Authors: Keiichiro Yamamura, Issa Oe, Hiroki Ishikura, Katsuki Fujisawa
Abstract: Deep neural networks are vulnerable to adversarial examples, and adversarial attacks that generate adversarial examples have been studied in this context. Existing studies imply that increasing the diversity of model outputs contributes to improving the attack performance. This study focuses on the Auto Conjugate Gradient (ACG) attack, which is inspired by the conjugate gradient method and has a high diversification performance. We hypothesized that increasing the distance between two consecutive search points would enhance the output diversity. To test our hypothesis, we propose Rescaling-ACG (ReACG), which automatically modifies the two components that significantly affect the distance between two consecutive search points, including the search direction and step size. ReACG showed higher attack performance than that of ACG, and is particularly effective for ImageNet models with several classification classes. Experimental results show that the distance between two consecutive search points enhances the output diversity and may help develop new potent attacks. The code is available at \url{https://github.com/yamamura-k/ReACG}
Authors: Mengting Li, Chuang Zhu
Abstract: Noisy labels, which are common in real-world datasets, can significantly impair the training of deep learning models. However, recent adversarial noise-combating methods overlook the long-tailed distribution of real data, which can significantly harm the effect of denoising strategies. Meanwhile, the mismanagement of noisy labels further compromises the model's ability to handle long-tailed data. To tackle this issue, we propose a novel approach to manage data characterized by both long-tailed distributions and noisy labels. First, we introduce a loss-distance cross-selection module, which integrates class predictions and feature distributions to filter clean samples, effectively addressing uncertainties introduced by noisy labels and long-tailed distributions. Subsequently, we employ optimal transport strategies to generate pseudo-labels for the noise set in a semi-supervised training manner, enhancing pseudo-label quality while mitigating the effects of sample scarcity caused by the long-tailed distribution. We conduct experiments on both synthetic and real-world datasets, and the comprehensive experimental results demonstrate that our method surpasses current state-of-the-art methods. Our code will be available in the future.
Authors: Joseph Cameron, Jiaee Cheong, Micol Spitale, Hatice Gunes
Abstract: Social agents and robots are increasingly being used in wellbeing settings. However, a key challenge is that these agents and robots typically rely on machine learning (ML) algorithms to detect and analyse an individual's mental wellbeing. The problem of bias and fairness in ML algorithms is becoming an increasingly greater source of concern. In concurrence, existing literature has also indicated that mental health conditions can manifest differently across genders and cultures. We hypothesise that the representation of features (acoustic, textual, and visual) and their inter-modal relations would vary among subjects from different cultures and genders, thus impacting the performance and fairness of various ML models. We present the very first evaluation of multimodal gender fairness in depression manifestation by undertaking a study on two different datasets from the USA and China. We undertake thorough statistical and ML experimentation and repeat the experiments for several different algorithms to ensure that the results are not algorithm-dependent. Our findings indicate that though there are differences between both datasets, it is not conclusive whether this is due to the difference in depression manifestation as hypothesised or other external factors such as differences in data collection methodology. Our findings further motivate a call for a more consistent and culturally aware data collection process in order to address the problem of ML bias in depression detection and to promote the development of fairer agents and robots for wellbeing.
Authors: Aida Afshar, Aldo Pacchiano
Abstract: The performance of reinforcement learning (RL) algorithms is sensitive to the choice of hyperparameters, with the learning rate being particularly influential. RL algorithms fail to reach convergence or demand an extensive number of samples when the learning rate is not optimally set. In this work, we show that model selection can help to improve the failure modes of RL that are due to suboptimal choices of learning rate. We present a model selection framework for Learning Rate-Free Reinforcement Learning that employs model selection methods to select the optimal learning rate on the fly. This approach of adaptive learning rate tuning neither depends on the underlying RL algorithm nor the optimizer and solely uses the reward feedback to select the learning rate; hence, the framework can input any RL algorithm and produce a learning rate-free version of it. We conduct experiments for policy optimization methods and evaluate various model selection strategies within our framework. Our results indicate that data-driven model selection algorithms are better alternatives to standard bandit algorithms when the optimal choice of hyperparameter is time-dependent and non-stationary.
Authors: Erfaneh Mahmoudzadeh, Parmis Naddaf, Kiarash Zahirnia, Oliver Schulte
Abstract: Graph Neural Networks (GNNs) are important across different domains, such as social network analysis and recommendation systems, due to their ability to model complex relational data. This paper introduces subgraph queries as a new task for deep graph learning. Unlike traditional graph prediction tasks that focus on individual components like link prediction or node classification, subgraph queries jointly predict the components of a target subgraph based on evidence that is represented by an observed subgraph. For instance, a subgraph query can predict a set of target links and/or node labels. To answer subgraph queries, we utilize a probabilistic deep Graph Generative Model. Specifically, we inductively train a Variational Graph Auto-Encoder (VGAE) model, augmented to represent a joint distribution over links, node features and labels. Bayesian optimization is used to tune a weighting for the relative importance of links, node features and labels in a specific domain. We describe a deterministic and a sampling-based inference method for estimating subgraph probabilities from the VGAE generative graph distribution, without retraining, in zero-shot fashion. For evaluation, we apply the inference methods on a range of subgraph queries on six benchmark datasets. We find that inference from a model achieves superior predictive performance, surpassing independent prediction baselines with improvements in AUC scores ranging from 0.06 to 0.2 points, depending on the dataset.
Authors: Shihao Tu, Yupeng Zhang, Jing Zhang, Yang Yang
Abstract: The emergence of abundant electricity time series (ETS) data provides ample opportunities for various applications in the power systems, including demand-side management, grid stability, and consumer behavior analysis. Deep learning models have advanced ETS modeling by effectively capturing sequence dependence. Nevertheless, learning a generic representation of ETS data for various applications remains challenging due to the inherently complex hierarchical structure of ETS data. Moreover, ETS data exhibits intricate temporal dependencies and is suscepti ble to the influence of exogenous variables. Furthermore, different instances exhibit diverse electricity consumption behavior. In this paper, we propose a foundation model PowerPM to model ETS data, providing a large-scale, off-the-shelf model for power systems. PowerPM consists of a temporal encoder and a hierarchical encoder. The temporal encoder captures both temporal dependencies in ETS data, considering exogenous variables. The hierarchical encoder models the correlation between hierarchy. Furthermore, PowerPM leverages a novel self-supervised pretraining framework consisting of masked ETS modeling and dual-view contrastive learning, which enable PowerPM to capture temporal dependency within ETS windows and aware the discrepancy across ETS windows, providing two different perspectives to learn generic representation. Our experiments involve five real world scenario datasets, comprising private and public data. Through pre-training on massive ETS data, PowerPM achieves SOTA performance on diverse downstream tasks within the private dataset. Impressively, when transferred to the public datasets, PowerPM maintains its superiority, showcasing its remarkable generalization ability across various tasks and domains. Moreover, ablation studies, few-shot experiments provide additional evidence of the effectiveness of our model.
Authors: Vasudev Shyam, Jonathan Pilault, Emily Shepperd, Quentin Anthony, Beren Millidge
Abstract: Self-attention is the core mathematical operation of modern transformer architectures and is also a significant computational bottleneck due to its quadratic complexity in the sequence length. In this work, we derive the scalar energy function whose gradient computes the self-attention block, thus elucidating the theoretical underpinnings of self-attention, providing a Bayesian interpretation of the operation and linking it closely with energy-based models such as Hopfield Networks. Moreover, due to this formulation, we discover that we can use efficient and optimized automatic-differentiation techniques to derive a highly efficient Tree Attention algorithm to compute the gradient of the energy and hence self-attention. Our formulation reveals that the reduction across the sequence axis can be efficiently computed in parallel through a tree reduction. Our algorithm, for parallelizing attention computation across multiple GPUs, enables cross-device decoding to be performed asymptotically faster (up to 8x faster) than alternative approaches such as Ring Attention, while also requiring significantly less communication volume and incurring 2x less peak memory. Our code is publicly available here: \url{https://github.com/Zyphra/tree_attention}
Authors: Zeyu Zhang, Haiying Shen
Abstract: In large-language models, memory constraints in the key-value cache (KVC) pose a challenge during inference, especially with long prompts. In this work, we observed that compressing KV values is more effective than compressing the model regarding accuracy and job completion time (JCT). However, quantizing KV values and dropping less-important tokens incur significant runtime computational time overhead, delaying JCT. These methods also cannot reduce computation time or high network communication time overhead in sequence-parallelism (SP) frameworks for long prompts. To tackle these issues, based on our insightful observations from experimental analysis, we propose ZeroC, a Zero-delay QKV Compression system that eliminates time overhead and even reduces computation and communication time of the model operations. ZeroC innovatively embeds compression and decompression operations within model operations and adaptively determines compression ratios at a hybrid layer-token level. Further, it enables a communication-efficient SP inference framework. Trace-driven experiments demonstrate that ZeroC achieves up to 80% lower average JCT, 35% lower average perplexity, and 2.8x higher throughput with the same latency compared to state-of-the-art compression methods. ZeroC also reduces the average JCT of current LLM serving systems by up to 91% with the constraint of 0.1 perplexity increase. We open-sourced the code.
Authors: Inas Bachiri, Hadjer Benmeziane, Smail Niar, Riyadh Baghdadi, Hamza Ouarnoughi, Abdelkrime Aries
Abstract: Deep Learning models have experienced exponential growth in complexity and resource demands in recent years. Accelerating these models for efficient execution on resource-constrained devices has become more crucial than ever. Two notable techniques employed to achieve this goal are Hardware-aware Neural Architecture Search (HW-NAS) and Automatic Code Optimization (ACO). HW-NAS automatically designs accurate yet hardware-friendly neural networks, while ACO involves searching for the best compiler optimizations to apply on neural networks for efficient mapping and inference on the target hardware. This survey explores recent works that combine these two techniques within a single framework. We present the fundamental principles of both domains and demonstrate their sub-optimality when performed independently. We then investigate their integration into a joint optimization process that we call Hardware Aware-Neural Architecture and Compiler Optimizations co-Search (NACOS).
Authors: Spyros Angelopoulos, Christoph D\"urr, Alex Elenter, Yanni Lefki
Abstract: The study of online algorithms with machine-learned predictions has gained considerable prominence in recent years. One of the common objectives in the design and analysis of such algorithms is to attain (Pareto) optimal tradeoffs between the consistency of the algorithm, i.e., its performance assuming perfect predictions, and its robustness, i.e., the performance of the algorithm under adversarial predictions. In this work, we demonstrate that this optimization criterion can be extremely brittle, in that the performance of Pareto-optimal algorithms may degrade dramatically even in the presence of imperceptive prediction error. To remedy this drawback, we propose a new framework in which the smoothness in the performance of the algorithm is enforced by means of a user-specified profile. This allows us to regulate the performance of the algorithm as a function of the prediction error, while simultaneously maintaining the analytical notion of consistency/robustness tradeoffs, adapted to the profile setting. We apply this new approach to a well-studied online problem, namely the one-way trading problem. For this problem, we further address another limitation of the state-of-the-art Pareto-optimal algorithms, namely the fact that they are tailored to worst-case, and extremely pessimistic inputs. We propose a new Pareto-optimal algorithm that leverages any deviation from the worst-case input to its benefit, and introduce a new metric that allows us to compare any two Pareto-optimal algorithms via a dominance relation.
Authors: Luca Reichmann, David H\"agele, Daniel Weiskopf
Abstract: Dimensionality reduction (DR) is a well-established approach for the visualization of high-dimensional data sets. While DR methods are often applied to typical DR benchmark data sets in the literature, they might suffer from high runtime complexity and memory requirements, making them unsuitable for large data visualization especially in environments outside of high-performance computing. To perform DR on large data sets, we propose the use of out-of-sample extensions. Such extensions allow inserting new data into existing projections, which we leverage to iteratively project data into a reference projection that consists only of a small manageable subset. This process makes it possible to perform DR out-of-core on large data, which would otherwise not be possible due to memory and runtime limitations. For metric multidimensional scaling (MDS), we contribute an implementation with out-of-sample projection capability since typical software libraries do not support it. We provide an evaluation of the projection quality of five common DR algorithms (MDS, PCA, t-SNE, UMAP, and autoencoders) using quality metrics from the literature and analyze the trade-off between the size of the reference set and projection quality. The runtime behavior of the algorithms is also quantified with respect to reference set size, out-of-sample batch size, and dimensionality of the data sets. Furthermore, we compare the out-of-sample approach to other recently introduced DR methods, such as PaCMAP and TriMAP, which claim to handle larger data sets than traditional approaches. To showcase the usefulness of DR on this large scale, we contribute a use case where we analyze ensembles of streamlines amounting to one billion projected instances.
Authors: Tong Liu, Hadi Meidani
Abstract: Traffic assignment and traffic flow prediction provide critical insights for urban planning, traffic management, and the development of intelligent transportation systems. An efficient model for calculating traffic flows over the entire transportation network could provide a more detailed and realistic understanding of traffic dynamics. However, existing traffic prediction approaches, such as those utilizing graph neural networks, are typically limited to locations where sensors are deployed and cannot predict traffic flows beyond sensor locations. To alleviate this limitation, inspired by fundamental relationship that exists between link flows and the origin-destination (OD) travel demands, we proposed the Heterogeneous Spatio-Temporal Graph Sequence Network (HSTGSN). HSTGSN exploits dependency between origin and destination nodes, even when it is long-range, and learns implicit vehicle route choices under different origin-destination demands. This model is based on a heterogeneous graph which consists of road links, OD links (virtual links connecting origins and destinations) and a spatio-temporal graph encoder-decoder that captures the spatio-temporal relationship between OD demands and flow distribution. We will show how the graph encoder-decoder is able to recover the incomplete information in the OD demand, by using node embedding from the graph decoder to predict the temporal changes in flow distribution. Using extensive experimental studies on real-world networks with complete/incomplete OD demands, we demonstrate that our method can not only capture the implicit spatio-temporal relationship between link traffic flows and OD demands but also achieve accurate prediction performance and generalization capability.
Authors: Judy Hanwen Shen, Inioluwa Deborah Raji, Irene Y. Chen
Abstract: In many machine learning for healthcare tasks, standard datasets are constructed by amassing data across many, often fundamentally dissimilar, sources. But when does adding more data help, and when does it hinder progress on desired model outcomes in real-world settings? We identify this situation as the \textit{Data Addition Dilemma}, demonstrating that adding training data in this multi-source scaling context can at times result in reduced overall accuracy, uncertain fairness outcomes, and reduced worst-subgroup performance. We find that this possibly arises from an empirically observed trade-off between model performance improvements due to data scaling and model deterioration from distribution shift. We thus establish baseline strategies for navigating this dilemma, introducing distribution shift heuristics to guide decision-making on which data sources to add in data scaling, in order to yield the expected model performance improvements. We conclude with a discussion of the required considerations for data collection and suggestions for studying data composition and scale in the age of increasingly larger models.
Authors: Frank Nielsen, Alexander Soen
Abstract: A Bregman manifold is a synonym for a dually flat space in information geometry which admits as a canonical divergence a Bregman divergence. Bregman manifolds are induced by smooth strictly convex functions like the cumulant or partition functions of regular exponential families, the negative entropy of mixture families, or the characteristic functions of regular cones just to list a few such convex Bregman generators. We describe the design of pyBregMan, a library which implements generic operations on Bregman manifolds and instantiate several common Bregman manifolds used in information sciences. At the core of the library is the notion of Legendre-Fenchel duality inducing a canonical pair of dual potential functions and dual Bregman divergences. The library also implements the Fisher-Rao manifolds of categorical/multinomial distributions and multivariate normal distributions. To demonstrate the use of the pyBregMan kernel manipulating those Bregman and Fisher-Rao manifolds, the library also provides several core algorithms for various applications in statistics, machine learning, information fusion, and so on.
Authors: Heewoong Choi, Sangwon Jung, Hongjoon Ahn, Taesup Moon
Abstract: In Reinforcement Learning (RL), designing precise reward functions remains to be a challenge, particularly when aligning with human intent. Preference-based RL (PbRL) was introduced to address this problem by learning reward models from human feedback. However, existing PbRL methods have limitations as they often overlook the second-order preference that indicates the relative strength of preference. In this paper, we propose Listwise Reward Estimation (LiRE), a novel approach for offline PbRL that leverages second-order preference information by constructing a Ranked List of Trajectories (RLT), which can be efficiently built by using the same ternary feedback type as traditional methods. To validate the effectiveness of LiRE, we propose a new offline PbRL dataset that objectively reflects the effect of the estimated rewards. Our extensive experiments on the dataset demonstrate the superiority of LiRE, i.e., outperforming state-of-the-art baselines even with modest feedback budgets and enjoying robustness with respect to the number of feedbacks and feedback noise. Our code is available at https://github.com/chwoong/LiRE
Authors: Zepu Wang, Xiaobo Ma, Huajie Yang, Weimin Lvu, Peng Sun, Sharath Chandra Guntuku
Abstract: Crime forecasting is a critical component of urban analysis and essential for stabilizing society today. Unlike other time series forecasting problems, crime incidents are sparse, particularly in small regions and within specific time periods. Traditional spatial-temporal deep learning models often struggle with this sparsity, as they typically cannot effectively handle the non-Gaussian nature of crime data, which is characterized by numerous zeros and over-dispersed patterns. To address these challenges, we introduce a novel approach termed Spatial Temporal Multivariate Zero-Inflated Negative Binomial Graph Neural Networks (STMGNN-ZINB). This framework leverages diffusion and convolution networks to analyze spatial, temporal, and multivariate correlations, enabling the parameterization of probabilistic distributions of crime incidents. By incorporating a Zero-Inflated Negative Binomial model, STMGNN-ZINB effectively manages the sparse nature of crime data, enhancing prediction accuracy and the precision of confidence intervals. Our evaluation on real-world datasets confirms that STMGNN-ZINB outperforms existing models, providing a more reliable tool for predicting and understanding crime dynamics.
Authors: Tomokaze Shiratori, Yuichi Takano
Abstract: Sparse estimation for Gaussian graphical models is a crucial technique for making the relationships among numerous observed variables more interpretable and quantifiable. Various methods have been proposed, including graphical lasso, which utilizes the $\ell_1$ norm as a regularization term, as well as methods employing non-convex regularization terms. However, most of these methods approximate the $\ell_0$ norm with convex functions. To estimate more accurate solutions, it is desirable to treat the $\ell_0$ norm directly as a regularization term. In this study, we formulate the sparse estimation problem for Gaussian graphical models using the $\ell_0$ norm and propose a method to solve this problem using the Difference of Convex functions Algorithm (DCA). Specifically, we convert the $\ell_0$ norm constraint into an equivalent largest-$K$ norm constraint, reformulate the constrained problem into a penalized form, and solve it using the DC algorithm (DCA). Furthermore, we designed an algorithm that efficiently computes using graphical lasso. Experimental results with synthetic data show that our method yields results that are equivalent to or better than existing methods. Comparisons of model learning through cross-validation confirm that our method is particularly advantageous in selecting true edges.
Authors: Oliver Broadrick, William Cao, Benjie Wang, Martin Trapp, Guy Van den Broeck
Abstract: A probabilistic circuit (PC) succinctly expresses a function that represents a multivariate probability distribution and, given sufficient structural properties of the circuit, supports efficient probabilistic inference. Typically a PC computes the probability mass (or density) function (PMF or PDF) of the distribution. We consider PCs instead computing the cumulative distribution function (CDF). We show that for distributions over binary random variables these representations (PMF and CDF) are essentially equivalent, in the sense that one can be transformed to the other in polynomial time. We then show how a similar equivalence holds for distributions over finite discrete variables using a modification of the standard encoding with binary variables that aligns with the CDF semantics. Finally we show that for continuous variables, smooth, decomposable PCs computing PDFs and CDFs can be efficiently transformed to each other by modifying only the leaves of the circuit.
Authors: Wei Zhang, Peng Tang
Abstract: Accurate traffic Flow Prediction can assist in traffic management, route planning, and congestion mitigation, which holds significant importance in enhancing the efficiency and reliability of intelligent transportation systems (ITS). However, existing traffic flow prediction models suffer from limitations in capturing the complex spatial-temporal dependencies within traffic networks. In order to address this issue, this study proposes a multi-segment fusion tensor graph convolutional network (MS-FTGCN) for traffic flow prediction with the following three-fold ideas: a) building a unified spatial-temporal graph convolutional framework based on Tensor M-product, which capture the spatial-temporal patterns simultaneously; b) incorporating hourly, daily, and weekly components to model multi temporal properties of traffic flows, respectively; c) fusing the outputs of the three components by attention mechanism to obtain the final traffic flow prediction results. The results of experiments conducted on two traffic flow datasets demonstrate that the proposed MS-FTGCN outperforms the state-of-the-art models.
Authors: Feiyi Chen, Yingying Zhang, Lunting Fan, Yuxuan Liang, Guansong Pang, Qingsong Wen, Shuiguang Deng
Abstract: Slow task detection is a critical problem in cloud operation and maintenance since it is highly related to user experience and can bring substantial liquidated damages. Most anomaly detection methods detect it from a single-task aspect. However, considering millions of concurrent tasks in large-scale cloud computing clusters, it becomes impractical and inefficient. Moreover, single-task slowdowns are very common and do not necessarily indicate a malfunction of a cluster due to its violent fluctuation nature in a virtual environment. Thus, we shift our attention to cluster-wide task slowdowns by utilizing the duration time distribution of tasks across a cluster, so that the computation complexity is not relevant to the number of tasks. The task duration time distribution often exhibits compound periodicity and local exceptional fluctuations over time. Though transformer-based methods are one of the most powerful methods to capture these time series normal variation patterns, we empirically find and theoretically explain the flaw of the standard attention mechanism in reconstructing subperiods with low amplitude when dealing with compound periodicity. To tackle these challenges, we propose SORN (i.e., Skimming Off subperiods in descending amplitude order and Reconstructing Non-slowing fluctuation), which consists of a Skimming Attention mechanism to reconstruct the compound periodicity and a Neural Optimal Transport module to distinguish cluster-wide slowdowns from other exceptional fluctuations. Furthermore, since anomalies in the training set are inevitable in a practical scenario, we propose a picky loss function, which adaptively assigns higher weights to reliable time slots in the training set. Extensive experiments demonstrate that SORN outperforms state-of-the-art methods on multiple real-world industrial datasets.
Authors: Marc Pickett, Aakash Kumar Nain, Joseph Modayil, Llion Jones
Abstract: Modern machine learning systems have demonstrated substantial abilities with methods that either embrace or ignore human-provided knowledge, but combining benefits of both styles remains a challenge. One particular challenge involves designing learning systems that exhibit built-in responses to specific abstract stimulus patterns, yet are still plastic enough to be agnostic about the modality and exact form of their inputs. In this paper, we investigate what we call The Ungrounded Alignment Problem, which asks How can we build in predefined knowledge in a system where we don't know how a given stimulus will be grounded? This paper examines a simplified version of the general problem, where an unsupervised learner is presented with a sequence of images for the characters in a text corpus, and this learner is later evaluated on its ability to recognize specific (possibly rare) sequential patterns. Importantly, the learner is given no labels during learning or evaluation, but must map images from an unknown font or permutation to its correct class label. That is, at no point is our learner given labeled images, where an image vector is explicitly associated with a class label. Despite ample work in unsupervised and self-supervised loss functions, all current methods require a labeled fine-tuning phase to map the learned representations to correct classes. Finding this mapping in the absence of labels may seem a fool's errand, but our main result resolves this seeming paradox. We show that leveraging only letter bigram frequencies is sufficient for an unsupervised learner both to reliably associate images to class labels and to reliably identify trigger words in the sequence of inputs. More generally, this method suggests an approach for encoding specific desired innate behaviour in modality-agnostic models.
Authors: Xin Zhou, Weiqing Wang, Wray Buntine, Shilin Qu, Abishek Sriramulu, Weicong Tan, Christoph Bergmeir
Abstract: Deep models for Multivariate Time Series (MTS) forecasting have recently demonstrated significant success. Channel-dependent models capture complex dependencies that channel-independent models cannot capture. However, the number of channels in real-world applications outpaces the capabilities of existing channel-dependent models, and contrary to common expectations, some models underperform the channel-independent models in handling high-dimensional data, which raises questions about the performance of channel-dependent models. To address this, our study first investigates the reasons behind the suboptimal performance of these channel-dependent models on high-dimensional MTS data. Our analysis reveals that two primary issues lie in the introduced noise from unrelated series that increases the difficulty of capturing the crucial inter-channel dependencies, and challenges in training strategies due to high-dimensional data. To address these issues, we propose STHD, the Scalable Transformer for High-Dimensional Multivariate Time Series Forecasting. STHD has three components: a) Relation Matrix Sparsity that limits the noise introduced and alleviates the memory issue; b) ReIndex applied as a training strategy to enable a more flexible batch size setting and increase the diversity of training data; and c) Transformer that handles 2-D inputs and captures channel dependencies. These components jointly enable STHD to manage the high-dimensional MTS while maintaining computational feasibility. Furthermore, experimental results show STHD's considerable improvement on three high-dimensional datasets: Crime-Chicago, Wiki-People, and Traffic. The source code and dataset are publicly available https://github.com/xinzzzhou/ScalableTransformer4HighDimensionMTSF.git.
URLs: https://github.com/xinzzzhou/ScalableTransformer4HighDimensionMTSF.git.
Authors: Zhou Qin, Kai Yuan, Pratik Lahiri, Wenyang Liu
Abstract: In a typical e-commerce setting, Content Ranking Optimization (CRO) mechanisms are employed to surface content on the search page to fulfill customers' shopping missions. CRO commonly utilizes models such as contextual deep bandits model to independently rank content at different positions, e.g., one optimizer dedicated to organic search results and another to sponsored results. However, this regional optimization approach does not necessarily translate to whole page optimization, e.g., maximizing revenue at the top of the page may inadvertently diminish the revenue of lower positions. In this paper, we propose a reinforcement learning based method for whole page ranking to jointly optimize across all positions by: 1) shifting from position level optimization to whole page level optimization to achieve an overall optimized ranking; 2) applying reinforcement learning to optimize for the cumulative rewards instead of the instant reward. We formulate page level CRO as a cooperative Multi-agent Markov Decision Process , and address it with the novel Multi-Agent Deep Deterministic Policy Gradient (MADDPG) model. MADDPG supports a flexible and scalable joint optimization framework by adopting a "centralized training and decentralized execution" approach. Extensive experiments demonstrate that MADDPG scales to a 2.5 billion action space in the public Mujoco environment, and outperforms the deep bandits modeling by 25.7% on the offline CRO data set from a leading e-commerce company. We foresee that this novel multi-agent optimization is applicable to similar joint optimization problems in the field of information retrieval.
Authors: Dongqi Fu, Yada Zhu, Hanghang Tong, Kommy Weldemariam, Onkar Bhardwaj, Jingrui He
Abstract: Understanding the causal interaction of time series variables can contribute to time series data analysis for many real-world applications, such as climate forecasting and extreme weather alerts. However, causal relationships are difficult to be fully observed in real-world complex settings, such as spatial-temporal data from deployed sensor networks. Therefore, to capture fine-grained causal relations among spatial-temporal variables for further a more accurate and reliable time series analysis, we first design a conceptual fine-grained causal model named TBN Granger Causality, which adds time-respecting Bayesian Networks to the previous time-lagged Neural Granger Causality to offset the instantaneous effects. Second, we propose an end-to-end deep generative model called TacSas, which discovers TBN Granger Causality in a generative manner to help forecast time series data and detect possible anomalies during the forecast. For evaluations, besides the causality discovery benchmark Lorenz-96, we also test TacSas on climate benchmark ERA5 for climate forecasting and the extreme weather benchmark of NOAA for extreme weather alerts.
Authors: Candi Zheng, Kun Liu, Yang Wang, Shiyi Chen, Hongli Li
Abstract: Background: Invasive coronary arteriography (ICA) is recognized as the gold standard for diagnosing cardiovascular diseases, including unstable angina (UA). The challenge lies in determining the optimal timing for ICA in UA patients, balancing the need for revascularization in high-risk patients against the potential complications in low-risk ones. Unlike myocardial infarction, UA does not have specific indicators like ST-segment deviation or cardiac enzymes, making risk assessment complex. Objectives: Our study aims to enhance the early risk assessment for UA patients by utilizing machine learning algorithms. These algorithms can potentially identify patients who would benefit most from ICA by analyzing less specific yet related indicators that are challenging for human physicians to interpret. Methods: We collected data from 640 UA patients at Shanghai General Hospital, including medical history and electrocardiograms (ECG). Machine learning algorithms were trained using multi-modal demographic characteristics including clinical risk factors, symptoms, biomarker levels, and ECG features extracted by pre-trained neural networks. The goal was to stratify patients based on their revascularization risk. Additionally, we translated our models into applicable and explainable look-up tables through discretization for practical clinical use. Results: The study achieved an Area Under the Curve (AUC) of $0.719 \pm 0.065$ in risk stratification, significantly surpassing the widely adopted GRACE score's AUC of $0.579 \pm 0.044$. Conclusions: The results suggest that machine learning can provide superior risk stratification for UA patients. This improved stratification could help in balancing the risks, costs, and complications associated with ICA, indicating a potential shift in clinical assessment practices for unstable angina.
Authors: Soutrik Roy Chowdhury
Abstract: In this paper we construct and theoretically analyse group equivariant convolutional kernel networks (CKNs) which are useful in understanding the geometry of (equivariant) CNNs through the lens of reproducing kernel Hilbert spaces (RKHSs). We then proceed to study the stability analysis of such equiv-CKNs under the action of diffeomorphism and draw a connection with equiv-CNNs, where the goal is to analyse the geometry of inductive biases of equiv-CNNs through the lens of reproducing kernel Hilbert spaces (RKHSs). Traditional deep learning architectures, including CNNs, trained with sophisticated optimization algorithms is vulnerable to perturbations, including `adversarial examples'. Understanding the RKHS norm of such models through CKNs is useful in designing the appropriate architecture and can be useful in designing robust equivariant representation learning models.
Authors: Xuefeng Jiang, Sheng Sun, Jia Li, Jingjing Xue, Runhan Li, Zhiyuan Wu, Gang Xu, Yuwei Wang, Min Liu
Abstract: Recently, federated learning (FL) has achieved wide successes for diverse privacy-sensitive applications without sacrificing the sensitive private information of clients. However, the data quality of client datasets can not be guaranteed since corresponding annotations of different clients often contain complex label noise of varying degrees, which inevitably causes the performance degradation. Intuitively, the performance degradation is dominated by clients with higher noise rates since their trained models contain more misinformation from data, thus it is necessary to devise an effective optimization scheme to mitigate the negative impacts of these noisy clients. In this work, we propose a two-stage framework FedELC to tackle this complicated label noise issue. The first stage aims to guide the detection of noisy clients with higher label noise, while the second stage aims to correct the labels of noisy clients' data via an end-to-end label correction framework which is achieved by learning possible ground-truth labels of noisy clients' datasets via back propagation. We implement sixteen related methods and evaluate five datasets with three types of complicated label noise scenarios for a comprehensive comparison. Extensive experimental results demonstrate our proposed framework achieves superior performance than its counterparts for different scenarios. Additionally, we effectively improve the data quality of detected noisy clients' local datasets with our label correction framework. The code is available at https://github.com/Sprinter1999/FedELC.
Authors: Duanyi Yao, Songze Li, Ye Xue, Jin Liu
Abstract: Vertical federated learning (VFL), where each participating client holds a subset of data features, has found numerous applications in finance, healthcare, and IoT systems. However, adversarial attacks, particularly through the injection of adversarial examples (AEs), pose serious challenges to the security of VFL models. In this paper, we investigate such vulnerabilities through developing a novel attack to disrupt the VFL inference process, under a practical scenario where the adversary is able to adaptively corrupt a subset of clients. We formulate the problem of finding optimal attack strategies as an online optimization problem, which is decomposed into an inner problem of adversarial example generation (AEG) and an outer problem of corruption pattern selection (CPS). Specifically, we establish the equivalence between the formulated CPS problem and a multi-armed bandit (MAB) problem, and propose the Thompson sampling with Empirical maximum reward (E-TS) algorithm for the adversary to efficiently identify the optimal subset of clients for corruption. The key idea of E-TS is to introduce an estimation of the expected maximum reward for each arm, which helps to specify a small set of competitive arms, on which the exploration for the optimal arm is performed. This significantly reduces the exploration space, which otherwise can quickly become prohibitively large as the number of clients increases. We analytically characterize the regret bound of E-TS, and empirically demonstrate its capability of efficiently revealing the optimal corruption pattern with the highest attack success rate, under various datasets of popular VFL tasks.
Authors: Wei Huo, Changxin Liu, Kemi Ding, Karl Henrik Johansson, Ling Shi
Abstract: This paper investigates the use of the cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in federated learning: privacy leakage and communication bottleneck. We introduce a federated learning algorithm called Differentially Private Federated Cubic Regularized Newton (DP-FCRN). By leveraging second-order techniques, our algorithm achieves lower iteration complexity compared to first-order methods. We also incorporate noise perturbation during local computations to ensure privacy. Furthermore, we employ sparsification in uplink transmission, which not only reduces the communication costs but also amplifies the privacy guarantee. Specifically, this approach reduces the necessary noise intensity without compromising privacy protection. We analyze the convergence properties of our algorithm and establish the privacy guarantee. Finally, we validate the effectiveness of the proposed algorithm through experiments on a benchmark dataset.
Authors: Xiaoyang Ji, Yuchen Zhou, Haofu Yang, Shiyue Xu, Jiahao Li
Abstract: Graph clustering, a classical task in graph learning, involves partitioning the nodes of a graph into distinct clusters. This task has applications in various real-world scenarios, such as anomaly detection, social network analysis, and community discovery. Current graph clustering methods commonly rely on module pre-training to obtain a reliable prior distribution for the model, which is then used as the optimization objective. However, these methods often overlook deeper supervised signals, leading to sub-optimal reliability of the prior distribution. To address this issue, we propose a novel deep graph clustering method called CGCN. Our approach introduces contrastive signals and deep structural information into the pre-training process. Specifically, CGCN utilizes a contrastive learning mechanism to foster information interoperability among multiple modules and allows the model to adaptively adjust the degree of information aggregation for different order structures. Our CGCN method has been experimentally validated on multiple real-world graph datasets, showcasing its ability to boost the dependability of prior clustering distributions acquired through pre-training. As a result, we observed notable enhancements in the performance of the model.
Authors: Subhasis Dasgupta, Arshi Naaz, Jayeeta Choudhury, Nancy Lahiri
Abstract: Road accidents are quite common in almost every part of the world, and, in majority, fatal accidents are attributed to over speeding of vehicles. The tendency to over speeding is usually tried to be controlled using check points at various parts of the road but not all traffic police have the device to check speed with existing speed estimating devices such as LIDAR based, or Radar based guns. The current project tries to address the issue of vehicle speed estimation with handheld devices such as mobile phones or wearable cameras with network connection to estimate the speed using deep learning frameworks.
Authors: Yejun Choi, Yeoneung Kim, Keun Park
Abstract: Metamaterial mechanisms are micro-architectured compliant structures that operate through the elastic deformation of specially designed flexible members. This study develops an efficient design methodology for compliant mechanisms using deep reinforcement learning (RL). For this purpose, design domains are digitized into finite cells with various hinge connections, and finite element analyses (FEAs) are conducted to evaluate the deformation behaviors of the compliance mechanism with different cell combinations. The FEA data are learned through the RL method to obtain optimal compliant mechanisms for desired functional requirements. The RL algorithm is applied to the design of a compliant door-latch mechanism, exploring the effect of human guidance and tiling direction. The optimal result is achieved with minimal human guidance and inward tiling, resulting in a threefold increase in the predefined reward compared to human-designed mechanisms. The proposed approach is extended to the design of a soft gripper mechanism, where the effect of hinge connections is additionally considered. The optimal design under hinge penalization reveals remarkably enhanced compliance, and its performance is validated by experimental tests using an additively manufactured gripper. These findings demonstrate that RL-optimized designs outperform those developed with human insight, providing an efficient design methodology for cell-based compliant mechanisms in practical applications.
Authors: Jiang You, Arben Cela, Ren\'e Natowicz, Jacob Ouanounou, Patrick Siarry
Abstract: Detecting anomalies in time series data is a critical challenge across various domains. Traditional methods typically focus on identifying anomalies in immediate subsequent steps, often underestimating the significance of temporal dynamics such as delay time and horizons of anomalies, which generally require extensive post-analysis. This paper introduces a novel approach for time series anomaly prediction, incorporating temporal information directly into the prediction results. We propose a new dataset specifically designed to evaluate this approach and conduct comprehensive experiments using several state-of-the-art methods. results demonstrate the efficacy of our approach in providing timely and accurate anomaly predictions, setting a new benchmark for future research in this field.
Authors: In\^es Martins, Jo\~ao Matos, Tiago Gon\c{c}alves, Leo A. Celi, A. Ian Wong, Jaime S. Cardoso
Abstract: Algorithmic bias in healthcare mirrors existing data biases. However, the factors driving unfairness are not always known. Medical devices capture significant amounts of data but are prone to errors; for instance, pulse oximeters overestimate the arterial oxygen saturation of darker-skinned individuals, leading to worse outcomes. The impact of this bias in machine learning (ML) models remains unclear. This study addresses the technical challenges of quantifying the impact of medical device bias in downstream ML. Our experiments compare a "perfect world", without pulse oximetry bias, using SaO2 (blood-gas), to the "actual world", with biased measurements, using SpO2 (pulse oximetry). Under this counterfactual design, two models are trained with identical data, features, and settings, except for the method of measuring oxygen saturation: models using SaO2 are a "control" and models using SpO2 a "treatment". The blood-gas oximetry linked dataset was a suitable test-bed, containing 163,396 nearly-simultaneous SpO2 - SaO2 paired measurements, aligned with a wide array of clinical features and outcomes. We studied three classification tasks: in-hospital mortality, respiratory SOFA score in the next 24 hours, and SOFA score increase by two points. Models using SaO2 instead of SpO2 generally showed better performance. Patients with overestimation of O2 by pulse oximetry of > 3% had significant decreases in mortality prediction recall, from 0.63 to 0.59, P < 0.001. This mirrors clinical processes where biased pulse oximetry readings provide clinicians with false reassurance of patients' oxygen levels. A similar degradation happened in ML models, with pulse oximetry biases leading to more false negatives in predicting adverse outcomes.
Authors: Xin Sun, Liang Wang, Qiang Liu, Shu Wu, Zilei Wang, Liang Wang
Abstract: This paper addresses the challenge of out-of-distribution (OOD) generalization in graph machine learning, a field rapidly advancing yet grappling with the discrepancy between source and target data distributions. Traditional graph learning algorithms, based on the assumption of uniform distribution between training and test data, falter in real-world scenarios where this assumption fails, resulting in suboptimal performance. A principal factor contributing to this suboptimal performance is the inherent simplicity bias of neural networks trained through Stochastic Gradient Descent (SGD), which prefer simpler features over more complex yet equally or more predictive ones. This bias leads to a reliance on spurious correlations, adversely affecting OOD performance in various tasks such as image recognition, natural language understanding, and graph classification. Current methodologies, including subgraph-mixup and information bottleneck approaches, have achieved partial success but struggle to overcome simplicity bias, often reinforcing spurious correlations. To tackle this, we propose DIVE, training a collection of models to focus on all label-predictive subgraphs by encouraging the models to foster divergence on the subgraph mask, which circumvents the limitation of a model solely focusing on the subgraph corresponding to simple structural patterns. Specifically, we employs a regularizer to punish overlap in extracted subgraphs across models, thereby encouraging different models to concentrate on distinct structural patterns. Model selection for robust OOD performance is achieved through validation accuracy. Tested across four datasets from GOOD benchmark and one dataset from DrugOOD benchmark, our approach demonstrates significant improvement over existing methods, effectively addressing the simplicity bias and enhancing generalization in graph machine learning.
Authors: Luca Pernigo, Rohan Sen, Davide Baroli
Abstract: Accurate energy demand forecasting is crucial for sustainable and resilient energy development. To meet the Net Zero Representative Concentration Pathways (RCP) $4.5$ scenario in the DACH countries, increased renewable energy production, energy storage, and reduced commercial building consumption are needed. This scenario's success depends on hydroelectric capacity and climatic factors. Informed decisions require quantifying uncertainty in forecasts. This study explores a non-parametric method based on \emph{reproducing kernel Hilbert spaces (RKHS)}, known as kernel quantile regression, for energy prediction. Our experiments demonstrate its reliability and sharpness, and we benchmark it against state-of-the-art methods in load and price forecasting for the DACH region. We offer our implementation in conjunction with additional scripts to ensure the reproducibility of our research.
Authors: Ryan Dempsey, Jonathan Ethier
Abstract: Path loss prediction for wireless communications is highly dependent on the local environment. Propagation models including clutter information have been shown to significantly increase model accuracy. This paper explores the application of deep learning to satellite imagery to identify environmental clutter types automatically. Recognizing these clutter types has numerous uses, but our main application is to use clutter information to enhance propagation prediction models. Knowing the type of obstruction (tree, building, and further classifications) can improve the prediction accuracy of key propagation metrics such as path loss.
Authors: Moritz Scherer, Luka Macan, Victor Jung, Philip Wiese, Luca Bompani, Alessio Burrello, Francesco Conti, Luca Benini
Abstract: With the rise of Embodied Foundation Models (EFMs), most notably Small Language Models (SLMs), adapting Transformers for edge applications has become a very active field of research. However, achieving end-to-end deployment of SLMs on microcontroller (MCU)-class chips without high-bandwidth off-chip main memory access is still an open challenge. In this paper, we demonstrate high-efficiency end-to-end SLM deployment on a multicore RISC-V (RV32) MCU augmented with ML instruction extensions and a hardware neural processing unit (NPU). To automate the exploration of the constrained, multi-dimensional memory vs. computation tradeoffs involved in aggressive SLM deployment on heterogeneous (multicore+NPU) resources, we introduce Deeploy, a novel Deep Neural Network (DNN) compiler, which generates highly-optimized C code requiring minimal runtime support. We demonstrate that Deeploy generates end-to-end code for executing SLMs, fully exploiting the RV32 cores' instruction extensions and the NPU: We achieve leading-edge energy and throughput of \SI{490}{\micro\joule \per Token}, at \SI{340}{Token \per \second} for an SLM trained on the TinyStories dataset, running for the first time on an MCU-class device without external memory.
Authors: Mubin Ul Haque, Joel Janek Dabrowski, Rebecca M. Rogers, Hazel Parry
Abstract: Detecting flying animals (e.g., birds, bats, and insects) using weather radar helps gain insights into animal movement and migration patterns, aids in management efforts (such as biosecurity) and enhances our understanding of the ecosystem.The conventional approach to detecting animals in weather radar involves thresholding: defining and applying thresholds for the radar variables, based on expert opinion. More recently, Deep Learning approaches have been shown to provide improved performance in detection. However, obtaining sufficient labelled weather radar data for flying animals to build learning-based models is time-consuming and labor-intensive. To address the challenge of data labelling, we propose a self-supervised learning method for detecting animal movement. In our proposed method, we pre-train our model on a large dataset with noisy labels produced by a threshold approach. The key advantage is that the pre-trained dataset size is limited only by the number of radar images available. We then fine-tune the model on a small human-labelled dataset. Our experiments on Australian weather radar data for waterbird segmentation show that the proposed method outperforms the current state-of-the art approach by 43.53% in the dice co-efficient statistic.
Authors: Ahmed Anwar, Brian Moser, Dayananda Herurkar, Federico Raue, Vinit Hegiste, Tatjana Legler, Andreas Dengel
Abstract: The emergence of federated learning (FL) presents a promising approach to leverage decentralized data while preserving privacy. Furthermore, the combination of FL and anomaly detection is particularly compelling because it allows for detecting rare and critical anomalies (usually also rare in locally gathered data) in sensitive data from multiple sources, such as cybersecurity and healthcare. However, benchmarking the performance of anomaly detection methods in FL environments remains an underexplored area. This paper introduces FedAD-Bench, a unified benchmark for evaluating unsupervised anomaly detection algorithms within the context of FL. We systematically analyze and compare the performance of recent deep learning anomaly detection models under federated settings, which were typically assessed solely in centralized settings. FedAD-Bench encompasses diverse datasets and metrics to provide a holistic evaluation. Through extensive experiments, we identify key challenges such as model aggregation inefficiencies and metric unreliability. We present insights into FL's regularization effects, revealing scenarios in which it outperforms centralized approaches due to its inherent ability to mitigate overfitting. Our work aims to establish a standardized benchmark to guide future research and development in federated anomaly detection, promoting reproducibility and fair comparison across studies.
Authors: Ben Crulis, Barthelemy Serres, Cyril de Runz, Gilles Venturini
Abstract: Current artificial neural networks are trained with parameters encoded as floating point numbers that occupy lots of memory space at inference time. Due to the increase in the size of deep learning models, it is becoming very difficult to consider training and using artificial neural networks on edge devices. Binary neural networks promise to reduce the size of deep neural network models, as well as to increase inference speed while decreasing energy consumption. Thus, they may allow the deployment of more powerful models on edge devices. However, binary neural networks are still proven to be difficult to train using the backpropagation-based gradient descent scheme. This paper extends the work of \cite{crulis2023alternatives}, which proposed adapting to binary neural networks two promising alternatives to backpropagation originally designed for continuous neural networks, and experimented with them on simple image classification datasets. This paper proposes new experiments on the ImageNette dataset, compares three different model architectures for image classification, and adds two additional alternatives to backpropagation.
Authors: Tobias Bernecker, Ghalia Rehawi, Francesco Paolo Casale, Janine Knauer-Arloth, Annalisa Marsico
Abstract: Graph generation addresses the problem of generating new graphs that have a data distribution similar to real-world graphs. While previous diffusion-based graph generation methods have shown promising results, they often struggle to scale to large graphs. In this work, we propose ARROW-Diff (AutoRegressive RandOm Walk Diffusion), a novel random walk-based diffusion approach for efficient large-scale graph generation. Our method encompasses two components in an iterative process of random walk sampling and graph pruning. We demonstrate that ARROW-Diff can scale to large graphs efficiently, surpassing other baseline methods in terms of both generation time and multiple graph statistics, reflecting the high quality of the generated graphs.
Authors: Sobhan Moazemi, Tim Adams, Hwei Geok NG, Lisa K\"uhnel, Julian Schneider, Anatol-Fiete N\"aher, Juliane Fluck, Holger Fr\"ohlich
Abstract: Individual health data is crucial for scientific advancements, particularly in developing Artificial Intelligence (AI); however, sharing real patient information is often restricted due to privacy concerns. A promising solution to this challenge is synthetic data generation. This technique creates entirely new datasets that mimic the statistical properties of real data, while preserving confidential patient information. In this paper, we present the workflow and different services developed in the context of Germany's National Data Infrastructure project NFDI4Health. First, two state-of-the-art AI tools (namely, VAMBN and MultiNODEs) for generating synthetic health data are outlined. Further, we introduce SYNDAT (a public web-based tool) which allows users to visualize and assess the quality and risk of synthetic data provided by desired generative models. Additionally, the utility of the proposed methods and the web-based tool is showcased using data from Alzheimer's Disease Neuroimaging Initiative (ADNI) and the Center for Cancer Registry Data of the Robert Koch Institute (RKI).
Authors: Jung-Hoon Cho, Vindula Jayawardana, Sirui Li, Cathy Wu
Abstract: Deep reinforcement learning is a powerful approach to complex decision making. However, one issue that limits its practical application is its brittleness, sometimes failing to train in the presence of small changes in the environment. This work is motivated by the empirical observation that directly applying an already trained model to a related task often works remarkably well, also called zero-shot transfer. We take this practical trick one step further to consider how to systematically select good tasks to train, maximizing overall performance across a range of tasks. Given the high cost of training, it is critical to choose a small set of training tasks. The key idea behind our approach is to explicitly model the performance loss (generalization gap) incurred by transferring a trained model. We hence introduce Model-Based Transfer Learning (MBTL) for solving contextual RL problems. In this work, we model the performance loss as a simple linear function of task context similarity. Furthermore, we leverage Bayesian optimization techniques to efficiently model and estimate the unknown training performance of the task space. We theoretically show that the method exhibits regret that is sublinear in the number of training tasks and discuss conditions to further tighten regret bounds. We experimentally validate our methods using urban traffic and standard control benchmarks. Despite the conceptual simplicity, the experimental results suggest that MBTL can achieve greater performance than strong baselines, including exhaustive training on all tasks, multi-task training, and random selection of training tasks. This work lays the foundations for investigating explicit modeling of generalization, thereby enabling principled yet effective methods for contextual RL.
Authors: Haowen Wan, Qianqian Yang, Jiancheng Tang, Zhiguo shi
Abstract: In this paper, we propose a semantic communication approach based on probabilistic graphical model (PGM). The proposed approach involves constructing a PGM from a training dataset, which is then shared as common knowledge between the transmitter and receiver. We evaluate the importance of various semantic features and present a PGM-based compression algorithm designed to eliminate predictable portions of semantic information. Furthermore, we introduce a technique to reconstruct the discarded semantic information at the receiver end, generating approximate results based on the PGM. Simulation results indicate a significant improvement in transmission efficiency over existing methods, while maintaining the quality of the transmitted images.
Authors: Daniil A. Boiko, Thiago Resch\"utzegger, Benjamin Sanchez-Lengeling, Samuel M. Blau, Gabe Gomes
Abstract: Molecular representation is a foundational element in our understanding of the physical world. Its importance ranges from the fundamentals of chemical reactions to the design of new therapies and materials. Previous molecular machine learning models have employed strings, fingerprints, global features, and simple molecular graphs that are inherently information-sparse representations. However, as the complexity of prediction tasks increases, the molecular representation needs to encode higher fidelity information. This work introduces a novel approach to infusing quantum-chemical-rich information into molecular graphs via stereoelectronic effects. We show that the explicit addition of stereoelectronic interactions significantly improves the performance of molecular machine learning models. Furthermore, stereoelectronics-infused representations can be learned and deployed with a tailored double graph neural network workflow, enabling its application to any downstream molecular machine learning task. Finally, we show that the learned representations allow for facile stereoelectronic evaluation of previously intractable systems, such as entire proteins, opening new avenues of molecular design.
Authors: Jimmy Wang, Ethan Che, Daniel R. Jiang, Hongseok Namkoong
Abstract: Innovations across science and industry are evaluated using randomized trials (a.k.a. A/B tests). While simple and robust, such static designs are inefficient or infeasible for testing many hypotheses. Adaptive designs can greatly improve statistical power in theory, but they have seen limited adoption due to their fragility in practice. We present a benchmark for adaptive experimentation based on real-world datasets, highlighting prominent practical challenges to operationalizing adaptivity: non-stationarity, batched/delayed feedback, multiple outcomes and objectives, and external validity. Our benchmark aims to spur methodological development that puts practical performance (e.g., robustness) as a central concern, rather than mathematical guarantees on contrived instances. We release an open source library, AExGym, which is designed with modularity and extensibility in mind to allow experimentation practitioners to develop custom environments and algorithms.
Authors: Xingwu Chen, Lei Zhao, Difan Zou
Abstract: Despite the remarkable success of transformer-based models in various real-world tasks, their underlying mechanisms remain poorly understood. Recent studies have suggested that transformers can implement gradient descent as an in-context learner for linear regression problems and have developed various theoretical analyses accordingly. However, these works mostly focus on the expressive power of transformers by designing specific parameter constructions, lacking a comprehensive understanding of their inherent working mechanisms post-training. In this study, we consider a sparse linear regression problem and investigate how a trained multi-head transformer performs in-context learning. We experimentally discover that the utilization of multi-heads exhibits different patterns across layers: multiple heads are utilized and essential in the first layer, while usually only a single head is sufficient for subsequent layers. We provide a theoretical explanation for this observation: the first layer preprocesses the context data, and the following layers execute simple optimization steps based on the preprocessed context. Moreover, we demonstrate that such a preprocess-then-optimize algorithm can significantly outperform naive gradient descent and ridge regression algorithms. Further experimental results support our explanations. Our findings offer insights into the benefits of multi-head attention and contribute to understanding the more intricate mechanisms hidden within trained transformers.
Authors: Bella Finkel, Jose Israel Rodriguez, Chenxi Wu, Thomas Yahl
Abstract: Polynomial neural networks have been implemented in a range of applications and present an advantageous framework for theoretical machine learning. A polynomial neural network of fixed architecture and activation degree gives an algebraic map from the network's weights to a set of polynomials. The image of this map is the space of functions representable by the network. Its Zariski closure is an affine variety known as a neurovariety. The dimension of a polynomial neural network's neurovariety provides a measure of its expressivity. In this work, we introduce the notion of the activation threshold of a network architecture which expresses when the dimension of a neurovariety achieves its theoretical maximum. In addition, we prove expressiveness results for polynomial neural networks with equi-width~architectures.
Authors: Ethan Che, Daniel R. Jiang, Hongseok Namkoong, Jimmy Wang
Abstract: Adaptive experimentation can significantly improve statistical power, but standard algorithms overlook important practical issues including batched and delayed feedback, personalization, non-stationarity, multiple objectives, and constraints. To address these issues, the current algorithm design paradigm crafts tailored methods for each problem instance. Since it is infeasible to devise novel algorithms for every real-world instance, practitioners often have to resort to suboptimal approximations that do not address all of their challenges. Moving away from developing bespoke algorithms for each setting, we present a mathematical programming view of adaptive experimentation that can flexibly incorporate a wide range of objectives, constraints, and statistical procedures. By formulating a dynamic program in the batched limit, our modeling framework enables the use of scalable optimization methods (e.g., SGD and auto-differentiation) to solve for treatment allocations. We evaluate our framework on benchmarks modeled after practical challenges such as non-stationarity, personalization, multi-objectives, and constraints. Unlike bespoke algorithms such as modified variants of Thomson sampling, our mathematical programming approach provides remarkably robust performance across instances.
Authors: Zahra Atashgahi, Tennison Liu, Mykola Pechenizkiy, Raymond Veldhuis, Decebal Constantin Mocanu, Mihaela van der Schaar
Abstract: Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically reducing computational overheads. Despite these advancements, several critical aspects remain insufficiently explored for feature selection. Questions persist regarding the choice of the DST algorithm for network training, the choice of metric for ranking features/neurons, and the comparative performance of these methods across diverse datasets when compared to dense networks. This paper addresses these gaps by presenting a comprehensive systematic analysis of feature selection with sparse neural networks. Moreover, we introduce a novel metric considering sparse neural network characteristics, which is designed to quantify feature importance within the context of SNNs. Our findings show that feature selection with SNNs trained with DST algorithms can achieve, on average, more than $50\%$ memory and $55\%$ FLOPs reduction compared to the dense networks, while outperforming them in terms of the quality of the selected features. Our code and the supplementary material are available on GitHub (\url{https://github.com/zahraatashgahi/Neuron-Attribution}).
Authors: Runxi Cheng, Yongxian Wei, Xianglong He, Wanyun Zhu, Songsong Huang, Fei Richard Yu, Fei Ma, Chun Yuan
Abstract: Meta-learning has been extensively applied in the domains of few-shot learning and fast adaptation, achieving remarkable performance. While Meta-learning methods like Model-Agnostic Meta-Learning (MAML) and its variants provide a good set of initial parameters for the model, the model still tends to learn shortcut features, which leads to poor generalization. In this paper, we propose the formal conception of "learn to learn more precisely", which aims to make the model learn precise target knowledge from data and reduce the effect of noisy knowledge, such as background and noise. To achieve this target, we proposed a simple and effective meta-learning framework named Meta Self-Distillation(MSD) to maximize the consistency of learned knowledge, enhancing the models' ability to learn precise target knowledge. In the inner loop, MSD uses different augmented views of the same support data to update the model respectively. Then in the outer loop, MSD utilizes the same query data to optimize the consistency of learned knowledge, enhancing the model's ability to learn more precisely. Our experiment demonstrates that MSD exhibits remarkable performance in few-shot classification tasks in both standard and augmented scenarios, effectively boosting the accuracy and consistency of knowledge learned by the model.
Authors: Aeree Cho, Grace C. Kim, Alexander Karpekov, Alec Helbling, Zijie J. Wang, Seongmin Lee, Benjamin Hoover, Duen Horng Chau
Abstract: Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2 model. Our tool helps users understand complex Transformer concepts by integrating a model overview and enabling smooth transitions across abstraction levels of mathematical operations and model structures. It runs a live GPT-2 instance locally in the user's browser, empowering users to experiment with their own input and observe in real-time how the internal components and parameters of the Transformer work together to predict the next tokens. Our tool requires no installation or special hardware, broadening the public's education access to modern generative AI techniques. Our open-sourced tool is available at https://poloclub.github.io/transformer-explainer/. A video demo is available at https://youtu.be/ECR4oAwocjs.
URLs: https://poloclub.github.io/transformer-explainer/., https://youtu.be/ECR4oAwocjs.
Authors: Katherine M. Collins, Ilia Sucholutsky, Umang Bhatt, Kartik Chandra, Lionel Wong, Mina Lee, Cedegao E. Zhang, Tan Zhi-Xuan, Mark Ho, Vikash Mansinghka, Adrian Weller, Joshua B. Tenenbaum, Thomas L. Griffiths
Abstract: What do we want from machine intelligence? We envision machines that are not just tools for thought, but partners in thought: reasonable, insightful, knowledgeable, reliable, and trustworthy systems that think with us. Current artificial intelligence (AI) systems satisfy some of these criteria, some of the time. In this Perspective, we show how the science of collaborative cognition can be put to work to engineer systems that really can be called ``thought partners,'' systems built to meet our expectations and complement our limitations. We lay out several modes of collaborative thought in which humans and AI thought partners can engage and propose desiderata for human-compatible thought partnerships. Drawing on motifs from computational cognitive science, we motivate an alternative scaling path for the design of thought partners and ecosystems around their use through a Bayesian lens, whereby the partners we construct actively build and reason over models of the human and world.
Authors: Kun Tong, Chengze Jiang, Jie Gui, Yuan Cao
Abstract: Adversarial training (AT) is an effective defense method against gradient-based attacks to enhance the robustness of neural networks. Among them, single-step AT has emerged as a hotspot topic due to its simplicity and efficiency, requiring only one gradient propagation in generating adversarial examples. Nonetheless, the problem of catastrophic overfitting (CO) that causes training collapse remains poorly understood, and there exists a gap between the robust accuracy achieved through single- and multi-step AT. In this paper, we present a surprising finding that the taxonomy of adversarial examples reveals the truth of CO. Based on this conclusion, we propose taxonomy driven fast adversarial training (TDAT) which jointly optimizes learning objective, loss function, and initialization method, thereby can be regarded as a new paradigm of single-step AT. Compared with other fast AT methods, TDAT can boost the robustness of neural networks, alleviate the influence of misclassified examples, and prevent CO during the training process while requiring almost no additional computational and memory resources. Our method achieves robust accuracy improvement of $1.59\%$, $1.62\%$, $0.71\%$, and $1.26\%$ on CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet-100 datasets, when against projected gradient descent PGD10 attack with perturbation budget 8/255. Furthermore, our proposed method also achieves state-of-the-art robust accuracy against other attacks. Code is available at https://github.com/bookman233/TDAT.
Authors: Jonas Van Der Donckt, Jeroen Van Der Donckt, Sofie Van Hoecke
Abstract: This work presents the solution of the Signal Sleuths team for the 2024 HASCA WEAR challenge. The challenge focuses on detecting 18 workout activities (and the null class) using accelerometer data from 4 wearables - one worn on each limb. Data analysis revealed inconsistencies in wearable orientation within and across participants, leading to exploring novel multi-wearable data augmentation techniques. We investigate three models using a fixed feature set: (i) "raw": using all data as is, (ii) "left-right swapping": augmenting data by swapping left and right limb pairs, and (iii) "upper-lower limb paring": stacking data by using upper-lower limb pair combinations (2 wearables). Our experiments utilize traditional machine learning with multi-window feature extraction and temporal smoothing. Using 3-fold cross-validation, the raw model achieves a macro F1-score of 90.01%, whereas left-right swapping and upper-lower limb paring improve the scores to 91.30% and 91.87% respectively.
Authors: Lili Chen, Jingge Zhu, Jamie Evans
Abstract: The optimal allocation of channels and power resources plays a crucial role in ensuring minimal interference, maximal data rates, and efficient energy utilisation. As a successful approach for tackling resource management problems in wireless networks, Graph Neural Networks (GNNs) have attracted a lot of attention. This article proposes a GNN-based algorithm to address the joint resource allocation problem in heterogeneous wireless networks. Concretely, we model the heterogeneous wireless network as a heterogeneous graph and then propose a graph neural network structure intending to allocate the available channels and transmit power to maximise the network throughput. Our proposed joint channel and power allocation graph neural network (JCPGNN) comprises a shared message computation layer and two task-specific layers, with a dedicated focus on channel and power allocation tasks, respectively. Comprehensive experiments demonstrate that the proposed algorithm achieves satisfactory performance but with higher computational efficiency compared to traditional optimisation algorithms.
Authors: Zikri Kholifah Nur, Rifki Wijaya, Gia Septiana Wulandari
Abstract: This research delves into the utilization of smartwatch sensor data and heart rate monitoring to discern individual emotions based on body movement and heart rate. Emotions play a pivotal role in human life, influencing mental well-being, quality of life, and even physical and physiological responses. The data were sourced from prior research by Juan C. Quiroz, PhD. The study enlisted 50 participants who donned smartwatches and heart rate monitors while completing a 250-meter walk. Emotions were induced through both audio-visual and audio stimuli, with participants' emotional states evaluated using the PANAS questionnaire. The study scrutinized three scenarios: viewing a movie before walking, listening to music before walking, and listening to music while walking. Personal baselines were established using DummyClassifier with the 'most_frequent' strategy from the sklearn library, and various models, including Linear Regression and Random Forest, were employed to gauge the impacts of these activities. Notably, a novel approach was undertaken by incorporating hyperparameter tuning to the Random Forest model using RandomizedSearchCV. The outcomes showcased substantial enhancements with hyperparameter tuning in the Random Forest model, yielding mean accuracies of 86.63% for happy vs. sad and 76.33% for happy vs. neutral vs. sad.
Authors: Tahar Zanouda, Meysam Masoudi, Fitsum Gaim Gebre, Mischa Dohler
Abstract: Telecom networks are becoming increasingly complex, with diversified deployment scenarios, multi-standards, and multi-vendor support. The intricate nature of the telecom network ecosystem presents challenges to effectively manage, operate, and optimize networks. To address these hurdles, Artificial Intelligence (AI) has been widely adopted to solve different tasks in telecom networks. However, these conventional AI models are often designed for specific tasks, rely on extensive and costly-to-collect labeled data that require specialized telecom expertise for development and maintenance. The AI models usually fail to generalize and support diverse deployment scenarios and applications. In contrast, Foundation Models (FMs) show effective generalization capabilities in various domains in language, vision, and decision-making tasks. FMs can be trained on multiple data modalities generated from the telecom ecosystem and leverage specialized domain knowledge. Moreover, FMs can be fine-tuned to solve numerous specialized tasks with minimal task-specific labeled data and, in some instances, are able to leverage context to solve previously unseen problems. At the dawn of 6G, this paper investigates the potential opportunities of using FMs to shape the future of telecom technologies and standards. In particular, the paper outlines a conceptual process for developing Telecom FMs (TFMs) and discusses emerging opportunities for orchestrating specialized TFMs for network configuration, operation, and maintenance. Finally, the paper discusses the limitations and challenges of developing and deploying TFMs.
Authors: Shunya Minami, Yoshihiro Hayashi, Stephen Wu, Kenji Fukumizu, Hiroki Sugisawa, Masashi Ishii, Isao Kuwajima, Kazuya Shiratori, Ryo Yoshida
Abstract: To address the challenge of limited experimental materials data, extensive physical property databases are being developed based on high-throughput computational experiments, such as molecular dynamics simulations. Previous studies have shown that fine-tuning a predictor pretrained on a computational database to a real system can result in models with outstanding generalization capabilities compared to learning from scratch. This study demonstrates the scaling law of simulation-to-real (Sim2Real) transfer learning for several machine learning tasks in materials science. Case studies of three prediction tasks for polymers and inorganic materials reveal that the prediction error on real systems decreases according to a power-law as the size of the computational data increases. Observing the scaling behavior offers various insights for database development, such as determining the sample size necessary to achieve a desired performance, identifying equivalent sample sizes for physical and computational experiments, and guiding the design of data production protocols for downstream real-world tasks.
Authors: Yu Liu, Roger Proksch, Jason Bemis, Utkarsh Pratiush, Astita Dubey, Mahshid Ahmadi, Reece Emery, Philip D. Rack, Yu-Chen Liu, Jan-Chi Yang, Sergei V. Kalinin
Abstract: Since the dawn of scanning probe microscopy (SPM), tapping or intermittent contact mode has been one of the most widely used imaging modes. Manual optimization of tapping mode not only takes a lot of instrument and operator time, but also often leads to frequent probe and sample damage, poor image quality and reproducibility issues for new types of samples or inexperienced users. Despite wide use, optimization of tapping mode imaging is an extremely hard problem, ill-suited to either classical control methods or machine learning. Here we introduce a reward-driven workflow to automate the optimization of SPM in the tapping mode. The reward function is defined based on multiple channels with physical and empirical knowledge of good scans encoded, representing a sample-agnostic measure of image quality and imitating the decision-making logic employed by human operators. This automated workflow gives optimal scanning parameters for different probes and samples and gives high-quality SPM images consistently in the attractive mode. This study broadens the application and accessibility of SPM and opens the door for fully automated SPM.
Authors: Mohamed Hassan, Aleksander Vakanski, Min Xian
Abstract: Effective clinical deployment of deep learning models in healthcare demands high generalization performance to ensure accurate diagnosis and treatment planning. In recent years, significant research has focused on improving the generalization of deep learning models by regularizing the sharpness of the loss landscape. Among the optimization approaches that explicitly minimize sharpness, Sharpness-Aware Minimization (SAM) has shown potential in enhancing generalization performance on general domain image datasets. This success has led to the development of several advanced sharpness-based algorithms aimed at addressing the limitations of SAM, such as Adaptive SAM, surrogate-Gap SAM, Weighted SAM, and Curvature Regularized SAM. These sharpness-based optimizers have shown improvements in model generalization compared to conventional stochastic gradient descent optimizers and their variants on general domain image datasets, but they have not been thoroughly evaluated on medical images. This work provides a review of recent sharpness-based methods for improving the generalization of deep learning networks and evaluates the methods performance on medical breast ultrasound images. Our findings indicate that the initial SAM method successfully enhances the generalization of various deep learning models. While Adaptive SAM improves generalization of convolutional neural networks, it fails to do so for vision transformers. Other sharpness-based optimizers, however, do not demonstrate consistent results. The results reveal that, contrary to findings in the non-medical domain, SAM is the only recommended sharpness-based optimizer that consistently improves generalization in medical image analysis, and further research is necessary to refine the variants of SAM to enhance generalization performance in this field
Authors: Yuqi Xue, Yiqi Liu, Lifeng Nai, Jian Huang
Abstract: Cloud platforms today have been deploying hardware accelerators like neural processing units (NPUs) for powering machine learning (ML) inference services. To maximize the resource utilization while ensuring reasonable quality of service, a natural approach is to virtualize NPUs for efficient resource sharing for multi-tenant ML services. However, virtualizing NPUs for modern cloud platforms is not easy. This is not only due to the lack of system abstraction support for NPU hardware, but also due to the lack of architectural and ISA support for enabling fine-grained dynamic operator scheduling for virtualized NPUs. We present TCloud, a holistic NPU virtualization framework. We investigate virtualization techniques for NPUs across the entire software and hardware stack. TCloud consists of (1) a flexible NPU abstraction called vNPU, which enables fine-grained virtualization of the heterogeneous compute units in a physical NPU (pNPU); (2) a vNPU resource allocator that enables pay-as-you-go computing model and flexible vNPU-to-pNPU mappings for improved resource utilization and cost-effectiveness; (3) an ISA extension of modern NPU architecture for facilitating fine-grained tensor operator scheduling for multiple vNPUs. We implement TCloud based on a production-level NPU simulator. Our experiments show that TCloud improves the throughput of ML inference services by up to 1.4$\times$ and reduces the tail latency by up to 4.6$\times$, while improving the NPU utilization by 1.2$\times$ on average, compared to state-of-the-art NPU sharing approaches.
Authors: Alireza Heidari, Amirhossein Ahmadi, Wei Zhang
Abstract: The emergence of learned indexes has caused a paradigm shift in our perception of indexing by considering indexes as predictive models that estimate keys' positions within a data set, resulting in notable improvements in key search efficiency and index size reduction; however, a significant challenge inherent in learned index modeling is its constrained support for update operations, necessitated by the requirement for a fixed distribution of records. Previous studies have proposed various approaches to address this issue with the drawback of high overhead due to multiple model retraining. In this paper, we present UpLIF, an adaptive self-tuning learned index that adjusts the model to accommodate incoming updates, predicts the distribution of updates for performance improvement, and optimizes its index structure using reinforcement learning. We also introduce the concept of balanced model adjustment, which determines the model's inherent properties (i.e. bias and variance), enabling the integration of these factors into the existing index model without the need for retraining with new data. Our comprehensive experiments show that the system surpasses state-of-the-art indexing solutions (both traditional and ML-based), achieving an increase in throughput of up to 3.12 times with 1000 times less memory usage.
Authors: Raunak Agarwal
Abstract: This work addresses the challenge of factual consistency in text generation systems. We unify the tasks of Natural Language Inference, Summarization Evaluation, Factuality Verification and Factual Consistency Evaluation to train models capable of evaluating the factual consistency of source-target pairs across diverse domains. We rigorously evaluate these against eight baselines on a comprehensive benchmark suite comprising 22 datasets that span various tasks, domains, and document lengths. Results demonstrate that our method achieves state-of-the-art performance on this heterogeneous benchmark while addressing efficiency concerns and attaining cross-domain generalization.
Authors: Seyed Shayan Daneshvar, Yu Nong, Xu Yang, Shaowei Wang, Haipeng Cai
Abstract: Detecting vulnerabilities is a crucial task for maintaining the integrity, availability, and security of software systems. Utilizing DL-based models for vulnerability detection has become commonplace in recent years. However, such deep learning-based vulnerability detectors (DLVD) suffer from a shortage of sizable datasets to train effectively. Data augmentation can potentially alleviate the shortage of data, but augmenting vulnerable code is challenging and requires designing a generative solution that maintains vulnerability. Hence, the work on generating vulnerable code samples has been limited and previous works have only focused on generating samples that contain single statements or specific types of vulnerabilities. Lately, large language models (LLMs) are being used for solving various code generation and comprehension tasks and have shown inspiring results, especially when fused with retrieval augmented generation (RAG). In this study, we explore three different strategies to augment vulnerabilities both single and multi-statement vulnerabilities, with LLMs, namely Mutation, Injection, and Extension. We conducted an extensive evaluation of our proposed approach on three vulnerability datasets and three DLVD models, using two LLMs. Our results show that our injection-based clustering-enhanced RAG method beats the baseline setting (NoAug), Vulgen, and VGX (two SOTA methods), and Random Oversampling (ROS) by 30.80\%, 27.48\%, 27.93\%, and 15.41\% in f1-score with 5K generated vulnerable samples on average, and 53.84\%, 54.10\%, 69.90\%, and 40.93\% with 15K generated vulnerable samples. Our approach demonstrates its feasibility for large-scale data augmentation by generating 1K samples at as cheap as US$ 1.88.
Authors: Khai Le-Duc, Quy-Anh Dang, Tan-Hanh Pham, Truong-Son Hy
Abstract: Knowledge graphs (KGs) enhance the performance of large language models (LLMs) and search engines by providing structured, interconnected data that improves reasoning and context-awareness. However, KGs only focus on text data, thereby neglecting other modalities such as speech. In this work, we introduce wav2graph, the first framework for supervised learning knowledge graph from speech data. Our pipeline are straightforward: (1) constructing a KG based on transcribed spoken utterances and a named entity database, (2) converting KG into embedding vectors, and (3) training graph neural networks (GNNs) for node classification and link prediction tasks. Through extensive experiments conducted in inductive and transductive learning contexts using state-of-the-art GNN models, we provide baseline results and error analysis for node classification and link prediction tasks on human transcripts and automatic speech recognition (ASR) transcripts, including evaluations using both encoder-based and decoder-based node embeddings, as well as monolingual and multilingual acoustic pre-trained models. All related code, data, and models are published online.
Authors: Zhang Kun, Liu Guangwu, Shi Wen
Abstract: Estimating the maximum mean finds a variety of applications in practice. In this paper, we study estimation of the maximum mean using an upper confidence bound (UCB) approach where the sampling budget is adaptively allocated to one of the systems. We study in depth the existing grand average (GA) estimator, and propose a new largest-size average (LSA) estimator. Specifically, we establish statistical guarantees, including strong consistency, asymptotic mean squared errors, and central limit theorems (CLTs) for both estimators, which are new to the literature. We show that LSA is preferable over GA, as the bias of the former decays at a rate much faster than that of the latter when sample size increases. By using the CLTs, we further construct asymptotically valid confidence intervals for the maximum mean, and propose a single hypothesis test for a multiple comparison problem with application to clinical trials. Statistical efficiency of the resulting point and interval estimates and the proposed single hypothesis test is demonstrated via numerical examples.
Authors: Justin Lovelace, Varsha Kishore, Yiwei Chen, Kilian Q. Weinberger
Abstract: Current language models demonstrate remarkable proficiency in text generation. However, for many applications it is desirable to control attributes, such as sentiment, or toxicity, of the generated language -- ideally tailored towards each specific use case and target audience. For auto-regressive language models, existing guidance methods are prone to decoding errors that cascade during generation and degrade performance. In contrast, text diffusion models can easily be guided with, for example, a simple linear sentiment classifier -- however they do suffer from significantly higher perplexity than auto-regressive alternatives. In this paper we use a guided diffusion model to produce a latent proposal that steers an auto-regressive language model to generate text with desired properties. Our model inherits the unmatched fluency of the auto-regressive approach and the plug-and-play flexibility of diffusion. We show that it outperforms previous plug-and-play guidance methods across a wide range of benchmark data sets. Further, controlling a new attribute in our framework is reduced to training a single logistic regression classifier.
Authors: Khanh Doan, Long Tung Vuong, Tuan Nguyen, Anh Tuan Bui, Quyen Tran, Thanh-Toan Do, Dinh Phung, Trung Le
Abstract: Diffusion models (DM) have become fundamental components of generative models, excelling across various domains such as image creation, audio generation, and complex data interpolation. Signal-to-Noise diffusion models constitute a diverse family covering most state-of-the-art diffusion models. While there have been several attempts to study Signal-to-Noise (S2N) diffusion models from various perspectives, there remains a need for a comprehensive study connecting different viewpoints and exploring new perspectives. In this study, we offer a comprehensive perspective on noise schedulers, examining their role through the lens of the signal-to-noise ratio (SNR) and its connections to information theory. Building upon this framework, we have developed a generalized backward equation to enhance the performance of the inference process.
Authors: Zian Meng, Qiang Li, Ashish Pandharipande, Xiaohu Ge
Abstract: The performance of conventional interference management strategies degrades when interference power is comparable to signal power. We consider a new perspective on interference management using semantic communication. Specifically, a multi-user semantic communication system is considered on moderate interference channels (ICs), for which a novel framework of deep learning-based prompt-assisted semantic interference cancellation (DeepPASIC) is proposed. Each transmitted signal is partitioned into common and private parts. The common parts of different users are transmitted simultaneously in a shared medium, resulting in superposition. The private part, on the other hand, serves as a prompt to assist in canceling the interference suffered by the common part at the semantic level. Simulation results demonstrate that the proposed DeepPASIC outperforms conventional interference management strategies under moderate interference conditions.
Authors: Alireza Saber, Pouria Parhami, Alimihammad Siahkarzadeh, Amirreza Fateh
Abstract: Pneumonia, a severe respiratory disease, poses significant diagnostic challenges, especially in underdeveloped regions. Traditional diagnostic methods, such as chest X-rays, suffer from variability in interpretation among radiologists, necessitating reliable automated tools. In this study, we propose a novel approach combining deep learning and transformer-based attention mechanisms to enhance pneumonia detection from chest X-rays. Our method begins with lung segmentation using a TransUNet model that integrates our specialized transformer module, which has fewer parameters compared to common transformers while maintaining performance. This model is trained on the "Chest Xray Masks and Labels" dataset and then applied to the Kermany and Cohen datasets to isolate lung regions, enhancing subsequent classification tasks. For classification, we employ pre-trained ResNet models (ResNet-50 and ResNet-101) to extract multi-scale feature maps, processed through our modified transformer module. By employing our specialized transformer, we attain superior results with significantly fewer parameters compared to common transformer models. Our approach achieves high accuracy rates of 92.79% on the Kermany dataset and 95.11% on the Cohen dataset, ensuring robust and efficient performance suitable for resource-constrained environments. "https://github.com/amirrezafateh/Multi-Scale-Transformer-Pneumonia"
URLs: https://github.com/amirrezafateh/Multi-Scale-Transformer-Pneumonia
Authors: Yuchen Wang, Ziyi Guo, Haixia Bi, Danfeng Hong, Chen Xu
Abstract: The annotation of polarimetric synthetic aperture radar (PolSAR) images is a labor-intensive and time-consuming process. Therefore, classifying PolSAR images with limited labels is a challenging task in remote sensing domain. In recent years, self-supervised learning approaches have proven effective in PolSAR image classification with sparse labels. However, we observe a lack of research on generative selfsupervised learning in the studied task. Motivated by this, we propose a dual-branch classification model based on generative self-supervised learning in this paper. The first branch is a superpixel-branch, which learns superpixel-level polarimetric representations using a generative self-supervised graph masked autoencoder. To acquire finer classification results, a convolutional neural networks-based pixel-branch is further incorporated to learn pixel-level features. Classification with fused dual-branch features is finally performed to obtain the predictions. Experimental results on the benchmark Flevoland dataset demonstrate that our approach yields promising classification results.
Authors: Aditya Kapoor, Benjamin Freed, Howie Choset, Jeff Schneider
Abstract: Multi-agent proximal policy optimization (MAPPO) has recently demonstrated state-of-the-art performance on challenging multi-agent reinforcement learning tasks. However, MAPPO still struggles with the credit assignment problem, wherein the sheer difficulty in ascribing credit to individual agents' actions scales poorly with team size. In this paper, we propose a multi-agent reinforcement learning algorithm that adapts recent developments in credit assignment to improve upon MAPPO. Our approach leverages partial reward decoupling (PRD), which uses a learned attention mechanism to estimate which of a particular agent's teammates are relevant to its learning updates. We use this estimate to dynamically decompose large groups of agents into smaller, more manageable subgroups. We empirically demonstrate that our approach, PRD-MAPPO, decouples agents from teammates that do not influence their expected future reward, thereby streamlining credit assignment. We additionally show that PRD-MAPPO yields significantly higher data efficiency and asymptotic performance compared to both MAPPO and other state-of-the-art methods across several multi-agent tasks, including StarCraft II. Finally, we propose a version of PRD-MAPPO that is applicable to \textit{shared} reward settings, where PRD was previously not applicable, and empirically show that this also leads to performance improvements over MAPPO.
Authors: Fran\c{c}ois Remy, Pieter Delobelle, Hayastan Avetisyan, Alfiya Khabibullina, Miryam de Lhoneux, Thomas Demeester
Abstract: The development of monolingual language models for low and mid-resource languages continues to be hindered by the difficulty in sourcing high-quality training data. In this study, we present a novel cross-lingual vocabulary transfer strategy, trans-tokenization, designed to tackle this challenge and enable more efficient language adaptation. Our approach focuses on adapting a high-resource monolingual LLM to an unseen target language by initializing the token embeddings of the target language using a weighted average of semantically similar token embeddings from the source language. For this, we leverage a translation resource covering both the source and target languages. We validate our method with the Tweeties, a series of trans-tokenized LLMs, and demonstrate their competitive performance on various downstream tasks across a small but diverse set of languages. Additionally, we introduce Hydra LLMs, models with multiple swappable language modeling heads and embedding tables, which further extend the capabilities of our trans-tokenization strategy. By designing a Hydra LLM based on the multilingual model TowerInstruct, we developed a state-of-the-art machine translation model for Tatar, in a zero-shot manner, completely bypassing the need for high-quality parallel data. This breakthrough is particularly significant for low-resource languages like Tatar, where high-quality parallel data is hard to come by. By lowering the data and time requirements for training high-quality models, our trans-tokenization strategy allows for the development of LLMs for a wider range of languages, especially those with limited resources. We hope that our work will inspire further research and collaboration in the field of cross-lingual vocabulary transfer and contribute to the empowerment of languages on a global scale.
Authors: Weilin Cai, Le Qin, Jiayi Huang
Abstract: As large language models continue to scale up, the imperative for fault tolerance in distributed deep learning systems intensifies, becoming a focal area of AI infrastructure research. Checkpoint has emerged as the predominant fault tolerance strategy, with extensive studies dedicated to optimizing its efficiency. However, the advent of the sparse Mixture-of-Experts (MoE) model presents new challenges for traditional checkpoint techniques due to the substantial increase in model size, despite comparable computational demands to dense models. Breaking new ground in the realm of efficient fault tolerance for MoE model training, we introduce a novel Partial Experts Checkpoint (PEC) mechanism alongside a corresponding PEC fault-tolerant system. Our approach strategically checkpoints a selected subset of experts, thereby significantly reducing the checkpoint size for MoE models to a level comparable with that of dense models. The empirical analysis on our 8-expert GPT-MoE model demonstrates that the proposed PEC approach facilitates a substantial 54.2% decrease in the size of non-redundant checkpoint (no data-parallel duplication), without compromising the final model quality. Moreover, our PEC fault-tolerant system achieves a 76.9% reduction in checkpoint workload per data-parallel distributed rank, thereby correspondingly diminishing the checkpointing time and facilitating complete overlap with the training process.
Authors: Silvan David Peter, Gerhard Widmer
Abstract: Note alignment refers to the task of matching individual notes of two versions of the same symbolically encoded piece. Methods addressing this task commonly rely on sequence alignment algorithms such as Hidden Markov Models or Dynamic Time Warping (DTW) applied directly to note or onset sequences. While successful in many cases, such methods struggle with large mismatches between the versions. In this work, we learn note-wise representations from data augmented with various complex mismatch cases, e.g. repeats, skips, block insertions, and long trills. At the heart of our approach lies a transformer encoder network - TheGlueNote - which predicts pairwise note similarities for two 512 note subsequences. We postprocess the predicted similarities using flavors of weightedDTW and pitch-separated onsetDTW to retrieve note matches for two sequences of arbitrary length. Our approach performs on par with the state of the art in terms of note alignment accuracy, is considerably more robust to version mismatches, and works directly on any pair of MIDI files.
Authors: Yuheng Ma, Ke Jia, Hanfang Yang
Abstract: Previous studies yielded discouraging results for item-level locally differentially private linear regression with $s^*$-sparsity assumption, where the minimax rate for $nm$ samples is $\mathcal{O}(s^{*}d / nm\varepsilon^2)$. This can be challenging for high-dimensional data, where the dimension $d$ is extremely large. In this work, we investigate user-level locally differentially private sparse linear regression. We show that with $n$ users each contributing $m$ samples, the linear dependency of dimension $d$ can be eliminated, yielding an error upper bound of $\mathcal{O}(s^{*2} / nm\varepsilon^2)$. We propose a framework that first selects candidate variables and then conducts estimation in the narrowed low-dimensional space, which is extendable to general sparse estimation problems with tight error bounds. Experiments on both synthetic and real datasets demonstrate the superiority of the proposed methods. Both the theoretical and empirical results suggest that, with the same number of samples, locally private sparse estimation is better conducted when multiple samples per user are available.
Authors: Yassine Habchi, Hamza Kheddar, Yassine Himeur, Abdelkrim Boukabou, Shadi Atalla, Wathiq Mansoor, Hussain Al-Ahmad
Abstract: Many incurable diseases prevalent across global societies stem from various influences, including lifestyle choices, economic conditions, social factors, and genetics. Research predominantly focuses on these diseases due to their widespread nature, aiming to decrease mortality, enhance treatment options, and improve healthcare standards. Among these, kidney disease stands out as a particularly severe condition affecting men and women worldwide. Nonetheless, there is a pressing need for continued research into innovative, early diagnostic methods to develop more effective treatments for such diseases. Recently, automatic diagnosis of Kidney Cancer has become an important challenge especially when using deep learning (DL) due to the importance of training medical datasets, which in most cases are difficult and expensive to obtain. Furthermore, in most cases, algorithms require data from the same domain and a powerful computer with efficient storage capacity. To overcome this issue, a new type of learning known as transfer learning (TL) has been proposed that can produce impressive results based on other different pre-trained data. This paper presents, to the best of the authors' knowledge, the first comprehensive survey of DL-based TL frameworks for kidney cancer diagnosis. This is a strong contribution to help researchers understand the current challenges and perspectives of this topic. Hence, the main limitations and advantages of each framework are identified and detailed critical analyses are provided. Looking ahead, the article identifies promising directions for future research. Moving on, the discussion is concluded by reflecting on the pivotal role of TL in the development of precision medicine and its effects on clinical practice and research in oncology.
Authors: Subhasis Dasgupta, Soumya Roy, Jaydip Sen
Abstract: In the internet era, almost every business entity is trying to have its digital footprint in digital media and other social media platforms. For these entities, word of mouse is also very important. Particularly, this is quite crucial for the hospitality sector dealing with hotels, restaurants etc. Consumers do read other consumers reviews before making final decisions. This is where it becomes very important to understand which aspects are affecting most in the minds of the consumers while giving their ratings. The current study focuses on the consumer reviews of Indian hotels to extract aspects important for final ratings. The study involves gathering data using web scraping methods, analyzing the texts using Latent Dirichlet Allocation for topic extraction and sentiment analysis for aspect-specific sentiment mapping. Finally, it incorporates Random Forest to understand the importance of the aspects in predicting the final rating of a user.
Authors: Julen Urain, Ajay Mandlekar, Yilun Du, Mahi Shafiullah, Danfei Xu, Katerina Fragkiadaki, Georgia Chalvatzaki, Jan Peters
Abstract: Learning from Demonstrations, the field that proposes to learn robot behavior models from data, is gaining popularity with the emergence of deep generative models. Although the problem has been studied for years under names such as Imitation Learning, Behavioral Cloning, or Inverse Reinforcement Learning, classical methods have relied on models that don't capture complex data distributions well or don't scale well to large numbers of demonstrations. In recent years, the robot learning community has shown increasing interest in using deep generative models to capture the complexity of large datasets. In this survey, we aim to provide a unified and comprehensive review of the last year's progress in the use of deep generative models in robotics. We present the different types of models that the community has explored, such as energy-based models, diffusion models, action value maps, or generative adversarial networks. We also present the different types of applications in which deep generative models have been used, from grasp generation to trajectory generation or cost learning. One of the most important elements of generative models is the generalization out of distributions. In our survey, we review the different decisions the community has made to improve the generalization of the learned models. Finally, we highlight the research challenges and propose a number of future directions for learning deep generative models in robotics.
Authors: Thomas Most, Lars Gr\"aning, Sebastian Wolff
Abstract: In this paper the accuracy and robustness of quality measures for the assessment of machine learning models are investigated. The prediction quality of a machine learning model is evaluated model-independent based on a cross-validation approach, where the approximation error is estimated for unknown data. The presented measures quantify the amount of explained variation in the model prediction. The reliability of these measures is assessed by means of several numerical examples, where an additional data set for the verification of the estimated prediction error is available. Furthermore, the confidence bounds of the presented quality measures are estimated and local quality measures are derived from the prediction residuals obtained by the cross-validation approach.
Authors: Nikolaus Vertovec, Kostas Margellos, Maria Prandini
Abstract: We consider a moving target that we seek to learn from samples. Our results extend randomized techniques developed in control and optimization for a constant target to the case where the target is changing. We derive a novel bound on the number of samples that are required to construct a probably approximately correct (PAC) estimate of the target. Furthermore, when the moving target is a convex polytope, we provide a constructive method of generating the PAC estimate using a mixed integer linear program (MILP). The proposed method is demonstrated on an application to autonomous emergency braking.
Authors: Michele Craighero, Sarah Solbiati, Federica Mozzini, Enrico Caiani, Giacomo Boracchi
Abstract: The seismocardiographic signal is a promising alternative to the traditional ECG in the analysis of the cardiac activity. In particular, the systolic complex is known to be the most informative part of the seismocardiogram, thus requiring further analysis. State-of-art solutions to detect the systolic complex are based on Deep Learning models, which have been proven effective in pioneering studies. However, these solutions have only been tested in a controlled scenario considering only clean signals acquired from users maintained still in supine position. On top of that, all these studies consider data coming from a single dataset, ignoring the benefits and challenges related to a cross-dataset scenario. In this work, a cross-dataset experimental analysis was performed considering also data from a real-world scenario. Our findings prove the effectiveness of a deep learning solution, while showing the importance of a personalization step to contrast the domain shift, namely a change in data distribution between training and testing data. Finally, we demonstrate the benefits of a multi-channels approach, leveraging the information extracted from both accelerometers and gyroscopes data.
Authors: Sriram Mandalika, Athira Nambiar
Abstract: Most of the sophisticated AI models utilize huge amounts of annotated data and heavy training to achieve high-end performance. However, there are certain challenges that hinder the deployment of AI models "in-the-wild" scenarios, i.e., inefficient use of unlabeled data, lack of incorporation of human expertise, and lack of interpretation of the results. To mitigate these challenges, we propose a novel Explainable Active Learning (XAL) model, XAL-based semantic segmentation model "SegXAL", that can (i) effectively utilize the unlabeled data, (ii) facilitate the "Human-in-the-loop" paradigm, and (iii) augment the model decisions in an interpretable way. In particular, we investigate the application of the SegXAL model for semantic segmentation in driving scene scenarios. The SegXAL model proposes the image regions that require labeling assistance from Oracle by dint of explainable AI (XAI) and uncertainty measures in a weakly-supervised manner. Specifically, we propose a novel Proximity-aware Explainable-AI (PAE) module and Entropy-based Uncertainty (EBU) module to get an Explainable Error Mask, which enables the machine teachers/human experts to provide intuitive reasoning behind the results and to solicit feedback to the AI system via an active learning strategy. Such a mechanism bridges the semantic gap between man and machine through collaborative intelligence, where humans and AI actively enhance each other's complementary strengths. A novel high-confidence sample selection technique based on the DICE similarity coefficient is also presented within the SegXAL framework. Extensive quantitative and qualitative analyses are carried out in the benchmarking Cityscape dataset. Results show the outperformance of our proposed SegXAL against other state-of-the-art models.
Authors: Kevin Tan, Wei Fan, Yuting Wei
Abstract: Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether hybrid RL can improve upon the existing lower bounds established in purely offline and purely online RL without relying on the single-policy concentrability assumption. While Li et al. (2023) provided an affirmative answer to this question in the tabular PAC RL case, the question remains unsettled for both the regret-minimizing RL case and the non-tabular case. In this work, building upon recent advancements in offline RL and reward-agnostic exploration, we develop computationally efficient algorithms for both PAC and regret-minimizing RL with linear function approximation, without single-policy concentrability. We demonstrate that these algorithms achieve sharper error or regret bounds that are no worse than, and can improve on, the optimal sample complexity in offline RL (the first algorithm, for PAC RL) and online RL (the second algorithm, for regret-minimizing RL) in linear Markov decision processes (MDPs), regardless of the quality of the behavior policy. To our knowledge, this work establishes the tightest theoretical guarantees currently available for hybrid RL in linear MDPs.
Authors: Zhengping Jay Luo, Tyler Stewart, Mourya Narasareddygari, Rui Duan, Shangqing Zhao
Abstract: Quantum computing has garnered significant attention in recent years from both academia and industry due to its potential to achieve a "quantum advantage" over classical computers. The advent of quantum computing introduces new challenges for security and privacy. This poster explores the performance and security implications of quantum computing through a case study of machine learning in a real-world application. We compare the performance of quantum machine learning (QML) algorithms to their classical counterparts using the Alzheimer's disease dataset. Our results indicate that QML algorithms show promising potential while they still have not surpassed classical algorithms in terms of learning capability and convergence difficulty, and running quantum algorithms through simulations on classical computers requires significantly large memory space and CPU time. Our study also indicates that QMLs have inherited vulnerabilities from classical machine learning algorithms while also introduce new attack vectors.
Authors: Yupeng Chang, Yi Chang, Yuan Wu
Abstract: Large language models (LLMs) have exhibited remarkable proficiency across a diverse array of natural language processing (NLP) tasks. However, adapting LLMs to downstream applications typically necessitates computationally intensive and memory-demanding fine-tuning procedures. To mitigate these burdens, parameter-efficient fine-tuning (PEFT) techniques have emerged as a promising approach to tailor LLMs with minimal computational overhead. While PEFT methods offer substantial advantages, they do not fully address the pervasive issue of bias propagation from pre-training data. In this work, we introduce Bias-Aware Low-Rank Adaptation (BA-LoRA), a novel PEFT method designed to counteract bias inheritance. BA-LoRA incorporates three distinct regularization terms: (1) consistency regularizer, (2) diversity regularizer, and (3) singular vector decomposition regularizer. These regularizers collectively aim to improve the generative models' consistency, diversity, and generalization capabilities during the fine-tuning process. Through extensive experiments on a variety of natural language understanding (NLU) and natural language generation (NLG) tasks, employing prominent LLMs such as LLaMA, Mistral, and Gemma, we demonstrate that BA-LoRA surpasses the performance of LoRA and its state-of-the-art variants. Moreover, our method effectively mitigates the deleterious effects of pre-training bias, leading to more reliable and robust model outputs. The code is available at https://github.com/cyp-jlu-ai/BA-LoRA.
Authors: Ravi Ramamoorthi
Abstract: Capturing and rendering novel views of complex real-world scenes is a long-standing problem in computer graphics and vision, with applications in augmented and virtual reality, immersive experiences and 3D photography. The advent of deep learning has enabled revolutionary advances in this area, classically known as image-based rendering. However, previous approaches require intractably dense view sampling or provide little or no guidance for how users should sample views of a scene to reliably render high-quality novel views. Local light field fusion proposes an algorithm for practical view synthesis from an irregular grid of sampled views that first expands each sampled view into a local light field via a multiplane image scene representation, then renders novel views by blending adjacent local light fields. Crucially, we extend traditional plenoptic sampling theory to derive a bound that specifies precisely how densely users should sample views of a given scene when using our algorithm. We achieve the perceptual quality of Nyquist rate view sampling while using up to 4000x fewer views. Subsequent developments have led to new scene representations for deep learning with view synthesis, notably neural radiance fields, but the problem of sparse view synthesis from a small number of images has only grown in importance. We reprise some of the recent results on sparse and even single image view synthesis, while posing the question of whether prescriptive sampling guidelines are feasible for the new generation of image-based rendering algorithms.
Authors: Koulik Khamaru, Cun-Hui Zhang
Abstract: In this paper, we discuss the asymptotic behavior of the Upper Confidence Bound (UCB) algorithm in the context of multiarmed bandit problems and discuss its implication in downstream inferential tasks. While inferential tasks become challenging when data is collected in a sequential manner, we argue that this problem can be alleviated when the sequential algorithm at hand satisfies certain stability property. This notion of stability is motivated from the seminal work of Lai and Wei (1982). Our first main result shows that such a stability property is always satisfied for the UCB algorithm, and as a result the sample means for each arm are asymptotically normal. Next, we examine the stability properties of the UCB algorithm when the number of arms $K$ is allowed to grow with the number of arm pulls $T$. We show that in such a case the arms are stable when $\frac{\log K}{\log T} \rightarrow 0$, and the number of near-optimal arms are large.
Authors: Alexander Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan
Abstract: Recent years have seen substantial advances in our understanding of high-dimensional ridge regression, but existing theories assume that training examples are independent. By leveraging recent techniques from random matrix theory and free probability, we provide sharp asymptotics for the in- and out-of-sample risks of ridge regression when the data points have arbitrary correlations. We demonstrate that in this setting, the generalized cross validation estimator (GCV) fails to correctly predict the out-of-sample risk. However, in the case where the noise residuals have the same correlations as the data points, one can modify the GCV to yield an efficiently-computable unbiased estimator that concentrates in the high-dimensional limit, which we dub CorrGCV. We further extend our asymptotic analysis to the case where the test point has nontrivial correlations with the training set, a setting often encountered in time series forecasting. Assuming knowledge of the correlation structure of the time series, this again yields an extension of the GCV estimator, and sharply characterizes the degree to which such test points yield an overly optimistic prediction of long-time risk. We validate the predictions of our theory across a variety of high dimensional data.
Authors: Thao Nguyen, Jeffrey Li, Sewoong Oh, Ludwig Schmidt, Jason Weston, Luke Zettlemoyer, Xian Li
Abstract: We propose a new method, instruction back-and-forth translation, to construct high-quality synthetic data grounded in world knowledge for aligning large language models (LLMs). Given documents from a web corpus, we generate and curate synthetic instructions using the backtranslation approach proposed by Li et al.(2023a), and rewrite the responses to improve their quality further based on the initial documents. Fine-tuning with the resulting (backtranslated instruction, rewritten response) pairs yields higher win rates on AlpacaEval than using other common instruction datasets such as Humpback, ShareGPT, Open Orca, Alpaca-GPT4 and Self-instruct. We also demonstrate that rewriting the responses with an LLM outperforms direct distillation, and the two generated text distributions exhibit significant distinction in embedding space. Further analysis shows that our backtranslated instructions are of higher quality than other sources of synthetic instructions, while our responses are more diverse and complex than those obtained from distillation. Overall we find that instruction back-and-forth translation combines the best of both worlds -- making use of the information diversity and quantity found on the web, while ensuring the quality of the responses which is necessary for effective alignment.
Authors: Gyeongho Kim
Abstract: This work proposes an overview of the recent semi-supervised learning approaches and related works. Despite the remarkable success of neural networks in various applications, there exist a few formidable constraints, including the need for a large amount of labeled data. Therefore, semi-supervised learning, which is a learning scheme in which scarce labels and a larger amount of unlabeled data are utilized to train models (e.g., deep neural networks), is getting more important. Based on the key assumptions of semi-supervised learning, which are the manifold assumption, cluster assumption, and continuity assumption, the work reviews the recent semi-supervised learning approaches. In particular, the methods in regard to using deep neural networks in a semi-supervised learning setting are primarily discussed. In addition, the existing works are first classified based on the underlying idea and explained, then the holistic approaches that unify the aforementioned ideas are detailed.
Authors: Alekh Agarwal, Tong Zhang
Abstract: Provably sample-efficient Reinforcement Learning (RL) with rich observations and function approximation has witnessed tremendous recent progress, particularly when the underlying function approximators are linear. In this linear regime, computationally and statistically efficient methods exist where the potentially infinite state and action spaces can be captured through a known feature embedding, with the sample complexity scaling with the (intrinsic) dimension of these features. When the action space is finite, significantly more sophisticated results allow non-linear function approximation under appropriate structural constraints on the underlying RL problem, permitting for instance, the learning of good features instead of assuming access to them. In this work, we present the first result for non-linear function approximation which holds for general action spaces under a linear embeddability condition, which generalizes all linear and finite action settings. We design a novel optimistic posterior sampling strategy, TS^3 for such problems, and show worst case sample complexity guarantees that scale with a rank parameter of the RL problem, the linear embedding dimension introduced in this work and standard measures of the function class complexity.
Authors: Edward Pearce-Crump
Abstract: Permutation equivariant neural networks are often constructed using tensor powers of $\mathbb{R}^{n}$ as their layer spaces. We show that all of the weight matrices that appear in these neural networks can be obtained from Schur-Weyl duality between the symmetric group and the partition algebra. In particular, we adapt Schur-Weyl duality to derive a simple, diagrammatic method for calculating the weight matrices themselves.
Authors: Oskar Nordenfors, Fredrik Ohlsson Axel Flinth
Abstract: We investigate the optimization of neural networks on symmetric data, and compare the strategy of constraining the architecture to be equivariant to that of using data augmentation. Our analysis reveals that that the relative geometry of the admissible and the equivariant layers, respectively, plays a key role. Under natural assumptions on the data, network, loss, and group of symmetries, we show that compatibility of the spaces of admissible layers and equivariant layers, in the sense that the corresponding orthogonal projections commute, implies that the sets of equivariant stationary points are identical for the two strategies. If the linear layers of the network also are given a unitary parametrization, the set of equivariant layers is even invariant under the gradient flow for augmented models. Our analysis however also reveals that even in the latter situation, stationary points may be unstable for augmented training although they are stable for the manifestly equivariant models.
Authors: Juan Terven, Diana M. Cordova-Esparza, Alfonso Ramirez-Pedraza, Edgar A. Chavez-Urbiola, Julio A. Romero-Gonzalez
Abstract: When training or evaluating deep learning models, two essential parts are picking the proper loss function and deciding on performance metrics. In this paper, we provide a comprehensive overview of the most common loss functions and metrics used across many different types of deep learning tasks, from general tasks such as regression and classification to more specific tasks in Computer Vision and Natural Language Processing. We introduce the formula for each loss and metric, discuss their strengths and limitations, and describe how these methods can be applied to various problems within deep learning. We hope this work serves as a reference for researchers and practitioners in the field, helping them make informed decisions when selecting the most appropriate loss function and performance metrics for their deep learning projects.
Authors: Weidong Huang, Jiaming Ji, Chunhe Xia, Borong Zhang, Yaodong Yang
Abstract: The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often fail to achieve zero-cost performance in complex scenarios, especially vision-only tasks. These limitations are primarily due to model inaccuracies and inadequate sample efficiency. The integration of the world model has proven effective in mitigating these shortcomings. In this work, we introduce SafeDreamer, a novel algorithm incorporating Lagrangian-based methods into world model planning processes within the superior Dreamer framework. Our method achieves nearly zero-cost performance on various tasks, spanning low-dimensional and vision-only input, within the Safety-Gymnasium benchmark, showcasing its efficacy in balancing performance and safety in RL tasks. Further details can be found in the code repository: \url{https://github.com/PKU-Alignment/SafeDreamer}.
Authors: Zahra Zamanzadeh Darban, Geoffrey I. Webb, Shirui Pan, Charu C. Aggarwal, Mahsa Salehi
Abstract: One main challenge in time series anomaly detection (TSAD) is the lack of labelled data in many real-life scenarios. Most of the existing anomaly detection methods focus on learning the normal behaviour of unlabelled time series in an unsupervised manner. The normal boundary is often defined tightly, resulting in slight deviations being classified as anomalies, consequently leading to a high false positive rate and a limited ability to generalise normal patterns. To address this, we introduce a novel end-to-end self-supervised ContrAstive Representation Learning approach for time series Anomaly detection (CARLA). While existing contrastive learning methods assume that augmented time series windows are positive samples and temporally distant windows are negative samples, we argue that these assumptions are limited as augmentation of time series can transform them to negative samples, and a temporally distant window can represent a positive sample. Our contrastive approach leverages existing generic knowledge about time series anomalies and injects various types of anomalies as negative samples. Therefore, CARLA not only learns normal behaviour but also learns deviations indicating anomalies. It creates similar representations for temporally closed windows and distinct ones for anomalies. Additionally, it leverages the information about representations' neighbours through a self-supervised approach to classify windows based on their nearest/furthest neighbours to further enhance the performance of anomaly detection. In extensive tests on seven major real-world time series anomaly detection datasets, CARLA shows superior performance over state-of-the-art self-supervised and unsupervised TSAD methods. Our research shows the potential of contrastive representation learning to advance time series anomaly detection.
Authors: Amitayush Thakur, George Tsoukalas, Yeming Wen, Jimmy Xin, Swarat Chaudhuri
Abstract: We present an in-context learning agent for formal theorem-proving in environments like Lean and Coq. Current state-of-the-art models for the problem are finetuned on environment-specific proof data. By contrast, our approach, called COPRA, repeatedly asks a high-capacity, general-purpose large language model (GPT-4) to propose tactic applications from within a stateful backtracking search. Proposed tactics are executed in the underlying proof environment. Feedback from the execution is used to build the prompt for the next model query, along with selected information from the search history and lemmas retrieved from an external database. We evaluate our implementation of COPRA on the miniF2F benchmark for Lean and a set of Coq tasks from the CompCert project. On these benchmarks, COPRA significantly outperforms few-shot invocations of GPT-4. It also compares favorably against finetuning-based approaches, outperforming ReProver, a state-of-the-art finetuned approach for Lean, in terms of the pass@1 metric. Our code and data are available at https://github.com/trishullab/copra.
Authors: Nicholas E. Corrado, Yuxiao Qu, John U. Balis, Adam Labiosa, Josiah P. Hanna
Abstract: In offline reinforcement learning (RL), an RL agent learns to solve a task using only a fixed dataset of previously collected data. While offline RL has been successful in learning real-world robot control policies, it typically requires large amounts of expert-quality data to learn effective policies that generalize to out-of-distribution states. Unfortunately, such data is often difficult and expensive to acquire in real-world tasks. Several recent works have leveraged data augmentation (DA) to inexpensively generate additional data, but most DA works apply augmentations in a random fashion and ultimately produce highly suboptimal augmented experience. In this work, we propose Guided Data Augmentation (GuDA), a human-guided DA framework that generates expert-quality augmented data. The key insight behind GuDA is that while it may be difficult to demonstrate the sequence of actions required to produce expert data, a user can often easily characterize when an augmented trajectory segment represents progress toward task completion. Thus, a user can restrict the space of possible augmentations to automatically reject suboptimal augmented data. To extract a policy from GuDA, we use off-the-shelf offline reinforcement learning and behavior cloning algorithms. We evaluate GuDA on a physical robot soccer task as well as simulated D4RL navigation tasks, a simulated autonomous driving task, and a simulated soccer task. Empirically, GuDA enables learning given a small initial dataset of potentially suboptimal experience and outperforms a random DA strategy as well as a model-based DA strategy.
Authors: Luca M. Schulze Buschoff, Elif Akata, Matthias Bethge, Eric Schulz
Abstract: A chief goal of artificial intelligence is to build machines that think like people. Yet it has been argued that deep neural network architectures fail to accomplish this. Researchers have asserted these models' limitations in the domains of causal reasoning, intuitive physics, and intuitive psychology. Yet recent advancements, namely the rise of large language models, particularly those designed for visual processing, have rekindled interest in the potential to emulate human-like cognitive abilities. This paper evaluates the current state of vision-based large language models in the domains of intuitive physics, causal reasoning, and intuitive psychology. Through a series of controlled experiments, we investigate the extent to which these modern models grasp complex physical interactions, causal relationships, and intuitive understanding of others' preferences. Our findings reveal that, while some of these models demonstrate a notable proficiency in processing and interpreting visual data, they still fall short of human capabilities in these areas. Our results emphasize the need for integrating more robust mechanisms for understanding causality, physical dynamics, and social cognition into modern-day, vision-based language models, and point out the importance of cognitively-inspired benchmarks.
Authors: Hyewon Jeong, Nassim Oufattole, Matthew Mcdermott, Aparna Balagopalan, Bryan Jangeesingh, Marzyeh Ghassemi, Collin Stultz
Abstract: In clinical practice, one often needs to identify whether a patient is at high risk of adverse outcomes after some key medical event. For example, quantifying the risk of adverse outcomes after an acute cardiovascular event helps healthcare providers identify those patients at the highest risk of poor outcomes; i.e., patients who benefit from invasive therapies that can lower their risk. Assessing the risk of adverse outcomes, however, is challenging due to the complexity, variability, and heterogeneity of longitudinal medical data, especially for individuals suffering from chronic diseases like heart failure. In this paper, we introduce Event-Based Contrastive Learning (EBCL) - a method for learning embeddings of heterogeneous patient data that preserves temporal information before and after key index events. We demonstrate that EBCL can be used to construct models that yield improved performance on important downstream tasks relative to other pretraining methods. We develop and test the method using a cohort of heart failure patients obtained from a large hospital network and the publicly available MIMIC-IV dataset consisting of patients in an intensive care unit at a large tertiary care center. On both cohorts, EBCL pretraining yields models that are performant with respect to a number of downstream tasks, including mortality, hospital readmission, and length of stay. In addition, unsupervised EBCL embeddings effectively cluster heart failure patients into subgroups with distinct outcomes, thereby providing information that helps identify new heart failure phenotypes. The contrastive framework around the index event can be adapted to a wide array of time-series datasets and provides information that can be used to guide personalized care.
Authors: Huy Hoang, Tien Mai, Pradeep Varakantham
Abstract: A popular framework for enforcing safe actions in Reinforcement Learning (RL) is Constrained RL, where trajectory based constraints on expected cost (or other cost measures) are employed to enforce safety and more importantly these constraints are enforced while maximizing expected reward. Most recent approaches for solving Constrained RL convert the trajectory based cost constraint into a surrogate problem that can be solved using minor modifications to RL methods. A key drawback with such approaches is an over or underestimation of the cost constraint at each state. Therefore, we provide an approach that does not modify the trajectory based cost constraint and instead imitates ``good'' trajectories and avoids ``bad'' trajectories generated from incrementally improving policies. We employ an oracle that utilizes a reward threshold (which is varied with learning) and the overall cost constraint to label trajectories as ``good'' or ``bad''. A key advantage of our approach is that we are able to work from any starting policy or set of trajectories and improve on it. In an exhaustive set of experiments, we demonstrate that our approach is able to outperform top benchmark approaches for solving Constrained RL problems, with respect to expected cost, CVaR cost, or even unknown cost constraints.
Authors: Son Nguyen Van, Hoai Nguyen Xuan
Abstract: The Poisson process, especially the nonhomogeneous Poisson process (NHPP), is an essentially important counting process with numerous real-world applications. Up to date, almost all works in the literature have been on the estimation of NHPPs with infinite data using non-data driven binning methods. In this paper, we formulate the problem of estimation of NHPPs from finite and limited data as a learning generalization problem. We mathematically show that while binning methods are essential for the estimation of NHPPs, they pose a threat of overfitting when the amount of data is limited. We propose a framework for regularized learning of NHPPs with two new adaptive and data-driven binning methods that help to remove the ad-hoc tuning of binning parameters. Our methods are experimentally tested on synthetic and real-world datasets and the results show their effectiveness.
Authors: Chaoyi Zhu, Jeroen Galjaard, Pin-Yu Chen, Lydia Y. Chen
Abstract: As large language models (LLM) are increasingly used for text generation tasks, it is critical to audit their usages, govern their applications, and mitigate their potential harms. Existing watermark techniques are shown effective in embedding single human-imperceptible and machine-detectable patterns without significantly affecting generated text quality and semantics. However, the efficiency in detecting watermarks, i.e., the minimum number of tokens required to assert detection with significance and robustness against post-editing, is still debatable. In this paper, we propose, Duwak, to fundamentally enhance the efficiency and quality of watermarking by embedding dual secret patterns in both token probability distribution and sampling schemes. To mitigate expression degradation caused by biasing toward certain tokens, we design a contrastive search to watermark the sampling scheme, which minimizes the token repetition and enhances the diversity. We theoretically explain the interdependency of the two watermarks within Duwak. We evaluate Duwak extensively on Llama2 under various post-editing attacks, against four state-of-the-art watermarking techniques and combinations of them. Our results show that Duwak marked text achieves the highest watermarked text quality at the lowest required token count for detection, up to 70% tokens less than existing approaches, especially under post paraphrasing.
Authors: Alireza Furutanpey, Qiyang Zhang, Philipp Raith, Tobias Pfandzelter, Shangguang Wang, Schahram Dustdar
Abstract: Nanosatellite constellations equipped with sensors capturing large geographic regions provide unprecedented opportunities for Earth observation. As constellation sizes increase, network contention poses a downlink bottleneck. Orbital Edge Computing (OEC) leverages limited onboard compute resources to reduce transfer costs by processing the raw captures at the source. However, current solutions have limited practicability due to reliance on crude filtering methods or over-prioritizing particular downstream tasks. This work presents FOOL, an OEC-native and task-agnostic feature compression method that preserves prediction performance. FOOL partitions high-resolution satellite imagery to maximize throughput. Further, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead. While FOOL is a feature compressor, it can recover images with competitive scores on quality measures at lower bitrates. We extensively evaluate transfer cost reduction by including the peculiarity of intermittently available network connections in low earth orbit. Lastly, we test the feasibility of our system for standardized nanosatellite form factors. We demonstrate that FOOL permits downlinking over 100x the data volume without relying on prior information on the downstream tasks.
Authors: Jackson Burns, William Green
Abstract: Quantitative Structure Property Relationship studies aim to define a mapping between molecular structure and arbitrary quantities of interest. This was historically accomplished via the development of descriptors which requires significant domain expertise and struggles to generalize. Thus the field has morphed into Molecular Property Prediction and been given over to learned representations which are highly generalizable. The paper introduces fastprop, a DeepQSPR framework which uses a cogent set of molecular level descriptors to meet and exceed the performance of learned representations on diverse datasets in dramatically less time. fastprop is freely available on github at github.com/JacksonBurns/fastprop.
Authors: Martin Waltz, Ostap Okhrin, Michael Schultz
Abstract: Urban air mobility is an innovative mode of transportation in which electric vertical takeoff and landing (eVTOL) vehicles operate between nodes called vertiports. We outline a self-organized vertiport arrival system based on deep reinforcement learning. The airspace around the vertiport is assumed to be circular, and the vehicles can freely operate inside. Each aircraft is considered an individual agent and follows a shared policy, resulting in decentralized actions that are based on local information. We investigate the development of the reinforcement learning policy during training and illustrate how the algorithm moves from suboptimal local holding patterns to a safe and efficient final policy. The latter is validated in simulation-based scenarios, including robustness analyses against sensor noise and a changing distribution of inbound traffic. Lastly, we deploy the final policy on small-scale unmanned aerial vehicles to showcase its real-world usability.
Authors: Yu Qin, Brittany Terese Fasy, Carola Wenk, Brian Summa
Abstract: Merge trees are a valuable tool in the scientific visualization of scalar fields; however, current methods for merge tree comparisons are computationally expensive, primarily due to the exhaustive matching between tree nodes. To address this challenge, we introduce the Merge Tree Neural Network (MTNN), a learned neural network model designed for merge tree comparison. The MTNN enables rapid and high-quality similarity computation. We first demonstrate how to train graph neural networks, which emerged as effective encoders for graphs, in order to produce embeddings of merge trees in vector spaces for efficient similarity comparison. Next, we formulate the novel MTNN model that further improves the similarity comparisons by integrating the tree and node embeddings with a new topological attention mechanism. We demonstrate the effectiveness of our model on real-world data in different domains and examine our model's generalizability across various datasets. Our experimental analysis demonstrates our approach's superiority in accuracy and efficiency. In particular, we speed up the prior state-of-the-art by more than $100\times$ on the benchmark datasets while maintaining an error rate below $0.1\%$.
Authors: Dominik Fuchsgruber, Tom Wollschl\"ager, Bertrand Charpentier, Antonio Oroz, Stephan G\"unnemann
Abstract: Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models by iteratively acquiring labels of data points with the highest uncertainty. While it has proven effective for independent data its applicability to graphs remains under-explored. We propose the first extensive study of Uncertainty Sampling for node classification: (1) We benchmark Uncertainty Sampling beyond predictive uncertainty and highlight a significant performance gap to other Active Learning strategies. (2) We develop ground-truth Bayesian uncertainty estimates in terms of the data generating process and prove their effectiveness in guiding Uncertainty Sampling toward optimal queries. We confirm our results on synthetic data and design an approximate approach that consistently outperforms other uncertainty estimators on real datasets. (3) Based on this analysis, we relate pitfalls in modeling uncertainty to existing methods. Our analysis enables and informs the development of principled uncertainty estimation on graphs.
Authors: Aaron Defazio, Xingyu Alice Yang, Harsh Mehta, Konstantin Mishchenko, Ahmed Khaled, Ashok Cutkosky
Abstract: Existing learning rate schedules that do not require specification of the optimization stopping step T are greatly out-performed by learning rate schedules that depend on T. We propose an approach that avoids the need for this stopping time by eschewing the use of schedules entirely, while exhibiting state-of-the-art performance compared to schedules across a wide family of problems ranging from convex problems to large-scale deep learning problems. Our Schedule-Free approach introduces no additional hyper-parameters over standard optimizers with momentum. Our method is a direct consequence of a new theory we develop that unifies scheduling and iterate averaging. An open source implementation of our method is available (https://github.com/facebookresearch/schedule_free).
Authors: Xuefeng Gao, Lingfei Li, Xun Yu Zhou
Abstract: We study continuous-time reinforcement learning (RL) for stochastic control in which system dynamics are governed by jump-diffusion processes. We formulate an entropy-regularized exploratory control problem with stochastic policies to capture the exploration--exploitation balance essential for RL. Unlike the pure diffusion case initially studied by Wang et al. (2020), the derivation of the exploratory dynamics under jump-diffusions calls for a careful formulation of the jump part. Through a theoretical analysis, we find that one can simply use the same policy evaluation and $q$-learning algorithms in Jia and Zhou (2022a, 2023), originally developed for controlled diffusions, without needing to check a priori whether the underlying data come from a pure diffusion or a jump-diffusion. However, we show that the presence of jumps ought to affect parameterizations of actors and critics in general. We investigate as an application the mean--variance portfolio selection problem with stock price modelled as a jump-diffusion, and show that both RL algorithms and parameterizations are invariant with respect to jumps. Finally, we present a detailed study on applying the general theory to option hedging.
Authors: Sebastian Sanokowski, Sepp Hochreiter, Sebastian Lehner
Abstract: Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based approaches rely primarily on generative models that yield exact sample likelihoods. This work introduces a method that lifts this restriction and opens the possibility to employ highly expressive latent variable models like diffusion models. Our approach is conceptually based on a loss that upper bounds the reverse Kullback-Leibler divergence and evades the requirement of exact sample likelihoods. We experimentally validate our approach in data-free Combinatorial Optimization and demonstrate that our method achieves a new state-of-the-art on a wide range of benchmark problems.
Authors: Vincent Cohen-Addad, Tommaso d'Orsi, Alessandro Epasto, Vahab Mirrokni, Peilin Zhong
Abstract: We revisit the input perturbations framework for differential privacy where noise is added to the input $A\in \mathcal{S}$ and the result is then projected back to the space of admissible datasets $\mathcal{S}$. Through this framework, we first design novel efficient algorithms to privately release pair-wise cosine similarities. Second, we derive a novel algorithm to compute $k$-way marginal queries over $n$ features. Prior work could achieve comparable guarantees only for $k$ even. Furthermore, we extend our results to $t$-sparse datasets, where our efficient algorithms yields novel, stronger guarantees whenever $t\le n^{5/6}/\log n\,.$ Finally, we provide a theoretical perspective on why \textit{fast} input perturbation algorithms works well in practice. The key technical ingredients behind our results are tight sum-of-squares certificates upper bounding the Gaussian complexity of sets of solutions.
Authors: Shwai He, Guoheng Sun, Zheyu Shen, Ang Li
Abstract: Scaling Transformer-based large language models (LLMs) has demonstrated promising performance across various tasks. However, it also introduces redundant structures, posing challenges for real-world deployment. Despite some recognition of redundancy in LLMs, the variability of redundancy across different modules, such as MLP and Attention layers, is under-explored. In this work, we investigate the varying redundancy across different modules within Transformers, including Blocks, MLP, and Attention layers, using a similarity-based metric. This metric operates on the premise that redundant structures produce outputs highly similar to their inputs. Surprisingly, while attention layers are essential for transformers and distinguish them from other mainstream architectures, we found that a large proportion of attention layers exhibit excessively high similarity and can be safely pruned without degrading performance, leading to reduced memory and computation costs. Additionally, we further propose a method that jointly drops Attention and MLP layers, achieving improved performance and dropping ratios. Extensive experiments demonstrate the effectiveness of our methods, e.g., Llama-3-70B maintains comparable performance even after pruning half of the attention layers. Our findings provide valuable insights for future network architecture design. The code is released at: \url{https://github.com/Shwai-He/LLM-Drop}.
Authors: Weilin Cai, Juyong Jiang, Fan Wang, Jing Tang, Sunghun Kim, Jiayi Huang
Abstract: Large language models (LLMs) have garnered unprecedented advancements across diverse fields, ranging from natural language processing to computer vision and beyond. The prowess of LLMs is underpinned by their substantial model size, extensive and diverse datasets, and the vast computational power harnessed during training, all of which contribute to the emergent abilities of LLMs (e.g., in-context learning) that are not present in small models. Within this context, the mixture of experts (MoE) has emerged as an effective method for substantially scaling up model capacity with minimal computation overhead, gaining significant attention from academia and industry. Despite its growing prevalence, there lacks a systematic and comprehensive review of the literature on MoE. This survey seeks to bridge that gap, serving as an essential resource for researchers delving into the intricacies of MoE. We first briefly introduce the structure of the MoE layer, followed by proposing a new taxonomy of MoE. Next, we overview the core designs for various MoE models including both algorithmic and systemic aspects, alongside collections of available open-source implementations, hyperparameter configurations and empirical evaluations. Furthermore, we delineate the multifaceted applications of MoE in practice, and outline some potential directions for future research. To facilitate ongoing updates and the sharing of cutting-edge developments in MoE research, we have established a resource repository accessible at https://github.com/withinmiaov/A-Survey-on-Mixture-of-Experts.
URLs: https://github.com/withinmiaov/A-Survey-on-Mixture-of-Experts.
Authors: Jiacheng Shen, Lihan Feng
Abstract: In human decision-making tasks, individuals learn through trials and prediction errors. When individuals learn the task, some are more influenced by good outcomes, while others weigh bad outcomes more heavily. Such confirmation bias can lead to different learning effects. In this study, we propose a new algorithm in Deep Reinforcement Learning, CM-DQN, which applies the idea of different update strategies for positive or negative prediction errors, to simulate the human decision-making process when the task's states are continuous while the actions are discrete. We test in Lunar Lander environment with confirmatory, disconfirmatory bias and non-biased to observe the learning effects. Moreover, we apply the confirmation model in a multi-armed bandit problem (environment in discrete states and discrete actions), which utilizes the same idea as our proposed algorithm, as a contrast experiment to algorithmically simulate the impact of different confirmation bias in decision-making process. In both experiments, confirmatory bias indicates a better learning effect.
Authors: C\'ecile Trottet, Manuel Sch\"urch, Ahmed Allam, Imon Barua, Liubov Petelytska, David Launay, Paolo Air\`o, Radim Be\v{c}v\'a\v{r}, Christopher Denton, Mislav Radic, Oliver Distler, Anna-Maria Hoffmann-Vold, Michael Krauthammer, the EUSTAR collaborators
Abstract: We propose a deep generative approach using latent temporal processes for modeling and holistically analyzing complex disease trajectories, with a particular focus on Systemic Sclerosis (SSc). We aim to learn temporal latent representations of the underlying generative process that explain the observed patient disease trajectories in an interpretable and comprehensive way. To enhance the interpretability of these latent temporal processes, we develop a semi-supervised approach for disentangling the latent space using established medical knowledge. By combining the generative approach with medical definitions of different characteristics of SSc, we facilitate the discovery of new aspects of the disease. We show that the learned temporal latent processes can be utilized for further data analysis and clinical hypothesis testing, including finding similar patients and clustering SSc patient trajectories into novel sub-types. Moreover, our method enables personalized online monitoring and prediction of multivariate time series with uncertainty quantification.
Authors: Kamyab Karimi, Ali Ghodratnama, Reza Tavakkoli-Moghaddam
Abstract: Breast cancer is not preventable because of its unknown causes. However, its early diagnosis increases patients' recovery chances. Machine learning (ML) can be utilized to improve treatment outcomes in healthcare operations while diminishing costs and time. In this research, we suggest two novel feature selection (FS) methods based upon an imperialist competitive algorithm (ICA) and a bat algorithm (BA) and their combination with ML algorithms. This study aims to enhance diagnostic models' efficiency and present a comprehensive analysis to help clinical physicians make much more precise and reliable decisions than before. K-nearest neighbors, support vector machine, decision tree, Naive Bayes, AdaBoost, linear discriminant analysis, random forest, logistic regression, and artificial neural network are some of the methods employed. This paper applied a distinctive integration of evaluation measures and ML algorithms using the wrapper feature selection based on ICA (WFSIC) and BA (WFSB) separately. We compared two proposed approaches for the performance of the classifiers. Also, we compared our best diagnostic model with previous works reported in the literature survey. Experimentations were performed on the Wisconsin diagnostic breast cancer dataset. Results reveal that the proposed framework that uses the BA with an accuracy of 99.12\%, surpasses the framework using the ICA and most previous works. Additionally, the RF classifier in the approach of FS based on BA emerges as the best model and outperforms others regarding its criteria. Besides, the results illustrate the role of our techniques in reducing the dataset dimensions up to 90\% and increasing the performance of diagnostic models by over 99\%. Moreover, the result demonstrates that there are more critical features than the optimum dataset obtained by proposed FS approaches that have been selected by most ML models.
Authors: Ikhtiyor Nematov, Dimitris Sacharidis, Tomer Sagi, Katja Hose
Abstract: For many use-cases, it is often important to explain the prediction of a black-box model by identifying the most influential training data samples. Existing approaches lack customization for user intent and often provide a homogeneous set of explanation samples, failing to reveal the model's reasoning from different angles. In this paper, we propose AIDE, an approach for providing antithetical (i.e., contrastive), intent-based, diverse explanations for opaque and complex models. AIDE distinguishes three types of explainability intents: interpreting a correct, investigating a wrong, and clarifying an ambiguous prediction. For each intent, AIDE selects an appropriate set of influential training samples that support or oppose the prediction either directly or by contrast. To provide a succinct summary, AIDE uses diversity-aware sampling to avoid redundancy and increase coverage of the training data. We demonstrate the effectiveness of AIDE on image and text classification tasks, in three ways: quantitatively, assessing correctness and continuity; qualitatively, comparing anecdotal evidence from AIDE and other example-based approaches; and via a user study, evaluating multiple aspects of AIDE. The results show that AIDE addresses the limitations of existing methods and exhibits desirable traits for an explainability method.
Authors: Jinhui Pang, Changqing Lin, Xiaoshuai Hao, Rong Yin, Zixuan Wang, Zhihui Zhang, Jinglin He, Huang Tai Sheng
Abstract: Continual graph learning (CGL) is an important and challenging task that aims to extend static GNNs to dynamic task flow scenarios. As one of the mainstream CGL methods, the experience replay (ER) method receives widespread attention due to its superior performance. However, existing ER methods focus on identifying samples by feature significance or topological relevance, which limits their utilization of comprehensive graph data. In addition, the topology-based ER methods only consider local topological information and add neighboring nodes to the buffer, which ignores the global topological information and increases memory overhead. To bridge these gaps, we propose a novel method called Feature-Topology Fusion-based Experience Replay (FTF-ER) to effectively mitigate the catastrophic forgetting issue with enhanced efficiency. Specifically, from an overall perspective to maximize the utilization of the entire graph data, we propose a highly complementary approach including both feature and global topological information, which can significantly improve the effectiveness of the sampled nodes. Moreover, to further utilize global topological information, we propose Hodge Potential Score (HPS) as a novel module to calculate the topological importance of nodes. HPS derives a global node ranking via Hodge decomposition on graphs, providing more accurate global topological information compared to neighbor sampling. By excluding neighbor sampling, HPS significantly reduces buffer storage costs for acquiring topological information and simultaneously decreases training time. Compared with state-of-the-art methods, FTF-ER achieves a significant improvement of 3.6% in AA and 7.1% in AF on the OGB-Arxiv dataset, demonstrating its superior performance in the class-incremental learning setting.
Authors: Wei Wang, Qing Li
Abstract: Neural networks are increasingly evolving towards training large models with big data, a method that has demonstrated superior performance across many tasks. However, this approach introduces an urgent problem: current deep learning models are predominantly serial, meaning that as the number of network layers increases, so do the training and inference times. This is unacceptable if deep learning is to continue advancing. Therefore, this paper proposes a deep learning parallelization strategy based on the Universal Approximation Theorem (UAT). From this foundation, we designed a parallel network called Para-Former to test our theory. Unlike traditional serial models, the inference time of Para-Former does not increase with the number of layers, significantly accelerating the inference speed of multi-layer networks. Experimental results validate the effectiveness of this network.
Authors: Josh Millar, Sarab Sethi, Hamed Haddadi, Anil Madhavapeddy
Abstract: In-situ sensing devices need to be deployed in remote environments for long periods of time; minimizing their power consumption is vital for maximising both their operational lifetime and coverage. We introduce Terracorder -- a versatile multi-sensor device -- and showcase its exceptionally low power consumption using an on-device reinforcement learning scheduler. We prototype a unique device setup for biodiversity monitoring and compare its battery life using our scheduler against a number of fixed schedules; the scheduler captures more than 80% of events at less than 50% of the number of activations of the best-performing fixed schedule. We then explore how a collaborative scheduler can maximise the useful operation of a network of devices, improving overall network power consumption and robustness.
Authors: Shengren Hou, Shuyi Gao, Weijie Xia, Edgar Mauricio Salazar Duque, Peter Palensky, Pedro P. Vergara
Abstract: Deep Reinforcement Learning (DRL) presents a promising avenue for optimizing Energy Storage Systems (ESSs) dispatch in distribution networks. This paper introduces RL-ADN, an innovative open-source library specifically designed for solving the optimal ESSs dispatch in active distribution networks. RL-ADN offers unparalleled flexibility in modeling distribution networks, and ESSs, accommodating a wide range of research goals. A standout feature of RL-ADN is its data augmentation module, based on Gaussian Mixture Model and Copula (GMC) functions, which elevates the performance ceiling of DRL agents. Additionally, RL-ADN incorporates the Laurent power flow solver, significantly reducing the computational burden of power flow calculations during training without sacrificing accuracy. The effectiveness of RL-ADN is demonstrated using in different sizes of distribution networks, showing marked performance improvements in the adaptability of DRL algorithms for ESS dispatch tasks. This enhancement is particularly beneficial from the increased diversity of training scenarios. Furthermore, RL-ADN achieves a tenfold increase in computational efficiency during training, making it highly suitable for large-scale network applications. The library sets a new benchmark in DRL-based ESSs dispatch in distribution networks and it is poised to advance DRL applications in distribution network operations significantly. RL-ADN is available at: https://github.com/ShengrenHou/RL-ADN and https://github.com/distributionnetworksTUDelft/RL-ADN.
URLs: https://github.com/ShengrenHou/RL-ADN, https://github.com/distributionnetworksTUDelft/RL-ADN.
Authors: Xuetong Wu, Jonathan H. Manton, Uwe Aickelin, Jingge Zhu
Abstract: Transfer learning, or domain adaptation, is concerned with machine learning problems in which training and testing data come from possibly different probability distributions. In this work, we give an information-theoretic analysis of the generalization error and excess risk of transfer learning algorithms. Our results suggest, perhaps as expected, that the Kullback-Leibler (KL) divergence $D(\mu\|\mu')$ plays an important role in the characterizations where $\mu$ and $\mu'$ denote the distribution of the training data and the testing data, respectively. Specifically, we provide generalization error and excess risk upper bounds for learning algorithms where data from both distributions are available in the training phase. Recognizing that the bounds could be sub-optimal in general, we provide improved excess risk upper bounds for a certain class of algorithms, including the empirical risk minimization (ERM) algorithm, by making stronger assumptions through the \textit{central condition}. To demonstrate the usefulness of the bounds, we further extend the analysis to the Gibbs algorithm and the noisy stochastic gradient descent method. We then generalize the mutual information bound with other divergences such as $\phi$-divergence and Wasserstein distance, which may lead to tighter bounds and can handle the case when $\mu$ is not absolutely continuous with respect to $\mu'$. Several numerical results are provided to demonstrate our theoretical findings. Lastly, to address the problem that the bounds are often not directly applicable in practice due to the absence of the distributional knowledge of the data, we develop an algorithm (called InfoBoost) that dynamically adjusts the importance weights for both source and target data based on certain information measures. The empirical results show the effectiveness of the proposed algorithm.
Authors: Fernando Moreno-Pino, Stefan Zohren
Abstract: Volatility forecasts play a central role among equity risk measures. Besides traditional statistical models, modern forecasting techniques based on machine learning can be employed when treating volatility as a univariate, daily time-series. Moreover, econometric studies have shown that increasing the number of daily observations with high-frequency intraday data helps to improve volatility predictions. In this work, we propose DeepVol, a model based on Dilated Causal Convolutions that uses high-frequency data to forecast day-ahead volatility. Our empirical findings demonstrate that dilated convolutional filters are highly effective at extracting relevant information from intraday financial time-series, proving that this architecture can effectively leverage predictive information present in high-frequency data that would otherwise be lost if realised measures were precomputed. Simultaneously, dilated convolutional filters trained with intraday high-frequency data help us avoid the limitations of models that use daily data, such as model misspecification or manually designed handcrafted features, whose devise involves optimising the trade-off between accuracy and computational efficiency and makes models prone to lack of adaptation into changing circumstances. In our analysis, we use two years of intraday data from NASDAQ-100 to evaluate the performance of DeepVol. Our empirical results suggest that the proposed deep learning-based approach effectively learns global features from high-frequency data, resulting in more accurate predictions compared to traditional methodologies and producing more accurate risk measures.
Authors: Johannes Thalhammer, Manuel Schultheiss, Tina Dorosti, Tobias Lasser, Franz Pfeiffer, Daniela Pfeiffer, Florian Schaff
Abstract: This is a preprint. The latest version has been published here: https://pubs.rsna.org/doi/10.1148/ryai.230275 Purpose: Sparse-view computed tomography (CT) is an effective way to reduce dose by lowering the total number of views acquired, albeit at the expense of image quality, which, in turn, can impact the ability to detect diseases. We explore deep learning-based artifact reduction in sparse-view cranial CT scans and its impact on automated hemorrhage detection. Methods: We trained a U-Net for artefact reduction on simulated sparse-view cranial CT scans from 3000 patients obtained from a public dataset and reconstructed with varying levels of sub-sampling. Additionally, we trained a convolutional neural network on fully sampled CT data from 17,545 patients for automated hemorrhage detection. We evaluated the classification performance using the area under the receiver operator characteristic curves (AUC-ROCs) with corresponding 95% confidence intervals (CIs) and the DeLong test, along with confusion matrices. The performance of the U-Net was compared to an analytical approach based on total variation (TV). Results: The U-Net performed superior compared to unprocessed and TV-processed images with respect to image quality and automated hemorrhage diagnosis. With U-Net post-processing, the number of views can be reduced from 4096 (AUC-ROC: 0.974; 95% CI: 0.972-0.976) views to 512 views (0.973; 0.971-0.975) with minimal decrease in hemorrhage detection (P<.001) and to 256 views (0.967; 0.964-0.969) with a slight performance decrease (P<.001). Conclusion: The results suggest that U-Net based artifact reduction substantially enhances automated hemorrhage detection in sparse-view cranial CTs. Our findings highlight that appropriate post-processing is crucial for optimal image quality and diagnostic accuracy while minimizing radiation dose.
Authors: Vipul Gupta, Pranav Narayanan Venkit, Hugo Lauren\c{c}on, Shomir Wilson, Rebecca J. Passonneau
Abstract: As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to compare performance across social groups, due to factors such as low diversity or limited number of templates. Also, most previous work considers only one NLP task. We introduce Comprehensive Assessment of Language Models (CALM) for robust measurement of two types of universally relevant sociodemographic bias, gender and race. CALM integrates sixteen datasets for question-answering, sentiment analysis and natural language inference. Examples from each dataset are filtered to produce 224 templates with high diversity (e.g., length, vocabulary). We assemble 50 highly frequent person names for each of seven distinct demographic groups to generate 78,400 prompts covering the three NLP tasks. Our empirical evaluation shows that CALM bias scores are more robust and far less sensitive than previous bias measurements to perturbations in the templates, such as synonym substitution, or to random subset selection of templates. We apply CALM to 20 large language models, and find that for 2 language model series, larger parameter models tend to be more biased than smaller ones. The T0 series is the least biased model families, of the 20 LLMs investigated here. The code is available at https://github.com/vipulgupta1011/CALM.
Authors: Ian Krupkin, Johanna Hardin
Abstract: In this paper, error estimates of classification Random Forests are quantitatively assessed. Based on the initial theoretical framework built by Bates et al. (2023), the true error rate and expected error rate are theoretically and empirically investigated in the context of a variety of error estimation methods common to Random Forests. We show that in the classification case, Random Forests' estimates of prediction error is closer on average to the true error rate instead of the average prediction error. This is opposite the findings of Bates et al. (2023) which are given for logistic regression. We further show that our result holds across different error estimation strategies such as cross-validation, bagging, and data splitting.
Authors: Baris Ata, J. Michael Harrison, Nian Si
Abstract: Motivated by applications in queueing theory, we consider a stochastic control problem whose state space is the $d$-dimensional positive orthant. The controlled process $Z$ evolves as a reflected Brownian motion whose covariance matrix is exogenously specified, as are its directions of reflection from the orthant's boundary surfaces. A system manager chooses a drift vector $\theta(t)$ at each time $t$ based on the history of $Z$, and the cost rate at time $t$ depends on both $Z(t)$ and $\theta(t)$. In our initial problem formulation, the objective is to minimize expected discounted cost over an infinite planning horizon, after which we treat the corresponding ergodic control problem. Extending earlier work by Han et al. (Proceedings of the National Academy of Sciences, 2018, 8505-8510), we develop and illustrate a simulation-based computational method that relies heavily on deep neural network technology. For test problems studied thus far, our method is accurate to within a fraction of one percent, and is computationally feasible in dimensions up to at least $d=30$.
Authors: Ernesto Araya Valdivia, Hemant Tyagi
Abstract: This paper addresses the Graph Matching problem, which consists of finding the best possible alignment between two input graphs, and has many applications in computer vision, network deanonymization and protein alignment. A common approach to tackle this problem is through convex relaxations of the NP-hard \emph{Quadratic Assignment Problem} (QAP). Here, we introduce a new convex relaxation onto the unit simplex and develop an efficient mirror descent scheme with closed-form iterations for solving this problem. Under the correlated Gaussian Wigner model, we show that the simplex relaxation admits a unique solution with high probability. In the noiseless case, this is shown to imply exact recovery of the ground truth permutation. Additionally, we establish a novel sufficiency condition for the input matrix in standard greedy rounding methods, which is less restrictive than the commonly used `diagonal dominance' condition. We use this condition to show exact one-step recovery of the ground truth (holding almost surely) via the mirror descent scheme, in the noiseless setting. We also use this condition to obtain significantly improved conditions for the GRAMPA algorithm [Fan et al. 2019] in the noiseless setting.
Authors: Hung Quoc To, Minh Huynh Nguyen, Nghi D. Q. Bui
Abstract: Code Large Language Models (CodeLLMs) have ushered in a new era in code generation advancements. However, selecting the best code solutions from all possible CodeLLM outputs remains a challenge. Previous methods often overlooked the intricate functional similarities and interactions between solution clusters. We introduce SRank, a novel reranking strategy for selecting the best solutions from code generation, focusing on modeling the relationships between clusters of solutions. By quantifying the functional overlap between solution clusters, our approach provides a better ranking strategy for code solutions. Empirical results show that our method achieves remarkable results on the pass@1 score. For instance, on the Human-Eval benchmark, we achieve 69.66% in pass@1 with Codex002, 75.31% with WizardCoder, 53.99% with StarCoder, and 60.55% with CodeGen, surpassing state-of-the-art code generation reranking methods such as CodeT and Coder-Reviewer on the same CodeLLM by a significant margin (approximately 6.1% improvement on average). Even in scenarios with a limited number of sampled solutions and test cases, our approach demonstrates robustness and superiority, marking a new benchmark in code generation reranking. Our implementation can be found at https://github.com/FSoft-AI4Code/SRank-CodeRanker.
Authors: Davis Yoshida, Kartik Goyal, Kevin Gimpel
Abstract: It has been widely observed that exact or approximate MAP (mode-seeking) decoding from natural language generation (NLG) models consistently leads to degenerate outputs (Holtzman et al., 2019; Stahlberg and Byrne, 2019). Prior work has attributed this behavior to either a fundamental and unavoidable inadequacy of modes in probabilistic models or weaknesses in language modeling. Contrastingly, we argue that degenerate modes can even occur in the absence of any modeling error, due to contamination of the training data. Specifically, we argue that mixing even a tiny amount of low-entropy noise with a population text distribution can cause the data distribution's mode to become degenerate. We therefore propose to apply MAP decoding to the model's true conditional distribution where the conditioning variable explicitly avoids specific degenerate behavior. Using exact search, we empirically verify that the length-conditional modes of machine translation models and language models are indeed more fluent and topical than their unconditional modes. For the first time, we also share many examples of exact modal sequences from these models, and from several variants of the LLaMA-7B model. Notably, we observe that various kinds of degenerate modes persist, even at the scale of LLaMA-7B. Although we cannot tractably address these degeneracies with exact search, we perform a classifier-based approximate search on LLaMA-7B, a model which was not trained for instruction following, and find that we are able to elicit reasonable outputs without any finetuning.
Authors: Junhao Zheng, Shengjie Qiu, Qianli Ma
Abstract: Incremental Learning (IL) has been a long-standing problem in both vision and Natural Language Processing (NLP) communities. In recent years, as Pre-trained Language Models (PLMs) have achieved remarkable progress in various NLP downstream tasks, utilizing PLMs as backbones has become a common practice in recent research of IL in NLP. Most assume that catastrophic forgetting is the biggest obstacle to achieving superior IL performance and propose various techniques to overcome this issue. However, we find that this assumption is problematic. Specifically, we revisit more than 20 methods on four classification tasks (Text Classification, Intent Classification, Relation Extraction, and Named Entity Recognition) under the two most popular IL settings (Class-Incremental and Task-Incremental) and reveal that most of them severely underestimate the inherent anti-forgetting ability of PLMs. Based on the observation, we propose a frustratingly easy method called SEQ* for IL with PLMs. The results show that SEQ* has competitive or superior performance compared to state-of-the-art (SOTA) IL methods and requires considerably less trainable parameters and training time. These findings urge us to revisit the IL with PLMs and encourage future studies to have a fundamental understanding of the catastrophic forgetting in PLMs. The data, code and scripts are publicly available at https://github.com/zzz47zzz/codebase-for-incremental-learning-with-llm.
URLs: https://github.com/zzz47zzz/codebase-for-incremental-learning-with-llm.
Authors: Philipp Altmann, Jonas Stein, Michael K\"olle, Adelina B\"arligea, Thomas Gabor, Thomy Phan, Sebastian Feld, Claudia Linnhoff-Popien
Abstract: Quantum computing (QC) in the current NISQ era is still limited in size and precision. Hybrid applications mitigating those shortcomings are prevalent to gain early insight and advantages. Hybrid quantum machine learning (QML) comprises both the application of QC to improve machine learning (ML) and ML to improve QC architectures. This work considers the latter, leveraging reinforcement learning (RL) to improve quantum circuit design (QCD), which we formalize by a set of generic objectives. Furthermore, we propose qcd-gym, a concrete framework formalized as a Markov decision process, to enable learning policies capable of controlling a universal set of continuously parameterized quantum gates. Finally, we provide benchmark comparisons to assess the shortcomings and strengths of current state-of-the-art RL algorithms.
Authors: Vandan Gorade, Sparsh Mittal, Debesh Jha, Rekha Singhal, Ulas Bagci
Abstract: Deep learning has demonstrated remarkable achievements in medical image segmentation. However, prevailing deep learning models struggle with poor generalization due to (i) intra-class variations, where the same class appears differently in different samples, and (ii) inter-class independence, resulting in difficulties capturing intricate relationships between distinct objects, leading to higher false negative cases. This paper presents a novel approach that synergies spatial and spectral representations to enhance domain-generalized medical image segmentation. We introduce the innovative Spectral Correlation Coefficient objective to improve the model's capacity to capture middle-order features and contextual long-range dependencies. This objective complements traditional spatial objectives by incorporating valuable spectral information. Extensive experiments reveal that optimizing this objective with existing architectures like UNet and TransUNet significantly enhances generalization, interpretability, and noise robustness, producing more confident predictions. For instance, in cardiac segmentation, we observe a 0.81 pp and 1.63 pp (pp = percentage point) improvement in DSC over UNet and TransUNet, respectively. Our interpretability study demonstrates that, in most tasks, objectives optimized with UNet outperform even TransUNet by introducing global contextual information alongside local details. These findings underscore the versatility and effectiveness of our proposed method across diverse imaging modalities and medical domains.
Authors: Santiago Cifuentes, Leopoldo Bertossi, Nina Pardal, Sergio Abriola, Maria Vanina Martinez, Miguel Romero
Abstract: Attribution scores reflect how important the feature values in an input entity are for the output of a machine learning model. One of the most popular attribution scores is the SHAP score, which is an instantiation of the general Shapley value used in coalition game theory. The definition of this score relies on a probability distribution on the entity population. Since the exact distribution is generally unknown, it needs to be assigned subjectively or be estimated from data, which may lead to misleading feature scores. In this paper, we propose a principled framework for reasoning on SHAP scores under unknown entity population distributions. In our framework, we consider an uncertainty region that contains the potential distributions, and the SHAP score of a feature becomes a function defined over this region. We study the basic problems of finding maxima and minima of this function, which allows us to determine tight ranges for the SHAP scores of all features. In particular, we pinpoint the complexity of these problems, and other related ones, showing them to be NP-complete. Finally, we present experiments on a real-world dataset, showing that our framework may contribute to a more robust feature scoring.
Authors: Thomas Pouplin, Hao Sun, Samuel Holt, Mihaela van der Schaar
Abstract: Large Language Models (LLMs) have demonstrated the strong potential to assist both clinicians and the general public with their extensive medical knowledge. However, their application in healthcare is constrained due to concerns about the privacy of data used in training, which prevents the integration of private and personal information because of security and ethical issues. Moreover, if their capabilities can be enhanced with information retrieval to access up-to-date knowledge, the current integration of LLMs with Information retrieval lacks robustness to imperfect retrieval, which can hinder their effectiveness and even reduce overall performance. In this work, we address this challenge by introducing the Retrieval-Augmented Thought Process (RATP). Given access to external knowledge, RATP formulates the thought generation of LLMs as a multiple-step decision process. To optimise such a thought process, RATP leverages Monte-Carlo Tree Search and learns a proxy reward function that permits cost-efficient inference. On a private dataset of electronic medical records, deliberately excluded from any LLM training set, RATP achieves 35% additional accuracy compared to in-context retrieval-augmented generation for the question-answering task.
Authors: Phillip Rust, Bowen Shi, Skyler Wang, Necati Cihan Camg\"oz, Jean Maillard
Abstract: A major impediment to the advancement of sign language translation (SLT) is data scarcity. Much of the sign language data currently available on the web cannot be used for training supervised models due to the lack of aligned captions. Furthermore, scaling SLT using large-scale web-scraped datasets bears privacy risks due to the presence of biometric information, which the responsible development of SLT technologies should account for. In this work, we propose a two-stage framework for privacy-aware SLT at scale that addresses both of these issues. We introduce SSVP-SLT, which leverages self-supervised video pretraining on anonymized and unannotated videos, followed by supervised SLT finetuning on a curated parallel dataset. SSVP-SLT achieves state-of-the-art finetuned and zero-shot gloss-free SLT performance on the How2Sign dataset, outperforming the strongest respective baselines by over 3 BLEU-4. Based on controlled experiments, we further discuss the advantages and limitations of self-supervised pretraining and anonymization via facial obfuscation for SLT.
Authors: Marcello Di Bello, Nicol\`o Cangiotti, Michele Loi
Abstract: By combining the philosophical literature on statistical evidence and the interdisciplinary literature on algorithmic fairness, we revisit recent objections against classification parity in light of causal analyses of algorithmic fairness and the distinction between predictive and diagnostic evidence. We focus on trial proceedings as a black-box classification algorithm in which defendants are sorted into two groups by convicting or acquitting them. We defend a novel principle, causal equal protection, that combines classification parity with the causal approach. In the do-calculus, causal equal protection requires that individuals should not be subject to uneven risks of classification error because of their protected or socially salient characteristics. The explicit use of protected characteristics, however, may be required if it equalizes these risks.
Authors: Vithursan Thangarasa, Mahmoud Salem, Shreyas Saxena, Kevin Leong, Joel Hestness, Sean Lie
Abstract: Large language models (LLMs) are typically trained on general source data for various domains, but a recent surge in domain-specific LLMs has shown their potential to outperform general-purpose models in domain-specific tasks (e.g., biomedicine). Although domain-specific pre-training enhances efficiency and leads to smaller models, the computational costs of training these LLMs remain high, posing budgeting challenges. We introduce MediSwift, a suite of biomedical LMs that leverage sparse pre-training on domain-specific biomedical text data. By inducing up to 75% weight sparsity during the pre-training phase, MediSwift achieves a 2-2.5x reduction in training FLOPs. Notably, all sparse pre-training was performed on the Cerebras CS-2 system, which is specifically designed to realize the acceleration benefits from unstructured weight sparsity, thereby significantly enhancing the efficiency of the MediSwift models. Through subsequent dense fine-tuning and strategic soft prompting, MediSwift models outperform existing LLMs up to 7B parameters on biomedical tasks, setting new benchmarks w.r.t efficiency-accuracy on tasks such as PubMedQA. Our results show that sparse pre-training, along with dense fine-tuning and soft prompting, offers an effective method for creating high-performing, computationally efficient models in specialized domains.
Authors: Peng Ding, Jiading Fang, Peng Li, Kangrui Wang, Xiaochen Zhou, Mo Yu, Jing Li, Matthew R. Walter, Hongyuan Mei
Abstract: Large language models such as ChatGPT and GPT-4 have recently achieved astonishing performance on a variety of natural language processing tasks. In this paper, we propose MANGO, a benchmark to evaluate their capabilities to perform text-based mapping and navigation. Our benchmark includes 53 mazes taken from a suite of textgames: each maze is paired with a walkthrough that visits every location but does not cover all possible paths. The task is question-answering: for each maze, a large language model reads the walkthrough and answers hundreds of mapping and navigation questions such as "How should you go to Attic from West of House?" and "Where are we if we go north and east from Cellar?". Although these questions are easy to humans, it turns out that even GPT-4, the best-to-date language model, performs poorly at answering them. Further, our experiments suggest that a strong mapping and navigation ability would benefit large language models in performing relevant downstream tasks, such as playing textgames. Our MANGO benchmark will facilitate future research on methods that improve the mapping and navigation capabilities of language models. We host our leaderboard, data, code, and evaluation program at https://mango.ttic.edu and https://github.com/oaklight/mango/.
URLs: https://mango.ttic.edu, https://github.com/oaklight/mango/.
Authors: Mandar Sharma, Rutuja Murlidhar Taware, Pravesh Koirala, Nikhil Muralidhar, Naren Ramakrishnan
Abstract: Off-the-shelf pre-trained language models have become the de facto standard in NLP pipelines for a multitude of downstream tasks. However, the inability of these models to properly encode numerals limits their performance on tasks requiring numeric comprehension. We introduce strategies to semantically prime numerals in any corpus by generating anchors governed by the distribution of numerals in said corpus, thereby enabling mathematically grounded representations of these numeral tokens. We establish the superiority of our proposed techniques through evaluation on a range of numeracy tasks for both in-domain (seen) and out-domain (unseen) numerals. Further, we expand our empirical evaluations to numerals ranging from 1 to 10 billion, a significantly broader range compared to previous studies of the same nature, and we demonstrate significant improvements in the mathematical grounding of our learned embeddings.
Authors: Yiming Zhang, Avi Schwarzschild, Nicholas Carlini, Zico Kolter, Daphne Ippolito
Abstract: Despite being trained specifically to follow user instructions, today's instructiontuned language models perform poorly when instructed to produce random outputs. For example, when prompted to pick a number uniformly between one and ten Llama-2-13B-chat disproportionately favors the number five, and when tasked with picking a first name at random, Mistral-7B-Instruct chooses Avery 40 times more often than we would expect based on the U.S. population. When these language models are used for real-world tasks where diversity of outputs is crucial, such as language model assisted dataset construction, their inability to produce diffuse distributions over valid choices is a major hurdle. In this work, we propose a fine-tuning method that encourages language models to output distributions that are diffuse over valid outcomes. The methods we introduce generalize across a variety of tasks and distributions and make large language models practical for synthetic dataset generation with little human intervention.
Authors: Mingyuan Zhou, Zhendong Wang, Huangjie Zheng, Hai Huang
Abstract: Diffusion-based text-to-image generation models trained on extensive text-image pairs have shown the capacity to generate photorealistic images consistent with textual descriptions. However, a significant limitation of these models is their slow sample generation, which requires iterative refinement through the same network. In this paper, we enhance Score identity Distillation (SiD) by developing long and short classifier-free guidance (LSG) to efficiently distill pretrained Stable Diffusion models without using real training data. SiD aims to optimize a model-based explicit score matching loss, utilizing a score-identity-based approximation alongside the proposed LSG for practical computation. By training exclusively with fake images synthesized with its one-step generator, SiD equipped with LSG rapidly improves FID and CLIP scores, achieving state-of-the-art FID performance while maintaining a competitive CLIP score. Specifically, its data-free distillation of Stable Diffusion 1.5 achieves a record low FID of 8.15 on the COCO-2014 validation set, with a CLIP score of 0.304 at an LSG scale of 1.5, and an FID of 9.56 with a CLIP score of 0.313 at an LSG scale of 2. Our code and distilled one-step text-to-image generators are available at https://github.com/mingyuanzhou/SiD-LSG.
Authors: Yufan Huang, David F. Gleich
Abstract: Semidefinite programs (SDPs) and their solvers are powerful tools with many applications in machine learning and data science. Designing scalable SDP solvers is challenging because by standard the positive semidefinite decision variable is an $n \times n$ dense matrix, even though the input is often $n \times n$ sparse matrices. However, the information in the solution may not correspond to a full-rank dense matrix as shown by Barvinok and Pataki. Two decades ago, Burer and Monteiro developed an SDP solver $\texttt{SDPLR}$ that optimizes over a low-rank factorization instead of the full matrix. This greatly decreases the storage cost and works well for many problems. The original solver $\texttt{SDPLR}$ tracks only the primal infeasibility of the solution, limiting the technique's flexibility to produce moderate accuracy solutions. We use a suboptimality bound for trace-bounded SDP problems that enables us to track the progress better and perform early termination. We then develop $\texttt{SDPLR+}$, which starts the optimization with an extremely low-rank factorization and dynamically updates the rank based on the primal infeasibility and suboptimality. This further speeds up the computation and saves the storage cost. Numerical experiments on Max Cut, Minimum Bisection, Cut Norm, and Lov\'{a}sz Theta problems with many recent memory-efficient scalable SDP solvers demonstrate its scalability up to problems with million-by-million decision variables and it is often the fastest solver to a moderate accuracy of $10^{-2}$.
Authors: Arthur Aubret, C\'eline Teuli\`ere, Jochen Triesch
Abstract: Self-supervised learning (SSL) has revolutionized visual representation learning, but has not achieved the robustness of human vision. A reason for this could be that SSL does not leverage all the data available to humans during learning. When learning about an object, humans often purposefully turn or move around objects and research suggests that these interactions can substantially enhance their learning. Here we explore whether such object-related actions can boost SSL. For this, we extract the actions performed to change from one ego-centric view of an object to another in four video datasets. We then introduce a new loss function to learn visual and action embeddings by aligning the performed action with the representations of two images extracted from the same clip. This permits the performed actions to structure the latent visual representation. Our experiments show that our method consistently outperforms previous methods on downstream category recognition. In our analysis, we find that the observed improvement is associated with a better viewpoint-wise alignment of different objects from the same category. Overall, our work demonstrates that embodied interactions with objects can improve SSL of object categories.
Authors: Ying Li, Rahul Singh, Tarun Joshi, Agus Sudjianto
Abstract: Recent work in behavioral testing for natural language processing (NLP) models, such as Checklist, is inspired by related paradigms in software engineering testing. They allow evaluation of general linguistic capabilities and domain understanding, hence can help evaluate conceptual soundness and identify model weaknesses. However, a major challenge is the creation of test cases. The current packages rely on semi-automated approach using manual development which requires domain expertise and can be time consuming. This paper introduces an automated approach to develop test cases by exploiting the power of large language models and statistical techniques. It clusters the text representations to carefully construct meaningful groups and then apply prompting techniques to automatically generate Minimal Functionality Tests (MFT). The well-known Amazon Reviews corpus is used to demonstrate our approach. We analyze the behavioral test profiles across four different classification algorithms and discuss the limitations and strengths of those models.
Authors: Thang Doan Viet, Zichong Wang, Minh Nhat Nguyen, Wenbin Zhang
Abstract: Large Language Models (LLMs) have demonstrated remarkable success across various domains but often lack fairness considerations, potentially leading to discriminatory outcomes against marginalized populations. Unlike fairness in traditional machine learning, fairness in LLMs involves unique backgrounds, taxonomies, and fulfillment techniques. This tutorial provides a systematic overview of recent advances in the literature concerning fair LLMs, beginning with real-world case studies to introduce LLMs, followed by an analysis of bias causes therein. The concept of fairness in LLMs is then explored, summarizing the strategies for evaluating bias and the algorithms designed to promote fairness. Additionally, resources for assessing bias in LLMs, including toolkits and datasets, are compiled, and current research challenges and open questions in the field are discussed. The repository is available at \url{https://github.com/LavinWong/Fairness-in-Large-Language-Models}.
URLs: https://github.com/LavinWong/Fairness-in-Large-Language-Models
Authors: Shixun Wu, Yitong Ding, Yujia Zhai, Jinyang Liu, Jiajun Huang, Zizhe Jian, Huangliang Dai, Sheng Di, Bryan M. Wong, Zizhong Chen, Franck Cappello
Abstract: K-means is a widely used algorithm in clustering, however, its efficiency is primarily constrained by the computational cost of distance computing. Existing implementations suffer from suboptimal utilization of computational units and lack resilience against soft errors. To address these challenges, we introduce FT K-means, a high-performance GPU-accelerated implementation of K-means with online fault tolerance. We first present a stepwise optimization strategy that achieves competitive performance compared to NVIDIA's cuML library. We further improve FT K-means with a template-based code generation framework that supports different data types and adapts to different input shapes. A novel warp-level tensor-core error correction scheme is proposed to address the failure of existing fault tolerance methods due to memory asynchronization during copy operations. Our experimental evaluations on NVIDIA T4 GPU and A100 GPU demonstrate that FT K-means without fault tolerance outperforms cuML's K-means implementation, showing a performance increase of 10\%-300\% in scenarios involving irregular data shapes. Moreover, the fault tolerance feature of FT K-means introduces only an overhead of 11\%, maintaining robust performance even with tens of errors injected per second.
Authors: Chao Shen, Wenkang Zhan, Hongyu Sun, Kaiyao Xin, Bo Xu, Zhanguo Wang, Chao Zhao
Abstract: The semiconductor industry has prioritized automating repetitive tasks by closed-loop, autonomous experimentation which enables accelerated optimization of complex multi-step processes. The emergence of machine learning (ML) has ushered in automated process with minimal human intervention. In this work, we develop SemiEpi, a self-driving automation platform capable of executing molecular beam epitaxy (MBE) growth with multi-steps, continuous in-situ monitoring, and on-the-fly feedback control. By integrating standard hardware, homemade software, curve fitting, and multiple ML models, SemiEpi operates autonomously, eliminating the need for extensive expertise in MBE processes to achieve optimal outcomes. The platform actively learns from previous experimental results, identifying favorable conditions and proposing new experiments to achieve the desired results. We standardize and optimize growth for InAs/GaAs quantum dots (QDs) heterostructures to showcase the power of ML-guided multi-step growth. A temperature calibration was implemented to get the initial growth condition, and fine control of the process was executed using ML. Leveraging RHEED movies acquired during the growth, SemiEpi successfully identified and optimized a novel route for multi-step heterostructure growth. This work demonstrates the capabilities of closed-loop, ML-guided systems in addressing challenges in multi-step growth for any device. Our method is critical to achieve repeatable materials growth using commercially scalable tools. Our strategy facilitates the development of a hardware-independent process and enhancing process repeatability and stability, even without exhaustive knowledge of growth parameters.