgroups in RCTs, proposing a novel framework for refining target populations to improve generalizability. We introduce an optimization-based approach, Rashomon Set of Optimal Trees (ROOT), to characterize underrepresented groups. ROOT optimizes the target subpopulation distribution by minimizing the variance of the target average treatment effect estimate, ensuring more precise treatment effect estimations. Notably, ROOT generates interpretable characteristics of the underrepresented population, aiding researchers in effective communication. Our approach demonstrates improved precision and interpretability compared to alternatives, as illustrated with synthetic data experiments. We apply our methodology to extend inferences from the Starting Treatment with Agonist Replacement Therapies (START) trial -- investigating the effectiveness of medication for opioid use disorder -- to the real-world population represented by the Treatment Episode Dataset: Admissions (TEDS-A). By refining target populations using ROOT, our framework offers a systematic approach to enhance decision-making accuracy and inform future trials in diverse populations.
Authors: Yu Shang, Yu Li, Fengli Xu, Yong Li
Abstract: Large language models (LLMs) have shown impressive emergent abilities in a wide range of tasks, but the associated expensive API cost greatly limits the real application. Previous works like chain-of-thought (CoT) and tree-of-thoughts (ToT) have predominately focused on enhancing accuracy, but overlook the rapidly increasing API cost, which could be particularly problematic for open-ended real-world tasks with huge solution spaces. Motivated by the dual process theory of human cognition, we propose "Synergy of Thoughts"(SoT) to unleash the synergistic potential of hybrid LLMs with different scales for efficient reasoning. By default, SoT uses smaller-scale language models to generate multiple low-cost intuitive thoughts, which resembles the parallel intuitions produced by System 1. We then design a confidence evaluator where the intuitive thoughts are cross-evaluated and introduce a controllable threshold mechanism to decide their mutual conflict. If these intuitive thoughts exhibit conflicts, SoT will invoke the reflective reasoning of scaled-up language models to emulate the intervention of System 2, which will override the intuitive thoughts and rectify the reasoning results. This framework is model-agnostic and training-free, which can be flexibly implemented with various off-the-shelf LLMs. Experiments on six representative reasoning tasks show that SoT substantially reduces the API cost by 38.3%-75.1%, and simultaneously achieves state-of-the-art reasoning accuracy and solution diversity. Notably, the average token cost reduction on open-ended tasks reaches up to 69.1%.
Authors: Andrew Fuchs, Andrea Passarella, Marco Conti
Abstract: When humans and autonomous systems operate together as what we refer to as a hybrid team, we of course wish to ensure the team operates successfully and effectively. We refer to team members as agents. In our proposed framework, we address the case of hybrid teams in which, at any time, only one team member (the control agent) is authorized to act as control for the team. To determine the best selection of a control agent, we propose the addition of an AI manager (via Reinforcement Learning) which learns as an outside observer of the team. The manager learns a model of behavior linking observations of agent performance and the environment/world the team is operating in, and from these observations makes the most desirable selection of a control agent. We restrict the manager task by introducing a set of constraints. The manager constraints indicate acceptable team operation, so a violation occurs if the team enters a condition which is unacceptable and requires manager intervention. To ensure minimal added complexity or potential inefficiency for the team, the manager should attempt to minimize the number of times the team reaches a constraint violation and requires subsequent manager intervention. Therefore our manager is optimizing its selection of authorized agents to boost overall team performance while minimizing the frequency of manager intervention. We demonstrate our manager performance in a simulated driving scenario representing the case of a hybrid team of agents composed of a human driver and autonomous driving system. We perform experiments for our driving scenario with interfering vehicles, indicating the need for collision avoidance and proper speed control. Our results indicate a positive impact of our manager, with some cases resulting in increased team performance up to ~187% that of the best solo agent performance.
Authors: Stefana Anita, Gabriel Turinici
Abstract: Although Multi Armed Bandit (MAB) on one hand and the policy gradient approach on the other hand are among the most used frameworks of Reinforcement Learning, the theoretical properties of the policy gradient algorithm used for MAB have not been given enough attention. We investigate in this work the convergence of such a procedure for the situation when a $L2$ regularization term is present jointly with the 'softmax' parametrization. We prove convergence under appropriate technical hypotheses and test numerically the procedure including situations beyond the theoretical setting. The tests show that a time dependent regularized procedure can improve over the canonical approach especially when the initial guess is far from the solution.
Authors: Ziyang Song, Qincheng Lu, He Zhu, David Buckeridge, Yue Li
Abstract: Learning time-series representations for discriminative tasks, such as classification and regression, has been a long-standing challenge in the healthcare domain. Current pre-training methods are limited in either unidirectional next-token prediction or randomly masked token prediction. We propose a novel architecture called Bidirectional Timely Generative Pre-trained Transformer (BiTimelyGPT), which pre-trains on biosignals and longitudinal clinical records by both next-token and previous-token prediction in alternating transformer layers. This pre-training task preserves original distribution and data shapes of the time-series. Additionally, the full-rank forward and backward attention matrices exhibit more expressive representation capabilities. Using biosignals and longitudinal clinical records, BiTimelyGPT demonstrates superior performance in predicting neurological functionality, disease diagnosis, and physiological signs. By visualizing the attention heatmap, we observe that the pre-trained BiTimelyGPT can identify discriminative segments from biosignal time-series sequences, even more so after fine-tuning on the task.
Authors: Xiongri Shen, Zhenxi Song, Zhiguo Zhang
Abstract: Diagnosis of mild cognitive impairment (MCI) and subjective cognitive decline (SCD) from fMRI functional connectivity (FC) has gained popularity, but most FC-based diagnostic models are black boxes lacking casual reasoning so they contribute little to the knowledge about FC-based neural biomarkers of cognitive decline.To enhance the explainability of diagnostic models, we propose a generative counterfactual attention-guided network (GCAN), which introduces counterfactual reasoning to recognize cognitive decline-related brain regions and then uses these regions as attention maps to boost the prediction performance of diagnostic models. Furthermore, to tackle the difficulty in the generation of highly-structured and brain-atlas-constrained FC, which is essential in counterfactual reasoning, an Atlas-Aware Bidirectional Transformer (AABT) method is developed. AABT employs a bidirectional strategy to encode and decode the tokens from each network of brain atlas, thereby enhancing the generation of high-quality target label FC. In the experiments of hospital-collected and ADNI datasets, the generated attention maps closely resemble FC abnormalities in the literature on SCD and MCI. The diagnostic performance is also superior to baseline models. The code is available at https://github.com/SXR3015/GCAN
Authors: Yibin Chen, Yifu Yuan, Zeyu Zhang, Yan Zheng, Jinyi Liu, Fei Ni, Jianye Hao
Abstract: Spreadsheet manipulation is widely existing in most daily works and significantly improves working efficiency. Large language model (LLM) has been recently attempted for automatic spreadsheet manipulation but has not yet been investigated in complicated and realistic tasks where reasoning challenges exist (e.g., long horizon manipulation with multi-step reasoning and ambiguous requirements). To bridge the gap with the real-world requirements, we introduce $\textbf{SheetRM}$, a benchmark featuring long-horizon and multi-category tasks with reasoning-dependent manipulation caused by real-life challenges. To mitigate the above challenges, we further propose $\textbf{SheetAgent}$, a novel autonomous agent that utilizes the power of LLMs. SheetAgent consists of three collaborative modules: $\textit{Planner}$, $\textit{Informer}$, and $\textit{Retriever}$, achieving both advanced reasoning and accurate manipulation over spreadsheets without human interaction through iterative task reasoning and reflection. Extensive experiments demonstrate that SheetAgent delivers 20-30% pass rate improvements on multiple benchmarks over baselines, achieving enhanced precision in spreadsheet manipulation and demonstrating superior table reasoning abilities. More details and visualizations are available at https://sheetagent.github.io.
Authors: Asad Aali, Dave Van Veen, Yamin Ishraq Arefeen, Jason Hom, Christian Bluethgen, Eduardo Pontes Reis, Sergios Gatidis, Namuun Clifford, Joseph Daws, Arash S. Tehrani, Jangwon Kim, Akshay S. Chaudhari
Abstract: Brief hospital course (BHC) summaries are clinical documents that summarize a patient's hospital stay. While large language models (LLMs) depict remarkable capabilities in automating real-world tasks, their capabilities for healthcare applications such as synthesizing BHCs from clinical notes have not been shown. We introduce a novel pre-processed dataset, the MIMIC-IV-BHC, encapsulating clinical note and brief hospital course (BHC) pairs to adapt LLMs for BHC synthesis. Furthermore, we introduce a benchmark of the summarization performance of two general-purpose LLMs and three healthcare-adapted LLMs. Using clinical notes as input, we apply prompting-based (using in-context learning) and fine-tuning-based adaptation strategies to three open-source LLMs (Clinical-T5-Large, Llama2-13B, FLAN-UL2) and two proprietary LLMs (GPT-3.5, GPT-4). We evaluate these LLMs across multiple context-length inputs using natural language similarity metrics. We further conduct a clinical study with five clinicians, comparing clinician-written and LLM-generated BHCs across 30 samples, focusing on their potential to enhance clinical decision-making through improved summary quality. We observe that the Llama2-13B fine-tuned LLM outperforms other domain-adapted models given quantitative evaluation metrics of BLEU and BERT-Score. GPT-4 with in-context learning shows more robustness to increasing context lengths of clinical note inputs than fine-tuned Llama2-13B. Despite comparable quantitative metrics, the reader study depicts a significant preference for summaries generated by GPT-4 with in-context learning compared to both Llama2-13B fine-tuned summaries and the original summaries, highlighting the need for qualitative clinical evaluation.
Authors: John Martinsson, Olof Mogren, Maria Sandsten, Tuomas Virtanen
Abstract: We propose an adaptive change point detection method (A-CPD) for machine guided weak label annotation of audio recording segments. The goal is to maximize the amount of information gained about the temporal activations of the target sounds. For each unlabeled audio recording, we use a prediction model to derive a probability curve used to guide annotation. The prediction model is initially pre-trained on available annotated sound event data with classes that are disjoint from the classes in the unlabeled dataset. The prediction model then gradually adapts to the annotations provided by the annotator in an active learning loop. We derive query segments to guide the weak label annotator towards strong labels, using change point detection on these probabilities. We show that it is possible to derive strong labels of high quality with a limited annotation budget, and show favorable results for A-CPD when compared to two baseline query segment strategies.
Authors: Xuanlei Zhao, Shenggan Cheng, Chang Chen, Zangwei Zheng, Ziming Liu, Zheming Yang, Yang You
Abstract: Scaling multi-dimensional transformers to long sequences is indispensable across various domains. However, the challenges of large memory requirements and slow speeds of such sequences necessitate sequence parallelism. All existing approaches fall under the category of embedded sequence parallelism, which are limited to shard along a single sequence dimension, thereby introducing significant communication overhead. However, the nature of multi-dimensional transformers involves independent calculations across multiple sequence dimensions. To this end, we propose Dynamic Sequence Parallelism (DSP) as a novel abstraction of sequence parallelism. DSP dynamically switches the parallel dimension among all sequences according to the computation stage with efficient resharding strategy. DSP offers significant reductions in communication costs, adaptability across modules, and ease of implementation with minimal constraints. Experimental evaluations demonstrate DSP's superiority over state-of-the-art embedded sequence parallelism methods by remarkable throughput improvements ranging from 32.2% to 10x, with less than 25% communication volume.
Authors: Sarthak Kumar Maharana, Baoming Zhang, Yunhui Guo
Abstract: Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continual test-time adaptation (CTTA) directly adjusts a pre-trained source discriminative model to these changing domains. A highly effective CTTA method involves applying layer-wise adaptive learning rates for selectively adapting pre-trained layers. However, it suffers from the poor estimation of domain shift and the inaccuracies arising from the pseudo-labels. This work aims to overcome these limitations by identifying layers for adaptation via quantifying model prediction uncertainty without relying on pseudo-labels. We utilize the magnitude of gradients as a metric, calculated by backpropagating the KL divergence between the softmax output and a uniform distribution, to select layers for further adaptation. Subsequently, for the parameters exclusively belonging to these selected layers, with the remaining ones frozen, we evaluate their sensitivity to approximate the domain shift and adjust their learning rates accordingly. We conduct extensive image classification experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C, demonstrating the superior efficacy of our method compared to prior approaches.
Authors: Justin Kay, Timm Haucke, Suzanne Stathatos, Siqi Deng, Erik Young, Pietro Perona, Sara Beery, Grant Van Horn
Abstract: Object detectors often perform poorly on data that differs from their training set. Domain adaptive object detection (DAOD) methods have recently demonstrated strong results on addressing this challenge. Unfortunately, we identify systemic benchmarking pitfalls that call past results into question and hamper further progress: (a) Overestimation of performance due to underpowered baselines, (b) Inconsistent implementation practices preventing transparent comparisons of methods, and (c) Lack of generality due to outdated backbones and lack of diversity in benchmarks. We address these problems by introducing: (1) A unified benchmarking and implementation framework, Align and Distill (ALDI), enabling comparison of DAOD methods and supporting future development, (2) A fair and modern training and evaluation protocol for DAOD that addresses benchmarking pitfalls, (3) A new DAOD benchmark dataset, CFC-DAOD, enabling evaluation on diverse real-world data, and (4) A new method, ALDI++, that achieves state-of-the-art results by a large margin. ALDI++ outperforms the previous state-of-the-art by +3.5 AP50 on Cityscapes to Foggy Cityscapes, +5.7 AP50 on Sim10k to Cityscapes (where ours is the only method to outperform a fair baseline), and +0.6 AP50 on CFC Kenai to Channel. Our framework, dataset, and state-of-the-art method offer a critical reset for DAOD and provide a strong foundation for future research. Code and data are available: https://github.com/justinkay/aldi and https://github.com/visipedia/caltech-fish-counting.
URLs: https://github.com/justinkay/aldi, https://github.com/visipedia/caltech-fish-counting.
Authors: Sayanton V. Dibbo, Adam Breuer, Juston Moore, Michael Teti
Abstract: Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private and potentially sensitive training data by repeatedly querying the network. In this work, we develop a novel network architecture that leverages sparse-coding layers to obtain superior robustness to this class of attacks. Three decades of computer science research has studied sparse coding in the context of image denoising, object recognition, and adversarial misclassification settings, but to the best of our knowledge, its connection to state-of-the-art privacy vulnerabilities remains unstudied. In this work, we hypothesize that sparse coding architectures suggest an advantageous means to defend against model inversion attacks because they allow us to control the amount of irrelevant private information encoded by a network in a manner that is known to have little effect on classification accuracy. Specifically, compared to networks trained with a variety of state-of-the-art defenses, our sparse-coding architectures maintain comparable or higher classification accuracy while degrading state-of-the-art training data reconstructions by factors of 1.1 to 18.3 across a variety of reconstruction quality metrics (PSNR, SSIM, FID). This performance advantage holds across 5 datasets ranging from CelebA faces to medical images and CIFAR-10, and across various state-of-the-art SGD-based and GAN-based inversion attacks, including Plug-&-Play attacks. We provide a cluster-ready PyTorch codebase to promote research and standardize defense evaluations.
Authors: Young Seok Jeon, Hongfei Yang, Huazhu Fu, Mengling Feng
Abstract: Imposing key anatomical features, such as the number of organs, their shapes and relative positions, is crucial for building a robust multi-organ segmentation model. Current attempts to incorporate anatomical features include broadening the effective receptive field (ERF) size with data-intensive modules, or introducing anatomical constraints that scales poorly to multi-organ segmentation. We introduce a novel architecture called the Anatomy-Informed Cascaded Segmentation Network (AIC-Net). AIC-Net incorporates a learnable input termed "Anatomical Prior", which can be adapted to patient-specific anatomy using a differentiable spatial deformation. The deformed prior later guides decoder layers towards more anatomy-informed predictions. We repeat this process at a local patch level to enhance the representation of intricate objects, resulting in a cascaded network structure. AIC-Net is a general method that enhances any existing segmentation models to be more anatomy-aware. We have validated the performance of AIC-Net, with various backbones, on two multi-organ segmentation tasks: abdominal organs and vertebrae. For each respective task, our benchmarks demonstrate improved dice score and Hausdorff distance.
Authors: Yangqiaoyu Zhou, Haokun Liu, Tejes Srivastava, Hongyuan Mei, Chenhao Tan
Abstract: Effective generation of novel hypotheses is instrumental to scientific progress. So far, researchers have been the main powerhouse behind hypothesis generation by painstaking data analysis and thinking (also known as the Eureka moment). In this paper, we examine the potential of large language models (LLMs) to generate hypotheses. We focus on hypothesis generation based on data (i.e., labeled examples). To enable LLMs to handle arbitrarily long contexts, we generate initial hypotheses from a small number of examples and then update them iteratively to improve the quality of hypotheses. Inspired by multi-armed bandits, we design a reward function to inform the exploitation-exploration tradeoff in the update process. Our algorithm is able to generate hypotheses that enable much better predictive performance than few-shot prompting in classification tasks, improving accuracy by 31.7% on a synthetic dataset and by 13.9%, 3.3% and, 24.9% on three real-world datasets. We also outperform supervised learning by 12.8% and 11.2% on two challenging real-world datasets. Furthermore, we find that the generated hypotheses not only corroborate human-verified theories but also uncover new insights for the tasks.
Authors: Ali Beikmohammadi, Sarit Khirirat, Sindri Magn\'usson
Abstract: Reinforcement learning has recently gained unprecedented popularity, yet it still grapples with sample inefficiency. Addressing this challenge, federated reinforcement learning (FedRL) has emerged, wherein agents collaboratively learn a single policy by aggregating local estimations. However, this aggregation step incurs significant communication costs. In this paper, we propose CompFedRL, a communication-efficient FedRL approach incorporating both \textit{periodic aggregation} and (direct/error-feedback) compression mechanisms. Specifically, we consider compressed federated $Q$-learning with a generative model setup, where a central server learns an optimal $Q$-function by periodically aggregating compressed $Q$-estimates from local agents. For the first time, we characterize the impact of these two mechanisms (which have remained elusive) by providing a finite-time analysis of our algorithm, demonstrating strong convergence behaviors when utilizing either direct or error-feedback compression. Our bounds indicate improved solution accuracy concerning the number of agents and other federated hyperparameters while simultaneously reducing communication costs. To corroborate our theory, we also conduct in-depth numerical experiments to verify our findings, considering Top-$K$ and Sparsified-$K$ sparsification operators.
Authors: Juan L. Gamella, Jonas Peters, Peter B\"uhlmann
Abstract: In some fields of AI, machine learning and statistics, the validation of new methods and algorithms is often hindered by the scarcity of suitable real-world datasets. Researchers must often turn to simulated data, which yields limited information about the applicability of the proposed methods to real problems. As a step forward, we have constructed two devices that allow us to quickly and inexpensively produce large datasets from non-trivial but well-understood physical systems. The devices, which we call causal chambers, are computer-controlled laboratories that allow us to manipulate and measure an array of variables from these physical systems, providing a rich testbed for algorithms from a variety of fields. We illustrate potential applications through a series of case studies in fields such as causal discovery, out-of-distribution generalization, change point detection, independent component analysis, and symbolic regression. For applications to causal inference, the chambers allow us to carefully perform interventions. We also provide and empirically validate a causal model of each chamber, which can be used as ground truth for different tasks. All hardware and software is made open source, and the datasets are publicly available at causalchamber.org or through the Python package causalchamber.
Authors: Haniyeh Ehsani Oskouie, Mohammad-Shahram Moin, Shohreh Kasaei
Abstract: Deep neural networks have made significant advancements in accurately estimating scene flow using point clouds, which is vital for many applications like video analysis, action recognition, and navigation. The robustness of these techniques, however, remains a concern, particularly in the face of adversarial attacks that have been proven to deceive state-of-the-art deep neural networks in many domains. Surprisingly, the robustness of scene flow networks against such attacks has not been thoroughly investigated. To address this problem, the proposed approach aims to bridge this gap by introducing adversarial white-box attacks specifically tailored for scene flow networks. Experimental results show that the generated adversarial examples obtain up to 33.7 relative degradation in average end-point error on the KITTI and FlyingThings3D datasets. The study also reveals the significant impact that attacks targeting point clouds in only one dimension or color channel have on average end-point error. Analyzing the success and failure of these attacks on the scene flow networks and their 2D optical flow network variants shows a higher vulnerability for the optical flow networks. Code is available at https://github.com/aheldis/Attack-on-Scene-Flow-using-Point-Clouds.git.
URLs: https://github.com/aheldis/Attack-on-Scene-Flow-using-Point-Clouds.git.
Authors: Xiaowei Chen, Hong Li, Yufan Lu, Rui Zhou
Abstract: This paper explores the implications of using machine learning models in the pricing of catastrophe (CAT) bonds. By integrating advanced machine learning techniques, our approach uncovers nonlinear relationships and complex interactions between key risk factors and CAT bond spreads -- dynamics that are often overlooked by traditional linear regression models. Using primary market CAT bond transaction records between January 1999 and March 2021, our findings demonstrate that machine learning models not only enhance the accuracy of CAT bond pricing but also provide a deeper understanding of how various risk factors interact and influence bond prices in a nonlinear way. These findings suggest that investors and issuers can benefit from incorporating machine learning to better capture the intricate interplay between risk factors when pricing CAT bonds. The results also highlight the potential for machine learning models to refine our understanding of asset pricing in markets characterized by complex risk structures.
Authors: Yaoyiran Li, Xiang Zhai, Moustafa Alzantot, Keyi Yu, Ivan Vuli\'c, Anna Korhonen, Mohamed Hammad
Abstract: Traditional recommender systems such as matrix factorization methods have primarily focused on learning a shared dense embedding space to represent both items and user preferences. Subsequently, sequence models such as RNN, GRUs, and, recently, Transformers have emerged and excelled in the task of sequential recommendation. This task requires understanding the sequential structure present in users' historical interactions to predict the next item they may like. Building upon the success of Large Language Models (LLMs) in a variety of tasks, researchers have recently explored using LLMs that are pretrained on vast corpora of text for sequential recommendation. To use LLMs for sequential recommendation, both the history of user interactions and the model's prediction of the next item are expressed in text form. We propose CALRec, a two-stage LLM finetuning framework that finetunes a pretrained LLM in a two-tower fashion using a mixture of two contrastive losses and a language modeling loss: the LLM is first finetuned on a data mixture from multiple domains followed by another round of target domain finetuning. Our model significantly outperforms many state-of-the-art baselines (+37% in Recall@1 and +24% in NDCG@10) and our systematic ablation studies reveal that (i) both stages of finetuning are crucial, and, when combined, we achieve improved performance, and (ii) contrastive alignment is effective among the target domains explored in our experiments.
Authors: Jakob Roche
Abstract: This paper presents the detection of a periodic dimming event in the lightcurve of the G1.5IV-V type star KIC 1718360. This is based on visible-light observations conducted by both the TESS and Kepler space telescopes. Analysis of the data seems to point toward a high rotation rate in the star, with a rotational period of 2.938 days. The high variability seen within the star's lightcurve points toward classification as a rotating variable. The initial observation was made in Kepler Quarter 16 data using the One-Class SVM machine learning method. Subsequent observations by the TESS space telescope corroborated these findings. It appears that KIC 1718360 is a nearby rotating variable that appears in little to no major catalogs as such. A secondary, additional periodic dip is also present, indicating a possible exoplanetary companion.
Authors: Andres Algaba, Carmen Mazijn, Vincent Holst, Floriano Tori, Sylvia Wenmackers, Vincent Ginis
Abstract: Citation practices are crucial in shaping the structure of scientific knowledge, yet they are often influenced by contemporary norms and biases. The emergence of Large Language Models (LLMs) introduces a new dynamic to these practices. Interestingly, the characteristics and potential biases of references recommended by LLMs that entirely rely on their parametric knowledge, and not on search or retrieval-augmented generation, remain unexplored. Here, we analyze these characteristics in an experiment using a dataset from AAAI, NeurIPS, ICML, and ICLR, published after GPT-4's knowledge cut-off date. In our experiment, LLMs are tasked with suggesting scholarly references for the anonymized in-text citations within these papers. Our findings reveal a remarkable similarity between human and LLM citation patterns, but with a more pronounced high citation bias, which persists even after controlling for publication year, title length, number of authors, and venue. The results hold for both GPT-4, and the more capable models GPT-4o and Claude 3.5 where the papers are part of the training data. Additionally, we observe a large consistency between the characteristics of LLM's existing and non-existent generated references, indicating the model's internalization of citation patterns. By analyzing citation graphs, we show that the references recommended are embedded in the relevant citation context, suggesting an even deeper conceptual internalization of the citation networks. While LLMs can aid in citation generation, they may also amplify existing biases, such as the Matthew effect, and introduce new ones, potentially skewing scientific knowledge dissemination.
Authors: Qian Wang, Chen Li, Yuchen Luo, Hefei Ling, Ping Li, Jiazhong Chen, Shijuan Huang, Ning Yu
Abstract: As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural and adversarial data. Although previous detection methods achieve high performance in detecting gradient-based adversarial attacks, new attacks based on generative models with imbalanced and anisotropic noise patterns evade detection. Even worse, existing techniques either necessitate access to attack data before deploying a defense or incur a significant time cost for inference, rendering them impractical for defending against newly emerging attacks that are unseen by defenders. In this paper, we explore the proximity relationship between adversarial noise distributions and demonstrate the existence of an open covering for them. By learning to distinguish this open covering from the distribution of natural data, we can develop a detector with strong generalization capabilities against all types of adversarial attacks. Based on this insight, we heuristically propose Perturbation Forgery, which includes noise distribution perturbation, sparse mask generation, and pseudo-adversarial data production, to train an adversarial detector capable of detecting unseen gradient-based, generative-model-based, and physical adversarial attacks, while remaining agnostic to any specific models. Comprehensive experiments conducted on multiple general and facial datasets, with a wide spectrum of attacks, validate the strong generalization of our method.
Authors: Wei Li, William Bishop, Alice Li, Chris Rawles, Folawiyo Campbell-Ajala, Divya Tyamagundlu, Oriana Riva
Abstract: Autonomous agents that control computer interfaces to accomplish human tasks are emerging. Leveraging LLMs to power such agents has been of special interest, but unless fine-tuned on human-collected task demonstrations, performance is still relatively low. In this work we study whether fine-tuning alone is a viable approach for building real-world computer control agents. In particularly, we investigate how performance measured on both high and low-level tasks in domain and out of domain scales as more training data is collected. To this end we collect and release a new dataset, AndroidControl, consisting of 15,283 demonstrations of everyday tasks with Android apps. Compared to existing datasets, each AndroidControl task instance includes both high and low-level human-generated instructions, allowing us to explore the level of task complexity an agent can handle. Moreover, AndroidControl is the most diverse computer control dataset to date, including 15,283 unique tasks over 833 Android apps, thus allowing us to conduct in-depth analysis of the model performance in and out of the domain of the training data. Using the dataset, we find that when tested in domain fine-tuned models outperform zero and few-shot baselines and scale in such a way that robust performance might feasibly be obtained simply by collecting more data. Out of domain, performance scales significantly more slowly and suggests that in particular for high-level tasks, fine-tuning on more data alone may be insufficient for achieving robust out-of-domain performance.
Authors: Liuyuan Jiang, Quan Xiao, Victor M. Tenorio, Fernando Real-Rojas, Antonio G. Marques, Tianyi Chen
Abstract: Interest in bilevel optimization has grown in recent years, partially due to its applications to tackle challenging machine-learning problems. Several exciting recent works have been centered around developing efficient gradient-based algorithms that can solve bilevel optimization problems with provable guarantees. However, the existing literature mainly focuses on bilevel problems either without constraints, or featuring only simple constraints that do not couple variables across the upper and lower levels, excluding a range of complex applications. Our paper studies this challenging but less explored scenario and develops a (fully) first-order algorithm, which we term BLOCC, to tackle BiLevel Optimization problems with Coupled Constraints. We establish rigorous convergence theory for the proposed algorithm and demonstrate its effectiveness on two well-known real-world applications - hyperparameter selection in support vector machine (SVM) and infrastructure planning in transportation networks using the real data from the city of Seville.
Authors: Aydin Abadi, Yvo Desmedt
Abstract: Oblivious Transfer (OT) is a fundamental cryptographic protocol with applications in secure Multi-Party Computation, Federated Learning, and Private Set Intersection. With the advent of quantum computing, it is crucial to develop unconditionally secure core primitives like OT to ensure their continued security in the post-quantum era. Despite over four decades since OT's introduction, the literature has predominantly relied on computational assumptions, except in cases using unconventional methods like noisy channels or a fully trusted party. Introducing "Supersonic OT", a highly efficient and unconditionally secure OT scheme that avoids public-key-based primitives, we offer an alternative to traditional approaches. Supersonic OT enables a receiver to obtain a response of size O(1). Its simple (yet non-trivial) design facilitates easy security analysis and implementation. The protocol employs a basic secret-sharing scheme, controlled swaps, the one-time pad, and a third-party helper who may be corrupted by a semi-honest adversary. Our implementation and runtime analysis indicate that a single instance of Supersonic OT completes in 0.35 milliseconds, making it up to 2000 times faster than the state-of-the-art base OT.
Authors: Karn N. Watcharasupat, Alexander Lerch
Abstract: Despite significant recent progress across multiple subtasks of audio source separation, few music source separation systems support separation beyond the four-stem vocals, drums, bass, and other (VDBO) setup. Of the very few current systems that support source separation beyond this setup, most continue to rely on an inflexible decoder setup that can only support a fixed pre-defined set of stems. Increasing stem support in these inflexible systems correspondingly requires increasing computational complexity, rendering extensions of these systems computationally infeasible for long-tail instruments. In this work, we propose Banquet, a system that allows source separation of multiple stems using just one decoder. A bandsplit source separation model is extended to work in a query-based setup in tandem with a music instrument recognition PaSST model. On the MoisesDB dataset, Banquet, at only 24.9 M trainable parameters, approached the performance level of the significantly more complex 6-stem Hybrid Transformer Demucs on VDBO stems and outperformed it on guitar and piano. The query-based setup allows for the separation of narrow instrument classes such as clean acoustic guitars, and can be successfully applied to the extraction of less common stems such as reeds and organs. Implementation is available at https://github.com/kwatcharasupat/query-bandit.
Authors: Amy Li, Sihang Liu, Yi Ding
Abstract: This paper represents the first effort to quantify uncertainty in carbon intensity forecasting for datacenter decarbonization. We identify and analyze two types of uncertainty -- temporal and spatial -- and discuss their system implications. To address the temporal dynamics in quantifying uncertainty for carbon intensity forecasting, we introduce a conformal prediction-based framework. Evaluation results show that our technique robustly achieves target coverages in uncertainty quantification across various significance levels. We conduct two case studies using production power traces, focusing on temporal and spatial load shifting respectively. The results show that incorporating uncertainty into scheduling decisions can prevent a 5% and 14% increase in carbon emissions, respectively. These percentages translate to an absolute reduction of 2.1 and 10.4 tons of carbon emissions in a 20 MW datacenter cluster.
Authors: Prarthana Bhattacharyya, Joshua Mitton, Ryan Page, Owen Morgan, Ben Menzies, Gabriel Homewood, Kemi Jacobs, Paolo Baesso, David Trickett, Chris Mair, Taru Muhonen, Rory Clark, Louis Berridge, Richard Vigars, Iain Wallace
Abstract: This paper introduces Helios, the first extremely low-power, real-time, event-based hand gesture recognition system designed for all-day on smart eyewear. As augmented reality (AR) evolves, current smart glasses like the Meta Ray-Bans prioritize visual and wearable comfort at the expense of functionality. Existing human-machine interfaces (HMIs) in these devices, such as capacitive touch and voice controls, present limitations in ergonomics, privacy and power consumption. Helios addresses these challenges by leveraging natural hand interactions for a more intuitive and comfortable user experience. Our system utilizes a extremely low-power and compact 3mmx4mm/20mW event camera to perform natural hand-based gesture recognition for always-on smart eyewear. The camera's output is processed by a convolutional neural network (CNN) running on a NXP Nano UltraLite compute platform, consuming less than 350mW. Helios can recognize seven classes of gestures, including subtle microgestures like swipes and pinches, with 91% accuracy. We also demonstrate real-time performance across 20 users at a remarkably low latency of 60ms. Our user testing results align with the positive feedback we received during our recent successful demo at AWE-USA-2024.
Authors: Karn N. Watcharasupat, Chih-Wei Wu, Iroro Orife
Abstract: Cinematic audio source separation (CASS), as a problem of extracting the dialogue, music, and effects stems from their mixture, is a relatively new subtask of audio source separation. To date, only one publicly available dataset exists for CASS, that is, the Divide and Remaster (DnR) dataset, which is currently at version 2. While DnR v2 has been an incredibly useful resource for CASS, several areas of improvement have been identified, particularly through its use in the 2023 Sound Demixing Challenge. In this work, we develop version 3 of the DnR dataset, addressing issues relating to vocal content in non-dialogue stems, loudness distributions, mastering process, and linguistic diversity. In particular, the dialogue stem of DnR v3 includes speech content from more than 30 languages from multiple families including but not limited to the Germanic, Romance, Indo-Aryan, Dravidian, Malayo-Polynesian, and Bantu families. Benchmark results using the Bandit model indicated that training on multilingual data yields significant generalizability to the model even in languages with low data availability. Even in languages with high data availability, the multilingual model often performs on par or better than dedicated models trained on monolingual CASS datasets. Dataset and model implementation will be made available at https://github.com/kwatcharasupat/source-separation-landing.
URLs: https://github.com/kwatcharasupat/source-separation-landing.
Authors: Li Li, Hubert P. H. Shum, Toby P. Breckon
Abstract: 3D point clouds play a pivotal role in outdoor scene perception, especially in the context of autonomous driving. Recent advancements in 3D LiDAR segmentation often focus intensely on the spatial positioning and distribution of points for accurate segmentation. However, these methods, while robust in variable conditions, encounter challenges due to sole reliance on coordinates and point intensity, leading to poor isometric invariance and suboptimal segmentation. To tackle this challenge, our work introduces Range-Aware Pointwise Distance Distribution (RAPiD) features and the associated RAPiD-Seg architecture. Our RAPiD features exhibit rigid transformation invariance and effectively adapt to variations in point density, with a design focus on capturing the localized geometry of neighboring structures. They utilize inherent LiDAR isotropic radiation and semantic categorization for enhanced local representation and computational efficiency, while incorporating a 4D distance metric that integrates geometric and surface material reflectivity for improved semantic segmentation. To effectively embed high-dimensional RAPiD features, we propose a double-nested autoencoder structure with a novel class-aware embedding objective to encode high-dimensional features into manageable voxel-wise embeddings. Additionally, we propose RAPiD-Seg which incorporates a channel-wise attention fusion and two effective RAPiD-Seg variants, further optimizing the embedding for enhanced performance and generalization. Our method outperforms contemporary LiDAR segmentation work in terms of mIoU on SemanticKITTI (76.1) and nuScenes (83.6) datasets.
Authors: Tiago Monteiro
Abstract: In quantitative finance, machine learning methods are essential for alpha generation. This study introduces a new approach that combines Hidden Markov Models (HMM) and neural networks, integrated with Black-Litterman portfolio optimization. During the COVID period (2019-2022), this dual-model approach achieved a 83% return with a Sharpe ratio of 0.77. It incorporates two risk models to enhance risk management, showing efficiency during volatile periods. The methodology was implemented on the QuantConnect platform, which was chosen for its robust framework and experimental reproducibility. The system, which predicts future price movements, includes a three-year warm-up to ensure proper algorithm function. It targets highly liquid, large-cap energy stocks to ensure stable and predictable performance while also considering broker payments. The dual-model alpha system utilizes log returns to select the optimal state based on the historical performance. It combines state predictions with neural network outputs, which are based on historical data, to generate trading signals. This study examined the architecture of the trading system, data pre-processing, training, and performance. The full code and backtesting data are available under the QuantConnect terms.
Authors: Asger Horn Brorholt, Andreas Holck H{\o}eg-Petersen, Kim Guldstrand Larsen, Christian Schilling
Abstract: We consider the problem of synthesizing safety strategies for control systems, also known as shields. Since the state space is infinite, shields are typically computed over a finite-state abstraction, with the most common abstraction being a rectangular grid. However, for many systems, such a grid does not align well with the safety property or the system dynamics. That is why a coarse grid is rarely sufficient, but a fine grid is typically computationally infeasible to obtain. In this paper, we show that appropriate state-space transformations can still allow to use a coarse grid at almost no computational overhead. We demonstrate in three case studies that our transformation-based synthesis outperforms a standard synthesis by several orders of magnitude. In the first two case studies, we use domain knowledge to select a suitable transformation. In the third case study, we instead report on results in engineering a transformation without domain knowledge.
Authors: Karn N. Watcharasupat, Chih-Wei Wu, Iroro Orife
Abstract: Cinematic audio source separation (CASS), as a standalone problem of extracting individual stems from their mixture, is a fairly new subtask of audio source separation. A typical setup of CASS is a three-stem problem, with the aim of separating the mixture into the dialogue (DX), music (MX), and effects (FX) stems. Given the creative nature of cinematic sound production, however, several edge cases exist; some sound sources do not fit neatly in any of these three stems, necessitating the use of additional auxiliary stems in production. One very common edge case is the singing voice in film audio, which may belong in either the DX or MX or neither, depending heavily on the cinematic context. In this work, we demonstrate a very straightforward extension of the dedicated-decoder Bandit and query-based single-decoder Banquet models to a four-stem problem, treating non-musical dialogue, instrumental music, singing voice, and effects as separate stems. Interestingly, the query-based Banquet model outperformed the dedicated-decoder Bandit model. We hypothesized that this is due to a better feature alignment at the bottleneck as enforced by the band-agnostic FiLM layer. Dataset and model implementation will be made available at https://github.com/kwatcharasupat/source-separation-landing.
URLs: https://github.com/kwatcharasupat/source-separation-landing.
Authors: Ragib Amin Nihal, Benjamin Yen, Katsutoshi Itoyama, Kazuhiro Nakadai
Abstract: Unmanned aerial vehicles (UAVs) have revolutionized search and rescue (SAR) operations, but the lack of specialized human detection datasets for training machine learning models poses a significant challenge.To address this gap, this paper introduces the Combination to Application (C2A) dataset, synthesized by overlaying human poses onto UAV-captured disaster scenes. Through extensive experimentation with state-of-the-art detection models, we demonstrate that models fine-tuned on the C2A dataset exhibit substantial performance improvements compared to those pre-trained on generic aerial datasets. Furthermore, we highlight the importance of combining the C2A dataset with general human datasets to achieve optimal performance and generalization across various scenarios. This points out the crucial need for a tailored dataset to enhance the effectiveness of SAR operations. Our contributions also include developing dataset creation pipeline and integrating diverse human poses and disaster scenes information to assess the severity of disaster scenarios. Our findings advocate for future developments, to ensure that SAR operations benefit from the most realistic and effective AI-assisted interventions possible.
Authors: Jiahui Jin, Yifan Song, Dong Kan, Haojia Zhu, Xiangguo Sun, Zhicheng Li, Xigang Sun, Jinghui Zhang
Abstract: Urban region representation is crucial for various urban downstream tasks. However, despite the proliferation of methods and their success, acquiring general urban region knowledge and adapting to different tasks remains challenging. Previous work often neglects the spatial structures and functional layouts between entities, limiting their ability to capture transferable knowledge across regions. Further, these methods struggle to adapt effectively to specific downstream tasks, as they do not adequately address the unique features and relationships required for different downstream tasks. In this paper, we propose a $\textbf{G}$raph-based $\textbf{U}$rban $\textbf{R}$egion $\textbf{P}$re-training and $\textbf{P}$rompting framework ($\textbf{GURPP}$) for region representation learning. Specifically, we first construct an urban region graph that integrates detailed spatial entity data for more effective urban region representation. Then, we develop a subgraph-centric urban region pre-training model to capture the heterogeneous and transferable patterns of interactions among entities. To further enhance the adaptability of these embeddings to different tasks, we design two graph-based prompting methods to incorporate explicit/hidden task knowledge. Extensive experiments on various urban region prediction tasks and different cities demonstrate the superior performance of our GURPP framework.
Authors: Michael Drolet, Simon Stepputtis, Siva Kailas, Ajinkya Jain, Jan Peters, Stefan Schaal, Heni Ben Amor
Abstract: Amidst the wide popularity of imitation learning algorithms in robotics, their properties regarding hyperparameter sensitivity, ease of training, data efficiency, and performance have not been well-studied in high-precision industry-inspired environments. In this work, we demonstrate the limitations and benefits of prominent imitation learning approaches and analyze their capabilities regarding these properties. We evaluate each algorithm on a complex bimanual manipulation task involving an over-constrained dynamics system in a setting involving multiple contacts between the manipulated object and the environment. While we find that imitation learning is well suited to solve such complex tasks, not all algorithms are equal in terms of handling environmental and hyperparameter perturbations, training requirements, performance, and ease of use. We investigate the empirical influence of these key characteristics by employing a carefully designed experimental procedure and learning environment. Paper website: https://bimanual-imitation.github.io/
Authors: Javid Akhavan, Chaitanya Krishna Vallabh, Xiayun Zhao, Souran Manoochehri
Abstract: In metal Additive Manufacturing (AM), monitoring the temperature of the Melt Pool (MP) is crucial for ensuring part quality, process stability, defect prevention, and overall process optimization. Traditional methods, are slow to converge and require extensive manual effort to translate data into actionable insights, rendering them impractical for real-time monitoring and control. To address this challenge, we propose an Artificial Intelligence (AI)-based solution aimed at reducing manual data processing reliance and improving the efficiency of transitioning from data to insight. In our study, we utilize a dataset comprising dual-wavelength real-time process monitoring data and corresponding temperature maps. We introduce a deep learning model called the "Binocular model," which exploits dual input observations to perform a precise analysis of MP temperature in Laser Powder Bed Fusion (L-PBF). Through advanced deep learning techniques, we seamlessly convert raw data into temperature maps, significantly streamlining the process and enabling batch processing at a rate of up to 750 frames per second, approximately 1000 times faster than conventional methods. Our Binocular model achieves high accuracy in temperature estimation, evidenced by a 0.95 R-squared score, while simultaneously enhancing processing efficiency by a factor of $\sim1000x$ times. This model directly addresses the challenge of real-time MP temperature monitoring and offers insights into the encountered constraints and the benefits of our Deep Learning-based approach. By combining efficiency and precision, our work contributes to the advancement of temperature monitoring in L-PBF, thus driving progress in the field of metal AM.
Authors: Zexu Sun, Hao Yang, Dugang Liu, Yunpeng Weng, Xing Tang, Xiuqiang He
Abstract: In modern online platforms, incentives are essential factors that enhance user engagement and increase platform revenue. Over recent years, uplift modeling has been introduced as a strategic approach to assign incentives to individual customers. Especially in many real-world applications, online platforms can only incentivize customers with specific budget constraints. This problem can be reformulated as the multi-choice knapsack problem. This optimization aims to select the optimal incentive for each customer to maximize the return on investment. Recent works in this field frequently tackle the budget allocation problem using a two-stage approach. However, this solution is confronted with the following challenges: (1) The causal inference methods often ignore the domain knowledge in online marketing, where the expected response curve of a customer should be monotonic and smooth as the incentive increases. (2) An optimality gap between the two stages results in inferior sub-optimal allocation performance due to the loss of the incentive recommendation information for the uplift prediction under the limited budget constraint. To address these challenges, we propose a novel End-to-End Cost-Effective Incentive Recommendation (E3IR) model under budget constraints. Specifically, our methods consist of two modules, i.e., the uplift prediction module and the differentiable allocation module. In the uplift prediction module, we construct prediction heads to capture the incremental improvement between adjacent treatments with the marketing domain constraints (i.e., monotonic and smooth). We incorporate integer linear programming (ILP) as a differentiable layer input in the allocation module. Furthermore, we conduct extensive experiments on public and real product datasets, demonstrating that our E3IR improves allocation performance compared to existing two-stage approaches.
Authors: Sharath Turuvekere Sreenivas, Saurav Muralidharan, Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, Pavlo Molchanov
Abstract: We present a comprehensive report on compressing the Llama 3.1 8B and Mistral NeMo 12B models to 4B and 8B parameters, respectively, using pruning and distillation. We explore two distinct pruning strategies: (1) depth pruning and (2) joint hidden/attention/MLP (width) pruning, and evaluate the results on common benchmarks from the LM Evaluation Harness. The models are then aligned with NeMo Aligner and tested in instruct-tuned versions. This approach produces a compelling 4B model from Llama 3.1 8B and a state-of-the-art Mistral-NeMo-Minitron-8B (MN-Minitron-8B for brevity) model from Mistral NeMo 12B. We found that with no access to the original data, it is beneficial to slightly fine-tune teacher models on the distillation dataset. We open-source our base model weights on Hugging Face with a permissive license.
Authors: Aishik Nagar, Yutong Liu, Andy T. Liu, Viktor Schlegel, Vijay Prakash Dwivedi, Arun-Kumar Kaliya-Perumal, Guna Pratheep Kalanchiam, Yili Tang, Robby T. Tan
Abstract: Medical abstractive summarization faces the challenge of balancing faithfulness and informativeness. Current methods often sacrifice key information for faithfulness or introduce confabulations when prioritizing informativeness. While recent advancements in techniques like in-context learning (ICL) and fine-tuning have improved medical summarization, they often overlook crucial aspects such as faithfulness and informativeness without considering advanced methods like model reasoning and self-improvement. Moreover, the field lacks a unified benchmark, hindering systematic evaluation due to varied metrics and datasets. This paper addresses these gaps by presenting a comprehensive benchmark of six advanced abstractive summarization methods across three diverse datasets using five standardized metrics. Building on these findings, we propose uMedSum, a modular hybrid summarization framework that introduces novel approaches for sequential confabulation removal followed by key missing information addition, ensuring both faithfulness and informativeness. Our work improves upon previous GPT-4-based state-of-the-art (SOTA) medical summarization methods, significantly outperforming them in both quantitative metrics and qualitative domain expert evaluations. Notably, we achieve an average relative performance improvement of 11.8% in reference-free metrics over the previous SOTA. Doctors prefer uMedSum's summaries 6 times more than previous SOTA in difficult cases where there are chances of confabulations or missing information. These results highlight uMedSum's effectiveness and generalizability across various datasets and metrics, marking a significant advancement in medical summarization.
Authors: Haojun Shi, Suyu Ye, Xinyu Fang, Chuanyang Jin, Leyla Isik, Yen-Ling Kuo, Tianmin Shu
Abstract: Understanding people's social interactions in complex real-world scenarios often relies on intricate mental reasoning. To truly understand how and why people interact with one another, we must infer the underlying mental states that give rise to the social interactions, i.e., Theory of Mind reasoning in multi-agent interactions. Additionally, social interactions are often multi-modal -- we can watch people's actions, hear their conversations, and/or read about their past behaviors. For AI systems to successfully and safely interact with people in real-world environments, they also need to understand people's mental states as well as their inferences about each other's mental states based on multi-modal information about their interactions. For this, we introduce MuMA-ToM, a Multi-modal Multi-Agent Theory of Mind benchmark. MuMA-ToM is the first multi-modal Theory of Mind benchmark that evaluates mental reasoning in embodied multi-agent interactions. In MuMA-ToM, we provide video and text descriptions of people's multi-modal behavior in realistic household environments. Based on the context, we then ask questions about people's goals, beliefs, and beliefs about others' goals. We validated MuMA-ToM in a human experiment and provided a human baseline. We also proposed a novel multi-modal, multi-agent ToM model, LIMP (Language model-based Inverse Multi-agent Planning). Our experimental results show that LIMP significantly outperforms state-of-the-art methods, including large multi-modal models (e.g., GPT-4o, Gemini-1.5 Pro) and a recent multi-modal ToM model, BIP-ALM.
Authors: Ling Lin, Yihang Zhou, Zhanqi Hu, Dian Jiang, Congcong Liu, Shuo Zhou, Yanjie Zhu, Jianxiang Liao, Dong Liang, Hairong Zheng, Haifeng Wang
Abstract: Tuberous sclerosis complex (TSC) manifests as a multisystem disorder with significant neurological implications. This study addresses the critical need for robust classification models tailored to TSC in pediatric patients, introducing QResNet,a novel deep learning model seamlessly integrating conventional convolutional neural networks with quantum neural networks. The model incorporates a two-layer quantum layer (QL), comprising ZZFeatureMap and Ansatz layers, strategically designed for processing classical data within a quantum framework. A comprehensive evaluation, demonstrates the superior performance of QResNet in TSC MRI image classification compared to conventional 3D-ResNet models. These compelling findings underscore the potential of quantum computing to revolutionize medical imaging and diagnostics.Remarkably, this method surpasses conventional CNNs in accuracy and Area Under the Curve (AUC) metrics with the current dataset. Future research endeavors may focus on exploring the scalability and practical implementation of quantum algorithms in real-world medical imaging scenarios.
Authors: Nithya Shikarpur, Krishna Maneesha Dendukuri, Yusong Wu, Antoine Caillon, Cheng-Zhi Anna Huang
Abstract: Hindustani music is a performance-driven oral tradition that exhibits the rendition of rich melodic patterns. In this paper, we focus on generative modeling of singers' vocal melodies extracted from audio recordings, as the voice is musically prominent within the tradition. Prior generative work in Hindustani music models melodies as coarse discrete symbols which fails to capture the rich expressive melodic intricacies of singing. Thus, we propose to use a finely quantized pitch contour, as an intermediate representation for hierarchical audio modeling. We propose GaMaDHaNi, a modular two-level hierarchy, consisting of a generative model on pitch contours, and a pitch contour to audio synthesis model. We compare our approach to non-hierarchical audio models and hierarchical models that use a self-supervised intermediate representation, through a listening test and qualitative analysis. We also evaluate audio model's ability to faithfully represent the pitch contour input using Pearson correlation coefficient. By using pitch contours as an intermediate representation, we show that our model may be better equipped to listen and respond to musicians in a human-AI collaborative setting by highlighting two potential interaction use cases (1) primed generation, and (2) coarse pitch conditioning.
Authors: Frank Nielsen
Abstract: We present a generalization of Bregman divergences in symplectic vector spaces that we term symplectic Bregman divergences. Symplectic Bregman divergences are derived from a symplectic generalization of the Fenchel-Young inequality which relies on the notion of symplectic subdifferentials. The symplectic Fenchel-Young inequality is obtained using the symplectic Fenchel transform which is defined with respect to a linear symplectic form. When the symplectic form is built from an inner product, we show that the corresponding symplectic Bregman divergences amount to ordinary Bregman divergences with respect to composite inner products. Some potential applications of symplectic divergences in geometric mechanics, information geometry, and learning dynamics in machine learning are touched upon.
Authors: Pascal Pernot
Abstract: This short study presents an opportunistic approach to a (more) reliable validation method for prediction uncertainty average calibration. Considering that variance-based calibration metrics (ZMS, NLL, RCE...) are quite sensitive to the presence of heavy tails in the uncertainty and error distributions, a shift is proposed to an interval-based metric, the Prediction Interval Coverage Probability (PICP). It is shown on a large ensemble of molecular properties datasets that (1) sets of z-scores are well represented by Student's-$t(\nu)$ distributions, $\nu$ being the number of degrees of freedom; (2) accurate estimation of 95 $\%$ prediction intervals can be obtained by the simple $2\sigma$ rule for $\nu>3$; and (3) the resulting PICPs are more quickly and reliably tested than variance-based calibration metrics. Overall, this method enables to test 20 $\%$ more datasets than ZMS testing. Conditional calibration is also assessed using the PICP approach.