Authors: Rosie Zhao, Depen Morwani, David Brandfonbrener, Nikhil Vyas, Sham Kakade
Abstract: Training language models becomes increasingly expensive with scale, prompting numerous attempts to improve optimization efficiency. Despite these efforts, the Adam optimizer remains the most widely used, due to a prevailing view that it is the most effective approach. We aim to compare several optimization algorithms, including SGD, Adafactor, Adam, and Lion, in the context of autoregressive language modeling across a range of model sizes, hyperparameters, and architecture variants. Our findings indicate that, except for SGD, these algorithms all perform comparably both in their optimal performance and also in terms of how they fare across a wide range of hyperparameter choices. Our results suggest to practitioners that the choice of optimizer can be guided by practical considerations like memory constraints and ease of implementation, as no single algorithm emerged as a clear winner in terms of performance or stability to hyperparameter misspecification. Given our findings, we further dissect these approaches, examining two simplified versions of Adam: a) signed momentum (Signum) which we see recovers both the performance and hyperparameter stability of Adam and b) Adalayer, a layerwise variant of Adam which we introduce to study Adam's preconditioning. Examining Adalayer leads us to the conclusion that the largest impact of Adam's preconditioning is restricted to the last layer and LayerNorm parameters, and, perhaps surprisingly, the remaining layers can be trained with SGD.
Authors: Jean Park, Sydney Pugh, Kaustubh Sridhar, Mengyu Liu, Navish Yarna, Ramneet Kaur, Souradeep Dutta, Elena Bernardis, Oleg Sokolsky, Insup Lee
Abstract: Large Deep Neural Networks (DNNs) are often data hungry and need high-quality labeled data in copious amounts for learning to converge. This is a challenge in the field of medicine since high quality labeled data is often scarce. Data programming has been the ray of hope in this regard, since it allows us to label unlabeled data using multiple weak labeling functions. Such functions are often supplied by a domain expert. Data-programming can combine multiple weak labeling functions and suggest labels better than simple majority voting over the different functions. However, it is not straightforward to express such weak labeling functions, especially in high-dimensional settings such as images and time-series data. What we propose in this paper is a way to bypass this issue, using distance functions. In high-dimensional spaces, it is easier to find meaningful distance metrics which can generalize across different labeling tasks. We propose an algorithm that queries an expert for labels of a few representative samples of the dataset. These samples are carefully chosen by the algorithm to capture the distribution of the dataset. The labels assigned by the expert on the representative subset induce a labeling on the full dataset, thereby generating weak labels to be used in the data programming pipeline. In our medical time series case study, labeling a subset of 50 to 130 out of 3,265 samples showed 17-28% improvement in accuracy and 13-28% improvement in F1 over the baseline using clinician-defined labeling functions. In our medical image case study, labeling a subset of about 50 to 120 images from 6,293 unlabeled medical images using our approach showed significant improvement over the baseline method, Snuba, with an increase of approximately 5-15% in accuracy and 12-19% in F1 score.
Authors: Abigail E. Whitlock, Gondy Leroy, Fariba M. Donovan, John N. Galgiani
Abstract: In medicine, machine learning (ML) datasets are often built using the International Classification of Diseases (ICD) codes. As new models are being developed, there is a need for larger datasets. However, ICD codes are intended for billing. We aim to determine how suitable ICD codes are for creating datasets to train ML models. We focused on a rare and common disease using the All of Us database. First, we compared the patient cohort created using ICD codes for Valley fever (coccidioidomycosis, CM) with that identified via serological confirmation. Second, we compared two similarly created patient cohorts for myocardial infarction (MI) patients. We identified significant discrepancies between these two groups, and the patient overlap was small. The CM cohort had 811 patients in the ICD-10 group, 619 patients in the positive-serology group, and 24 with both. The MI cohort had 14,875 patients in the ICD-10 group, 23,598 in the MI laboratory-confirmed group, and 6,531 in both. Demographics, rates of disease symptoms, and other clinical data varied across our case study cohorts.
Authors: Raghav Singhal, Mark Goldstein, Rajesh Ranganath
Abstract: Reversing a diffusion process by learning its score forms the heart of diffusion-based generative modeling and for estimating properties of scientific systems. The diffusion processes that are tractable center on linear processes with a Gaussian stationary distribution. This limits the kinds of models that can be built to those that target a Gaussian prior or more generally limits the kinds of problems that can be generically solved to those that have conditionally linear score functions. In this work, we introduce a family of tractable denoising score matching objectives, called local-DSM, built using local increments of the diffusion process. We show how local-DSM melded with Taylor expansions enables automated training and score estimation with nonlinear diffusion processes. To demonstrate these ideas, we use automated-DSM to train generative models using non-Gaussian priors on challenging low dimensional distributions and the CIFAR10 image dataset. Additionally, we use the automated-DSM to learn the scores for nonlinear processes studied in statistical physics.
Authors: Ritesh Mehta, Aleksandar Pramov, Shashank Verma
Abstract: Amyotrophic Lateral Sclerosis (ALS) is characterized as a rapidly progressive neurodegenerative disease that presents individuals with limited treatment options in the realm of medical interventions and therapies. The disease showcases a diverse range of onset patterns and progression trajectories, emphasizing the critical importance of early detection of functional decline to enable tailored care strategies and timely therapeutic interventions. The present investigation, spearheaded by the iDPP@CLEF 2024 challenge, focuses on utilizing sensor-derived data obtained through an app. This data is used to construct various machine learning models specifically designed to forecast the advancement of the ALS Functional Rating Scale-Revised (ALSFRS-R) score, leveraging the dataset provided by the organizers. In our analysis, multiple predictive models were evaluated to determine their efficacy in handling ALS sensor data. The temporal aspect of the sensor data was compressed and amalgamated using statistical methods, thereby augmenting the interpretability and applicability of the gathered information for predictive modeling objectives. The models that demonstrated optimal performance were a naive baseline and ElasticNet regression. The naive model achieved a Mean Absolute Error (MAE) of 0.20 and a Root Mean Square Error (RMSE) of 0.49, slightly outperforming the ElasticNet model, which recorded an MAE of 0.22 and an RMSE of 0.50. Our comparative analysis suggests that while the naive approach yielded marginally better predictive accuracy, the ElasticNet model provides a robust framework for understanding feature contributions.
Authors: Fulong Yao, Wanqing Zhao, Matthew Forshaw, Yang Song
Abstract: This paper proposes a new self-organizing interval type-2 fuzzy neural network with multiple outputs (SOIT2FNN-MO) for multi-step time series prediction. Differing from the traditional six-layer IT2FNN, a nine-layer network is developed to improve prediction accuracy, uncertainty handling and model interpretability. First, a new co-antecedent layer and a modified consequent layer are devised to improve the interpretability of the fuzzy model for multi-step predictions. Second, a new transformation layer is designed to address the potential issues in the vanished rule firing strength caused by highdimensional inputs. Third, a new link layer is proposed to build temporal connections between multi-step predictions. Furthermore, a two-stage self-organizing mechanism is developed to automatically generate the fuzzy rules, in which the first stage is used to create the rule base from empty and perform the initial optimization, while the second stage is to fine-tune all network parameters. Finally, various simulations are carried out on chaotic and microgrid time series prediction problems, demonstrating the superiority of our approach in terms of prediction accuracy, uncertainty handling and model interpretability.
Authors: Linying Yang, Vik Shirvaikar, Oscar Clivio, Fabian Falck
Abstract: Numerous benchmarks aim to evaluate the capabilities of Large Language Models (LLMs) for causal inference and reasoning. However, many of them can likely be solved through the retrieval of domain knowledge, questioning whether they achieve their purpose. In this review, we present a comprehensive overview of LLM benchmarks for causality. We highlight how recent benchmarks move towards a more thorough definition of causal reasoning by incorporating interventional or counterfactual reasoning. We derive a set of criteria that a useful benchmark or set of benchmarks should aim to satisfy. We hope this work will pave the way towards a general framework for the assessment of causal understanding in LLMs and the design of novel benchmarks.
Authors: Jianzhe Xue (Sherman), Dongcheng Yuan (Sherman), Yu Sun (Sherman), Tianqi Zhang (Sherman), Wenchao Xu (Sherman), Haibo Zhou (Sherman), Xuemin (Sherman), Shen
Abstract: The growing number of connected vehicles offers an opportunity to leverage internet of vehicles (IoV) data for traffic state estimation (TSE) which plays a crucial role in intelligent transportation systems (ITS). By utilizing only a portion of IoV data instead of the entire dataset, the significant overheads associated with collecting and processing large amounts of data can be avoided. In this paper, we introduce a novel framework that utilizes sparse IoV data to achieve cost-effective TSE. Particularly, we propose a novel spatial-temporal attention model called the convolutional retentive network (CRNet) to improve the TSE accuracy by mining spatial-temporal traffic state correlations. The model employs the convolutional neural network (CNN) for spatial correlation aggregation and the retentive network (RetNet) based on the attention mechanism to extract temporal correlations. Extensive simulations on a real-world IoV dataset validate the advantage of the proposed TSE approach in achieving accurate TSE using sparse IoV data, demonstrating its cost effectiveness and practicality for real-world applications.
Authors: Nikolaos Dimitriadis, Pascal Frossard, Francois Fleuret
Abstract: Dealing with multi-task trade-offs during inference can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front with a single model, contrary to traditional Multi-Task Learning (MTL) approaches that optimize for a single trade-off which has to be decided prior to training. However, recent PFL methodologies suffer from limited scalability, slow convergence and excessive memory requirements compared to MTL approaches while exhibiting inconsistent mappings from preference space to objective space. In this paper, we introduce PaLoRA, a novel parameter-efficient method that augments the original model with task-specific low-rank adapters and continuously parameterizes the Pareto Front in their convex hull. Our approach dedicates the original model and the adapters towards learning general and task-specific features, respectively. Additionally, we propose a deterministic sampling schedule of preference vectors that reinforces this division of labor, enabling faster convergence and scalability to real world networks. Our experimental results show that PaLoRA outperforms MTL and PFL baselines across various datasets, scales to large networks and provides a continuous parameterization of the Pareto Front, reducing the memory overhead $23.8-31.7$ times compared with competing PFL baselines in scene understanding benchmarks.
Authors: Yezi Liu, Yanning Shen
Abstract: Training graph neural networks (GNNs) on large-scale graphs can be challenging due to the high computational expense caused by the massive number of nodes and high-dimensional nodal features. Existing graph condensation studies tackle this problem only by reducing the number of nodes in the graph. However, the resulting condensed graph data can still be cumbersome. Specifically, although the nodes of the Citeseer dataset are reduced to 0.9% (30 nodes) in training, the number of features is 3,703, severely exceeding the training sample magnitude. Faced with this challenge, we study the problem of joint condensation for both features and nodes in large-scale graphs. This task is challenging mainly due to 1) the intertwined nature of the node features and the graph structure calls for the feature condensation solver to be structure-aware; and 2) the difficulty of keeping useful information in the condensed graph. To address these challenges, we propose a novel framework TinyGraph, to condense features and nodes simultaneously in graphs. Specifically, we cast the problem as matching the gradients of GNN weights trained on the condensed graph and the gradients obtained from training over the original graph, where the feature condensation is achieved by a trainable function. The condensed graph obtained by minimizing the matching loss along the training trajectory can henceforth retain critical information in the original graph. Extensive experiments were carried out to demonstrate the effectiveness of the proposed TinyGraph. For example, a GNN trained with TinyGraph retains 98.5% and 97.5% of the original test accuracy on the Cora and Citeseer datasets, respectively, while significantly reducing the number of nodes by 97.4% and 98.2%, and the number of features by 90.0% on both datasets.
Authors: Martha Baldwin, Nicholas A. Meisel, Christopher McComb
Abstract: Additive manufacturing has revolutionized structural optimization by enhancing component strength and reducing material requirements. One approach used to achieve these improvements is the application of multi-lattice structures, where the macro-scale performance relies on the detailed design of mesostructural lattice elements. Many current approaches to designing such structures use data-driven design to generate multi-lattice transition regions, making use of machine learning models that are informed solely by the geometry of the mesostructures. However, it remains unclear if the integration of mechanical properties into the dataset used to train such machine learning models would be beneficial beyond using geometric data alone. To address this issue, this work implements and evaluates a hybrid geometry/property Variational Autoencoder (VAE) for generating multi-lattice transition regions. In our study, we found that hybrid VAEs demonstrate enhanced performance in maintaining stiffness continuity through transition regions, indicating their suitability for design tasks requiring smooth mechanical properties.
Authors: Peter Mostowsky, Vincent Dutordoir, Iskander Azangulov, No\'emie Jaquier, Michael John Hutchinson, Aditya Ravuri, Leonel Rozo, Alexander Terenin, Viacheslav Borovitskiy
Abstract: Kernels are a fundamental technical primitive in machine learning. In recent years, kernel-based methods such as Gaussian processes are becoming increasingly important in applications where quantifying uncertainty is of key interest. In settings that involve structured data defined on graphs, meshes, manifolds, or other related spaces, defining kernels with good uncertainty-quantification behavior, and computing their value numerically, is less straightforward than in the Euclidean setting. To address this difficulty, we present GeometricKernels, a software package which implements the geometric analogs of classical Euclidean squared exponential - also known as heat - and Mat\'ern kernels, which are widely-used in settings where uncertainty is of key interest. As a byproduct, we obtain the ability to compute Fourier-feature-type expansions, which are widely used in their own right, on a wide set of geometric spaces. Our implementation supports automatic differentiation in every major current framework simultaneously via a backend-agnostic design. In this companion paper to the package and its documentation, we outline the capabilities of the package and present an illustrated example of its interface. We also include a brief overview of the theory the package is built upon and provide some historic context in the appendix.
Authors: Steffen Dereich, Robin Graeber, Arnulf Jentzen
Abstract: Deep learning algorithms - typically consisting of a class of deep neural networks trained by a stochastic gradient descent (SGD) optimization method - are nowadays the key ingredients in many artificial intelligence (AI) systems and have revolutionized our ways of working and living in modern societies. For example, SGD methods are used to train powerful large language models (LLMs) such as versions of ChatGPT and Gemini, SGD methods are employed to create successful generative AI based text-to-image creation models such as Midjourney, DALL-E, and Stable Diffusion, but SGD methods are also used to train DNNs to approximately solve scientific models such as partial differential equation (PDE) models from physics and biology and optimal control and stopping problems from engineering. It is known that the plain vanilla standard SGD method fails to converge even in the situation of several convex optimization problems if the learning rates are bounded away from zero. However, in many practical relevant training scenarios, often not the plain vanilla standard SGD method but instead adaptive SGD methods such as the RMSprop and the Adam optimizers, in which the learning rates are modified adaptively during the training process, are employed. This naturally rises the question whether such adaptive optimizers, in which the learning rates are modified adaptively during the training process, do converge in the situation of non-vanishing learning rates. In this work we answer this question negatively by proving that adaptive SGD methods such as the popular Adam optimizer fail to converge to any possible random limit point if the learning rates are asymptotically bounded away from zero. In our proof of this non-convergence result we establish suitable pathwise a priori bounds for a class of accelerated and adaptive SGD methods, which are also of independent interest.
Authors: MohammadAmin Ansari Khoushabar, Parviz Ghafariasl
Abstract: Sepsis, a critical condition from the body's response to infection, poses a major global health crisis affecting all age groups. Timely detection and intervention are crucial for reducing healthcare expenses and improving patient outcomes. This paper examines the limitations of traditional sepsis screening tools like Systemic Inflammatory Response Syndrome, Modified Early Warning Score, and Quick Sequential Organ Failure Assessment, highlighting the need for advanced approaches. We propose using machine learning techniques - Random Forest, Extreme Gradient Boosting, and Decision Tree models - to predict sepsis onset. Our study evaluates these models individually and in a combined meta-ensemble approach using key metrics such as Accuracy, Precision, Recall, F1 score, and Area Under the Receiver Operating Characteristic Curve. Results show that the meta-ensemble model outperforms individual models, achieving an AUC-ROC score of 0.96, indicating superior predictive accuracy for early sepsis detection. The Random Forest model also performs well with an AUC-ROC score of 0.95, while Extreme Gradient Boosting and Decision Tree models score 0.94 and 0.90, respectively.
Authors: Jerry Huang
Abstract: Long sequences occur in abundance within real-world scenarios, hence properly modelling them opens numerous down-stream use-cases. Deep neural networks, however, have often struggled with these for a variety of reasons. Recent advances, both in system engineering as well as model design, have enabled the scaling up of model that are purported to support extended context length. In particular, the state-space and linear recurrent neural network families of models hypothetically can entend to infinite sequence lenth. However, is this too good to be true? We conduct an evaluation to show that while such claims may be sound theoretically, there remain large practical gaps that are empirically observed. In particular, recurrent models still suffer in the same settings as long-context LLMs with attention. We further show that different inductive biases have inconsistent extrapolation capabilities, highlighting the need to further study such paradigms and investigate why long-context models seemingly fail to behave as one might expect.
Authors: Yixin Jin, Meiqi Wang, Meng Li, Wenjing Zhou, Yi Shen, Hao Liu
Abstract: In this paper, we describe our approaches to TREC Real-Time Summarization of Twitter. We focus on real time push notification scenario, which requires a system monitors the stream of sampled tweets and returns the tweets relevant and novel to given interest profiles. Dirichlet score with and with very little smoothing (baseline) are employed to classify whether a tweet is relevant to a given interest profile. Using metrics including Mean Average Precision (MAP, cumulative gain (CG) and discount cumulative gain (DCG), the experiment indicates that our approach has a good performance. It is also desired to remove the redundant tweets from the pushing queue. Due to the precision limit, we only describe the algorithm in this paper.
Authors: Mikhail Kulyabin, Paul A. Constable, Aleksei Zhdanov, Irene O. Lee, David H. Skuse, Dorothy A. Thompson, Andreas Maier
Abstract: The electroretinogram (ERG) is a clinical test that records the retina's electrical response to light. The ERG is a promising way to study different neurodevelopmental and neurodegenerative disorders, including autism spectrum disorder (ASD) - a neurodevelopmental condition that impacts language, communication, and reciprocal social interactions. However, in heterogeneous populations, such as ASD, where the ability to collect large datasets is limited, the application of artificial intelligence (AI) is complicated. Synthetic ERG signals generated from real ERG recordings carry similar information as natural ERGs and, therefore, could be used as an extension for natural data to increase datasets so that AI applications can be fully utilized. As proof of principle, this study presents a Generative Adversarial Network capable of generating synthetic ERG signals of children with ASD and typically developing control individuals. We applied a Time Series Transformer and Visual Transformer with Continuous Wavelet Transform to enhance classification results on the extended synthetic signals dataset. This approach may support classification models in related psychiatric conditions where the ERG may help classify disorders.
Authors: Omri Lev, Ashia Wilson
Abstract: We address the challenge of efficiently and reliably deleting data from machine learning models trained using Empirical Risk Minimization (ERM), a process known as machine unlearning. To avoid retraining models from scratch, we propose a novel algorithm leveraging Natural Gradient Descent (NGD). Our theoretical framework ensures strong privacy guarantees for convex models, while a practical Min/Max optimization algorithm is developed for non-convex models. Comprehensive evaluations show significant improvements in privacy, computational efficiency, and generalization compared to state-of-the-art methods, advancing both the theoretical and practical aspects of machine unlearning.
Authors: Dora Zhao, Jerone T. A. Andrews, Orestis Papakyriakopoulos, Alice Xiang
Abstract: Machine learning (ML) datasets, often perceived as neutral, inherently encapsulate abstract and disputed social constructs. Dataset curators frequently employ value-laden terms such as diversity, bias, and quality to characterize datasets. Despite their prevalence, these terms lack clear definitions and validation. Our research explores the implications of this issue by analyzing "diversity" across 135 image and text datasets. Drawing from social sciences, we apply principles from measurement theory to identify considerations and offer recommendations for conceptualizing, operationalizing, and evaluating diversity in datasets. Our findings have broader implications for ML research, advocating for a more nuanced and precise approach to handling value-laden properties in dataset construction.
Authors: Arya Fayyazi, Mehdi Kamal, Massoud Pedram
Abstract: This paper presents ARCO, an adaptive Multi-Agent Reinforcement Learning (MARL)-based co-optimizing compilation framework designed to enhance the efficiency of mapping machine learning (ML) models - such as Deep Neural Networks (DNNs) - onto diverse hardware platforms. The framework incorporates three specialized actor-critic agents within MARL, each dedicated to a distinct aspect of compilation/optimization at an abstract level: one agent focuses on hardware, while two agents focus on software optimizations. This integration results in a collaborative hardware/software co-optimization strategy that improves the precision and speed of DNN deployments. Concentrating on high-confidence configurations simplifies the search space and delivers superior performance compared to current optimization methods. The ARCO framework surpasses existing leading frameworks, achieving a throughput increase of up to 37.95% while reducing the optimization time by up to 42.2% across various DNNs.
Authors: Li Yuepan, Fan Lyu, Yuyang Li, Wei Feng, Guangcan Liu, Fanhua Shang
Abstract: Parallel Continual Learning (PCL) tasks investigate the training methods for continual learning with multi-source input, where data from different tasks are learned as they arrive. PCL offers high training efficiency and is well-suited for complex multi-source data systems, such as autonomous vehicles equipped with multiple sensors. However, at any time, multiple tasks need to be trained simultaneously, leading to severe training instability in PCL. This instability manifests during both forward and backward propagation, where features are entangled and gradients are conflict. This paper introduces Stable Parallel Continual Learning (SPCL), a novel approach that enhances the training stability of PCL for both forward and backward propagation. For the forward propagation, we apply Doubly-block Toeplit (DBT) Matrix based orthogonality constraints to network parameters to ensure stable and consistent propagation. For the backward propagation, we employ orthogonal decomposition for gradient management stabilizes backpropagation and mitigates gradient conflicts across tasks. By optimizing gradients by ensuring orthogonality and minimizing the condition number, SPCL effectively stabilizing the gradient descent in complex optimization tasks. Experimental results demonstrate that SPCL outperforms state-of-the-art methjods and achieve better training stability.
Authors: Seyed Amir Hossein Aqajari, Ziyu Wang, Ali Tazarv, Sina Labbaf, Salar Jafarlou, Brenda Nguyen, Nikil Dutt, Marco Levorato, Amir M. Rahmani
Abstract: In today's fast-paced world, accurately monitoring stress levels is crucial. Sensor-based stress monitoring systems often need large datasets for training effective models. However, individual-specific models are necessary for personalized and interactive scenarios. Traditional methods like Ecological Momentary Assessments (EMAs) assess stress but struggle with efficient data collection without burdening users. The challenge is to timely send EMAs, especially during stress, balancing monitoring efficiency and user convenience. This paper introduces a novel context-aware active reinforcement learning (RL) algorithm for enhanced stress detection using Photoplethysmography (PPG) data from smartwatches and contextual data from smartphones. Our approach dynamically selects optimal times for deploying EMAs, utilizing the user's immediate context to maximize label accuracy and minimize intrusiveness. Initially, the study was executed in an offline environment to refine the label collection process, aiming to increase accuracy while reducing user burden. Later, we integrated a real-time label collection mechanism, transitioning to an online methodology. This shift resulted in an 11% improvement in stress detection efficiency. Incorporating contextual data improved model accuracy by 4%. Personalization studies indicated a 10% enhancement in AUC-ROC scores, demonstrating better stress level differentiation. This research marks a significant move towards personalized, context-driven real-time stress monitoring methods.
Authors: Jamshaid Ul Rahman, Rubiqa Zulfiqar, Asad Khan, Nimra
Abstract: ReLU, a commonly used activation function in deep neural networks, is prone to the issue of "Dying ReLU". Several enhanced versions, such as ELU, SeLU, and Swish, have been introduced and are considered to be less commonly utilized. However, replacing ReLU can be somewhat challenging due to its inconsistent advantages. While Swish offers a smoother transition similar to ReLU, its utilization generally incurs a greater computational burden compared to ReLU. This paper proposes SwishReLU, a novel activation function combining elements of ReLU and Swish. Our findings reveal that SwishReLU outperforms ReLU in performance with a lower computational cost than Swish. This paper undertakes an examination and comparison of different types of ReLU variants with SwishReLU. Specifically, we compare ELU and SeLU along with Tanh on three datasets: CIFAR-10, CIFAR-100 and MNIST. Notably, applying SwishReLU in the VGG16 model described in Algorithm 2 yields a 6% accuracy improvement on the CIFAR-10 dataset.
Authors: Ding Chen, Chen Liu
Abstract: We present a novel approach called differentially private stochastic block coordinate descent (DP-SBCD) for training neural networks with provable guarantees of differential privacy under the hidden state assumption. Our methodology incorporates Lipschitz neural networks and decomposes the training process of the neural network into sub-problems, each corresponding to the training of a specific layer. By doing so, we extend the analysis of differential privacy under the hidden state assumption to encompass non-convex problems and algorithms employing proximal gradient descent. Furthermore, in contrast to existing methods, we adopt a novel approach by utilizing calibrated noise sampled from adaptive distributions, yielding improved empirical trade-offs between utility and privacy.
Authors: Seunghan Yang, Seokeon Choi, Hyunsin Park, Sungha Choi, Simyung Chang, Sungrack Yun
Abstract: Federated learning, a distributed learning paradigm, utilizes multiple clients to build a robust global model. In real-world applications, local clients often operate within their limited domains, leading to a `domain shift' across clients. Privacy concerns limit each client's learning to its own domain data, which increase the risk of overfitting. Moreover, the process of aggregating models trained on own limited domain can be potentially lead to a significant degradation in the global model performance. To deal with these challenges, we introduce the concept of federated feature diversification. Each client diversifies the own limited domain data by leveraging global feature statistics, i.e., the aggregated average statistics over all participating clients, shared through the global model's parameters. This data diversification helps local models to learn client-invariant representations while preserving privacy. Our resultant global model shows robust performance on unseen test domain data. To enhance performance further, we develop an instance-adaptive inference approach tailored for test domain data. Our proposed instance feature adapter dynamically adjusts feature statistics to align with the test input, thereby reducing the domain gap between the test and training domains. We show that our method achieves state-of-the-art performance on several domain generalization benchmarks within a federated learning setting.
Authors: Benjamin Fuhrer, Chen Tessler, Gal Dalal
Abstract: Neural networks (NN) achieve remarkable results in various tasks, but lack key characteristics: interpretability, support for categorical features, and lightweight implementations suitable for edge devices. While ongoing efforts aim to address these challenges, Gradient Boosting Trees (GBT) inherently meet these requirements. As a result, GBTs have become the go-to method for supervised learning tasks in many real-world applications and competitions. However, their application in online learning scenarios, notably in reinforcement learning (RL), has been limited. In this work, we bridge this gap by introducing Gradient-Boosting RL (GBRL), a framework that extends the advantages of GBT to the RL domain. Using the GBRL framework, we implement various actor-critic algorithms and compare their performance with their NN counterparts. Inspired by shared backbones in NN we introduce a tree-sharing approach for policy and value functions with distinct learning rates, enhancing learning efficiency over millions of interactions. GBRL achieves competitive performance across a diverse array of tasks, excelling in domains with structured or categorical features. Additionally, we present a high-performance, GPU-accelerated implementation that integrates seamlessly with widely-used RL libraries (available at https://github.com/NVlabs/gbrl). GBRL expands the toolkit for RL practitioners, demonstrating the viability and promise of GBT within the RL paradigm, particularly in domains characterized by structured or categorical features.
Authors: Aur\'elien Pion, Emmanuel Vazquez
Abstract: This article advocates the use of conformal prediction (CP) methods for Gaussian process (GP) interpolation to enhance the calibration of prediction intervals. We begin by illustrating that using a GP model with parameters selected by maximum likelihood often results in predictions that are not optimally calibrated. CP methods can adjust the prediction intervals, leading to better uncertainty quantification while maintaining the accuracy of the underlying GP model. We compare different CP variants and introduce a novel variant based on an asymmetric score. Our numerical experiments demonstrate the effectiveness of CP methods in improving calibration without compromising accuracy. This work aims to facilitate the adoption of CP methods in the GP community.
Authors: Hiba Najjar, Miro Miranda, Marlon Nuske, Ribana Roscher, Andreas Dengel
Abstract: Crop yield forecasting plays a significant role in addressing growing concerns about food security and guiding decision-making for policymakers and farmers. When deep learning is employed, understanding the learning and decision-making processes of the models, as well as their interaction with the input data, is crucial for establishing trust in the models and gaining insight into their reliability. In this study, we focus on the task of crop yield prediction, specifically for soybean, wheat, and rapeseed crops in Argentina, Uruguay, and Germany. Our goal is to develop and explain predictive models for these crops, using a large dataset of satellite images, additional data modalities, and crop yield maps. We employ a long short-term memory network and investigate the impact of using different temporal samplings of the satellite data and the benefit of adding more relevant modalities. For model explainability, we utilize feature attribution methods to quantify input feature contributions, identify critical growth stages, analyze yield variability at the field level, and explain less accurate predictions. The modeling results show an improvement when adding more modalities or using all available instances of satellite data. The explainability results reveal distinct feature importance patterns for each crop and region. We further found that the most influential growth stages on the prediction are dependent on the temporal sampling of the input data. We demonstrated how these critical growth stages, which hold significant agronomic value, closely align with the existing literature in agronomy and crop development biology.
Authors: Zhenyu Zhang, Ajay Jaiswal, Lu Yin, Shiwei Liu, Jiawei Zhao, Yuandong Tian, Zhangyang Wang
Abstract: Training Large Language Models (LLMs) is memory-intensive due to the large number of parameters and associated optimization states. GaLore, a recent method, reduces memory usage by projecting weight gradients into a low-rank subspace without compromising performance. However, GaLore relies on time-consuming Singular Value Decomposition (SVD) operations to identify the subspace, and the frequent subspace updates lead to significant training time overhead. Moreover, GaLore offers minimal improvements in accuracy and efficiency compared to LoRA in more accessible fine-tuning scenarios. To address these limitations, we introduce Q-Galore, a novel approach that substantially reduces memory usage by combining quantization and low-rank projection, surpassing the benefits of GaLore. Our method is based on two key observations: (i) the gradient subspace exhibits diverse properties, with some layers converging early in training while others are subject to frequent changes; (ii) the projection matrices are highly resilient to low-bit quantization. Leveraging these insights, Q-GaLore adaptively updates the gradient subspace based on its convergence statistics, achieving comparable performance while significantly reducing the number of SVD operations. We maintain the projection matrices in INT4 format and weights in INT8 format, incorporating stochastic rounding to capture accumulated gradient information. This approach enables a high-precision training trajectory using only low-precision weights. We demonstrate that Q-GaLore achieves highly competitive performance with exceptional memory efficiency. At pre-training, Q-GaLore facilitates training a LLaMA-7B model from scratch on a single NVIDIA RTX 4060 Ti with only 16 GB memory. At fine-tuning, it reduces memory consumption by up to 50% compared to LoRA and GaLore, while consistently outperforming QLoRA at the same memory cost.
Authors: Ali Ramlaoui, Th\'eo Saulus, Basile Terver, Victor Schmidt, David Rolnick, Fragkiskos D. Malliaros, Alexandre Duval
Abstract: Rapid advancements in machine learning (ML) are transforming materials science by significantly speeding up material property calculations. However, the proliferation of ML approaches has made it challenging for scientists to keep up with the most promising techniques. This paper presents an empirical study on Geometric Graph Neural Networks for 3D atomic systems, focusing on the impact of different (1) canonicalization methods, (2) graph creation strategies, and (3) auxiliary tasks, on performance, scalability and symmetry enforcement. Our findings and insights aim to guide researchers in selecting optimal modeling components for molecular modeling tasks.
Authors: Adrien Banse, Venkatraman Renganathan, Rapha\"el M. Jungers
Abstract: We extend the notion of Cantor-Kantorovich distance between Markov chains introduced by (Banse et al., 2023) in the context of Markov Decision Processes (MDPs). The proposed metric is well-defined and can be efficiently approximated given a finite horizon. Then, we provide numerical evidences that the latter metric can lead to interesting applications in the field of reinforcement learning. In particular, we show that it could be used for forecasting the performance of transfer learning algorithms.
Authors: Haoyu He, Markus Flicke, Jan Buchmann, Iryna Gurevych, Andreas Geiger
Abstract: In this paper, we propose the Hierarchical Document Transformer (HDT), a novel sparse Transformer architecture tailored for structured hierarchical documents. Such documents are extremely important in numerous domains, including science, law or medicine. However, most existing solutions are inefficient and fail to make use of the structure inherent to documents. HDT exploits document structure by introducing auxiliary anchor tokens and redesigning the attention mechanism into a sparse multi-level hierarchy. This approach facilitates information exchange between tokens at different levels while maintaining sparsity, thereby enhancing computational and memory efficiency while exploiting the document structure as an inductive bias. We address the technical challenge of implementing HDT's sample-dependent hierarchical attention pattern by developing a novel sparse attention kernel that considers the hierarchical structure of documents. As demonstrated by our experiments, utilizing structural information present in documents leads to faster convergence, higher sample efficiency and better performance on downstream tasks.
Authors: Haolin Yu, Guojun Zhang, Pascal Poupart
Abstract: In federated learning (FL), the common paradigm that FedAvg proposes and most algorithms follow is that clients train local models with their private data, and the model parameters are shared for central aggregation, mostly averaging. In this paradigm, the communication cost is often a challenge, as modern massive neural networks can contain millions to billions parameters. We suggest that clients do not share model parameters but local data summaries, to decrease the cost of sharing. We develop a new algorithm FedLog with Bayesian inference, which shares only sufficient statistics of local data. FedLog transmits messages as small as the last layer of the original model. We conducted comprehensive experiments to show we outperform other FL algorithms that aim at decreasing the communication cost. To provide formal privacy guarantees, we further extend FedLog with differential privacy and show the trade-off between privacy budget and accuracy.
Authors: Zhangci Xiong, Meng Cao
Abstract: In recent years, Multi-View Clustering (MVC) has attracted increasing attention for its potential to reduce the annotation burden associated with large datasets. The aim of MVC is to exploit the inherent consistency and complementarity among different views, thereby integrating information from multiple perspectives to improve clustering outcomes. Despite extensive research in MVC, most existing methods focus predominantly on harnessing complementary information across views to enhance clustering effectiveness, often neglecting the structural information among samples, which is crucial for exploring sample correlations. To address this gap, we introduce a novel framework, termed Structured Latent Representation Learning based Multi-View Clustering method (SLRL). SLRL leverages both the complementary and structural information. Initially, it learns a common latent representation for all views. Subsequently, to exploit the structural information among samples, a k-nearest neighbor graph is constructed from this common latent representation. This graph facilitates enhanced sample interaction through graph learning techniques, leading to a structured latent representation optimized for clustering. Extensive experiments demonstrate that SLRL not only competes well with existing methods but also sets new benchmarks in various multi-view datasets.
Authors: Freek Hens, Mohammad Mahdi Dehshibi, Leila Bagheriye, Mahyar Shahsavari, Ana Tajadura-Jim\'enez
Abstract: This paper presents the first application of spiking neural networks (SNNs) for the classification of chronic lower back pain (CLBP) using the EmoPain dataset. Our work has two main contributions. We introduce Spike Threshold Adaptive Learning (STAL), a trainable encoder that effectively converts continuous biosignals into spike trains. Additionally, we propose an ensemble of Spiking Recurrent Neural Network (SRNN) classifiers for the multi-stream processing of sEMG and IMU data. To tackle the challenges of small sample size and class imbalance, we implement minority over-sampling with weighted sample replacement during batch creation. Our method achieves outstanding performance with an accuracy of 80.43%, AUC of 67.90%, F1 score of 52.60%, and Matthews Correlation Coefficient (MCC) of 0.437, surpassing traditional rate-based and latency-based encoding methods. The STAL encoder shows superior performance in preserving temporal dynamics and adapting to signal characteristics. Importantly, our approach (STAL-SRNN) outperforms the best deep learning method in terms of MCC, indicating better balanced class prediction. This research contributes to the development of neuromorphic computing for biosignal analysis. It holds promise for energy-efficient, wearable solutions in chronic pain management.
Authors: Gaspard Lambrechts, Yann Claes, Pierre Geurts, Damien Ernst
Abstract: Attention-based models such as Transformers and recurrent models like state space models (SSMs) have emerged as successful methods for autoregressive sequence modeling. Although both enable parallel training, none enable parallel generation due to their autoregressiveness. We propose the variational SSM (VSSM), a variational autoencoder (VAE) where both the encoder and decoder are SSMs. Since sampling the latent variables and decoding them with the SSM can be parallelized, both training and generation can be conducted in parallel. Moreover, the decoder recurrence allows generation to be resumed without reprocessing the whole sequence. Finally, we propose the autoregressive VSSM that can be conditioned on a partial realization of the sequence, as is common in language generation tasks. Interestingly, the autoregressive VSSM still enables parallel generation. We highlight on toy problems (MNIST, CIFAR) the empirical gains in speed-up and show that it competes with traditional models in terms of generation quality (Transformer, Mamba SSM).
Authors: Karla Sch\"afer, Jeong-Eun Choi, Inna Vogel, Martin Steinebach
Abstract: Topic modeling is frequently being used for analysing large text corpora such as news articles or social media data. BERTopic, consisting of sentence embedding, dimension reduction, clustering, and topic extraction, is the newest and currently the SOTA topic modeling method. However, current topic modeling methods have room for improvement because, as unsupervised methods, they require careful tuning and selection of hyperparameters, e.g., for dimension reduction and clustering. This paper aims to analyse the technical application of BERTopic in practice. For this purpose, it compares and selects different methods and hyperparameters for each stage of BERTopic through density based clustering validation and six different topic coherence measures. Moreover, it also aims to analyse the results of topic modeling on real world data as a use case. For this purpose, the German fake news dataset (GermanFakeNCovid) on Covid-19 was created by us and in order to experiment with topic modeling in a multilingual (English and German) setting combined with the FakeCovid dataset. With the final results, we were able to determine thematic similarities between the United States and Germany. Whereas, distinguishing the topics of fake news from India proved to be more challenging.
Authors: ZiDong Wang, Zeyu Lu, Di Huang, Tong He, Xihui Liu, Wanli Ouyang, Lei Bai
Abstract: In this paper, we introduce PredBench, a benchmark tailored for the holistic evaluation of spatio-temporal prediction networks. Despite significant progress in this field, there remains a lack of a standardized framework for a detailed and comparative analysis of various prediction network architectures. PredBench addresses this gap by conducting large-scale experiments, upholding standardized and appropriate experimental settings, and implementing multi-dimensional evaluations. This benchmark integrates 12 widely adopted methods with 15 diverse datasets across multiple application domains, offering extensive evaluation of contemporary spatio-temporal prediction networks. Through meticulous calibration of prediction settings across various applications, PredBench ensures evaluations relevant to their intended use and enables fair comparisons. Moreover, its multi-dimensional evaluation framework broadens the analysis with a comprehensive set of metrics, providing deep insights into the capabilities of models. The findings from our research offer strategic directions for future developments in the field. Our codebase is available at https://github.com/WZDTHU/PredBench.
Authors: Paul Fischer, Hannah Willms, Moritz Schneider, Daniela Thorwarth, Michael Muehlebach, Christian F. Baumgartner
Abstract: Cancer remains a leading cause of death, highlighting the importance of effective radiotherapy (RT). Magnetic resonance-guided linear accelerators (MR-Linacs) enable imaging during RT, allowing for inter-fraction, and perhaps even intra-fraction, adjustments of treatment plans. However, achieving this requires fast and accurate dose calculations. While Monte Carlo simulations offer accuracy, they are computationally intensive. Deep learning frameworks show promise, yet lack uncertainty quantification crucial for high-risk applications like RT. Risk-controlling prediction sets (RCPS) offer model-agnostic uncertainty quantification with mathematical guarantees. However, we show that naive application of RCPS may lead to only certain subgroups such as the image background being risk-controlled. In this work, we extend RCPS to provide prediction intervals with coverage guarantees for multiple subgroups with unknown subgroup membership at test time. We evaluate our algorithm on real clinical planing volumes from five different anatomical regions and show that our novel subgroup RCPS (SG-RCPS) algorithm leads to prediction intervals that jointly control the risk for multiple subgroups. In particular, our method controls the risk of the crucial voxels along the radiation beam significantly better than conventional RCPS.
Authors: Lukas Moosbrugger, Valentin Seiler, Gerhard Huber, Peter Kepplinger
Abstract: According to a conservative estimate, a 1% reduction in forecast error for a 10 GW energy utility can save up to $ 1.6 million annually. In our context, achieving precise forecasts of future power consumption is crucial for operating flexible energy assets using model predictive control approaches. Specifically, this work focuses on the load profile forecast of a first-year energy community with the common practical challenge of limited historical data availability. We propose to pre-train the load prediction models with open-access synthetic load profiles using transfer learning techniques to tackle this challenge. Results show that this approach improves both, the training stability and prediction error. In a test case with 74 households, the prediction mean squared error (MSE) decreased from 0.34 to 0.13, showing transfer learning based on synthetic load profiles to be a viable approach to compensate for a lack of historic data.
Authors: Linglong Qian, Tao Wang, Jun Wang, Hugh Logan Ellis, Robin Mitra, Richard Dobson, Zina Ibrahim
Abstract: We introduce a novel classification framework for time-series imputation using deep learning, with a particular focus on clinical data. By identifying conceptual gaps in the literature and existing reviews, we devise a taxonomy grounded on the inductive bias of neural imputation frameworks, resulting in a classification of existing deep imputation strategies based on their suitability for specific imputation scenarios and data-specific properties. Our review further examines the existing methodologies employed to benchmark deep imputation models, evaluating their effectiveness in capturing the missingness scenarios found in clinical data and emphasising the importance of reconciling mathematical abstraction with clinical insights. Our classification aims to serve as a guide for researchers to facilitate the selection of appropriate deep learning imputation techniques tailored to their specific clinical data. Our novel perspective also highlights the significance of bridging the gap between computational methodologies and medical insights to achieve clinically sound imputation models.
Authors: Shulin Song, Zheng Zhang, Qiong Wu, Qiang Fan, Pingyi Fan
Abstract: Autonomous driving may be the most important application scenario of next generation, the development of wireless access technologies enabling reliable and low-latency vehicle communication becomes crucial. To address this, 3GPP has developed Vehicle-to-Everything (V2X) specifications based on 5G New Radio (NR) technology, where Mode 2 Side-Link (SL) communication resembles Mode 4 in LTE-V2X, allowing direct communication between vehicles. This supplements SL communication in LTE-V2X and represents the latest advancement in cellular V2X (C-V2X) with improved performance of NR-V2X. However, in NR-V2X Mode 2, resource collisions still occur, and thus degrade the age of information (AOI). Therefore, a interference cancellation method is employed to mitigate this impact by combining NR-V2X with Non-Orthogonal multiple access (NOMA) technology. In NR-V2X, when vehicles select smaller resource reservation interval (RRI), higher-frequency transmissions take ore energy to reduce AoI. Hence, it is important to jointly consider AoI and communication energy consumption based on NR-V2X communication. Then, we formulate such an optimization problem and employ the Deep Reinforcement Learning (DRL) algorithm to compute the optimal transmission RRI and transmission power for each transmitting vehicle to reduce the energy consumption of each transmitting vehicle and the AoI of each receiving vehicle. Extensive simulations have demonstrated the performance of our proposed algorithm.
Authors: Cui Zhang, Wenjun Zhang, Qiong Wu, Pingyi Fan, Qiang Fan, Jiangzhou Wang, Khaled B. Letaief
Abstract: Federated Learning (FL) can protect the privacy of the vehicles in vehicle edge computing (VEC) to a certain extent through sharing the gradients of vehicles' local models instead of local data. The gradients of vehicles' local models are usually large for the vehicular artificial intelligence (AI) applications, thus transmitting such large gradients would cause large per-round latency. Gradient quantization has been proposed as one effective approach to reduce the per-round latency in FL enabled VEC through compressing gradients and reducing the number of bits, i.e., the quantization level, to transmit gradients. The selection of quantization level and thresholds determines the quantization error, which further affects the model accuracy and training time. To do so, the total training time and quantization error (QE) become two key metrics for the FL enabled VEC. It is critical to jointly optimize the total training time and QE for the FL enabled VEC. However, the time-varying channel condition causes more challenges to solve this problem. In this paper, we propose a distributed deep reinforcement learning (DRL)-based quantization level allocation scheme to optimize the long-term reward in terms of the total training time and QE. Extensive simulations identify the optimal weighted factors between the total training time and QE, and demonstrate the feasibility and effectiveness of the proposed scheme.
Authors: Junik Bae, Kwanyoung Park, Youngwoon Lee
Abstract: Unsupervised goal-conditioned reinforcement learning (GCRL) is a promising paradigm for developing diverse robotic skills without external supervision. However, existing unsupervised GCRL methods often struggle to cover a wide range of states in complex environments due to their limited exploration and sparse or noisy rewards for GCRL. To overcome these challenges, we propose a novel unsupervised GCRL method that leverages TemporaL Distance-aware Representations (TLDR). TLDR selects faraway goals to initiate exploration and computes intrinsic exploration rewards and goal-reaching rewards, based on temporal distance. Specifically, our exploration policy seeks states with large temporal distances (i.e. covering a large state space), while the goal-conditioned policy learns to minimize the temporal distance to the goal (i.e. reaching the goal). Our experimental results in six simulated robotic locomotion environments demonstrate that our method significantly outperforms previous unsupervised GCRL methods in achieving a wide variety of states.
Authors: Daniel F. Perez-Ramirez, Carlos P\'erez-Penichet, Nicolas Tsiftes, Dejan Kostic, Magnus Boman, Thiemo Voigt
Abstract: Battery-free sensor tags are devices that leverage backscatter techniques to communicate with standard IoT devices, thereby augmenting a network's sensing capabilities in a scalable way. For communicating, a sensor tag relies on an unmodulated carrier provided by a neighboring IoT device, with a schedule coordinating this provisioning across the network. Carrier scheduling--computing schedules to interrogate all sensor tags while minimizing energy, spectrum utilization, and latency--is an NP-Hard optimization problem. Recent work introduces learning-based schedulers that achieve resource savings over a carefully-crafted heuristic, generalizing to networks of up to 60 nodes. However, we find that their advantage diminishes in networks with hundreds of nodes, and degrades further in larger setups. This paper introduces RobustGANTT, a GNN-based scheduler that improves generalization (without re-training) to networks up to 1000 nodes (100x training topology sizes). RobustGANTT not only achieves better and more consistent generalization, but also computes schedules requiring up to 2x less resources than existing systems. Our scheduler exhibits average runtimes of hundreds of milliseconds, allowing it to react fast to changing network conditions. Our work not only improves resource utilization in large-scale backscatter networks, but also offers valuable insights in learning-based scheduling.
Authors: Yuxing Tian, Yiyan Qi, Aiwen Jiang, Qi Huang, Jian Guo
Abstract: Continuous-Time Dynamic Graph (CTDG) precisely models evolving real-world relationships, drawing heightened interest in dynamic graph learning across academia and industry. However, existing CTDG models encounter challenges stemming from noise and limited historical data. Graph Data Augmentation (GDA) emerges as a critical solution, yet current approaches primarily focus on static graphs and struggle to effectively address the dynamics inherent in CTDGs. Moreover, these methods often demand substantial domain expertise for parameter tuning and lack theoretical guarantees for augmentation efficacy. To address these issues, we propose Conda, a novel latent diffusion-based GDA method tailored for CTDGs. Conda features a sandwich-like architecture, incorporating a Variational Auto-Encoder (VAE) and a conditional diffusion model, aimed at generating enhanced historical neighbor embeddings for target nodes. Unlike conventional diffusion models trained on entire graphs via pre-training, Conda requires historical neighbor sequence embeddings of target nodes for training, thus facilitating more targeted augmentation. We integrate Conda into the CTDG model and adopt an alternating training strategy to optimize performance. Extensive experimentation across six widely used real-world datasets showcases the consistent performance improvement of our approach, particularly in scenarios with limited historical data.
Authors: Jay Shah, Ganesh Bikshandi, Ying Zhang, Vijay Thakkar, Pradeep Ramani, Tri Dao
Abstract: Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. FlashAttention elaborated an approach to speed up attention on GPUs through minimizing memory reads/writes. However, it has yet to take advantage of new capabilities present in recent hardware, with FlashAttention-2 achieving only 35% utilization on the H100 GPU. We develop three main techniques to speed up attention on Hopper GPUs: exploiting asynchrony of the Tensor Cores and TMA to (1) overlap overall computation and data movement via warp-specialization and (2) interleave block-wise matmul and softmax operations, and (3) block quantization and incoherent processing that leverages hardware support for FP8 low-precision. We demonstrate that our method, FlashAttention-3, achieves speedup on H100 GPUs by 1.5-2.0$\times$ with FP16 reaching up to 740 TFLOPs/s (75% utilization), and with FP8 reaching close to 1.2 PFLOPs/s. We validate that FP8 FlashAttention-3 achieves 2.6$\times$ lower numerical error than a baseline FP8 attention.
Authors: Federico Tessari, Neville Hogan
Abstract: The advancement in computational power and hardware efficiency has enabled the tackling of increasingly complex and high-dimensional problems. While artificial intelligence (AI) has achieved remarkable results in various scientific and technological fields, the interpretability of these high-dimensional solutions remains challenging. A critical issue in this context is the comparison of multidimensional quantities, which is essential in techniques like Principal Component Analysis (PCA), Singular Value Decomposition (SVD), and k-means clustering. Common metrics such as cosine similarity, Euclidean distance, and Manhattan distance are often used for such comparisons - for example in muscular synergies of the human motor control system. However, their applicability and interpretability diminish as dimensionality increases. This paper provides a comprehensive analysis of the effects of dimensionality on these three widely used metrics. Our results reveal significant limitations of cosine similarity, particularly its dependency on the dimensionality of the vectors, leading to biased and less interpretable outcomes. To address this, we introduce the Dimension Insensitive Euclidean Metric (DIEM), derived from the Euclidean distance, which demonstrates superior robustness and generalizability across varying dimensions. DIEM maintains consistent variability and eliminates the biases observed in traditional metrics, making it a more reliable tool for high-dimensional comparisons. This novel metric has the potential to replace cosine similarity, providing a more accurate and insightful method to analyze multidimensional data in fields ranging from neuromotor control to machine learning and deep learning.
Authors: Kevin Qiu, Krzysztof Ciebiera, Pawe{\l} Fija{\l}kowski, Marek Cygan, {\L}ukasz Kuci\'nski
Abstract: We introduce RoboMorph, an automated approach for generating and optimizing modular robot designs using large language models (LLMs) and evolutionary algorithms. In this framework, we represent each robot design as a grammar and leverage the capabilities of LLMs to navigate the extensive robot design space, which is traditionally time-consuming and computationally demanding. By integrating automatic prompt design and a reinforcement learning based control algorithm, RoboMorph iteratively improves robot designs through feedback loops. Our experimental results demonstrate that RoboMorph can successfully generate nontrivial robots that are optimized for a single terrain while showcasing improvements in morphology over successive evolutions. Our approach demonstrates the potential of using LLMs for data-driven and modular robot design, providing a promising methodology that can be extended to other domains with similar design frameworks.
Authors: Haoxiang Ye, Qing Ling
Abstract: Recently, decentralized learning has emerged as a popular peer-to-peer signal and information processing paradigm that enables model training across geographically distributed agents in a scalable manner, without the presence of any central server. When some of the agents are malicious (also termed as Byzantine), resilient decentralized learning algorithms are able to limit the impact of these Byzantine agents without knowing their number and identities, and have guaranteed optimization errors. However, analysis of the generalization errors, which are critical to implementations of the trained models, is still lacking. In this paper, we provide the first analysis of the generalization errors for a class of popular Byzantine-resilient decentralized stochastic gradient descent (DSGD) algorithms. Our theoretical results reveal that the generalization errors cannot be entirely eliminated because of the presence of the Byzantine agents, even if the number of training samples are infinitely large. Numerical experiments are conducted to confirm our theoretical results.
Authors: Yuanzhao Zhang, Sean P. Cornelius
Abstract: It has been found recently that more data can, counter-intuitively, hurt the performance of deep neural networks. Here, we show that a more extreme version of the phenomenon occurs in data-driven models of dynamical systems. To elucidate the underlying mechanism, we focus on next-generation reservoir computing (NGRC) -- a popular framework for learning dynamics from data. We find that, despite learning a better representation of the flow map with more training data, NGRC can adopt an ill-conditioned ``integrator'' and lose stability. We link this data-induced instability to the auxiliary dimensions created by the delayed states in NGRC. Based on these findings, we propose simple strategies to mitigate the instability, either by increasing regularization strength in tandem with data size, or by carefully introducing noise during training. Our results highlight the importance of proper regularization in data-driven modeling of dynamical systems.
Authors: Juhani Kivim\"aki, Jakub Bia{\l}ek, Jukka K. Nurminen, Wojtek Kuberski
Abstract: After a machine learning model has been deployed into production, its predictive performance needs to be monitored. Ideally, such monitoring can be carried out by comparing the model's predictions against ground truth labels. For this to be possible, the ground truth labels must be available relatively soon after inference. However, there are many use cases where ground truth labels are available only after a significant delay, or in the worst case, not at all. In such cases, directly monitoring the model's predictive performance is impossible. Recently, novel methods for estimating the predictive performance of a model when ground truth is unavailable have been developed. Many of these methods leverage model confidence or other uncertainty estimates and are experimentally compared against a naive baseline method, namely Average Confidence (AC), which estimates model accuracy as the average of confidence scores for a given set of predictions. However, until now the theoretical properties of the AC method have not been properly explored. In this paper, we try to fill this gap by reviewing the AC method and show that under certain general assumptions, it is an unbiased and consistent estimator of model accuracy with many desirable properties. We also compare this baseline estimator against some more complex estimators empirically and show that in many cases the AC method is able to beat the others, although the comparative quality of the different estimators is heavily case-dependent.
Authors: Shuangqi Li, Chen Liu, Tong Zhang, Hieu Le, Sabine S\"usstrunk, Mathieu Salzmann
Abstract: We introduce an approach to bias deep generative models, such as GANs and diffusion models, towards generating data with either enhanced fidelity or increased diversity. Our approach involves manipulating the distribution of training and generated data through a novel metric for individual samples, named pseudo density, which is based on the nearest-neighbor information from real samples. Our approach offers three distinct techniques to adjust the fidelity and diversity of deep generative models: 1) Per-sample perturbation, enabling precise adjustments for individual samples towards either more common or more unique characteristics; 2) Importance sampling during model inference to enhance either fidelity or diversity in the generated data; 3) Fine-tuning with importance sampling, which guides the generative model to learn an adjusted distribution, thus controlling fidelity and diversity. Furthermore, our fine-tuning method demonstrates the ability to improve the Frechet Inception Distance (FID) for pre-trained generative models with minimal iterations.
Authors: Zihan Ding, Kexin Jin, Jonas Latz, Chenguang Liu
Abstract: Deep neural networks and other modern machine learning models are often susceptible to adversarial attacks. Indeed, an adversary may often be able to change a model's prediction through a small, directed perturbation of the model's input - an issue in safety-critical applications. Adversarially robust machine learning is usually based on a minmax optimisation problem that minimises the machine learning loss under maximisation-based adversarial attacks. In this work, we study adversaries that determine their attack using a Bayesian statistical approach rather than maximisation. The resulting Bayesian adversarial robustness problem is a relaxation of the usual minmax problem. To solve this problem, we propose Abram - a continuous-time particle system that shall approximate the gradient flow corresponding to the underlying learning problem. We show that Abram approximates a McKean-Vlasov process and justify the use of Abram by giving assumptions under which the McKean-Vlasov process finds the minimiser of the Bayesian adversarial robustness problem. We discuss two ways to discretise Abram and show its suitability in benchmark adversarial deep learning experiments.
Authors: Anton Alexandrov, Veselin Raychev, Mark Niklas M\"uller, Ce Zhang, Martin Vechev, Kristina Toutanova
Abstract: As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different languages. However, such language adaptation is often accompanied by catastrophic forgetting of the base model's capabilities, severely limiting the usefulness of the resulting model. We address this issue by proposing Branch-and-Merge (BaM), a new adaptation method based on iteratively merging multiple models, fine-tuned on a subset of the available training data. BaM is based on the insight that this yields lower magnitude but higher quality weight changes, reducing forgetting of the source domain while maintaining learning on the target domain. We demonstrate in an extensive empirical study on Bulgarian and German that BaM can significantly reduce forgetting while matching or even improving target domain performance compared to both standard continued pretraining and instruction finetuning across different model architectures.
Authors: Dina Hussein, Lubah Nelson, Ganapati Bhat
Abstract: Time-series data processing is an important component of many real-world applications, such as health monitoring, environmental monitoring, and digital agriculture. These applications collect distinct windows of sensor data (e.g., few seconds) and process them to assess the environment. Machine learning (ML) models are being employed in time-series applications due to their generalization abilities for classification. State-of-the-art time-series applications wait for entire sensor data window to become available before processing the data using ML algorithms, resulting in high sensor energy consumption. However, not all situations require processing full sensor window to make accurate inference. For instance, in activity recognition, sitting and standing activities can be inferred with partial windows. Using this insight, we propose to employ early exit classifiers with partial sensor windows to minimize energy consumption while maintaining accuracy. Specifically, we first utilize multiple early exits with successively increasing amount of data as they become available in a window. If early exits provide inference with high confidence, we return the label and enter low power mode for sensors. The proposed approach has potential to enable significant energy savings in time series applications. We utilize neural networks and random forest classifiers to evaluate our approach. Our evaluations with six datasets show that the proposed approach enables up to 50-60% energy savings on average without any impact on accuracy. The energy savings can enable time-series applications in remote locations with limited energy availability.
Authors: Rayna Andreeva, Benjamin Dupuis, Rik Sarkar, Tolga Birdal, Umut \c{S}im\c{s}ekli
Abstract: We present a novel set of rigorous and computationally efficient topology-based complexity notions that exhibit a strong correlation with the generalization gap in modern deep neural networks (DNNs). DNNs show remarkable generalization properties, yet the source of these capabilities remains elusive, defying the established statistical learning theory. Recent studies have revealed that properties of training trajectories can be indicative of generalization. Building on this insight, state-of-the-art methods have leveraged the topology of these trajectories, particularly their fractal dimension, to quantify generalization. Most existing works compute this quantity by assuming continuous- or infinite-time training dynamics, complicating the development of practical estimators capable of accurately predicting generalization without access to test data. In this paper, we respect the discrete-time nature of training trajectories and investigate the underlying topological quantities that can be amenable to topological data analysis tools. This leads to a new family of reliable topological complexity measures that provably bound the generalization error, eliminating the need for restrictive geometric assumptions. These measures are computationally friendly, enabling us to propose simple yet effective algorithms for computing generalization indices. Moreover, our flexible framework can be extended to different domains, tasks, and architectures. Our experimental results demonstrate that our new complexity measures correlate highly with generalization error in industry-standards architectures such as transformers and deep graph networks. Our approach consistently outperforms existing topological bounds across a wide range of datasets, models, and optimizers, highlighting the practical relevance and effectiveness of our complexity measures.
Authors: Joseph Miller, Bilal Chughtai, William Saunders
Abstract: Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subgraphs of the full model that explain behaviour on specific tasks. But how do we measure the performance of such circuits? Prior work has attempted to measure circuit 'faithfulness' -- the degree to which the circuit replicates the performance of the full model. In this work, we survey many considerations for designing experiments that measure circuit faithfulness by ablating portions of the model's computation. Concerningly, we find existing methods are highly sensitive to seemingly insignificant changes in the ablation methodology. We conclude that existing circuit faithfulness scores reflect both the methodological choices of researchers as well as the actual components of the circuit - the task a circuit is required to perform depends on the ablation used to test it. The ultimate goal of mechanistic interpretability work is to understand neural networks, so we emphasize the need for more clarity in the precise claims being made about circuits. We open source a library at https://github.com/UFO-101/auto-circuit that includes highly efficient implementations of a wide range of ablation methodologies and circuit discovery algorithms.
Authors: D\'avid Hidv\'egi, Khashayar Etemadi, Sofia Bobadilla, Martin Monperrus
Abstract: Large language models (LLM) have proven to be effective at automated program repair (APR). However, using LLMs can be costly, with companies invoicing users by the number of tokens. In this paper, we propose CigaR, the first LLM-based APR tool that focuses on minimizing the repair cost. CigaR works in two major steps: generating a first plausible patch and multiplying plausible patches. CigaR optimizes the prompts and the prompt setting to maximize the information given to LLMs using the smallest possible number of tokens. Our experiments on 429 bugs from the widely used Defects4J and HumanEval-Java datasets shows that CigaR reduces the token cost by 73%. On average, CigaR spends 127k tokens per bug while the baseline uses 467k tokens per bug. On the subset of bugs that are fixed by both, CigaR spends 20k per bug while the baseline uses 608k tokens, a cost saving of 96%. Our extensive experiments show that CigaR is a cost-effective LLM-based program repair tool that uses a low number of tokens to automatically generate patches.
Authors: Yannis Karmim, Elias Ramzi, Rapha\"el Fournier-S'niehotta, Nicolas Thome
Abstract: Graph Neural Networks (GNNs), especially message-passing-based models, have become prominent in top-k recommendation tasks, outperforming matrix factorization models due to their ability to efficiently aggregate information from a broader context. Although GNNs are evaluated with ranking-based metrics, e.g NDCG@k and Recall@k, they remain largely trained with proxy losses, e.g the BPR loss. In this work we explore the use of ranking loss functions to directly optimize the evaluation metrics, an area not extensively investigated in the GNN community for collaborative filtering. We take advantage of smooth approximations of the rank to facilitate end-to-end training of GNNs and propose a Personalized PageRank-based negative sampling strategy tailored for ranking loss functions. Moreover, we extend the evaluation of GNN models for top-k recommendation tasks with an inductive user-centric protocol, providing a more accurate reflection of real-world applications. Our proposed method significantly outperforms the standard BPR loss and more advanced losses across four datasets and four recent GNN architectures while also exhibiting faster training. Demonstrating the potential of ranking loss functions in improving GNN training for collaborative filtering tasks.
Authors: Rainer Feichtinger, Florian Gr\"otschla, Lioba Heimbach, Roger Wattenhofer
Abstract: The Bitcoin Lightning Network is a layer 2 protocol designed to facilitate fast and inexpensive Bitcoin transactions. It operates by establishing channels between users, where Bitcoin is locked and transactions are conducted off-chain until the channels are closed, with only the initial and final transactions recorded on the blockchain. Routing transactions through intermediary nodes is crucial for users without direct channels, allowing these routing nodes to collect fees for their services. Nodes announce their channels to the network, forming a graph with channels as edges. In this paper, we analyze the graph structure of the Lightning Network and investigate the statistical relationships between node properties using machine learning, particularly Graph Neural Networks (GNNs). We formulate a series of tasks to explore these relationships and provide benchmarks for GNN architectures, demonstrating how topological and neighbor information enhances performance. Our evaluation of several models reveals the effectiveness of GNNs in these tasks and highlights the insights gained from their application.
Authors: Tuan Nguyen, Dung Thuy Nguyen, Khoa D Doan, Kok-Seng Wong
Abstract: Despite the promise of Federated Learning (FL) for privacy-preserving model training on distributed data, it remains susceptible to backdoor attacks. These attacks manipulate models by embedding triggers (specific input patterns) in the training data, forcing misclassification as predefined classes during deployment. Traditional single-trigger attacks and recent work on cooperative multiple-trigger attacks, where clients collaborate, highlight limitations in attack realism due to coordination requirements. We investigate a more alarming scenario: non-cooperative multiple-trigger attacks. Here, independent adversaries introduce distinct triggers targeting unique classes. These parallel attacks exploit FL's decentralized nature, making detection difficult. Our experiments demonstrate the alarming vulnerability of FL to such attacks, where individual backdoors can be successfully learned without impacting the main task. This research emphasizes the critical need for robust defenses against diverse backdoor attacks in the evolving FL landscape. While our focus is on empirical analysis, we believe it can guide backdoor research toward more realistic settings, highlighting the crucial role of FL in building robust defenses against diverse backdoor threats. The code is available at \url{https://anonymous.4open.science/r/nba-980F/}.
Authors: Oladipo A. Madamidola, Felix Ngobigha, Adnane Ez-zizi
Abstract: Machine learning has been successfully applied in developing malware detection systems, with a primary focus on accuracy, and increasing attention to reducing computational overhead and improving model interpretability. However, an important question remains underexplored: How well can machine learning-based models detect entirely new forms of malware not present in the training data? In this study, we present a machine learning-based system for detecting obfuscated malware that is not only highly accurate, lightweight and interpretable, but also capable of successfully adapting to new types of malware attacks. Our system is capable of detecting 15 malware subtypes despite being exclusively trained on one malware subtype, namely the Transponder from the Spyware family. This system was built after training 15 distinct random forest-based models, each on a different malware subtype from the CIC-MalMem-2022 dataset. These models were evaluated against the entire range of malware subtypes, including all unseen malware subtypes. To maintain the system's streamlined nature, training was confined to the top five most important features, which also enhanced interpretability. The Transponder-focused model exhibited high accuracy, exceeding 99.8%, with an average processing speed of 5.7 microseconds per file. We also illustrate how the Shapley additive explanations technique can facilitate the interpretation of the model predictions. Our research contributes to advancing malware detection methodologies, pioneering the feasibility of detecting obfuscated malware by exclusively training a model on a single or a few carefully selected malware subtypes and applying it to detect unseen subtypes.
Authors: Junfei Wang, He Huang, Jingze Feng, Steven Wong, Lihua Xie, Jianfei Yang
Abstract: There is a significant demand for indoor localization technology in smart buildings, and the most promising solution in this field is using RF sensors and fingerprinting-based methods that employ machine learning models trained on crowd-sourced user data gathered from IoT devices. However, this raises security and privacy issues in practice. Some researchers propose to use federated learning to partially overcome privacy problems, but there still remain security concerns, e.g., single-point failure and malicious attacks. In this paper, we propose a framework named DFLoc to achieve precise 3D localization tasks while considering the following two security concerns. Particularly, we design a specialized blockchain to decentralize the framework by distributing the tasks such as model distribution and aggregation which are handled by a central server to all clients in most previous works, to address the issue of the single-point failure for a reliable and accurate indoor localization system. Moreover, we introduce an updated model verification mechanism within the blockchain to alleviate the concern of malicious node attacks. Experimental results substantiate the framework's capacity to deliver accurate 3D location predictions and its superior resistance to the impacts of single-point failure and malicious attacks when compared to conventional centralized federated learning systems.
Authors: Christopher De Baets, Basem Suleiman, Armin Chitizadeh, Imran Razzak
Abstract: In the growing field of blockchain technology, smart contracts exist as transformative digital agreements that execute transactions autonomously in decentralised networks. However, these contracts face challenges in the form of security vulnerabilities, posing significant financial and operational risks. While traditional methods to detect and mitigate vulnerabilities in smart contracts are limited due to a lack of comprehensiveness and effectiveness, integrating advanced machine learning technologies presents an attractive approach to increasing effective vulnerability countermeasures. We endeavour to fill an important gap in the existing literature by conducting a rigorous systematic review, exploring the intersection between machine learning and smart contracts. Specifically, the study examines the potential of machine learning techniques to improve the detection and mitigation of vulnerabilities in smart contracts. We analysed 88 articles published between 2018 and 2023 from the following databases: IEEE, ACM, ScienceDirect, Scopus, and Google Scholar. The findings reveal that classical machine learning techniques, including KNN, RF, DT, XG-Boost, and SVM, outperform static tools in vulnerability detection. Moreover, multi-model approaches integrating deep learning and classical machine learning show significant improvements in precision and recall, while hybrid models employing various techniques achieve near-perfect performance in vulnerability detection accuracy. By integrating state-of-the-art solutions, this work synthesises current methods, thoroughly investigates research gaps, and suggests directions for future studies. The insights gathered from this study are intended to serve as a seminal reference for academics, industry experts, and bodies interested in leveraging machine learning to enhance smart contract security.
Authors: Jihai Zhang, Wei Wang, Siyan Guo, Li Wang, Fangquan Lin, Cheng Yang, Wotao Yin
Abstract: Optimization problems seek to find the best solution to an objective under a set of constraints, and have been widely investigated in real-world applications. Modeling and solving optimization problems in a specific domain typically require a combination of domain knowledge, mathematical skills, and programming ability, making it difficult for general users and even domain professionals. In this paper, we propose a novel framework called OptLLM that augments LLMs with external solvers. Specifically, OptLLM accepts user queries in natural language, convert them into mathematical formulations and programming codes, and calls the solvers to calculate the results for decision-making. In addition, OptLLM supports multi-round dialogues to gradually refine the modeling and solving of optimization problems. To illustrate the effectiveness of OptLLM, we provide tutorials on three typical optimization applications and conduct experiments on both prompt-based GPT models and a fine-tuned Qwen model using a large-scale selfdeveloped optimization dataset. Experimental results show that OptLLM works with various LLMs, and the fine-tuned model achieves an accuracy boost compared to the promptbased models. Some features of OptLLM framework have been available for trial since June 2023 (https://opt.alibabacloud.com/chat or https://opt.aliyun.com/chat).
URLs: https://opt.alibabacloud.com/chat, https://opt.aliyun.com/chat).
Authors: Fatima Jahan Sarmin, Atiquer Rahman Sarkar, Yang Wang, Noman Mohammed
Abstract: Synthetic data has been considered a better privacy-preserving alternative to traditionally sanitized data across various applications. However, a recent article challenges this notion, stating that synthetic data does not provide a better trade-off between privacy and utility than traditional anonymization techniques, and that it leads to unpredictable utility loss and highly unpredictable privacy gain. The article also claims to have identified a breach in the differential privacy guarantees provided by PATEGAN and PrivBayes. When a study claims to refute or invalidate prior findings, it is crucial to verify and validate the study. In our work, we analyzed the implementation of the privacy game described in the article and found that it operated in a highly specialized and constrained environment, which limits the applicability of its findings to general cases. Our exploration also revealed that the game did not satisfy a crucial precondition concerning data distributions, which contributed to the perceived violation of the differential privacy guarantees offered by PATEGAN and PrivBayes. We also conducted a privacy-utility trade-off analysis in a more general and unconstrained environment. Our experimentation demonstrated that synthetic data achieves a more favorable privacy-utility trade-off compared to the provided implementation of k-anonymization, thereby reaffirming earlier conclusions.
Authors: Jike Wang, Rui Qin, Mingyang Wang, Meijing Fang, Yangyang Zhang, Yuchen Zhu, Qun Su, Qiaolin Gou, Chao Shen, Odin Zhang, Zhenxing Wu, Dejun Jiang, Xujun Zhang, Huifeng Zhao, Xiaozhe Wan, Zhourui Wu, Liwei Liu, Yu Kang, Chang-Yu Hsieh, Tingjun Hou
Abstract: Significant interests have recently risen in leveraging sequence-based large language models (LLMs) for drug design. However, most current applications of LLMs in drug discovery lack the ability to comprehend three-dimensional (3D) structures, thereby limiting their effectiveness in tasks that explicitly involve molecular conformations. In this study, we introduced Token-Mol, a token-only 3D drug design model. This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in drug discovery into probabilistic prediction problems, thereby enabling learning through a unified paradigm. Token-Mol is built on the transformer decoder architecture and trained using random causal masking techniques. Additionally, we proposed the Gaussian cross-entropy (GCE) loss function to overcome the challenges in regression tasks, significantly enhancing the capacity of LLMs to learn continuous numerical values. Through a combination of fine-tuning and reinforcement learning (RL), Token-Mol achieves performance comparable to or surpassing existing task-specific methods across various downstream tasks, including pocket-based molecular generation, conformation generation, and molecular property prediction. Compared to existing molecular pre-trained models, Token-Mol exhibits superior proficiency in handling a wider range of downstream tasks essential for drug design. Notably, our approach improves regression task accuracy by approximately 30% compared to similar token-only methods. Token-Mol overcomes the precision limitations of token-only models and has the potential to integrate seamlessly with general models such as ChatGPT, paving the way for the development of a universal artificial intelligence drug design model that facilitates rapid and high-quality drug design by experts.
Authors: Yuzhou Yang, Yangming Zhou, Qichao Ying, Zhenxing Qian, Xinpeng Zhang
Abstract: Pioneer researches recognize evidences as crucial elements in fake news detection apart from patterns. Existing evidence-aware methods either require laborious pre-processing procedures to assure relevant and high-quality evidence data, or incorporate the entire spectrum of available evidences in all news cases, regardless of the quality and quantity of the retrieved data. In this paper, we propose an approach named \textbf{SEE} that retrieves useful information from web-searched annotation-free evidences with an early-termination mechanism. The proposed SEE is constructed by three main phases: \textbf{S}earching online materials using the news as a query and directly using their titles as evidences without any annotating or filtering procedure, sequentially \textbf{E}xamining the news alongside with each piece of evidence via attention mechanisms to produce new hidden states with retrieved information, and allowing \textbf{E}arly-termination within the examining loop by assessing whether there is adequate confidence for producing a correct prediction. We have conducted extensive experiments on datasets with unprocessed evidences, i.e., Weibo21, GossipCop, and pre-processed evidences, namely Snopes and PolitiFact. The experimental results demonstrate that the proposed method outperforms state-of-the-art approaches.
Authors: Feng Xie, Zhen Yao, Lin Xie, Yan Zeng, Zhi Geng
Abstract: We consider the challenging problem of estimating causal effects from purely observational data in the bi-directional Mendelian randomization (MR), where some invalid instruments, as well as unmeasured confounding, usually exist. To address this problem, most existing methods attempt to find proper valid instrumental variables (IVs) for the target causal effect by expert knowledge or by assuming that the causal model is a one-directional MR model. As such, in this paper, we first theoretically investigate the identification of the bi-directional MR from observational data. In particular, we provide necessary and sufficient conditions under which valid IV sets are correctly identified such that the bi-directional MR model is identifiable, including the causal directions of a pair of phenotypes (i.e., the treatment and outcome). Moreover, based on the identification theory, we develop a cluster fusion-like method to discover valid IV sets and estimate the causal effects of interest. We theoretically demonstrate the correctness of the proposed algorithm. Experimental results show the effectiveness of our method for estimating causal effects in bi-directional MR.
Authors: Sai Srivatsa Ravindranath, Zhe Feng, Di Wang, Manzil Zaheer, Aranyak Mehta, David C. Parkes
Abstract: Revenue-optimal auction design is a challenging problem with significant theoretical and practical implications. Sequential auction mechanisms, known for their simplicity and strong strategyproofness guarantees, are often limited by theoretical results that are largely existential, except for certain restrictive settings. Although traditional reinforcement learning methods such as Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) are applicable in this domain, they struggle with computational demands and convergence issues when dealing with large and continuous action spaces. In light of this and recognizing that we can model transitions differentiable for our settings, we propose using a new reinforcement learning framework tailored for sequential combinatorial auctions that leverages first-order gradients. Our extensive evaluations show that our approach achieves significant improvement in revenue over both analytical baselines and standard reinforcement learning algorithms. Furthermore, we scale our approach to scenarios involving up to 50 agents and 50 items, demonstrating its applicability in complex, real-world auction settings. As such, this work advances the computational tools available for auction design and contributes to bridging the gap between theoretical results and practical implementations in sequential auction design.
Authors: Xijie Huang, Zechun Liu, Shih-Yang Liu, Kwang-Ting Cheng
Abstract: Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the weights in Large Language Models (LLMs). Recently, weight-only quantization techniques have also been applied to LoRA methods to reduce the memory footprint of fine-tuning. However, applying weight-activation quantization to the LoRA pipeline is under-explored, and we observe substantial performance degradation primarily due to the presence of activation outliers. In this work, we propose RoLoRA, the first LoRA-based scheme for effective weight-activation quantization. RoLoRA utilizes rotation for outlier elimination and proposes rotation-aware fine-tuning to preserve the outlier-free characteristics in rotated LLMs. Experimental results show RoLoRA consistently improves low-bit LoRA convergence and post-training quantization robustness in weight-activation settings. We evaluate RoLoRA across LLaMA2-7B/13B, LLaMA3-8B models, achieving up to 29.5% absolute accuracy gain of 4-bit weight-activation quantized LLaMA2- 13B on commonsense reasoning tasks compared to LoRA baseline. We further demonstrate its effectiveness on Large Multimodal Models (LLaVA-1.5-7B). Codes are available at https://github.com/HuangOwen/RoLoRA
Authors: Isaac Sheidlower, Reuben Aronson, Elaine Schaertl Short
Abstract: Foundation models are a promising path toward general-purpose and user-friendly robots. The prevalent approach involves training a generalist policy that, like a reinforcement learning policy, uses observations to output actions. Although this approach has seen much success, several concerns arise when considering deployment and end-user interaction with these systems. In particular, the lack of modularity between tasks means that when model weights are updated (e.g., when a user provides feedback), the behavior in other, unrelated tasks may be affected. This can negatively impact the system's interpretability and usability. We present an alternative approach to the design of robot foundation models, Diffusion for Policy Parameters (DPP), which generates stand-alone, task-specific policies. Since these policies are detached from the foundation model, they are updated only when a user wants, either through feedback or personalization, allowing them to gain a high degree of familiarity with that policy. We demonstrate a proof-of-concept of DPP in simulation then discuss its limitations and the future of interpretable foundation models.
Authors: Donghyun Kim, Aws Khalil, Haewoon Nam, Jaerock Kwon
Abstract: Autonomous Vehicles (AV) and Advanced Driver Assistant Systems (ADAS) prioritize safety over comfort. The intertwining factors of safety and comfort emerge as pivotal elements in ensuring the effectiveness of Autonomous Driving (AD). Users often experience discomfort when AV or ADAS drive the vehicle on their behalf. Providing a personalized human-like AD experience, tailored to match users' unique driving styles while adhering to safety prerequisites, presents a significant opportunity to boost the acceptance of AVs. This paper proposes a novel approach, Neural Driving Style Transfer (NDST), inspired by Neural Style Transfer (NST), to address this issue. NDST integrates a Personalized Block (PB) into the conventional Baseline Driving Model (BDM), allowing for the transfer of a user's unique driving style while adhering to safety parameters. The PB serves as a self-configuring system, learning and adapting to an individual's driving behavior without requiring modifications to the BDM. This approach enables the personalization of AV models, aligning the driving style more closely with user preferences while ensuring baseline safety critical actuation. Two contrasting driving styles (Style A and Style B) were used to validate the proposed NDST methodology, demonstrating its efficacy in transferring personal driving styles to the AV system. Our work highlights the potential of NDST to enhance user comfort in AVs by providing a personalized and familiar driving experience. The findings affirm the feasibility of integrating NDST into existing AV frameworks to bridge the gap between safety and individualized driving styles, promoting wider acceptance and improved user experiences.
Authors: Matteo Carli, Aldo Glielmo, Alex Rodriguez, Alessandro Laio
Abstract: We introduce the Binless Multidimensional Thermodynamic Integration (BMTI) method for nonparametric, robust, and data-efficient density estimation. BMTI estimates the logarithm of the density by initially computing log-density differences between neighbouring data points. Subsequently, such differences are integrated, weighted by their associated uncertainties, using a maximum-likelihood formulation. This procedure can be seen as an extension to a multidimensional setting of the thermodynamic integration, a technique developed in statistical physics. The method leverages the manifold hypothesis, estimating quantities within the intrinsic data manifold without defining an explicit coordinate map. It does not rely on any binning or space partitioning, but rather on the construction of a neighbourhood graph based on an adaptive bandwidth selection procedure. BMTI mitigates the limitations commonly associated with traditional nonparametric density estimators, effectively reconstructing smooth profiles even in high-dimensional embedding spaces. The method is tested on a variety of complex synthetic high-dimensional datasets, where it is shown to outperform traditional estimators, and is benchmarked on realistic datasets from the chemical physics literature.
Authors: Hossein Entezari Zarch, Abdulla Alshabanah, Chaoyi Jiang, Murali Annavaram
Abstract: Deep learning recommendation models (DLRMs) are at the heart of the current e-commerce industry. However, the amount of training data used to train these large models is growing exponentially, leading to substantial training hurdles. The training dataset contains two primary types of information: content-based information (features of users and items) and collaborative information (interactions between users and items). One approach to reduce the training dataset is to remove user-item interactions. But that significantly diminishes collaborative information, which is crucial for maintaining accuracy due to its inclusion of interaction histories. This loss profoundly impacts DLRM performance. This paper makes an important observation that if one can capture the user-item interaction history to enrich the user and item embeddings, then the interaction history can be compressed without losing model accuracy. Thus, this work, Collaborative Aware Data Compression (CADC), takes a two-step approach to training dataset compression. In the first step, we use matrix factorization of the user-item interaction matrix to create a novel embedding representation for both the users and items. Once the user and item embeddings are enriched by the interaction history information the approach then applies uniform random sampling of the training dataset to drastically reduce the training dataset size while minimizing model accuracy drop. The source code of CADC is available at \href{https://anonymous.4open.science/r/DSS-RM-8C1D/README.md}{https://anonymous.4open.science/r/DSS-RM-8C1D/README.md}.
URLs: https://anonymous.4open.science/r/DSS-RM-8C1D/README.md, https://anonymous.4open.science/r/DSS-RM-8C1D/README.md
Authors: Suqi Song, Chenxu Zhang, Peng Zhang, Pengkun Li, Fenglong Song, Lei Zhang
Abstract: Urban waterlogging poses a major risk to public safety and infrastructure. Conventional methods using water-level sensors need high-maintenance to hardly achieve full coverage. Recent advances employ surveillance camera imagery and deep learning for detection, yet these struggle amidst scarce data and adverse environmental conditions. In this paper, we establish a challenging Urban Waterlogging Benchmark (UW-Bench) under diverse adverse conditions to advance real-world applications. We propose a Large-Small Model co-adapter paradigm (LSM-adapter), which harnesses the substantial generic segmentation potential of large model and the specific task-directed guidance of small model. Specifically, a Triple-S Prompt Adapter module alongside a Dynamic Prompt Combiner are proposed to generate then merge multiple prompts for mask decoder adaptation. Meanwhile, a Histogram Equalization Adap-ter module is designed to infuse the image specific information for image encoder adaptation. Results and analysis show the challenge and superiority of our developed benchmark and algorithm. Project page: \url{https://github.com/zhang-chenxu/LSM-Adapter}
Authors: A. Noorizadegan, Y. C. Hon, D. L. Young, C. S. Chen
Abstract: Surface reconstruction from point clouds is a fundamental challenge in computer graphics and medical imaging. In this paper, we explore the application of advanced neural network architectures for the accurate and efficient reconstruction of surfaces from data points. We introduce a novel variant of the Highway network (Hw) called Square-Highway (SqrHw) within the context of multilayer perceptrons and investigate its performance alongside plain neural networks and a simplified Hw in various numerical examples. These examples include the reconstruction of simple and complex surfaces, such as spheres, human hands, and intricate models like the Stanford Bunny. We analyze the impact of factors such as the number of hidden layers, interior and exterior points, and data distribution on surface reconstruction quality. Our results show that the proposed SqrHw architecture outperforms other neural network configurations, achieving faster convergence and higher-quality surface reconstructions. Additionally, we demonstrate the SqrHw's ability to predict surfaces over missing data, a valuable feature for challenging applications like medical imaging. Furthermore, our study delves into further details, demonstrating that the proposed method based on highway networks yields more stable weight norms and backpropagation gradients compared to the Plain Network architecture. This research not only advances the field of computer graphics but also holds utility for other purposes such as function interpolation and physics-informed neural networks, which integrate multilayer perceptrons into their algorithms.
Authors: Aydin Abadi, Vishnu Asutosh Dasu, Sumanta Sarkar
Abstract: Deduplication is a vital preprocessing step that enhances machine learning model performance and saves training time and energy. However, enhancing federated learning through deduplication poses challenges, especially regarding scalability and potential privacy violations if deduplication involves sharing all clients' data. In this paper, we address the problem of deduplication in a federated setup by introducing a pioneering protocol, Efficient Privacy-Preserving Multi-Party Deduplication (EP-MPD). It efficiently removes duplicates from multiple clients' datasets without compromising data privacy. EP-MPD is constructed in a modular fashion, utilizing two novel variants of the Private Set Intersection protocol. Our extensive experiments demonstrate the significant benefits of deduplication in federated learning of large language models. For instance, we observe up to 19.61% improvement in perplexity and up to 27.95% reduction in running time. EP-MPD effectively balances privacy and performance in federated learning, making it a valuable solution for large-scale applications.
Authors: Giorgio Severi, Simona Boboila, John Holodnak, Kendra Kratkiewicz, Rauf Izmailov, Alina Oprea
Abstract: The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security classification tasks without altering the training labels. With this work, we propose new techniques that leverage insights in cybersecurity threat models to effectively mitigate these clean-label poisoning attacks, while preserving the model utility. By performing density-based clustering on a carefully chosen feature subspace, and progressively isolating the suspicious clusters through a novel iterative scoring procedure, our defensive mechanism can mitigate the attacks without requiring many of the common assumptions in the existing backdoor defense literature. To show the generality of our proposed mitigation, we evaluate it on two clean-label model-agnostic attacks on two different classic cybersecurity data modalities: network flows classification and malware classification, using gradient boosting and neural network models.
Authors: Dezhi Ran, Mengzhou Wu, Wei Yang, Tao Xie
Abstract: By treating data and models as the source code, Foundation Models (FMs) become a new type of software. Mirroring the concept of software crisis, the increasing complexity of FMs making FM crisis a tangible concern in the coming decade, appealing for new theories and methodologies from the field of software engineering. In this paper, we outline our vision of introducing Foundation Model (FM) engineering, a strategic response to the anticipated FM crisis with principled engineering methodologies. FM engineering aims to mitigate potential issues in FM development and application through the introduction of declarative, automated, and unified programming interfaces for both data and model management, reducing the complexities involved in working with FMs by providing a more structured and intuitive process for developers. Through the establishment of FM engineering, we aim to provide a robust, automated, and extensible framework that addresses the imminent challenges, and discovering new research opportunities for the software engineering field.
Authors: Sopam Dasgupta, Joaqu\'in Arias, Elmer Salazar, Gopal Gupta
Abstract: Machine learning models are increasingly used in areas such as loan approvals and hiring, yet they often function as black boxes, obscuring their decision-making processes. Transparency is crucial, and individuals need explanations to understand decisions, especially for the ones not desired by the user. Ethical and legal considerations require informing individuals of changes in input attribute values (features) that could lead to a desired outcome for the user. Our work aims to generate counterfactual explanations by considering causal dependencies between features. We present the CoGS (Counterfactual Generation with s(CASP)) framework that utilizes the goal-directed Answer Set Programming system s(CASP) to generate counterfactuals from rule-based machine learning models, specifically the FOLD-SE algorithm. CoGS computes realistic and causally consistent changes to attribute values taking causal dependencies between them into account. It finds a path from an undesired outcome to a desired one using counterfactuals. We present details of the CoGS framework along with its evaluation.
Authors: Febin Sunny, Amin Shafiee, Abhishek Balasubramaniam, Mahdi Nikdast, Sudeep Pasricha
Abstract: Recent advances in machine learning (ML) have spotlighted the pressing need for computing architectures that bridge the gap between memory bandwidth and processing power. The advent of deep neural networks has pushed traditional Von Neumann architectures to their limits due to the high latency and energy consumption costs associated with data movement between the processor and memory for these workloads. One of the solutions to overcome this bottleneck is to perform computation within the main memory through processing-in-memory (PIM), thereby limiting data movement and the costs associated with it. However, DRAM-based PIM struggles to achieve high throughput and energy efficiency due to internal data movement bottlenecks and the need for frequent refresh operations. In this work, we introduce OPIMA, a PIM-based ML accelerator, architected within an optical main memory. OPIMA has been designed to leverage the inherent massive parallelism within main memory while performing high-speed, low-energy optical computation to accelerate ML models based on convolutional neural networks. We present a comprehensive analysis of OPIMA to guide design choices and operational mechanisms. Additionally, we evaluate the performance and energy consumption of OPIMA, comparing it with conventional electronic computing systems and emerging photonic PIM architectures. The experimental results show that OPIMA can achieve 2.98x higher throughput and 137x better energy efficiency than the best-known prior work.
Authors: Chihcheng Hsieh, Catarina Moreira, Isabel Blanco Nobre, Sandra Costa Sousa, Chun Ouyang, Margot Brereton, Joaquim Jorge, Jacinto C. Nascimento
Abstract: X-ray images are vital in medical diagnostics, but their effectiveness is limited without clinical context. Radiologists often find chest X-rays insufficient for diagnosing underlying diseases, necessitating comprehensive clinical features and data integration. We present a novel technique to enhance the clinical context through augmentation techniques with clinical tabular data, thereby improving its applicability and reliability in AI medical diagnostics. To address this, we introduce a pioneering approach to clinical data augmentation that employs large language models (LLMs) to generate patient contextual synthetic data. This methodology is crucial for training more robust deep learning models in healthcare. It preserves the integrity of real patient data while enriching the dataset with contextually relevant synthetic features, significantly enhancing model performance. DALL-M uses a three-phase feature generation process: (i) clinical context storage, (ii) expert query generation, and (iii) context-aware feature augmentation. DALL-M generates new, clinically relevant features by synthesizing chest X-ray images and reports. Applied to 799 cases using nine features from the MIMIC-IV dataset, it created an augmented set of 91 features. This is the first work to generate contextual values for existing and new features based on patients' X-ray reports, gender, and age and to produce new contextual knowledge during data augmentation. Empirical validation with machine learning models, including Decision Trees, Random Forests, XGBoost, and TabNET, showed significant performance improvements. Incorporating augmented features increased the F1 score by 16.5% and Precision and Recall by approximately 25%. DALL-M addresses a critical gap in clinical data augmentation, offering a robust framework for generating contextually enriched datasets.
Authors: Siding Zeng, Jiangyan Yi, Jianhua Tao, Yujie Chen, Shan Liang, Yong Ren, Xiaohui Zhang
Abstract: When the task of locating manipulation regions in partially-fake audio (PFA) involves cross-domain datasets, the performance of deep learning models drops significantly due to the shift between the source and target domains. To address this issue, existing approaches often employ data augmentation before training. However, they overlook the characteristics in target domain that are absent in source domain. Inspired by the mixture-of-experts model, we propose an unsupervised method named Samples mining with Diversity and Entropy (SDE). Our method first learns from a collection of diverse experts that achieve great performance from different perspectives in the source domain, but with ambiguity on target samples. We leverage these diverse experts to select the most informative samples by calculating their entropy. Furthermore, we introduced a label generation method tailored for these selected samples that are incorporated in the training process in source domain integrating the target domain information. We applied our method to a cross-domain partially fake audio detection dataset, ADD2023Track2. By introducing 10% of unknown samples from the target domain, we achieved an F1 score of 43.84%, which represents a relative increase of 77.2% compared to the second-best method.
Authors: Aitao Yang, Min Li, Yao Ding, Leyuan Fang, Yaoming Cai, Yujie He
Abstract: Efficient extraction of spectral sequences and geospatial information has always been a hot topic in hyperspectral image classification. In terms of spectral sequence feature capture, RNN and Transformer have become mainstream classification frameworks due to their long-range feature capture capabilities. In terms of spatial information aggregation, CNN enhances the receptive field to retain integrated spatial information as much as possible. However, the spectral feature-capturing architectures exhibit low computational efficiency, and CNNs lack the flexibility to perceive spatial contextual information. To address these issues, this paper proposes GraphMamba--an efficient graph structure learning vision Mamba classification framework that fully considers HSI characteristics to achieve deep spatial-spectral information mining. Specifically, we propose a novel hyperspectral visual GraphMamba processing paradigm (HVGM) that preserves spatial-spectral features by constructing spatial-spectral cubes and utilizes linear spectral encoding to enhance the operability of subsequent tasks. The core components of GraphMamba include the HyperMamba module for improving computational efficiency and the SpectralGCN module for adaptive spatial context awareness. The HyperMamba mitigates clutter interference by employing the global mask (GM) and introduces a parallel training inference architecture to alleviate computational bottlenecks. The SpatialGCN incorporates weighted multi-hop aggregation (WMA) spatial encoding to focus on highly correlated spatial structural features, thus flexibly aggregating contextual information while mitigating spatial noise interference. Extensive experiments were conducted on three different scales of real HSI datasets, and compared with the state-of-the-art classification frameworks, GraphMamba achieved optimal performance.
Authors: Noam Elata, Tomer Michaeli, Michael Elad
Abstract: Compressed Sensing (CS) facilitates rapid image acquisition by selecting a small subset of measurements sufficient for high-fidelity reconstruction. Adaptive CS seeks to further enhance this process by dynamically choosing future measurements based on information gleaned from data that is already acquired. However, many existing frameworks are often tailored to specific tasks and require intricate training procedures. We propose AdaSense, a novel Adaptive CS approach that leverages zero-shot posterior sampling with pre-trained diffusion models. By sequentially sampling from the posterior distribution, we can quantify the uncertainty of each possible future linear measurement throughout the acquisition process. AdaSense eliminates the need for additional training and boasts seamless adaptation to diverse domains with minimal tuning requirements. Our experiments demonstrate the effectiveness of AdaSense in reconstructing facial images from a small number of measurements. Furthermore, we apply AdaSense for active acquisition of medical images in the domains of magnetic resonance imaging (MRI) and computed tomography (CT), highlighting its potential for tangible real-world acceleration.
Authors: Seonwhee Jin
Abstract: Models based on convolutional neural networks (CNN) and transformers have steadily been improved. They also have been applied in various computer vision downstream tasks. However, in object detection tasks, accurately localizing and classifying almost infinite categories of foods in images remains challenging. To address these problems, we first segmented the food as the region-of-interest (ROI) by using the segment-anything model (SAM) and masked the rest of the region except ROI as black pixels. This process simplified the problems into a single classification for which annotation and training were much simpler than object detection. The images in which only the ROI was preserved were fed as inputs to fine-tune various off-the-shelf models that encoded their own inductive biases. Among them, Data-efficient image Transformers (DeiTs) had the best classification performance. Nonetheless, when foods' shapes and textures were similar, the contextual features of the ROI-only images were not enough for accurate classification. Therefore, we introduced a novel type of combined architecture, RveRNet, which consisted of ROI, extra-ROI, and integration modules that allowed it to account for both the ROI's and global contexts. The RveRNet's F1 score was 10% better than other individual models when classifying ambiguous food images. If the RveRNet's modules were DeiT with the knowledge distillation from the CNN, performed the best. We investigated how architectures can be made robust against input noise caused by permutation and translocation. The results indicated that there was a trade-off between how much the CNN teacher's knowledge could be distilled to DeiT and DeiT's innate strength. Code is publicly available at: https://github.com/Seonwhee-Genome/RveRNet.
Authors: Anand Babu
Abstract: Assessing different material properties to predict specific attributes, such as band gap, resistivity, young modulus, work function, and refractive index, is a fundamental requirement for materials science-based applications. However, the process is time-consuming and often requires extensive literature reviews and numerous experiments. Our study addresses these challenges by leveraging machine learning to analyze material properties with greater precision and efficiency. By automating the data extraction process and using the extracted information to train machine learning models, our developed model, SciQu, optimizes material properties. As a proof of concept, we predicted the refractive index of materials using data extracted from numerous research articles with SciQu, considering input descriptors such as space group, volume, and bandgap with Root Mean Square Error (RMSE) 0.068 and R2 0.94. Thus, SciQu not only predicts the properties of materials but also plays a key role in self-driving laboratories by optimizing the synthesis parameters to achieve precise shape, size, and phase of the materials subjected to the input parameters.
Authors: Muralikrishnan Srinivasan, Linda Senigagliesi, Hui Chen, Arsenia Chorti, Marco Baldi, Henk Wymeersch
Abstract: We discuss the use of angle of arrival (AoA) as an authentication measure in analog array multiple-input multiple-output (MIMO) systems. A base station equipped with an analog array authenticates users based on the AoA estimated from certified pilot transmissions, while active attackers manipulate their transmitted signals to mount impersonation attacks. We study several attacks of increasing intensity (captured through the availability of side information at the attackers) and assess the performance of AoA-based authentication using one-class classifiers. Our results show that some attack techniques with knowledge of the combiners at the verifier are effective in falsifying the AoA and compromising the security of the considered type of physical layer authentication.
Authors: Ershadul Haque, Manoranjan Paul, Faranak Tohidi
Abstract: Cardiovascular diseases (CVDs) encompass a group of disorders affecting the heart and blood vessels, including conditions such as coronary artery disease, heart failure, stroke, and hypertension. In cardiovascular diseases, heart failure is one of the main causes of death and also long-term suffering in patients worldwide. Prediction is one of the risk factors that is highly valuable for treatment and intervention to minimize heart failure. In this work, an attention learning-based heart failure prediction approach is proposed on EHR(electronic health record) cardiovascular data such as ejection fraction and serum creatinine. Moreover, different optimizers with various learning rate approaches are applied to fine-tune the proposed approach. Serum creatinine and ejection fraction are the two most important features to predict the patient's heart failure. The computational result shows that the RMSProp optimizer with 0.001 learning rate has a better prediction based on serum creatinine. On the other hand, the combination of SGD optimizer with 0.01 learning rate exhibits optimum performance based on ejection fraction features. Overall, the proposed attention learning-based approach performs very efficiently in predicting heart failure compared to the existing state-of-the-art such as LSTM approach.
Authors: Hiba Najjar, Francisco Mena, Marlon Nuske, Andreas Dengel
Abstract: Vegetation indices allow to efficiently monitor vegetation growth and agricultural activities. Previous generations of satellites were capturing a limited number of spectral bands, and a few expert-designed vegetation indices were sufficient to harness their potential. New generations of multi- and hyperspectral satellites can however capture additional bands, but are not yet efficiently exploited. In this work, we propose an explainable-AI-based method to select and design suitable vegetation indices. We first train a deep neural network using multispectral satellite data, then extract feature importance to identify the most influential bands. We subsequently select suitable existing vegetation indices or modify them to incorporate the identified bands and retrain our model. We validate our approach on a crop classification task. Our results indicate that models trained on individual indices achieve comparable results to the baseline model trained on all bands, while the combination of two indices surpasses the baseline in certain cases.
Authors: Sandra Garc\'ia-Ponsoda, Alejandro Mat\'e, Juan Trujillo
Abstract: Background: Attention-Deficit/Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder that significantly impacts various key aspects of life, requiring accurate diagnostic methods. Electroencephalogram (EEG) signals are used in diagnosing ADHD, but proper preprocessing is crucial to avoid noise and artifacts that could lead to unreliable results. Method: This study utilized a public EEG dataset from children diagnosed with ADHD and typically developing (TD) children. Four preprocessing techniques were applied: no preprocessing (Raw), Finite Impulse Response (FIR) filtering, Artifact Subspace Reconstruction (ASR), and Independent Component Analysis (ICA). EEG recordings were segmented, and features were extracted and selected based on statistical significance. Classification was performed using Machine Learning models, as XGBoost, Support Vector Machine, and K-Nearest Neighbors. Results: The absence of preprocessing leads to artificially high classification accuracy due to noise. In contrast, ASR and ICA preprocessing techniques significantly improved the reliability of results. Segmenting EEG recordings revealed that later segments provided better classification accuracy, likely due to the manifestation of ADHD symptoms over time. The most relevant EEG channels were P3, P4, and C3. The top features for classification included Kurtosis, Katz fractal dimension, and power spectral density of Delta, Theta, and Alpha bands. Conclusions: Effective preprocessing is essential in EEG-based ADHD diagnosis to prevent noise-induced biases. This study identifies crucial EEG channels and features, providing a foundation for further research and improving ADHD diagnostic accuracy. Future work should focus on expanding datasets, refining preprocessing methods, and enhancing feature interpretability to improve diagnostic accuracy and model robustness for clinical use.
Authors: Georgina Cosma, Mohit Kumar Singh, Patrick Waterson, Gyuchan Thomas Jun, Jonathan Back
Abstract: This study applies Natural Language Processing techniques, including Latent Dirichlet Allocation, to analyse anonymised maternity incident investigation reports from the Healthcare Safety Investigation Branch. The reports underwent preprocessing, annotation using the Safety Intelligence Research taxonomy, and topic modelling to uncover prevalent topics and detect differences in maternity care across ethnic groups. A combination of offline and online methods was utilised to ensure data protection whilst enabling advanced analysis, with offline processing for sensitive data and online processing for non-sensitive data using the `Claude 3 Opus' language model. Interactive topic analysis and semantic network visualisation were employed to extract and display thematic topics and visualise semantic relationships among keywords. The analysis revealed disparities in care among different ethnic groups, with distinct focus areas for the Black, Asian, and White British ethnic groups. The study demonstrates the effectiveness of topic modelling and NLP techniques in analysing maternity incident investigation reports and highlighting disparities in care. The findings emphasise the crucial role of advanced data analysis in improving maternity care quality and equity.
Authors: Liang Zeng, Liangjun Zhong, Liang Zhao, Tianwen Wei, Liu Yang, Jujie He, Cheng Cheng, Rui Hu, Yang Liu, Shuicheng Yan, Han Fang, Yahui Zhou
Abstract: In this paper, we investigate the underlying factors that potentially enhance the mathematical reasoning capabilities of large language models (LLMs). We argue that the data scaling law for math reasoning capabilities in modern LLMs is far from being saturated, highlighting how the model's quality improves with increases in data quantity. To support this claim, we introduce the Skywork-Math model series, supervised fine-tuned (SFT) on common 7B LLMs using our proposed 2.5M-instance Skywork-MathQA dataset. Skywork-Math 7B has achieved impressive accuracies of 51.2% on the competition-level MATH benchmark and 83.9% on the GSM8K benchmark using only SFT data, outperforming an early version of GPT-4 on MATH. The superior performance of Skywork-Math models contributes to our novel two-stage data synthesis and model SFT pipelines, which include three different augmentation methods and a diverse seed problem set, ensuring both the quantity and quality of Skywork-MathQA dataset across varying difficulty levels. Most importantly, we provide several practical takeaways to enhance math reasoning abilities in LLMs for both research and industry applications.
Authors: Xiang Lisa Li, Evan Zheran Liu, Percy Liang, Tatsunori Hashimoto
Abstract: Evaluation is critical for assessing capabilities, tracking scientific progress, and informing model selection. In this paper, we present three desiderata for a good benchmark for language models: (i) salience (e.g., knowledge about World War II is more salient than a random day in history), (ii) novelty (i.e., the benchmark reveals new trends in model rankings not shown by previous benchmarks), and (iii) difficulty (i.e., the benchmark should be difficult for existing models, leaving headroom for future improvement). We operationalize these three desiderata and cast benchmark creation as a search problem, that of finding benchmarks that that satisfy all three desiderata. To tackle this search problem, we present AutoBencher, which uses a language model to automatically search for datasets that meet the three desiderata. AutoBencher uses privileged information (e.g. relevant documents) to construct reliable datasets, and adaptivity with reranking to optimize for the search objective. We use AutoBencher to create datasets for math, multilingual, and knowledge-intensive question answering. The scalability of AutoBencher allows it to test fine-grained categories and tail knowledge, creating datasets that are on average 27% more novel and 22% more difficult than existing benchmarks. A closer investigation of our constructed datasets shows that we can identify specific gaps in LM knowledge in language models that are not captured by existing benchmarks, such as Gemini Pro performing much worse on question answering about the Permian Extinction and Fordism, while OpenAGI-7B performing surprisingly well on QA about COVID-19.
Authors: Ilya Trofimov, Daria Voronkova, Eduard Tulchinskii, Evgeny Burnaev, Serguei Barannikov
Abstract: We propose a new topological tool for computer vision - Scalar Function Topology Divergence (SFTD), which measures the dissimilarity of multi-scale topology between sublevel sets of two functions having a common domain. Functions can be defined on an undirected graph or Euclidean space of any dimensionality. Most of the existing methods for comparing topology are based on Wasserstein distance between persistence barcodes and they don't take into account the localization of topological features. On the other hand, the minimization of SFTD ensures that the corresponding topological features of scalar functions are located in the same places. The proposed tool provides useful visualizations depicting areas where functions have topological dissimilarities. We provide applications of the proposed method to 3D computer vision. In particular, experiments demonstrate that SFTD improves the reconstruction of cellular 3D shapes from 2D fluorescence microscopy images, and helps to identify topological errors in 3D segmentation.
Authors: Nicola Muca Cirone, Jad Hamdan, Cristopher Salvi
Abstract: We present a unified approach to obtain scaling limits of neural networks using the genus expansion technique from random matrix theory. This approach begins with a novel expansion of neural networks which is reminiscent of Butcher series for ODEs, and is obtained through a generalisation of Fa\`a di Bruno's formula to an arbitrary number of compositions. In this expansion, the role of monomials is played by random multilinear maps indexed by directed graphs whose edges correspond to random matrices, which we call operator graphs. This expansion linearises the effect of the activation functions, allowing for the direct application of Wick's principle to compute the expectation of each of its terms. We then determine the leading contribution to each term by embedding the corresponding graphs onto surfaces, and computing their Euler characteristic. Furthermore, by developing a correspondence between analytic and graphical operations, we obtain similar graph expansions for the neural tangent kernel as well as the input-output Jacobian of the original neural network, and derive their infinite-width limits with relative ease. Notably, we find explicit formulae for the moments of the limiting singular value distribution of the Jacobian. We then show that all of these results hold for networks with more general weights, such as general matrices with i.i.d. entries satisfying moment assumptions, complex matrices and sparse matrices.
Authors: Yihan Zhang, Xuanshuo Zhang, Wei Wu, Haohan Wang
Abstract: Saliency maps have been widely used to interpret deep learning classifiers for Alzheimer's disease (AD). However, since AD is heterogeneous and has multiple subtypes, the pathological mechanism of AD remains not fully understood and may vary from patient to patient. Due to the lack of such understanding, it is difficult to comprehensively and effectively assess the saliency map of AD classifier. In this paper, we utilize the anatomical segmentation to allocate saliency values into different brain regions. By plotting the distributions of saliency maps corresponding to AD and NC (Normal Control), we can gain a comprehensive view of the model's decisions process. In order to leverage the fact that the brain volume shrinkage happens in AD patients during disease progression, we define a new evaluation metric, brain volume change score (VCS), by computing the average Pearson correlation of the brain volume changes and the saliency values of a model in different brain regions for each patient. Thus, the VCS metric can help us gain some knowledge of how saliency maps resulting from different models relate to the changes of the volumes across different regions in the whole brain. We trained candidate models on the ADNI dataset and tested on three different datasets. Our results indicate: (i) models with higher VCSs tend to demonstrate saliency maps with more details relevant to the AD pathology, (ii) using gradient-based adversarial training strategies such as FGSM and stochastic masking can improve the VCSs of the models.
Authors: Yuqian Zhang, Jelena Bradic
Abstract: Deep neural networks (DNNs) have demonstrated remarkable empirical performance in large-scale supervised learning problems, particularly in scenarios where both the sample size $n$ and the dimension of covariates $p$ are large. This study delves into the application of DNNs across a wide spectrum of intricate causal inference tasks, where direct estimation falls short and necessitates multi-stage learning. Examples include estimating the conditional average treatment effect and dynamic treatment effect. In this framework, DNNs are constructed sequentially, with subsequent stages building upon preceding ones. To mitigate the impact of estimation errors from early stages on subsequent ones, we integrate DNNs in a doubly robust manner. In contrast to previous research, our study offers theoretical assurances regarding the effectiveness of DNNs in settings where the dimensionality $p$ expands with the sample size. These findings are significant independently and extend to degenerate single-stage learning problems.
Authors: Konstantinos Panagiotis Alexandridis, Jiankang Deng, Anh Nguyen, Shan Luo
Abstract: The activation function plays a crucial role in model optimisation, yet the optimal choice remains unclear. For example, the Sigmoid activation is the de-facto activation in balanced classification tasks, however, in imbalanced classification, it proves inappropriate due to bias towards frequent classes. In this work, we delve deeper in this phenomenon by performing a comprehensive statistical analysis in the classification and intermediate layers of both balanced and imbalanced networks and we empirically show that aligning the activation function with the data distribution, enhances the performance in both balanced and imbalanced tasks. To this end, we propose the Adaptive Parametric Activation (APA) function, a novel and versatile activation function that unifies most common activation functions under a single formula. APA can be applied in both intermediate layers and attention layers, significantly outperforming the state-of-the-art on several imbalanced benchmarks such as ImageNet-LT, iNaturalist2018, Places-LT, CIFAR100-LT and LVIS and balanced benchmarks such as ImageNet1K, COCO and V3DET. The code is available at https://github.com/kostas1515/AGLU.
Authors: Alex Oesterling, Claudio Mayrink Verdun, Carol Xuan Long, Alex Glynn, Lucas Monteiro Paes, Sajani Vithana, Martina Cardone, Flavio P. Calmon
Abstract: Image search and retrieval tasks can perpetuate harmful stereotypes, erase cultural identities, and amplify social disparities. Current approaches to mitigate these representational harms balance the number of retrieved items across population groups defined by a small number of (often binary) attributes. However, most existing methods overlook intersectional groups determined by combinations of group attributes, such as gender, race, and ethnicity. We introduce Multi-Group Proportional Representation (MPR), a novel metric that measures representation across intersectional groups. We develop practical methods for estimating MPR, provide theoretical guarantees, and propose optimization algorithms to ensure MPR in retrieval. We demonstrate that existing methods optimizing for equal and proportional representation metrics may fail to promote MPR. Crucially, our work shows that optimizing MPR yields more proportional representation across multiple intersectional groups specified by a rich function class, often with minimal compromise in retrieval accuracy.
Authors: Zhen Qin, Daoyuan Chen, Wenhao Zhang, Liuyi Yao, Yilun Huang, Bolin Ding, Yaliang Li, Shuiguang Deng
Abstract: The rapid development of large language models (LLMs) has been witnessed in recent years. Based on the powerful LLMs, multi-modal LLMs (MLLMs) extend the modality from text to a broader spectrum of domains, attracting widespread attention due to the broader range of application scenarios. As LLMs and MLLMs rely on vast amounts of model parameters and data to achieve emergent capabilities, the importance of data is receiving increasingly widespread attention and recognition. Tracing and analyzing recent data-oriented works for MLLMs, we find that the development of models and data is not two separate paths but rather interconnected. On the one hand, vaster and higher-quality data contribute to better performance of MLLMs, on the other hand, MLLMs can facilitate the development of data. The co-development of multi-modal data and MLLMs requires a clear view of 1) at which development stage of MLLMs can specific data-centric approaches be employed to enhance which capabilities, and 2) by utilizing which capabilities and acting as which roles can models contribute to multi-modal data. To promote the data-model co-development for MLLM community, we systematically review existing works related to MLLMs from the data-model co-development perspective. A regularly maintained project associated with this survey is accessible at https://github.com/modelscope/data-juicer/blob/main/docs/awesome_llm_data.md.
URLs: https://github.com/modelscope/data-juicer/blob/main/docs/awesome_llm_data.md.
Authors: Bowen Jiang, Yilin Wu, Wenxuan Zhou, Chris Paxton, David Held
Abstract: Although end-to-end robot learning has shown some success for robot manipulation, the learned policies are often not sufficiently robust to variations in object pose or geometry. To improve the policy generalization, we introduce spatially-grounded parameterized motion primitives in our method HACMan++. Specifically, we propose an action representation consisting of three components: what primitive type (such as grasp or push) to execute, where the primitive will be grounded (e.g. where the gripper will make contact with the world), and how the primitive motion is executed, such as parameters specifying the push direction or grasp orientation. These three components define a novel discrete-continuous action space for reinforcement learning. Our framework enables robot agents to learn to chain diverse motion primitives together and select appropriate primitive parameters to complete long-horizon manipulation tasks. By grounding the primitives on a spatial location in the environment, our method is able to effectively generalize across object shape and pose variations. Our approach significantly outperforms existing methods, particularly in complex scenarios demanding both high-level sequential reasoning and object generalization. With zero-shot sim-to-real transfer, our policy succeeds in challenging real-world manipulation tasks, with generalization to unseen objects. Videos can be found on the project website: https://sgmp-rss2024.github.io.
Authors: Michael Kaup, Cornelius Wolff, Hyerim Hwang, Julius Mayer, Elia Bruni
Abstract: We present a review of popular simulation engines and frameworks used in reinforcement learning (RL) research, aiming to guide researchers in selecting tools for creating simulated physical environments for RL and training setups. It evaluates nine frameworks (Brax, Chrono, Gazebo, MuJoCo, ODE, PhysX, PyBullet, Webots, and Unity) based on their popularity, feature range, quality, usability, and RL capabilities. We highlight the challenges in selecting and utilizing physics engines for RL research, including the need for detailed comparisons and an understanding of each framework's capabilities. Key findings indicate MuJoCo as the leading framework due to its performance and flexibility, despite usability challenges. Unity is noted for its ease of use but lacks scalability and simulation fidelity. The study calls for further development to improve simulation engines' usability and performance and stresses the importance of transparency and reproducibility in RL research. This review contributes to the RL community by offering insights into the selection process for simulation engines, facilitating informed decision-making.
Authors: Tural Mammadov, Dietrich Klakow, Alexander Koller, Andreas Zeller
Abstract: We introduce Modelizer - a novel framework that, given a black-box program, learns a _model from its input/output behavior_ using _neural machine translation_. The resulting model _mocks_ the original program: Given an input, the model predicts the output that would have been produced by the program. However, the model is also _reversible_ - that is, the model can predict the input that would have produced a given output. Finally, the model is _differentiable_ and can be efficiently restricted to predict only a certain aspect of the program behavior. Modelizer uses _grammars_ to synthesize inputs and to parse the resulting outputs, allowing it to learn sequence-to-sequence associations between token streams. Other than input and output grammars, Modelizer only requires the ability to execute the program. The resulting models are _small_, requiring fewer than 6.3 million parameters for languages such as Markdown or HTML; and they are _accurate_, achieving up to 95.4% accuracy and a BLEU score of 0.98 with standard error 0.04 in mocking real-world applications. We foresee several _applications_ of these models, especially as the output of the program can be any aspect of program behavior. Besides mocking and predicting program behavior, the model can also synthesize inputs that are likely to produce a particular behavior, such as failures or coverage.
Authors: Yanfu Yan, Nathan Cooper, Oscar Chaparro, Kevin Moran, Denys Poshyvanyk
Abstract: Video-based bug reports are increasingly being used to document bugs for programs centered around a graphical user interface (GUI). However, developing automated techniques to manage video-based reports is challenging as it requires identifying and understanding often nuanced visual patterns that capture key information about a reported bug. In this paper, we aim to overcome these challenges by advancing the bug report management task of duplicate detection for video-based reports. To this end, we introduce a new approach, called JANUS, that adapts the scene-learning capabilities of vision transformers to capture subtle visual and textual patterns that manifest on app UI screens - which is key to differentiating between similar screens for accurate duplicate report detection. JANUS also makes use of a video alignment technique capable of adaptive weighting of video frames to account for typical bug manifestation patterns. In a comprehensive evaluation on a benchmark containing 7,290 duplicate detection tasks derived from 270 video-based bug reports from 90 Android app bugs, the best configuration of our approach achieves an overall mRR/mAP of 89.8%/84.7%, and for the large majority of duplicate detection tasks, outperforms prior work by around 9% to a statistically significant degree. Finally, we qualitatively illustrate how the scene-learning capabilities provided by Janus benefits its performance.
Authors: Junkang Wu, Yuexiang Xie, Zhengyi Yang, Jiancan Wu, Jinyang Gao, Bolin Ding, Xiang Wang, Xiangnan He
Abstract: Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO is sensitive to the fine-tuning of its trade-off parameter $\beta$, as well as to the quality of the preference data. We analyze the impact of $\beta$ and data quality on DPO, uncovering that optimal $\beta$ values vary with the informativeness of pairwise data. Addressing the limitations of static $\beta$ values, we introduce a novel framework that dynamically calibrates $\beta$ at the batch level, informed by data quality considerations. Additionally, our method incorporates $\beta$-guided data filtering to safeguard against the influence of outliers. Through empirical evaluation, we demonstrate that our dynamic $\beta$ adjustment technique significantly improves DPO's performance across a range of models and datasets, offering a more robust and adaptable training paradigm for aligning LLMs with human feedback. The code is available at \url{https://github.com/junkangwu/beta-DPO}.
Authors: Dorian Desblancs, Gabriel Meseguer-Brocal, Romain Hennequin, Manuel Moussallam
Abstract: Cloned voices of popular singers sound increasingly realistic and have gained popularity over the past few years. They however pose a threat to the industry due to personality rights concerns. As such, methods to identify the original singer in synthetic voices are needed. In this paper, we investigate how singer identification methods could be used for such a task. We present three embedding models that are trained using a singer-level contrastive learning scheme, where positive pairs consist of segments with vocals from the same singers. These segments can be mixtures for the first model, vocals for the second, and both for the third. We demonstrate that all three models are highly capable of identifying real singers. However, their performance deteriorates when classifying cloned versions of singers in our evaluation set. This is especially true for models that use mixtures as an input. These findings highlight the need to understand the biases that exist within singer identification systems, and how they can influence the identification of voice deepfakes in music.
Authors: Joe Suk
Abstract: We study a $K$-armed non-stationary bandit model where rewards change smoothly, as captured by H\"{o}lder class assumptions on rewards as functions of time. Such smooth changes are parametrized by a H\"{o}lder exponent $\beta$ and coefficient $\lambda$. While various sub-cases of this general model have been studied in isolation, we first establish the minimax dynamic regret rate generally for all $K,\beta,\lambda$. Next, we show this optimal dynamic regret can be attained adaptively, without knowledge of $\beta,\lambda$. To contrast, even with parameter knowledge, upper bounds were only previously known for limited regimes $\beta\leq 1$ and $\beta=2$ (Slivkins, 2014; Krishnamurthy and Gopalan, 2021; Manegueu et al., 2021; Jia et al.,2023). Thus, our work resolves open questions raised by these disparate threads of the literature. We also study the problem of attaining faster gap-dependent regret rates in non-stationary bandits. While such rates are long known to be impossible in general (Garivier and Moulines, 2011), we show that environments admitting a safe arm (Suk and Kpotufe, 2022) allow for much faster rates than the worst-case scaling with $\sqrt{T}$. While previous works in this direction focused on attaining the usual logarithmic regret bounds, as summed over stationary periods, our new gap-dependent rates reveal new optimistic regimes of non-stationarity where even the logarithmic bounds are pessimistic. We show our new gap-dependent rate is tight and that its achievability (i.e., as made possible by a safe arm) has a surprisingly simple and clean characterization within the smooth H\"{o}lder class model.
Authors: Chethan Radhakrishna, Karthikesh Varma Chintalapati, Sri Chandana Hudukula Ram Kumar, Raviteja Sutrave, Hendrik Mattern, Oliver Speck, Andreas N\"urnberger, Soumick Chatterjee
Abstract: Identification of vessel structures of different sizes in biomedical images is crucial in the diagnosis of many neurodegenerative diseases. However, the sparsity of good-quality annotations of such images makes the task of vessel segmentation challenging. Deep learning offers an efficient way to segment vessels of different sizes by learning their high-level feature representations and the spatial continuity of such features across dimensions. Semi-supervised patch-based approaches have been effective in identifying small vessels of one to two voxels in diameter. This study focuses on improving the segmentation quality by considering the spatial correlation of the features using the Maximum Intensity Projection~(MIP) as an additional loss criterion. Two methods are proposed with the incorporation of MIPs of label segmentation on the single~(z-axis) and multiple perceivable axes of the 3D volume. The proposed MIP-based methods produce segmentations with improved vessel continuity, which is evident in visual examinations of ROIs. Patch-based training is improved by introducing an additional loss term, MIP loss, to penalise the predicted discontinuity of vessels. A training set of 14 volumes is selected from the StudyForrest dataset comprising of 18 7-Tesla 3D Time-of-Flight~(ToF) Magnetic Resonance Angiography (MRA) images. The generalisation performance of the method is evaluated using the other unseen volumes in the dataset. It is observed that the proposed method with multi-axes MIP loss produces better quality segmentations with a median Dice of $80.245 \pm 0.129$. Also, the method with single-axis MIP loss produces segmentations with a median Dice of $79.749 \pm 0.109$. Furthermore, a visual comparison of the ROIs in the predicted segmentation reveals a significant improvement in the continuity of the vessels when MIP loss is incorporated into training.
Authors: Christopher B\"ulte, Lisa Leimenstoll, Melanie Schienle
Abstract: Recent methods in modeling spatial extreme events have focused on utilizing parametric max-stable processes and their underlying dependence structure. In this work, we provide a unified approach for analyzing spatial extremes with little available data by estimating the distribution of model parameters or the spatial dependence directly. By employing recent developments in generative neural networks we predict a full sample-based distribution, allowing for direct assessment of uncertainty regarding model parameters or other parameter dependent functionals. We validate our method by fitting several simulated max-stable processes, showing a high accuracy of the approach, regarding parameter estimation, as well as uncertainty quantification. Additional robustness checks highlight the generalization and extrapolation capabilities of the model, while an application to precipitation extremes across Western Germany demonstrates the usability of our approach in real-world scenarios.
Authors: Marcin Paluch, Florian Bolli, Xiang Deng, Antonio Rios Navarro, Chang Gao, Tobi Delbruck
Abstract: Nonlinear model predictive control (NMPC) has proven to be an effective control method, but it is expensive to compute. This work demonstrates the use of hardware FPGA neural network controllers trained to imitate NMPC with supervised learning. We use these Neural Controllers (NCs) implemented on inexpensive embedded FPGA hardware for high frequency control on physical cartpole and F1TENTH race car. Our results show that the NCs match the control performance of the NMPCs in simulation and outperform it in reality, due to the faster control rate that is afforded by the quick FPGA NC inference. We demonstrate kHz control rates for a physical cartpole and offloading control to the FPGA hardware on the F1TENTH car. Code and hardware implementation for this paper are available at https:// github.com/SensorsINI/Neural-Control-Tools.
Authors: Alex Oesterling, Usha Bhalla, Suresh Venkatasubramanian, Himabindu Lakkaraju
Abstract: As Artificial Intelligence (AI) tools are increasingly employed in diverse real-world applications, there has been significant interest in regulating these tools. To this end, several regulatory frameworks have been introduced by different countries worldwide. For example, the European Union recently passed the AI Act, the White House issued an Executive Order on safe, secure, and trustworthy AI, and the White House Office of Science and Technology Policy issued the Blueprint for an AI Bill of Rights (AI BoR). Many of these frameworks emphasize the need for auditing and improving the trustworthiness of AI tools, underscoring the importance of safety, privacy, explainability, fairness, and human fallback options. Although these regulatory frameworks highlight the necessity of enforcement, practitioners often lack detailed guidance on implementing them. Furthermore, the extensive research on operationalizing each of these aspects is frequently buried in technical papers that are difficult for practitioners to parse. In this write-up, we address this shortcoming by providing an accessible overview of existing literature related to operationalizing regulatory principles. We provide easy-to-understand summaries of state-of-the-art literature and highlight various gaps that exist between regulatory guidelines and existing AI research, including the trade-offs that emerge during operationalization. We hope that this work not only serves as a starting point for practitioners interested in learning more about operationalizing the regulatory guidelines outlined in the Blueprint for an AI BoR but also provides researchers with a list of critical open problems and gaps between regulations and state-of-the-art AI research. Finally, we note that this is a working paper and we invite feedback in line with the purpose of this document as described in the introduction.
Authors: Zawalski Micha{\l}, Chen William, Pertsch Karl, Mees Oier, Finn Chelsea, Levine Sergey
Abstract: A key limitation of learned robot control policies is their inability to generalize outside their training data. Recent works on vision-language-action models (VLAs) have shown that the use of large, internet pre-trained vision-language models as the backbone of learned robot policies can substantially improve their robustness and generalization ability. Yet, one of the most exciting capabilities of large vision-language models in other domains is their ability to reason iteratively through complex problems. Can that same capability be brought into robotics to allow policies to improve performance by reasoning about a given task before acting? Naive use of "chain-of-thought" (CoT) style prompting is significantly less effective with standard VLAs because of the relatively simple training examples that are available to them. Additionally, purely semantic reasoning about sub-tasks, as is common in regular CoT, is insufficient for robot policies that need to ground their reasoning in sensory observations and the robot state. To this end, we introduce Embodied Chain-of-Thought Reasoning (ECoT) for VLAs, in which we train VLAs to perform multiple steps of reasoning about plans, sub-tasks, motions, and visually grounded features like object bounding boxes and end effector positions, before predicting the robot action. We design a scalable pipeline for generating synthetic training data for ECoT on large robot datasets. We demonstrate, that ECoT increases the absolute success rate of OpenVLA, the current strongest open-source VLA policy, by 28% across challenging generalization tasks, without any additional robot training data. Additionally, ECoT makes it easier for humans to interpret a policy's failures and correct its behavior using natural language.
Authors: Zhiqiang Xie, Yujia Zheng, Lizi Ottens, Kun Zhang, Christos Kozyrakis, Jonathan Mace
Abstract: Runtime failure and performance degradation is commonplace in modern cloud systems. For cloud providers, automatically determining the root cause of incidents is paramount to ensuring high reliability and availability as prompt fault localization can enable faster diagnosis and triage for timely resolution. A compelling solution explored in recent work is causal reasoning using causal graphs to capture relationships between varied cloud system performance metrics. To be effective, however, systems developers must correctly define the causal graph of their system, which is a time-consuming, brittle, and challenging task that increases in difficulty for large and dynamic systems and requires domain expertise. Alternatively, automated data-driven approaches have limited efficacy for cloud systems due to the inherent rarity of incidents. In this work, we present Atlas, a novel approach to automatically synthesizing causal graphs for cloud systems. Atlas leverages large language models (LLMs) to generate causal graphs using system documentation, telemetry, and deployment feedback. Atlas is complementary to data-driven causal discovery techniques, and we further enhance Atlas with a data-driven validation step. We evaluate Atlas across a range of fault localization scenarios and demonstrate that Atlas is capable of generating causal graphs in a scalable and generalizable manner, with performance that far surpasses that of data-driven algorithms and is commensurate to the ground-truth baseline.
Authors: Mohammed Elbtity, Peyton Chandarana, Ramtin Zand
Abstract: Tensor processing units (TPUs) are one of the most well-known machine learning (ML) accelerators utilized at large scale in data centers as well as in tiny ML applications. TPUs offer several improvements and advantages over conventional ML accelerators, like graphical processing units (GPUs), being designed specifically to perform the multiply-accumulate (MAC) operations required in the matrix-matrix and matrix-vector multiplies extensively present throughout the execution of deep neural networks (DNNs). Such improvements include maximizing data reuse and minimizing data transfer by leveraging the temporal dataflow paradigms provided by the systolic array architecture. While this design provides a significant performance benefit, the current implementations are restricted to a single dataflow consisting of either input, output, or weight stationary architectures. This can limit the achievable performance of DNN inference and reduce the utilization of compute units. Therefore, the work herein consists of developing a reconfigurable dataflow TPU, called the Flex-TPU, which can dynamically change the dataflow per layer during run-time. Our experiments thoroughly test the viability of the Flex-TPU comparing it to conventional TPU designs across multiple well-known ML workloads. The results show that our Flex-TPU design achieves a significant performance increase of up to 2.75x compared to conventional TPU, with only minor area and power overheads.
Authors: James Seekings, Peyton Chandarana, Mahsa Ardakani, MohammadReza Mohammadi, Ramtin Zand
Abstract: This paper explores the synergistic potential of neuromorphic and edge computing to create a versatile machine learning (ML) system tailored for processing data captured by dynamic vision sensors. We construct and train hybrid models, blending spiking neural networks (SNNs) and artificial neural networks (ANNs) using PyTorch and Lava frameworks. Our hybrid architecture integrates an SNN for temporal feature extraction and an ANN for classification. We delve into the challenges of deploying such hybrid structures on hardware. Specifically, we deploy individual components on Intel's Neuromorphic Processor Loihi (for SNN) and Jetson Nano (for ANN). We also propose an accumulator circuit to transfer data from the spiking to the non-spiking domain. Furthermore, we conduct comprehensive performance analyses of hybrid SNN-ANN models on a heterogeneous system of neuromorphic and edge AI hardware, evaluating accuracy, latency, power, and energy consumption. Our findings demonstrate that the hybrid spiking networks surpass the baseline ANN model across all metrics and outperform the baseline SNN model in accuracy and latency.
Authors: Francesco Pinto, Nathalie Rauschmayr, Florian Tram\`er, Philip Torr, Federico Tombari
Abstract: Vision-Language Models (VLMs) have made remarkable progress in document-based Visual Question Answering (i.e., responding to queries about the contents of an input document provided as an image). In this work, we show these models can memorize responses for training samples and regurgitate them even when the relevant visual information has been removed. This includes Personal Identifiable Information (PII) repeated once in the training set, indicating these models could divulge memorised sensitive information and therefore pose a privacy risk. We quantitatively measure the extractability of information in controlled experiments and differentiate between cases where it arises from generalization capabilities or from memorization. We further investigate the factors that influence memorization across multiple state-of-the-art models and propose an effective heuristic countermeasure that empirically prevents the extractability of PII.
Authors: Timothee Chauvin
Abstract: Long contexts of recent LLMs have enabled a new use case: asking models to find security vulnerabilities in entire codebases. To evaluate model performance on this task, we introduce eyeballvul: a benchmark designed to test the vulnerability detection capabilities of language models at scale, that is sourced and updated weekly from the stream of published vulnerabilities in open-source repositories. The benchmark consists of a list of revisions in different repositories, each associated with the list of known vulnerabilities present at that revision. An LLM-based scorer is used to compare the list of possible vulnerabilities returned by a model to the list of known vulnerabilities for each revision. As of July 2024, eyeballvul contains 24,000+ vulnerabilities across 6,000+ revisions and 5,000+ repositories, and is around 55GB in size.
Authors: Sizhe Lester Li, Annan Zhang, Boyuan Chen, Hanna Matusik, Chao Liu, Daniela Rus, Vincent Sitzmann
Abstract: Mirroring the complex structures and diverse functions of natural organisms is a long-standing challenge in robotics. Modern fabrication techniques have dramatically expanded feasible hardware, yet deploying these systems requires control software to translate desired motions into actuator commands. While conventional robots can easily be modeled as rigid links connected via joints, it remains an open challenge to model and control bio-inspired robots that are often multi-material or soft, lack sensing capabilities, and may change their material properties with use. Here, we introduce Neural Jacobian Fields, an architecture that autonomously learns to model and control robots from vision alone. Our approach makes no assumptions about the robot's materials, actuation, or sensing, requires only a single camera for control, and learns to control the robot without expert intervention by observing the execution of random commands. We demonstrate our method on a diverse set of robot manipulators, varying in actuation, materials, fabrication, and cost. Our approach achieves accurate closed-loop control and recovers the causal dynamic structure of each robot. By enabling robot control with a generic camera as the only sensor, we anticipate our work will dramatically broaden the design space of robotic systems and serve as a starting point for lowering the barrier to robotic automation.
Authors: Stefanos Pertigkiozoglou, Evangelos Chatzipantazis, Kostas Daniilidis
Abstract: The goal of this paper is to address the problem of \textit{global} point cloud registration (PCR) i.e., finding the optimal alignment between point clouds irrespective of the initial poses of the scans. This problem is notoriously challenging for classical optimization methods due to computational constraints. First, we show that state-of-the-art deep learning methods suffer from huge performance degradation when the point clouds are arbitrarily placed in space. We propose that \textit{equivariant deep learning} should be utilized for solving this task and we characterize the specific type of bi-equivariance of PCR. Then, we design BiEquiformer a novel and scalable \textit{bi-equivariant} pipeline i.e. equivariant to the independent transformations of the input point clouds. While a naive approach would process the point clouds independently we design expressive bi-equivariant layers that fuse the information from both point clouds. This allows us to extract high-quality superpoint correspondences and in turn, robust point-cloud registration. Extensive comparisons against state-of-the-art methods show that our method achieves comparable performance in the canonical setting and superior performance in the robust setting in both the 3DMatch and the challenging low-overlap 3DLoMatch dataset.
Authors: Mihir Prabhudesai, Russell Mendonca, Zheyang Qin, Katerina Fragkiadaki, Deepak Pathak
Abstract: We have made significant progress towards building foundational video diffusion models. As these models are trained using large-scale unsupervised data, it has become crucial to adapt these models to specific downstream tasks. Adapting these models via supervised fine-tuning requires collecting target datasets of videos, which is challenging and tedious. In this work, we utilize pre-trained reward models that are learned via preferences on top of powerful vision discriminative models to adapt video diffusion models. These models contain dense gradient information with respect to generated RGB pixels, which is critical to efficient learning in complex search spaces, such as videos. We show that backpropagating gradients from these reward models to a video diffusion model can allow for compute and sample efficient alignment of the video diffusion model. We show results across a variety of reward models and video diffusion models, demonstrating that our approach can learn much more efficiently in terms of reward queries and computation than prior gradient-free approaches. Our code, model weights,and more visualization are available at https://vader-vid.github.io.
Authors: Dobrik Georgiev, Pietro Li\`o
Abstract: Graph neural networks (GNNs) have found application for learning in the space of algorithms. However, the algorithms chosen by existing research (sorting, Breadth-First search, shortest path finding, etc.) usually align perfectly with a standard GNN architecture. This report describes how neural execution is applied to a complex algorithm, such as finding maximum bipartite matching by reducing it to a flow problem and using Ford-Fulkerson to find the maximum flow. This is achieved via neural execution based only on features generated from a single GNN. The evaluation shows strongly generalising results with the network achieving optimal matching almost 100% of the time.
Authors: Christoph Hertrich, Martin Skutella
Abstract: The development of a satisfying and rigorous mathematical understanding of the performance of neural networks is a major challenge in artificial intelligence. Against this background, we study the expressive power of neural networks through the example of the classical NP-hard Knapsack Problem. Our main contribution is a class of recurrent neural networks (RNNs) with rectified linear units that are iteratively applied to each item of a Knapsack instance and thereby compute optimal or provably good solution values. We show that an RNN of depth four and width depending quadratically on the profit of an optimum Knapsack solution is sufficient to find optimum Knapsack solutions. We also prove the following tradeoff between the size of an RNN and the quality of the computed Knapsack solution: for Knapsack instances consisting of $n$ items, an RNN of depth five and width $w$ computes a solution of value at least $1-\mathcal{O}(n^2/\sqrt{w})$ times the optimum solution value. Our results build upon a classical dynamic programming formulation of the Knapsack Problem as well as a careful rounding of profit values that are also at the core of the well-known fully polynomial-time approximation scheme for the Knapsack Problem. A carefully conducted computational study qualitatively supports our theoretical size bounds. Finally, we point out that our results can be generalized to many other combinatorial optimization problems that admit dynamic programming solution methods, such as various Shortest Path Problems, the Longest Common Subsequence Problem, and the Traveling Salesperson Problem.
Authors: M. H. Rahman, S. M. Rifaat, S. N. Sadeek, M. Abrar, D. Wang
Abstract: Ride-hailing system requires efficient management of dynamic demand and supply to ensure optimal service delivery, pricing strategies, and operational efficiency. Designing spatio-temporal forecasting models separately in a task-wise and city-wise manner to forecast demand and supply-demand gap in a ride-hailing system poses a burden for the expanding transportation network companies. Therefore, a multi-task learning architecture is proposed in this study by developing gated ensemble of spatio-temporal mixture of experts network (GESME-Net) with convolutional recurrent neural network (CRNN), convolutional neural network (CNN), and recurrent neural network (RNN) for simultaneously forecasting these spatio-temporal tasks in a city as well as across different cities. Furthermore, a task adaptation layer is integrated with the architecture for learning joint representation in multi-task learning and revealing the contribution of the input features utilized in prediction. The proposed architecture is tested with data from Didi Chuxing for: (i) simultaneously forecasting demand and supply-demand gap in Beijing, and (ii) simultaneously forecasting demand across Chengdu and Xian. In both scenarios, models from our proposed architecture outperformed the single-task and multi-task deep learning benchmarks and ensemble-based machine learning algorithms.
Authors: Alind Khare, Animesh Agrawal, Aditya Annavajjala, Payman Behnam, Myungjin Lee, Hugo Latapie, Alexey Tumanov
Abstract: Neural Architecture Search (NAS) for Federated Learning (FL) is an emerging field. It automates the design and training of Deep Neural Networks (DNNs) when data cannot be centralized due to privacy, communication costs, or regulatory restrictions. Recent federated NAS methods not only reduce manual effort but also help achieve higher accuracy than traditional FL methods like FedAvg. Despite the success, existing federated NAS methods still fall short in satisfying diverse deployment targets common in on-device inference like hardware, latency budgets, or variable battery levels. Most federated NAS methods search for only a limited range of neuro-architectural patterns, repeat them in a DNN, thereby restricting achievable performance. Moreover, these methods incur prohibitive training costs to satisfy deployment targets. They perform the training and search of DNN architectures repeatedly for each case. SuperFedNAS addresses these challenges by decoupling the training and search in federated NAS. SuperFedNAS co-trains a large number of diverse DNN architectures contained inside one supernet in the FL setting. Post-training, clients perform NAS locally to find specialized DNNs by extracting different parts of the trained supernet with no additional training. SuperFedNAS takes O(1) (instead of O(N)) cost to find specialized DNN architectures in FL for any N deployment targets. As part of SuperFedNAS, we introduce MaxNet - a novel FL training algorithm that performs multi-objective federated optimization of a large number of DNN architectures ($\approx 5*10^8$) under different client data distributions. Overall, SuperFedNAS achieves upto 37.7% higher accuracy for the same MACs or upto 8.13x reduction in MACs for the same accuracy than existing federated NAS methods.
Authors: Grzegorz Rype\'s\'c, Daniel Marczak, Sebastian Cygert, Tomasz Trzci\'nski, Bart{\l}omiej Twardowski
Abstract: Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend on feature distillation to prevent forgetting the old knowledge. However, this strategy restricts the model's ability to adapt and effectively distinguish new categories. To address this, we introduce a novel technique integrating a learnable projector with feature distillation, thus enhancing model adaptability without sacrificing past knowledge. The resulting distribution shift of the previously learned categories is mitigated with the auxiliary category adaptation network. We demonstrate that while each component offers modest benefits individually, their combination -- dubbed CAMP (Category Adaptation Meets Projected distillation) -- significantly improves the balance between learning new information and retaining old. CAMP exhibits superior performance across several GCCD scenarios with or without exemplars. Additionally, CAMP translates to a well-established Class Incremental Learning setting, achieving state-of-the-art results.
Authors: Stephanie Abrecht, Alexander Hirsch, Shervin Raafatnia, Matthias Woehrle
Abstract: Recent advances in the field of deep learning and impressive performance of deep neural networks (DNNs) for perception have resulted in an increased demand for their use in automated driving (AD) systems. The safety of such systems is of utmost importance and thus requires to consider the unique properties of DNNs. In order to achieve safety of AD systems with DNN-based perception components in a systematic and comprehensive approach, so-called safety concerns have been introduced as a suitable structuring element. On the one hand, the concept of safety concerns is -- by design -- well aligned to existing standards relevant for safety of AD systems such as ISO 21448 (SOTIF). On the other hand, it has already inspired several academic publications and upcoming standards on AI safety such as ISO PAS 8800. While the concept of safety concerns has been previously introduced, this paper extends and refines it, leveraging feedback from various domain and safety experts in the field. In particular, this paper introduces an additional categorization for a better understanding as well as enabling cross-functional teams to jointly address the concerns.
Authors: Xiaowei Gao, Xinke Jiang, Dingyi Zhuang, Huanfa Chen, Shenhao Wang, Stephen Law, James Haworth
Abstract: Traffic accidents present substantial challenges to human safety and socio-economic development in urban areas. Developing a reliable and responsible traffic accident prediction model is crucial to addressing growing public safety concerns and enhancing the safety of urban mobility systems. Traditional methods face limitations at fine spatiotemporal scales due to the sporadic nature of highrisk accidents and the predominance of non-accident characteristics. Furthermore, while most current models show promising occurrence prediction, they overlook the uncertainties arising from the inherent nature of accidents, and then fail to adequately map the hierarchical ranking of accident risk values for more precise insights. To address these issues, we introduce the Spatiotemporal Zero-Inflated Tweedie Graph Neural Network STZITDGNN -- the first uncertainty-aware probabilistic graph deep learning model in roadlevel traffic accident prediction for multisteps. This model integrates the interpretability of the statistical Tweedie family model and the expressive power of graph neural networks. Its decoder innovatively employs a compound Tweedie model,a Poisson distribution to model the frequency of accident occurrences and a Gamma distribution to assess injury severity, supplemented by a zeroinflated component to effectively identify exessive nonincident instances. Empirical tests using realworld traffic data from London, UK, demonstrate that the STZITDGNN surpasses other baseline models across multiple benchmarks and metrics, including accident risk value prediction, uncertainty minimisation, non-accident road identification and accident occurrence accuracy. Our study demonstrates that STZTIDGNN can effectively inform targeted road monitoring, thereby improving urban road safety strategies.
Authors: Zixiang Chen, Yihe Deng, Yuanzhi Li, Quanquan Gu
Abstract: Multi-modal learning has become increasingly popular due to its ability to leverage information from different data sources (e.g., text and images) to improve the model performance. Recently, CLIP has emerged as an effective approach that employs vision-language contrastive pretraining to learn joint image and text representations and exhibits remarkable performance in zero-shot learning and text-guided natural image generation. Despite the huge practical success of CLIP, its theoretical understanding remains elusive. In this paper, we formally study transferrable representation learning underlying CLIP and demonstrate how features from different modalities get aligned. We also analyze its zero-shot transfer performance on the downstream tasks. Inspired by our analysis, we propose a new CLIP-type approach, which achieves better performance than CLIP and other state-of-the-art methods on benchmark datasets.
Authors: Thomas L. Lee, Amos Storkey
Abstract: Work on continual learning (CL) has thus far largely focused on the problems arising from shifts in the data distribution. However, CL can be decomposed into two sub-problems: (a) shifts in the data distribution, and (b) dealing with the fact that the data is split into chunks and so only a part of the data is available to be trained on at any point in time. In this work, we look at the latter sub-problem, the chunking of data. We show that chunking is an important part of CL, accounting for around half of the performance drop from offline learning in our experiments. Furthermore, our results reveal that current CL algorithms do not address the chunking sub-problem, only performing as well as plain SGD training when there is no shift in the data distribution. Therefore, we show that chunking is both an important and currently unaddressed sub-problem and until it is addressed CL methods will be capped in performance. Additionally, we analyse why performance drops when learning occurs on identically distributed chunks of data, and find that forgetting, which is often seen to be a problem due to distribution shift, still arises and is a significant problem. We also show that performance on the chunking sub-problem can be increased and that this performance transfers to the full CL setting, where there is distribution shift. Hence, we argue that work on chunking can help advance CL in general.
Authors: Xumeng Wen, Han Zhang, Shun Zheng, Wei Xu, Jiang Bian
Abstract: Tabular data is foundational to predictive modeling in various crucial industries, including healthcare, finance, retail, sustainability, etc. Despite the progress made in specialized models, there is an increasing demand for universal models that can transfer knowledge, generalize from limited data, and follow human instructions. These are challenges that current tabular deep learning approaches have not fully tackled. Here we introduce Generative Tabular Learning (GTL), a novel framework that integrates the advanced functionalities of large language models (LLMs)-such as prompt-based zero-shot generalization and in-context learning-into tabular deep learning. GTL capitalizes on the pre-training of LLMs on diverse tabular data, enhancing their understanding of domain-specific knowledge, numerical sequences, and statistical dependencies critical for accurate predictions. Our empirical study spans 384 public datasets, rigorously analyzing GTL's convergence and scaling behaviors and assessing the impact of varied data templates. The GTL-enhanced LLaMA-2 model demonstrates superior zero-shot and in-context learning capabilities across numerous classification and regression tasks. Notably, it achieves this without fine-tuning, outperforming traditional methods and rivaling state-of-the-art models like GPT-4 in certain cases. Through GTL, we not only foster a deeper integration of LLMs' sophisticated abilities into tabular data comprehension and application but also offer a new training resource and a test bed for LLMs to enhance their ability to comprehend tabular data. To facilitate reproducible research, we release our code, data, and model checkpoints at https://github.com/microsoft/Industrial-Foundation-Models.
URLs: https://github.com/microsoft/Industrial-Foundation-Models.
Authors: Harshavardhan Kamarthi, B. Aditya Prakash
Abstract: Large pre-trained models have been vital in recent advancements in domains like language and vision, making model training for individual downstream tasks more efficient and provide superior performance. However, tackling time-series analysis tasks usually involves designing and training a separate model from scratch leveraging training data and domain expertise specific to the task. We tackle a significant challenge for pre-training a foundational time-series model from multi-domain time-series datasets: extracting semantically useful tokenized inputs to the model across heterogenous time-series from different domains. We propose Large Pre-trained Time-series Models (LPTM) that introduces a novel method of \textit{adaptive segmentation} that automatically identifies optimal dataset-specific segmentation strategy during pre-training. This enables LPTM to perform similar to or better than domain-specific state-of-art model when fine-tuned to different downstream time-series analysis tasks and under zero-shot settings. LPTM achieves superior forecasting and time-series classification results taking up to 40% less data and 50% less training time compared to state-of-art baselines.
Authors: Daesoo Lee, Sara Malacarne, Erlend Aune
Abstract: We present a novel time series anomaly detection method that achieves excellent detection accuracy while offering a superior level of explainability. Our proposed method, TimeVQVAE-AD, leverages masked generative modeling adapted from the cutting-edge time series generation method known as TimeVQVAE. The prior model is trained on the discrete latent space of a time-frequency domain. Notably, the dimensional semantics of the time-frequency domain are preserved in the latent space, enabling us to compute anomaly scores across different frequency bands, which provides a better insight into the detected anomalies. Additionally, the generative nature of the prior model allows for sampling likely normal states for detected anomalies, enhancing the explainability of the detected anomalies through counterfactuals. Our experimental evaluation on the UCR Time Series Anomaly archive demonstrates that TimeVQVAE-AD significantly surpasses the existing methods in terms of detection accuracy and explainability. We provide our implementation on GitHub: \url{https://github.com/ML4ITS/TimeVQVAE-AnomalyDetection}.
Authors: Naman Agarwal, Daniel Suo, Xinyi Chen, Elad Hazan
Abstract: This paper studies sequence modeling for prediction tasks with long range dependencies. We propose a new formulation for state space models (SSMs) based on learning linear dynamical systems with the spectral filtering algorithm (Hazan et al. (2017)). This gives rise to a novel sequence prediction architecture we call a spectral state space model. Spectral state space models have two primary advantages. First, they have provable robustness properties as their performance depends on neither the spectrum of the underlying dynamics nor the dimensionality of the problem. Second, these models are constructed with fixed convolutional filters that do not require learning while still outperforming SSMs in both theory and practice. The resulting models are evaluated on synthetic dynamical systems and long-range prediction tasks of various modalities. These evaluations support the theoretical benefits of spectral filtering for tasks requiring very long range memory.
Authors: Shuze Liu, Shuhang Chen, Shangtong Zhang
Abstract: Stochastic approximation is a class of algorithms that update a vector iteratively, incrementally, and stochastically, including, e.g., stochastic gradient descent and temporal difference learning. One fundamental challenge in analyzing a stochastic approximation algorithm is to establish its stability, i.e., to show that the stochastic vector iterates are bounded almost surely. In this paper, we extend the celebrated Borkar-Meyn theorem for stability from the Martingale difference noise setting to the Markovian noise setting, which greatly improves its applicability in reinforcement learning, especially in those off-policy reinforcement learning algorithms with linear function approximation and eligibility traces. Central to our analysis is the diminishing asymptotic rate of change of a few functions, which is implied by both a form of strong law of large numbers and a commonly used V4 Lyapunov drift condition and trivially holds if the Markov chain is finite and irreducible.
Authors: Ruixin Song, Gabriel Spadon, Ronald Pelot, Stan Matwin, Amilcar Soares
Abstract: Aquatic non-indigenous species (NIS) pose significant threats to biodiversity, disrupting ecosystems and inflicting substantial economic damages across agriculture, forestry, and fisheries. Due to the fast growth of global trade and transportation networks, NIS has been introduced and spread unintentionally in new environments. This study develops a new physics-informed model to forecast maritime shipping traffic between port regions worldwide. The predicted information provided by these models, in turn, is used as input for risk assessment of NIS spread through transportation networks to evaluate the capability of our solution. Inspired by the gravity model for international trades, our model considers various factors that influence the likelihood and impact of vessel activities, such as shipping flux density, distance between ports, trade flow, and centrality measures of transportation hubs. Accordingly, this paper introduces transformers to gravity models to rebuild the short- and long-term dependencies that make the risk analysis feasible. Thus, we introduce a physics-inspired framework that achieves an 89% binary accuracy for existing and non-existing trajectories and an 84.8% accuracy for the number of vessels flowing between key port areas, representing more than 10% improvement over the traditional deep-gravity model. Along these lines, this research contributes to a better understanding of NIS risk assessment. It allows policymakers, conservationists, and stakeholders to prioritize management actions by identifying high-risk invasion pathways. Besides, our model is versatile and can include new data sources, making it suitable for assessing international vessel traffic flow in a changing global landscape.
Authors: Catherine Weaver, Chen Tang, Ce Hao, Kenta Kawamoto, Masayoshi Tomizuka, Wei Zhan
Abstract: Imitation learning learns a policy from demonstrations without requiring hand-designed reward functions. In many robotic tasks, such as autonomous racing, imitated policies must model complex environment dynamics and human decision-making. Sequence modeling is highly effective in capturing intricate patterns of motion sequences but struggles to adapt to new environments or distribution shifts that are common in real-world robotics tasks. In contrast, Adversarial Imitation Learning (AIL) can mitigate this effect, but struggles with sample inefficiency and handling complex motion patterns. Thus, we propose BeTAIL: Behavior Transformer Adversarial Imitation Learning, which combines a Behavior Transformer (BeT) policy from human demonstrations with online AIL. BeTAIL adds an AIL residual policy to the BeT policy to model the sequential decision-making process of human experts and correct for out-of-distribution states or shifts in environment dynamics. We test BeTAIL on three challenges with expert-level demonstrations of real human gameplay in Gran Turismo Sport. Our proposed residual BeTAIL reduces environment interactions and improves racing performance and stability, even when the BeT is pretrained on different tracks than downstream learning. Videos and code available at: https://sites.google.com/berkeley.edu/BeTAIL/home.
Authors: Kaiqi Chen, Eugene Lim, Kelvin Lin, Yiyang Chen, Harold Soh
Abstract: Imitation learning empowers artificial agents to mimic behavior by learning from demonstrations. Recently, diffusion models, which have the ability to model high-dimensional and multimodal distributions, have shown impressive performance on imitation learning tasks. These models learn to shape a policy by diffusing actions (or states) from standard Gaussian noise. However, the target policy to be learned is often significantly different from Gaussian and this mismatch can result in poor performance when using a small number of diffusion steps (to improve inference speed) and under limited data. The key idea in this work is that initiating from a more informative source than Gaussian enables diffusion methods to mitigate the above limitations. We contribute both theoretical results, a new method, and empirical findings that show the benefits of using an informative source policy. Our method, which we call BRIDGER, leverages the stochastic interpolants framework to bridge arbitrary policies, thus enabling a flexible approach towards imitation learning. It generalizes prior work in that standard Gaussians can still be applied, but other source policies can be used if available. In experiments on challenging simulation benchmarks and on real robots, BRIDGER outperforms state-of-the-art diffusion policies. We provide further analysis on design considerations when applying BRIDGER. Code for BRIDGER is available at https://github.com/clear-nus/bridger.
Authors: Milin Zhang, Mohammad Abdi, Shahriar Rifat, Francesco Restuccia
Abstract: Distributed deep neural networks (DNNs) have emerged as a key technique to reduce communication overhead without sacrificing performance in edge computing systems. Recently, entropy coding has been introduced to further reduce the communication overhead. The key idea is to train the distributed DNN jointly with an entropy model, which is used as side information during inference time to adaptively encode latent representations into bit streams with variable length. To the best of our knowledge, the resilience of entropy models is yet to be investigated. As such, in this paper we formulate and investigate the resilience of entropy models to intentional interference (e.g., adversarial attacks) and unintentional interference (e.g., weather changes and motion blur). Through an extensive experimental campaign with 3 different DNN architectures, 2 entropy models and 4 rate-distortion trade-off factors, we demonstrate that the entropy attacks can increase the communication overhead by up to 95%. By separating compression features in frequency and spatial domain, we propose a new defense mechanism that can reduce the transmission overhead of the attacked input by about 9% compared to unperturbed data, with only about 2% accuracy loss. Importantly, the proposed defense mechanism is a standalone approach which can be applied in conjunction with approaches such as adversarial training to further improve robustness. Code will be shared for reproducibility.
Authors: Oliver Schulte, Pascal Poupart
Abstract: Reinforcement learning (RL) and causal modelling naturally complement each other. The goal of causal modelling is to predict the effects of interventions in an environment, while the goal of reinforcement learning is to select interventions that maximize the rewards the agent receives from the environment. Reinforcement learning includes the two most powerful sources of information for estimating causal relationships: temporal ordering and the ability to act on an environment. This paper examines which reinforcement learning settings we can expect to benefit from causal modelling, and how. In online learning, the agent has the ability to interact directly with their environment, and learn from exploring it. Our main argument is that in online learning, conditional probabilities are causal, and therefore offline RL is the setting where causal learning has the most potential to make a difference. Essentially, the reason is that when an agent learns from their {\em own} experience, there are no unobserved confounders that influence both the agent's own exploratory actions and the rewards they receive. Our paper formalizes this argument. For offline RL, where an agent may and typically does learn from the experience of {\em others}, we describe previous and new methods for leveraging a causal model, including support for counterfactual queries.
Authors: Yi Zhang, Dongyuan Lu, Jitao Sang
Abstract: Machine learning models often make predictions based on biased features such as gender, race, and other social attributes, posing significant fairness risks, especially in societal applications, such as hiring, banking, and criminal justice. Traditional approaches to addressing this issue involve retraining or fine-tuning neural networks with fairness-aware optimization objectives. However, these methods can be impractical due to significant computational resources, complex industrial tests, and the associated CO2 footprint. Additionally, regular users often fail to fine-tune models because they lack access to model parameters In this paper, we introduce the Inference-Time Rule Eraser (Eraser), a novel method designed to address fairness concerns by removing biased decision-making rules from deployed models during inference without altering model weights. We begin by establishing a theoretical foundation for modifying model outputs to eliminate biased rules through Bayesian analysis. Next, we present a specific implementation of Eraser that involves two stages: (1) distilling the biased rules from the deployed model into an additional patch model, and (2) removing these biased rules from the output of the deployed model during inference. Extensive experiments validate the effectiveness of our approach, showcasing its superior performance in addressing fairness concerns in AI systems.
Authors: Krzysztof Kotowski, Irena Roterman, Katarzyna Stapor
Abstract: The prediction of intrinsic disorder regions has significant implications for understanding protein function, structure, and dynamics. It can help to discover novel functions or protein-protein interactions essential to designing new drugs, therapies, or enzymes. Recently, a new generation of predictors based on protein language models is emerging. These algorithms reach state-of-the-art accuracy without calculating time-consuming multiple sequence alignments (MSAs). The article pre-sents a new protein intrinsic disorder predictor DisorderUnetLM based on the Attention U-Net convolutional neural network using features from the protein language model ProtTrans. DisorderUnetLM shows top results in the direct comparison with flDPnn and IDP-CRF predictors using MSAs and with the SETH predictor using features from the same ProtTrans model. Moreover, among 41 predictors from the latest Critical Assessment of Protein Intrinsic Disorder Prediction (CAID-2) benchmark, it ranks 9th for the Disorder-PDB subset (with ROC-AUC of 0.924) and 1st for the Disorder-NOX subset (with ROC-AUC of 0.844) which confirms its potential to perform well in the upcoming CAID-3 challenge for which Disor-derUnetLM was submitted.
Authors: Zahra Zamanzadeh Darban, Yiyuan Yang, Geoffrey I. Webb, Charu C. Aggarwal, Qingsong Wen, Mahsa Salehi
Abstract: In time series anomaly detection (TSAD), the scarcity of labeled data poses a challenge to the development of accurate models. Unsupervised domain adaptation (UDA) offers a solution by leveraging labeled data from a related domain to detect anomalies in an unlabeled target domain. However, existing UDA methods assume consistent anomalous classes across domains. To address this limitation, we propose a novel Domain Adaptation Contrastive learning model for Anomaly Detection in multivariate time series (DACAD), combining UDA with contrastive learning. DACAD utilizes an anomaly injection mechanism that enhances generalization across unseen anomalous classes, improving adaptability and robustness. Additionally, our model employs supervised contrastive loss for the source domain and self-supervised contrastive triplet loss for the target domain, ensuring comprehensive feature representation learning and domain-invariant feature extraction. Finally, an effective Centre-based Entropy Classifier (CEC) accurately learns normal boundaries in the source domain. Extensive evaluations on multiple real-world datasets and a synthetic dataset highlight DACAD's superior performance in transferring knowledge across domains and mitigating the challenge of limited labeled data in TSAD.
Authors: Ming Lu, Zhen Gao, Ying Zou, Zuguo Chen, Pei Li
Abstract: With the development of technology, the chemical production process is becoming increasingly complex and large-scale, making fault detection particularly important. However, current detective methods struggle to address the complexities of large-scale production processes. In this paper, we integrate the strengths of deep learning and machine learning technologies, combining the advantages of bidirectional long and short-term memory neural networks, fully connected neural networks, and the extra trees algorithm to propose a novel fault detection model named three-layer deep learning network random trees (TDLN-trees). First, the deep learning component extracts temporal features from industrial data, combining and transforming them into a higher-level data representation. Second, the machine learning component processes and classifies the features extracted in the first step. An experimental analysis based on the Tennessee Eastman process verifies the superiority of the proposed method.
Authors: Ce Ge, Zhijian Ma, Daoyuan Chen, Yaliang Li, Bolin Ding
Abstract: Large language models exhibit exceptional generalization capabilities, primarily attributed to the utilization of diversely sourced data. However, conventional practices in integrating this diverse data heavily rely on heuristic schemes, lacking theoretical guidance. This research tackles these limitations by investigating strategies based on low-cost proxies for data mixtures, with the aim of streamlining data curation to enhance training efficiency. Specifically, we propose a unified scaling law, termed $\textbf{BiMix}$, which accurately models the bivariate scaling behaviors of both data quantity and mixing proportions. We conduct systematic experiments and provide empirical evidence for the predictive power and fundamental principles of $\textbf{BiMix}$. Notably, our findings reveal that entropy-driven training-free data mixtures can achieve comparable or even better performance than more resource-intensive methods. We hope that our quantitative insights can shed light on further judicious research and development in cost-effective language modeling.
Authors: D\'aniel R\'acz, Mih\'aly Petreczky, B\'alint Dar\'oczy
Abstract: Many state-of-the-art models trained on long-range sequences, for example S4, S5 or LRU, are made of sequential blocks combining State-Space Models (SSMs) with neural networks. In this paper we provide a PAC bound that holds for these kind of architectures with stable SSM blocks and does not depend on the length of the input sequence. Imposing stability of the SSM blocks is a standard practice in the literature, and it is known to help performance. Our results provide a theoretical justification for the use of stable SSM blocks as the proposed PAC bound decreases as the degree of stability of the SSM blocks increases.
Authors: Marianna Nezhurina, Lucia Cipolina-Kun, Mehdi Cherti, Jenia Jitsev
Abstract: Large Language Models (LLMs) are often described as being instances of foundation models - that is, models that transfer strongly across various tasks and conditions in few-show or zero-shot manner, while exhibiting scaling laws that predict function improvement when increasing the pre-training scale. These claims of excelling in different functions and tasks rely on measurements taken across various sets of standardized benchmarks showing high scores for such models. We demonstrate here a dramatic breakdown of function and reasoning capabilities of state-of-the-art models trained at the largest available scales which claim strong function, using a simple, short, conventional common sense problem (AIW problem) formulated in concise natural language, easily solvable by humans. The breakdown is dramatic, as models show strong fluctuations across even slight problem variations that should not affect problem solving, also expressing strong overconfidence in the wrong solutions, often backed up by plausible sounding explanation-like confabulations. Various standard interventions in an attempt to get the right solution, like various type of enhanced prompting, or urging the models to reconsider the wrong solutions again by multi step re-evaluation, fail. We take these initial observations to the scientific and technological community to stimulate urgent re-assessment of the claimed capabilities of current generation of LLMs. Such re-assessment also requires common action to create standardized benchmarks that would allow proper detection of such basic reasoning deficits that obviously manage to remain undiscovered by current state-of-the-art evaluation procedures and benchmarks. Code for reproducing experiments in the paper and raw experiments data can be found at https://github.com/LAION-AI/AIW
Authors: Bj\"orn Nieth, Thomas Altstidl, Leo Schwinn, Bj\"orn Eskofier
Abstract: Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models to real-world systems. Adversarial training has proven to be one of the most promising strategies against these attacks, at the expense of a substantial increase in training time. With the ongoing trend of integrating large-scale synthetic data this is only expected to increase even further. Thus, the need for data-centric approaches that reduce the number of training samples while maintaining accuracy and robustness arises. While data pruning and active learning are prominent research topics in deep learning, they are as of now largely unexplored in the adversarial training literature. We address this gap and propose a new data pruning strategy based on extrapolating data importance scores from a small set of data to a larger set. In an empirical evaluation, we demonstrate that extrapolation-based pruning can efficiently reduce dataset size while maintaining robustness.
Authors: Zuzanna Gawrysiak, Agata \.Zywot, Agnieszka {\L}awrynowicz
Abstract: We present WineGraph, an extended version of FlavorGraph, a heterogeneous graph incorporating wine data into its structure. This integration enables food-wine pairing based on taste and sommelier-defined rules. Leveraging a food dataset comprising 500,000 reviews and a wine reviews dataset with over 130,000 entries, we computed taste descriptors for both food and wine. This information was then utilised to pair food items with wine and augment FlavorGraph with additional data. The results demonstrate the potential of heterogeneous graphs to acquire supplementary information, proving beneficial for wine pairing.
Authors: 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: Mingjia Yin, Chuhan Wu, Yufei Wang, Hao Wang, Wei Guo, Yasheng Wang, Yong Liu, Ruiming Tang, Defu Lian, Enhong Chen
Abstract: Data is the cornerstone of large language models (LLMs), but not all data is useful for model learning. Carefully selected data can better elicit the capabilities of LLMs with much less computational overhead. Most methods concentrate on evaluating the quality of individual samples in data selection, while the combinatorial effects among samples are neglected. Even if each sample is of perfect quality, their combinations may be suboptimal in teaching LLMs due to their intrinsic homogeneity or contradiction. In this paper, we aim to uncover the underlying relationships between LLM performance and data selection. Inspired by the information compression nature of LLMs, we uncover an ``entropy law'' that connects LLM performance with data compression ratio and first-epoch training loss, which reflect the information redundancy of a dataset and the mastery of inherent knowledge encoded in this dataset, respectively. Through both theoretical deduction and empirical evaluation, we find that model performance is negatively correlated to the compression ratio of training data, which usually yields a lower training loss. Based on the findings of the entropy law, we propose a quite efficient and universal data selection method named \textbf{ZIP} for training LLMs, which aim to prioritize data subsets exhibiting a low compression ratio. Based on a multi-stage algorithm that selects diverse data in a greedy manner, we can obtain a good data subset with satisfactory diversity. Extensive experiments have been conducted to validate the entropy law and the superiority of ZIP across different LLM backbones and alignment stages. We also present an interesting application of entropy law that can detect potential performance risks at the beginning of model training.
Authors: Yuhan Li, Peisong Wang, Xiao Zhu, Aochuan Chen, Haiyun Jiang, Deng Cai, Victor Wai Kin Chan, Jia Li
Abstract: The emergence of large language models (LLMs) has revolutionized the way we interact with graphs, leading to a new paradigm called GraphLLM. Despite the rapid development of GraphLLM methods in recent years, the progress and understanding of this field remain unclear due to the lack of a benchmark with consistent experimental protocols. To bridge this gap, we introduce GLBench, the first comprehensive benchmark for evaluating GraphLLM methods in both supervised and zero-shot scenarios. GLBench provides a fair and thorough evaluation of different categories of GraphLLM methods, along with traditional baselines such as graph neural networks. Through extensive experiments on a collection of real-world datasets with consistent data processing and splitting strategies, we have uncovered several key findings. Firstly, GraphLLM methods outperform traditional baselines in supervised settings, with LLM-as-enhancers showing the most robust performance. However, using LLMs as predictors is less effective and often leads to uncontrollable output issues. We also notice that no clear scaling laws exist for current GraphLLM methods. In addition, both structures and semantics are crucial for effective zero-shot transfer, and our proposed simple baseline can even outperform several models tailored for zero-shot scenarios. The data and code of the benchmark can be found at https://github.com/NineAbyss/GLBench.
Authors: Ben Cohen, Emaad Khwaja, Kan Wang, Charles Masson, Elise Ram\'e, Youssef Doubli, Othmane Abou-Amal
Abstract: This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Datadog. In addition to advancing the state of the art on generalized time series benchmarks in domains such as electricity and weather, this model is the first general-purpose time series forecasting foundation model to be specifically tuned for observability metrics. Toto was trained on a dataset of one trillion time series data points, the largest among all currently published time series foundation models. Alongside publicly available time series datasets, 75% of the data used to train Toto consists of fully anonymous numerical metric data points from the Datadog platform. In our experiments, Toto outperforms existing time series foundation models on observability data. It does this while also excelling at general-purpose forecasting tasks, achieving state-of-the-art zero-shot performance on multiple open benchmark datasets.
Authors: Ryan Cohn, Elizabeth Holm
Abstract: Recent developments in graph neural networks show promise for predicting the occurrence of abnormal grain growth, which has been a particularly challenging area of research due to its apparent stochastic nature. In this study, we generate a large dataset of Monte Carlo simulations of abnormal grain growth. We train simple graph convolution networks to predict which initial microstructures will exhibit abnormal grain growth, and compare the results to a standard computer vision approach for the same task. The graph neural network outperformed the computer vision method and achieved 73% prediction accuracy and fewer false positives. It also provided some physical insight into feature importance and the relevant length scale required to maximize predictive performance. Analysis of the uncertainty in the Monte Carlo simulations provides additional insights for ongoing work in this area.
Authors: Yeguang Qin, Yilin Yang, Fengxiao Tang, Xin Yao, Ming Zhao, Nei Kato
Abstract: The Space-Air-Ground Integrated Network (SAGIN) plays a pivotal role as a comprehensive foundational network communication infrastructure, presenting opportunities for highly efficient global data transmission. Nonetheless, given SAGIN's unique characteristics as a dynamically heterogeneous network, conventional network optimization methodologies encounter challenges in satisfying the stringent requirements for network latency and stability inherent to data transmission within this network environment. Therefore, this paper proposes the use of differentiated federated reinforcement learning (DFRL) to solve the traffic offloading problem in SAGIN, i.e., using multiple agents to generate differentiated traffic offloading policies. Considering the differentiated characteristics of each region of SAGIN, DFRL models the traffic offloading policy optimization process as the process of solving the Decentralized Partially Observable Markov Decision Process (DEC-POMDP) problem. The paper proposes a novel Differentiated Federated Soft Actor-Critic (DFSAC) algorithm to solve the problem. The DFSAC algorithm takes the network packet delay as the joint reward value and introduces the global trend model as the joint target action-value function of each agent to guide the update of each agent's policy. The simulation results demonstrate that the traffic offloading policy based on the DFSAC algorithm achieves better performance in terms of network throughput, packet loss rate, and packet delay compared to the traditional federated reinforcement learning approach and other baseline approaches.
Authors: Yao Qiang, Chengyin Li, Prashant Khanduri, Dongxiao Zhu
Abstract: Vision Transformer (ViT) has recently gained significant attention in solving computer vision (CV) problems due to its capability of extracting informative features and modeling long-range dependencies through the attention mechanism. Whereas recent works have explored the trustworthiness of ViT, including its robustness and explainability, the issue of fairness has not yet been adequately addressed. We establish that the existing fairness-aware algorithms designed for CNNs do not perform well on ViT, which highlights the need to develop our novel framework via Debiased Self-Attention (DSA). DSA is a fairness-through-blindness approach that enforces ViT to eliminate spurious features correlated with the sensitive label for bias mitigation and simultaneously retain real features for target prediction. Notably, DSA leverages adversarial examples to locate and mask the spurious features in the input image patches with an additional attention weights alignment regularizer in the training objective to encourage learning real features for target prediction. Importantly, our DSA framework leads to improved fairness guarantees over prior works on multiple prediction tasks without compromising target prediction performance. Code is available at \href{https://github.com/qiangyao1988/DSA}{https://github.com/qiangyao1988/DSA}.
URLs: https://github.com/qiangyao1988/DSA, https://github.com/qiangyao1988/DSA
Authors: Bernard Keenan, Kacper Sokol
Abstract: Over the past decade explainable artificial intelligence has evolved from a predominantly technical discipline into a field that is deeply intertwined with social sciences. Insights such as human preference for contrastive -- more precisely, counterfactual -- explanations have played a major role in this transition, inspiring and guiding the research in computer science. Other observations, while equally important, have nevertheless received much less consideration. The desire of human explainees to communicate with artificial intelligence explainers through a dialogue-like interaction has been mostly neglected by the community. This poses many challenges for the effectiveness and widespread adoption of such technologies as delivering a single explanation optimised according to some predefined objectives may fail to engender understanding in its recipients and satisfy their unique needs given the diversity of human knowledge and intention. Using insights elaborated by Niklas Luhmann and, more recently, Elena Esposito we apply social systems theory to highlight challenges in explainable artificial intelligence and offer a path forward, striving to reinvigorate the technical research in the direction of interactive and iterative explainers. Specifically, this paper demonstrates the potential of systems theoretical approaches to communication in elucidating and addressing the problems and limitations of human-centred explainable artificial intelligence.
Authors: Rui-Jie Zhu, Qihang Zhao, Guoqi Li, Jason K. Eshraghian
Abstract: As the size of large language models continue to scale, so does the computational resources required to run it. Spiking Neural Networks (SNNs) have emerged as an energy-efficient approach to deep learning that leverage sparse and event-driven activations to reduce the computational overhead associated with model inference. While they have become competitive with non-spiking models on many computer vision tasks, SNNs have also proven to be more challenging to train. As a result, their performance lags behind modern deep learning, and we are yet to see the effectiveness of SNNs in language generation. In this paper, inspired by the Receptance Weighted Key Value (RWKV) language model, we successfully implement `SpikeGPT', a generative language model with binary, event-driven spiking activation units. We train the proposed model on two model variants: 45M and 216M parameters. To the best of our knowledge, SpikeGPT is the largest backpropagation-trained SNN model to date, rendering it suitable for both the generation and comprehension of natural language. We achieve this by modifying the transformer block to replace multi-head self attention to reduce quadratic computational complexity O(N^2) to linear complexity O(N) with increasing sequence length. Input tokens are instead streamed in sequentially to our attention mechanism (as with typical SNNs). Our preliminary experiments show that SpikeGPT remains competitive with non-spiking models on tested benchmarks, while maintaining 20x fewer operations when processed on neuromorphic hardware that can leverage sparse, event-driven activations. Our code implementation is available at https://github.com/ridgerchu/SpikeGPT.
Authors: Alexander Hoelzemann, Kristof Van Laerhoven
Abstract: Research into the detection of human activities from wearable sensors is a highly active field, benefiting numerous applications, from ambulatory monitoring of healthcare patients via fitness coaching to streamlining manual work processes. We present an empirical study that evaluates and contrasts four commonly employed annotation methods in user studies focused on in-the-wild data collection. For both the user-driven, in situ annotations, where participants annotate their activities during the actual recording process, and the recall methods, where participants retrospectively annotate their data at the end of each day, the participants had the flexibility to select their own set of activity classes and corresponding labels. Our study illustrates that different labeling methodologies directly impact the annotations' quality, as well as the capabilities of a deep learning classifier trained with the data. We noticed that in situ methods produce less but more precise labels than recall methods. Furthermore, we combined an activity diary with a visualization tool that enables the participant to inspect and label their activity data. Due to the introduction of such a tool were able to decrease missing annotations and increase the annotation consistency, and therefore the F1-Score of the deep learning model by up to 8% (ranging between 82.1 and 90.4% F1-Score). Furthermore, we discuss the advantages and disadvantages of the methods compared in our study, the biases they could introduce, and the consequences of their usage on human activity recognition studies as well as possible solutions.
Authors: Dor H. Shmuel, Julian P. Merkofer, Guy Revach, Ruud J. G. van Sloun, Nir Shlezinger
Abstract: Direction of arrival (DoA) estimation is a fundamental task in array processing. A popular family of DoA estimation algorithms are subspace methods, which operate by dividing the measurements into distinct signal and noise subspaces. Subspace methods, such as Multiple Signal Classification (MUSIC) and Root-MUSIC, rely on several restrictive assumptions, including narrowband non-coherent sources and fully calibrated arrays, and their performance is considerably degraded when these do not hold. In this work we propose SubspaceNet; a data-driven DoA estimator which learns how to divide the observations into distinguishable subspaces. This is achieved by utilizing a dedicated deep neural network to learn the empirical autocorrelation of the input, by training it as part of the Root-MUSIC method, leveraging the inherent differentiability of this specific DoA estimator, while removing the need to provide a ground-truth decomposable autocorrelation matrix. Once trained, the resulting SubspaceNet serves as a universal surrogate covariance estimator that can be applied in combination with any subspace-based DoA estimation method, allowing its successful application in challenging setups. SubspaceNet is shown to enable various DoA estimation algorithms to cope with coherent sources, wideband signals, low SNR, array mismatches, and limited snapshots, while preserving the interpretability and the suitability of classic subspace methods.
Authors: Mu Cai, Zeyi Huang, Yuheng Li, Utkarsh Ojha, Haohan Wang, Yong Jae Lee
Abstract: Large language models (LLMs) have made significant advancements in natural language understanding. However, through that enormous semantic representation that the LLM has learnt, is it somehow possible for it to understand images as well? This work investigates this question. To enable the LLM to process images, we convert them into a representation given by Scalable Vector Graphics (SVG). To study what the LLM can do with this XML-based textual description of images, we test the LLM on three broad computer vision tasks: (i) visual reasoning and question answering, (ii) image classification under distribution shift, few-shot learning, and (iii) generating new images using visual prompting. Even though we do not naturally associate LLMs with any visual understanding capabilities, our results indicate that the LLM can often do a decent job in many of these tasks, potentially opening new avenues for research into LLMs' ability to understand image data. Our code, data, and models can be found here https://github.com/mu-cai/svg-llm.
Authors: Prasann Singhal, Tanya Goyal, Jiacheng Xu, Greg Durrett
Abstract: Great success has been reported using Reinforcement Learning from Human Feedback (RLHF) to align large language models, with open preference datasets enabling wider experimentation, particularly for "helpfulness" in tasks like dialogue and web question answering. Alongside these improvements, however, RLHF also often drives models to produce longer outputs. This paper demonstrates, on three diverse settings, that optimizing for response length is, much more than previously thought, a significant factor behind RLHF. Studying the strategies RL optimization uses to maximize reward, we find improvements in reward to largely be driven by increasing response length, instead of other features. Indeed, we find that even a purely length-based reward reproduces most downstream RLHF improvements over supervised fine-tuned models. Testing a comprehensive set of length-countering interventions, we identify the dominant source of these biases to be reward models, which, by studying training dynamics, we find are non-robust and easily influenced by length biases in preference data.
Authors: Nicholas Kroeger, Dan Ley, Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju
Abstract: Recent advancements in Large Language Models (LLMs) have demonstrated exceptional capabilities in complex tasks like machine translation, commonsense reasoning, and language understanding. One of the primary reasons for the adaptability of LLMs in such diverse tasks is their in-context learning (ICL) capability, which allows them to perform well on new tasks by simply using a few task samples in the prompt. Despite their effectiveness in enhancing the performance of LLMs on diverse language and tabular tasks, these methods have not been thoroughly explored for their potential to generate post hoc explanations. In this work, we carry out one of the first explorations to analyze the effectiveness of LLMs in explaining other complex predictive models using ICL. To this end, we propose a novel framework, In-Context Explainers, comprising of three novel approaches that exploit the ICL capabilities of LLMs to explain the predictions made by other predictive models. We conduct extensive analysis with these approaches on real-world tabular and text datasets and demonstrate that LLMs are capable of explaining other predictive models similar to state-of-the-art post hoc explainers, opening up promising avenues for future research into LLM-based post hoc explanations of complex predictive models.
Authors: Dzung Pham, Shreyas Kulkarni, Amir Houmansadr
Abstract: Federated learning has emerged as a promising privacy-preserving solution for machine learning domains that rely on user interactions, particularly recommender systems and online learning to rank. While there has been substantial research on the privacy of traditional federated learning, little attention has been paid to the privacy properties of these interaction-based settings. In this work, we show that users face an elevated risk of having their private interactions reconstructed by the central server when the server can control the training features of the items that users interact with. We introduce RAIFLE, a novel optimization-based attack framework where the server actively manipulates the features of the items presented to users to increase the success rate of reconstruction. Our experiments with federated recommendation and online learning-to-rank scenarios demonstrate that RAIFLE is significantly more powerful than existing reconstruction attacks like gradient inversion, achieving high performance consistently in most settings. We discuss the pros and cons of several possible countermeasures to defend against RAIFLE in the context of interaction-based federated learning. Our code is open-sourced at https://github.com/dzungvpham/raifle.
Authors: Randall Balestriero, Romain Cosentino, Sarath Shekkizhar
Abstract: Large Language Models (LLMs) drive current AI breakthroughs despite very little being known about their internal representations. In this work, we propose to shed the light on LLMs inner mechanisms through the lens of geometry. In particular, we develop in closed form $(i)$ the intrinsic dimension in which the Multi-Head Attention embeddings are constrained to exist and $(ii)$ the partition and per-region affine mappings of the feedforward (MLP) network of LLMs' layers. Our theoretical findings further enable the design of novel principled solutions applicable to state-of-the-art LLMs. First, we show that, through our geometric understanding, we can bypass LLMs' RLHF protection by controlling the embedding's intrinsic dimension through informed prompt manipulation. Second, we derive interpretable geometrical features that can be extracted from any (pre-trained) LLM, providing a rich abstract representation of their inputs. We observe that these features are sufficient to help solve toxicity detection, and even allow the identification of various types of toxicity. Our results demonstrate how, even in large-scale regimes, exact theoretical results can answer practical questions in LLMs. Code: https://github.com/RandallBalestriero/SplineLLM
Authors: Vincent Taboga, Hanane Dagdougui
Abstract: The increasing electricity use and reliance on intermittent renewable energy sources challenge power grid management during peak demand, making Demand Response programs and energy conservation measures essential. This research combines distributed optimization using ADMM with deep learning models to plan indoor temperature setpoints effectively. A two-layer hierarchical structure is used, with a central building coordinator at the upper layer and local controllers at the thermal zone layer. The coordinator must limit the building's maximum power by translating the building's total power to local power targets for each zone. Local controllers can modify the temperature setpoints to meet the local power targets. While most algorithms are either centralized or require prior knowledge about the building's structure, our approach is distributed and fully data-driven. The proposed algorithm, called Distributed Planning Networks, is designed to be both adaptable and scalable to many types of buildings, tackling two of the main challenges in the development of such systems. The proposed approach is tested on an 18-zone building modeled in EnergyPlus. The algorithm successfully manages Demand Response peak events.
Authors: Wei "Wayne" Chen, Rachel Sun, Doksoo Lee, Carlos M. Portela, Wei Chen
Abstract: Metamaterials with functional responses, such as wave-based responses or deformation-induced property variation under external stimuli, can exhibit varying properties or functionalities under different conditions. Herein, we aim at rapid inverse design of these metamaterials to meet target qualitative functional behaviors. This inverse problem is challenging due to its intractability and the existence of non-unique solutions. Past works mainly focus on deep-learning-based methods that are data-demanding, require time-consuming training and hyperparameter tuning, and are non-interpretable. To overcome these limitations, we propose the Random-forest-based Interpretable Generative Inverse Design (RIGID), an iteration-free, single-shot inverse design method to achieve the fast generation of metamaterial designs with on-demand functional behaviors. Unlike most existing methods, by exploiting the interpretability of the random forest, we eliminate the need to train an inverse model mapping responses to designs. Based on the likelihood of target satisfaction derived from the trained forward model, one can sample design solutions using Markov chain Monte Carlo methods. The RIGID method therefore functions as a generative model that captures the conditional distribution of satisfying solutions given a design target. We demonstrate the effectiveness and efficiency of RIGID on both acoustic and optical metamaterial design problems where only small datasets (less than 250 training samples) are available. Synthetic design problems are created to further illustrate and validate the mechanism of likelihood estimation in RIGID. This work offers a new perspective on solving on-demand inverse design problems, showcasing the potential for incorporating interpretable machine learning into generative design and eliminating its large data requirement.
Authors: Jaebak Kim
Abstract: Experimental particle physics uses machine learning for many tasks, where one application is to classify signal and background events. This classification can be used to bin an analysis region to enhance the expected significance for a mass resonance search. In natural language processing, one of the leading neural network architectures is the transformer. In this work, an event classifier transformer is proposed to bin an analysis region, in which the network is trained with special techniques. The techniques developed here can enhance the significance and reduce the correlation between the network's output and the reconstructed mass. It is found that this trained network can perform better than boosted decision trees and feed-forward networks.
Authors: Hongye Jin, Xiaotian Han, Jingfeng Yang, Zhimeng Jiang, Zirui Liu, Chia-Yuan Chang, Huiyuan Chen, Xia Hu
Abstract: It is well known that LLMs cannot generalize well to long contexts whose lengths are larger than the training sequence length. This poses challenges when employing LLMs for processing long input sequences during inference. In this work, we argue that LLMs themselves have inherent capabilities to handle long contexts without fine-tuning. To achieve this goal, we propose SelfExtend to extend the context window of LLMs by constructing bi-level attention information: the grouped attention and the neighbor attention. The grouped attention captures the dependencies among tokens that are far apart, while neighbor attention captures dependencies among adjacent tokens within a specified range. The two-level attentions are computed based on the original model's self-attention mechanism during inference. With minor code modification, our SelfExtend can effortlessly extend existing LLMs' context window without any fine-tuning. We conduct comprehensive experiments on multiple benchmarks and the results show that our SelfExtend can effectively extend existing LLMs' context window length. The code can be found at \url{https://github.com/datamllab/LongLM}.
Authors: Jiquan Wang, Sha Zhao, Haiteng Jiang, Shijian Li, Tao Li, Gang Pan
Abstract: Automatic sleep staging is essential for sleep assessment and disorder diagnosis. Most existing methods depend on one specific dataset and are limited to be generalized to other unseen datasets, for which the training data and testing data are from the same dataset. In this paper, we introduce domain generalization into automatic sleep staging and propose the task of generalizable sleep staging which aims to improve the model generalization ability to unseen datasets. Inspired by existing domain generalization methods, we adopt the feature alignment idea and propose a framework called SleepDG to solve it. Considering both of local salient features and sequential features are important for sleep staging, we propose a Multi-level Feature Alignment combining epoch-level and sequence-level feature alignment to learn domain-invariant feature representations. Specifically, we design an Epoch-level Feature Alignment to align the feature distribution of each single sleep epoch among different domains, and a Sequence-level Feature Alignment to minimize the discrepancy of sequential features among different domains. SleepDG is validated on five public datasets, achieving the state-of-the-art performance.
Authors: Chuangtao Chen, Qinglin Zhao, MengChu Zhou, Zhimin He, Zhili Sun, Haozhen Situ
Abstract: Classical diffusion models have shown superior generative results. Exploring them in the quantum domain can advance the field of quantum generative learning. This work introduces Quantum Generative Diffusion Model (QGDM) as their simple and elegant quantum counterpart. Through a non-unitary forward process, any target quantum state can be transformed into a completely mixed state that has the highest entropy and maximum uncertainty about the system. A trainable backward process is used to recover the former from the latter. The design requirements for its backward process includes non-unitarity and small parameter count. We introduce partial trace operations to enforce non-unitary and reduce the number of trainable parameters by using a parameter-sharing strategy and incorporating temporal information as an input in the backward process. We present QGDM's resource-efficient version to reduce auxiliary qubits while preserving generative capabilities. QGDM exhibits faster convergence than Quantum Generative Adversarial Network (QGAN) because its adopted convex-based optimization can result in faster convergence. The results of comparing it with QGAN demonstrate its effectiveness in generating both pure and mixed quantum states. It can achieve 53.02% higher fidelity in mixed-state generation than QGAN. The results highlight its great potential to tackle challenging quantum generation tasks.
Authors: Weide Liu, Huijing Zhan, Hao Chen, Fengmao Lv
Abstract: Multimodal sentiment analysis aims to identify the emotions expressed by individuals through visual, language, and acoustic cues. However, most of the existing research efforts assume that all modalities are available during both training and testing, making their algorithms susceptible to the missing modality scenario. In this paper, we propose a novel knowledge-transfer network to translate between different modalities to reconstruct the missing audio modalities. Moreover, we develop a cross-modality attention mechanism to retain the maximal information of the reconstructed and observed modalities for sentiment prediction. Extensive experiments on three publicly available datasets demonstrate significant improvements over baselines and achieve comparable results to the previous methods with complete multi-modality supervision.
Authors: Tobias Golling, Lukas Heinrich, Michael Kagan, Samuel Klein, Matthew Leigh, Margarita Osadchy, John Andrew Raine
Abstract: We propose masked particle modeling (MPM) as a self-supervised method for learning generic, transferable, and reusable representations on unordered sets of inputs for use in high energy physics (HEP) scientific data. This work provides a novel scheme to perform masked modeling based pre-training to learn permutation invariant functions on sets. More generally, this work provides a step towards building large foundation models for HEP that can be generically pre-trained with self-supervised learning and later fine-tuned for a variety of down-stream tasks. In MPM, particles in a set are masked and the training objective is to recover their identity, as defined by a discretized token representation of a pre-trained vector quantized variational autoencoder. We study the efficacy of the method in samples of high energy jets at collider physics experiments, including studies on the impact of discretization, permutation invariance, and ordering. We also study the fine-tuning capability of the model, showing that it can be adapted to tasks such as supervised and weakly supervised jet classification, and that the model can transfer efficiently with small fine-tuning data sets to new classes and new data domains.
Authors: Wilka Carvalho, Momchil S. Tomov, William de Cothi, Caswell Barry, Samuel J. Gershman
Abstract: Adaptive behavior often requires predicting future events. The theory of reinforcement learning prescribes what kinds of predictive representations are useful and how to compute them. This paper integrates these theoretical ideas with work on cognition and neuroscience. We pay special attention to the successor representation (SR) and its generalizations, which have been widely applied both as engineering tools and models of brain function. This convergence suggests that particular kinds of predictive representations may function as versatile building blocks of intelligence.
Authors: Leonard Henckel, Theo W\"urtzen, Sebastian Weichwald
Abstract: Evaluating graphs learned by causal discovery algorithms is difficult: The number of edges that differ between two graphs does not reflect how the graphs differ with respect to the identifying formulas they suggest for causal effects. We introduce a framework for developing causal distances between graphs which includes the structural intervention distance for directed acyclic graphs as a special case. We use this framework to develop improved adjustment-based distances as well as extensions to completed partially directed acyclic graphs and causal orders. We develop new reachability algorithms to compute the distances efficiently and to prove their low polynomial time complexity. In our package gadjid (open source at https://github.com/CausalDisco/gadjid), we provide implementations of our distances; they are orders of magnitude faster with proven lower time complexity than the structural intervention distance and thereby provide a success metric for causal discovery that scales to graph sizes that were previously prohibitive.
Authors: Changyu Chen, Xiting Wang, Ting-En Lin, Ang Lv, Yuchuan Wu, Xin Gao, Ji-Rong Wen, Rui Yan, Yongbin Li
Abstract: In reasoning tasks, even a minor error can cascade into inaccurate results, leading to suboptimal performance of large language models in such domains. Earlier fine-tuning approaches sought to mitigate this by leveraging more precise supervisory signals from human labeling, larger models, or self-sampling, although at a high cost. Conversely, we develop a method that avoids external resources, relying instead on introducing perturbations to the input. Our training approach randomly masks certain tokens within the chain of thought, a technique we found to be particularly effective for reasoning tasks. When applied to fine-tuning with GSM8K on Llama-2-7B, this method achieved a 5\% improvement in GSM8K accuracy and a 10\% improvement in GSM-IC accuracy over standard supervised fine-tuning with a few codes modified. Furthermore, it is complementary to existing methods. When integrated with related explicit data augmentation methods, it leads to improvements across five datasets of various augmentation methods, as well as two different base models. We further investigate the mechanisms behind this improvement through case studies and quantitative analysis, suggesting that our approach may provide superior support for the model in capturing long-distance dependencies, especially those related to questions. This enhancement could deepen understanding of the premises in questions and prior steps. Our code is available at Github.
Authors: Jose Blanchet, Jiajin Li, Markus Pelger, Greg Zanotti
Abstract: In this paper, we propose a novel conceptual framework to detect outliers using optimal transport with a concave cost function. Conventional outlier detection approaches typically use a two-stage procedure: first, outliers are detected and removed, and then estimation is performed on the cleaned data. However, this approach does not inform outlier removal with the estimation task, leaving room for improvement. To address this limitation, we propose an automatic outlier rectification mechanism that integrates rectification and estimation within a joint optimization framework. We take the first step to utilize the optimal transport distance with a concave cost function to construct a rectification set in the space of probability distributions. Then, we select the best distribution within the rectification set to perform the estimation task. Notably, the concave cost function we introduced in this paper is the key to making our estimator effectively identify the outlier during the optimization process. We demonstrate the effectiveness of our approach over conventional approaches in simulations and empirical analyses for mean estimation, least absolute regression, and the fitting of option implied volatility surfaces.
Authors: Kashyap Chitta, Daniel Dauner, Andreas Geiger
Abstract: SLEDGE is the first generative simulator for vehicle motion planning trained on real-world driving logs. Its core component is a learned model that is able to generate agent bounding boxes and lane graphs. The model's outputs serve as an initial state for rule-based traffic simulation. The unique properties of the entities to be generated for SLEDGE, such as their connectivity and variable count per scene, render the naive application of most modern generative models to this task non-trivial. Therefore, together with a systematic study of existing lane graph representations, we introduce a novel raster-to-vector autoencoder. It encodes agents and the lane graph into distinct channels in a rasterized latent map. This facilitates both lane-conditioned agent generation and combined generation of lanes and agents with a Diffusion Transformer. Using generated entities in SLEDGE enables greater control over the simulation, e.g. upsampling turns or increasing traffic density. Further, SLEDGE can support 500m long routes, a capability not found in existing data-driven simulators like nuPlan. It presents new challenges for planning algorithms, evidenced by failure rates of over 40% for PDM, the winner of the 2023 nuPlan challenge, when tested on hard routes and dense traffic generated by our model. Compared to nuPlan, SLEDGE requires 500$\times$ less storage to set up (<4 GB), making it a more accessible option and helping with democratizing future research in this field.
Authors: Scott C. Lowe, Benjamin Misiuk, Isaac Xu, Shakhboz Abdulazizov, Amit R. Baroi, Alex C. Bastos, Merlin Best, Vicki Ferrini, Ariell Friedman, Deborah Hart, Ove Hoegh-Guldberg, Daniel Ierodiaconou, Julia Mackin-McLaughlin, Kathryn Markey, Pedro S. Menandro, Jacquomo Monk, Shreya Nemani, John O'Brien, Elizabeth Oh, Luba Y. Reshitnyk, Katleen Robert, Chris M. Roelfsema, Jessica A. Sameoto, Alexandre C. G. Schimel, Jordan A. Thomson, Brittany R. Wilson, Melisa C. Wong, Craig J. Brown, Thomas Trappenberg
Abstract: Advances in underwater imaging enable the collection of extensive seafloor image datasets that are necessary for monitoring important benthic ecosystems. The ability to collect seafloor imagery has outpaced our capacity to analyze it, hindering expedient mobilization of this crucial environmental information. Recent machine learning approaches provide opportunities to increase the efficiency with which seafloor image datasets are analyzed, yet large and consistent datasets necessary to support development of such approaches are scarce. Here we present BenthicNet: a global compilation of seafloor imagery designed to support the training and evaluation of large-scale image recognition models. An initial set of over 11.4 million images was collected and curated to represent a diversity of seafloor environments using a representative subset of 1.3 million images. These are accompanied by 2.6 million annotations translated to the CATAMI scheme, which span 190,000 of the images. A large deep learning model was trained on this compilation and preliminary results suggest it has utility for automating large and small-scale image analysis tasks. The compilation and model are made openly available for use by the scientific community at https://doi.org/10.20383/103.0614.
Authors: Jihwan Kwak, Sungmin Cha, Taesup Moon
Abstract: This paper addresses the unrealistic aspect of the commonly adopted Continuous Incremental Semantic Segmentation (CISS) scenario, termed overlapped. We point out that overlapped allows the same image to reappear in future tasks with different pixel labels, which is far from practical incremental learning scenarios. Moreover, we identified that this flawed scenario may lead to biased results for two commonly used techniques in CISS, pseudo-labeling and exemplar memory, resulting in unintended advantages or disadvantages for certain techniques. To mitigate this, a practical scenario called partitioned is proposed, in which the dataset is first divided into distinct subsets representing each class, and then the subsets are assigned to each corresponding task. This efficiently addresses the issue above while meeting the requirement of CISS scenario, such as capturing the background shifts. Furthermore, we identify and address the code implementation issues related to retrieving data from the exemplar memory, which was ignored in previous works. Lastly, we introduce a simple yet competitive memory-based baseline, MiB-AugM, that handles background shifts of current tasks in the exemplar memory. This baseline achieves state-of-the-art results across multiple tasks involving learning numerous new classes.
Authors: Carolina Fortuna, Vid Han\v{z}el, Bla\v{z} Bertalani\v{c}
Abstract: Domain specific digital twins, representing a digital replica of various segments of the smart grid, are foreseen as able to model, simulate, and control the respective segments. At the same time, knowledge-based digital twins, coupled with AI, may also empower humans to understand aspects of the system through natural language interaction in view of planning and policy making. This paper is the first to assess and report on the potential of Retrieval Augmented Generation (RAG) question answers related to household electrical energy measurement aspects leveraging a knowledge-based energy digital twin. Relying on the recently published electricity consumption knowledge graph that actually represents a knowledge-based digital twin, we study the capabilities of ChatGPT, Gemini and Llama in answering electricity related questions. Furthermore, we compare the answers with the ones generated through a RAG techniques that leverages an existing electricity knowledge-based digital twin. Our findings illustrate that the RAG approach not only reduces the incidence of incorrect information typically generated by LLMs but also significantly improves the quality of the output by grounding responses in verifiable data. This paper details our methodology, presents a comparative analysis of responses with and without RAG, and discusses the implications of our findings for future applications of AI in specialized sectors like energy data analysis.
Authors: Michelle Zhao, Reid Simmons, Henny Admoni, Andrea Bajcsy
Abstract: Assistive robotic arms often have more degrees-of-freedom than a human teleoperator can control with a low-dimensional input, like a joystick. To overcome this challenge, existing approaches use data-driven methods to learn a mapping from low-dimensional human inputs to high-dimensional robot actions. However, determining if such a black-box mapping can confidently infer a user's intended high-dimensional action from low-dimensional inputs remains an open problem. Our key idea is to adapt the assistive map at training time to additionally estimate high-dimensional action quantiles, and then calibrate these quantiles via rigorous uncertainty quantification methods. Specifically, we leverage adaptive conformal prediction which adjusts the intervals over time, reducing the uncertainty bounds when the mapping is performant and increasing the bounds when the mapping consistently mis-predicts. Furthermore, we propose an uncertainty-interval-based mechanism for detecting high-uncertainty user inputs and robot states. We evaluate the efficacy of our proposed approach in a 2D assistive navigation task and two 7DOF Kinova Jaco tasks involving assistive cup grasping and goal reaching. Our findings demonstrate that conformalized assistive teleoperation manages to detect (but not differentiate between) high uncertainty induced by diverse preferences and induced by low-precision trajectories in the mapping's training dataset. On the whole, we see this work as a key step towards enabling robots to quantify their own uncertainty and proactively seek intervention when needed.
Authors: Peiyan Zhang, Yuchen Yan, Xi Zhang, Liying Kang, Chaozhuo Li, Feiran Huang, Senzhang Wang, Sunghun Kim
Abstract: In the realm of personalized recommender systems, the challenge of adapting to evolving user preferences and the continuous influx of new users and items is paramount. Conventional models, typically reliant on a static training-test approach, struggle to keep pace with these dynamic demands. Streaming recommendation, particularly through continual graph learning, has emerged as a novel solution. However, existing methods in this area either rely on historical data replay, which is increasingly impractical due to stringent data privacy regulations; or are inability to effectively address the over-stability issue; or depend on model-isolation and expansion strategies. To tackle these difficulties, we present GPT4Rec, a Graph Prompt Tuning method for streaming Recommendation. Given the evolving user-item interaction graph, GPT4Rec first disentangles the graph patterns into multiple views. After isolating specific interaction patterns and relationships in different views, GPT4Rec utilizes lightweight graph prompts to efficiently guide the model across varying interaction patterns within the user-item graph. Firstly, node-level prompts are employed to instruct the model to adapt to changes in the attributes or properties of individual nodes within the graph. Secondly, structure-level prompts guide the model in adapting to broader patterns of connectivity and relationships within the graph. Finally, view-level prompts are innovatively designed to facilitate the aggregation of information from multiple disentangled views. These prompt designs allow GPT4Rec to synthesize a comprehensive understanding of the graph, ensuring that all vital aspects of the user-item interactions are considered and effectively integrated. Experiments on four diverse real-world datasets demonstrate the effectiveness and efficiency of our proposal.
Authors: Romina Yalovetzky, Niraj Kumar, Changhao Li, Marco Pistoia
Abstract: Random Forest (RF) is a popular tree-ensemble method for supervised learning, prized for its ease of use and flexibility. Online RF models require to account for new training data to maintain model accuracy. This is particularly important in applications where data is periodically and sequentially generated over time in data streams, such as auto-driving systems, and credit card payments. In this setting, performing periodic model retraining with the old and new data accumulated is beneficial as it fully captures possible drifts in the data distribution over time. However, this is unpractical with state-of-the-art classical algorithms for RF as they scale linearly with the accumulated number of samples. We propose QC-Forest, a classical-quantum algorithm designed to time-efficiently retrain RF models in the streaming setting for multi-class classification and regression, achieving a runtime poly-logarithmic in the total number of accumulated samples. QC-Forest leverages Des-q, a quantum algorithm for single tree construction and retraining proposed by Kumar et al. by expanding to multi-class classification, as the original proposal was limited to binary classes, and introducing an exact classical method to replace an underlying quantum subroutine incurring a finite error, while maintaining the same poly-logarithmic dependence. Finally, we showcase that QC-Forest achieves competitive accuracy in comparison to state-of-the-art RF methods on widely used benchmark datasets with up to 80,000 samples, while significantly speeding up the model retrain.
Authors: Boyi Wei, Weijia Shi, Yangsibo Huang, Noah A. Smith, Chiyuan Zhang, Luke Zettlemoyer, Kai Li, Peter Henderson
Abstract: Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content similar to their training data, posing potential concerns. Therefore, model creators are motivated to develop mitigation methods that prevent generating protected content. We term this procedure as copyright takedowns for LMs, noting the conceptual similarity to (but legal distinction from) the DMCA takedown This paper introduces the first evaluation of the feasibility and side effects of copyright takedowns for LMs. We propose CoTaEval, an evaluation framework to assess the effectiveness of copyright takedown methods, the impact on the model's ability to retain uncopyrightable factual knowledge from the training data whose recitation is embargoed, and how well the model maintains its general utility and efficiency. We examine several strategies, including adding system prompts, decoding-time filtering interventions, and unlearning approaches. Our findings indicate that no tested method excels across all metrics, showing significant room for research in this unique problem setting and indicating potential unresolved challenges for live policy proposals.
Authors: Quoc Hoan Tran, Yasuhiro Endo, Hirotaka Oshima
Abstract: Quantum machine learning (QML) requires significant quantum resources to achieve quantum advantage. Research should prioritize both the efficient design of quantum architectures and the development of learning strategies to optimize resource usage. We propose a framework called quantum curriculum learning (Q-CurL) for quantum data, where the curriculum introduces simpler tasks or data to the learning model before progressing to more challenging ones. We define the curriculum criteria based on the data density ratio between tasks to determine the curriculum order. We also implement a dynamic learning schedule to emphasize the significance of quantum data in optimizing the loss function. Empirical evidence shows that Q-CurL significantly enhances the training convergence and the generalization for unitary learning tasks and improves the robustness of quantum phase recognition tasks. Our framework provides a general learning strategy, bringing QML closer to realizing practical advantages.
Authors: Yingfang Yuan, Kefan Chen, Mehdi Rizvi, Lynne Baillie, Wei Pang
Abstract: The growing interest in fair AI development is evident. The ''Leave No One Behind'' initiative urges us to address multiple and intersecting forms of inequality in accessing services, resources, and opportunities, emphasising the significance of fairness in AI. This is particularly relevant as an increasing number of AI tools are applied to decision-making processes, such as resource allocation and service scheme development, across various sectors such as health, energy, and housing. Therefore, exploring joint inequalities in these sectors is significant and valuable for thoroughly understanding overall inequality and unfairness. This research introduces an innovative approach to quantify cross-sectoral intersecting discrepancies among user-defined groups using latent class analysis. These discrepancies can be used to approximate inequality and provide valuable insights to fairness issues. We validate our approach using both proprietary and public datasets, including EVENS and Census 2021 (England & Wales) datasets, to examine cross-sectoral intersecting discrepancies among different ethnic groups. We also verify the reliability of the quantified discrepancy by conducting a correlation analysis with a government public metric. Our findings reveal significant discrepancies between minority ethnic groups, highlighting the need for targeted interventions in real-world AI applications. Additionally, we demonstrate how the proposed approach can be used to provide insights into the fairness of machine learning.
Authors: Federico Girella, Ziyue Liu, Franco Fummi, Francesco Setti, Marco Cristani, Luigi Capogrosso
Abstract: Defect detection is the task of identifying defects in production samples. Usually, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the latter are consistently fewer than normal samples. State-of-the-art data augmentation procedures add synthetic defect data by superimposing artifacts to normal samples to mitigate problems related to unbalanced training data. These techniques often produce out-of-distribution images, resulting in systems that learn what is not a normal sample but cannot accurately identify what a defect looks like. In this work, we introduce DIAG, a training-free Diffusion-based In-distribution Anomaly Generation pipeline for data augmentation. Unlike conventional image generation techniques, we implement a human-in-the-loop pipeline, where domain experts provide multimodal guidance to the model through text descriptions and region localization of the possible anomalies. This strategic shift enhances the interpretability of results and fosters a more robust human feedback loop, facilitating iterative improvements of the generated outputs. Remarkably, our approach operates in a zero-shot manner, avoiding time-consuming fine-tuning procedures while achieving superior performance. We demonstrate the efficacy and versatility of DIAG with respect to state-of-the-art data augmentation approaches on the challenging KSDD2 dataset, with an improvement in AP of approximately 18% when positive samples are available and 28% when they are missing. The source code is available at https://github.com/intelligolabs/DIAG.
Authors: Prarthana Bhattacharyya, Joshua Mitton, Ryan Page, Owen Morgan, Ben Menzies, Gabriel Homewood, Kemi Jacobs, Paolo Baesso, Dave 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: Henry Shaowu Yuchi, Shixiang Zhu, Li Dong, Yigit M. Arisoy, Matthew C. Spencer
Abstract: Modeling and analysis for event series generated by heterogeneous users of various behavioral patterns are closely involved in our daily lives, including credit card fraud detection, online platform user recommendation, and social network analysis. The most commonly adopted approach to this task is to classify users into behavior-based categories and analyze each of them separately. However, this approach requires extensive data to fully understand user behavior, presenting challenges in modeling newcomers without historical knowledge. In this paper, we propose a novel discrete event prediction framework for new users through the lens of causal inference. Our method offers an unbiased prediction for new users without needing to know their categories. We treat the user event history as the ''treatment'' for future events and the user category as the key confounder. Thus, the prediction problem can be framed as counterfactual outcome estimation, with the new user model trained on an adjusted dataset where each event is re-weighted by its inverse propensity score. We demonstrate the superior performance of the proposed framework with a numerical simulation study and two real-world applications, including Netflix rating prediction and seller contact prediction for customer support at Amazon.
Authors: Sofia Strukova, Sergei Gleyzer, Patrick Peplowski, Jason P. Terry
Abstract: This study introduces a data-driven approach using machine learning (ML) techniques to explore and predict albedo anomalies on the Moon's surface. The research leverages diverse planetary datasets, including high-spatial-resolution albedo maps and element maps (LPFe, LPK, LPTh, LPTi) derived from laser and gamma-ray measurements. The primary objective is to identify relationships between chemical elements and albedo, thereby expanding our understanding of planetary surfaces and offering predictive capabilities for areas with incomplete datasets. To bridge the gap in resolution between the albedo and element maps, we employ Gaussian blurring techniques, including an innovative adaptive Gaussian blur. Our methodology culminates in the deployment of an Extreme Gradient Boosting Regression Model, optimized to predict full albedo based on elemental composition. Furthermore, we present an interactive analytical tool to visualize prediction errors, delineating their spatial and chemical characteristics. The findings not only pave the way for a more comprehensive understanding of the Moon's surface but also provide a framework for similar studies on other celestial bodies.
Authors: Mujtaba Hussain Mirza, Maria Rosaria Briglia, Senad Beadini, Iacopo Masi
Abstract: By reinterpreting a robust discriminative classifier as Energy-based Model (EBM), we offer a new take on the dynamics of adversarial training (AT). Our analysis of the energy landscape during AT reveals that untargeted attacks generate adversarial images much more in-distribution (lower energy) than the original data from the point of view of the model. Conversely, we observe the opposite for targeted attacks. On the ground of our thorough analysis, we present new theoretical and practical results that show how interpreting AT energy dynamics unlocks a better understanding: (1) AT dynamic is governed by three phases and robust overfitting occurs in the third phase with a drastic divergence between natural and adversarial energies (2) by rewriting the loss of TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization (TRADES) in terms of energies, we show that TRADES implicitly alleviates overfitting by means of aligning the natural energy with the adversarial one (3) we empirically show that all recent state-of-the-art robust classifiers are smoothing the energy landscape and we reconcile a variety of studies about understanding AT and weighting the loss function under the umbrella of EBMs. Motivated by rigorous evidence, we propose Weighted Energy Adversarial Training (WEAT), a novel sample weighting scheme that yields robust accuracy matching the state-of-the-art on multiple benchmarks such as CIFAR-10 and SVHN and going beyond in CIFAR-100 and Tiny-ImageNet. We further show that robust classifiers vary in the intensity and quality of their generative capabilities, and offer a simple method to push this capability, reaching a remarkable Inception Score (IS) and FID using a robust classifier without training for generative modeling. The code to reproduce our results is available at http://github.com/OmnAI-Lab/Robust-Classifiers-under-the-lens-of-EBM/ .
URLs: http://github.com/OmnAI-Lab/Robust-Classifiers-under-the-lens-of-EBM/
Authors: Nikita Chernyadev, Nicholas Backshall, Xiao Ma, Yunfan Lu, Younggyo Seo, Stephen James
Abstract: We introduce BiGym, a new benchmark and learning environment for mobile bi-manual demo-driven robotic manipulation. BiGym features 40 diverse tasks set in home environments, ranging from simple target reaching to complex kitchen cleaning. To capture the real-world performance accurately, we provide human-collected demonstrations for each task, reflecting the diverse modalities found in real-world robot trajectories. BiGym supports a variety of observations, including proprioceptive data and visual inputs such as RGB, and depth from 3 camera views. To validate the usability of BiGym, we thoroughly benchmark the state-of-the-art imitation learning algorithms and demo-driven reinforcement learning algorithms within the environment and discuss the future opportunities.
Authors: Oguzhan Topsakal, Colby Jacob Edell, Jackson Bailey Harper
Abstract: We introduce a novel and extensible benchmark for large language models (LLMs) through grid-based games such as Tic-Tac-Toe, Connect Four, and Gomoku. The open-source game simulation code, available on GitHub, allows LLMs to compete and generates detailed data files in JSON, CSV, TXT, and PNG formats for leaderboard rankings and further analysis. We present the results of games among leading LLMs, including Claude 3.5 Sonnet and Claude 3 Sonnet by Anthropic, Gemini 1.5 Pro and Gemini 1.5 Flash by Google, GPT-4 Turbo and GPT-4o by OpenAI, and Llama3-70B by Meta. We also encourage submissions of results from other LLMs. In total, we simulated 2,310 matches (5 sessions for each pair among 7 LLMs and a random player) across three types of games, using three distinct prompt types: list, illustration, and image. The results revealed significant variations in LLM performance across different games and prompt types, with analysis covering win and disqualification rates, missed opportunity analysis, and invalid move analysis. The details of the leaderboard and result matrix data are available as open-access data on GitHub. This study enhances our understanding of LLMs' capabilities in playing games they were not specifically trained for, helping to assess their rule comprehension and strategic thinking. On the path to Artificial General Intelligence (AGI), this study lays the groundwork for future exploration into their utility in complex decision-making scenarios, illuminating their strategic thinking abilities and offering directions for further inquiry into the limits of LLMs within game-based frameworks.
Authors: Jongsuk Kim, Jiwon Shin, Junmo Kim
Abstract: In recent years, advancements in representation learning and language models have propelled Automated Captioning (AC) to new heights, enabling the generation of human-level descriptions. Leveraging these advancements, we propose AVCap, an Audio-Visual Captioning framework, a simple yet powerful baseline approach applicable to audio-visual captioning. AVCap utilizes audio-visual features as text tokens, which has many advantages not only in performance but also in the extensibility and scalability of the model. AVCap is designed around three pivotal dimensions: the exploration of optimal audio-visual encoder architectures, the adaptation of pre-trained models according to the characteristics of generated text, and the investigation into the efficacy of modality fusion in captioning. Our method outperforms existing audio-visual captioning methods across all metrics and the code is available on https://github.com/JongSuk1/AVCap