Authors: Md Abrar Jahin, Saleh Akram Naife, Anik Kumar Saha, M. F. Mridha
Supply chain risk assessment (SCRA) has witnessed a profound evolution through the integration of artificial intelligence (AI) and machine learning (ML) techniques, revolutionizing predictive capabilities and risk mitigation strategies. The significance of this evolution stems from the critical role of robust risk management strategies in ensuring operational resilience and continuity within modern supply chains. Previous reviews have outlined established methodologies but have overlooked emerging AI/ML techniques, leaving a notable research gap in understanding their practical implications within SCRA. This paper conducts a systematic literature review combined with a comprehensive bibliometric analysis. We meticulously examined 1,717 papers and derived key insights from a select group of 48 articles published between 2014 and 2023. The review fills this research gap by addressing pivotal research questions, and exploring existing AI/ML techniques, methodologies, findings, and future trajectories, thereby providing a more encompassing view of the evolving landscape of SCRA. Our study unveils the transformative impact of AI/ML models, such as Random Forest, XGBoost, and hybrids, in substantially enhancing precision within SCRA. It underscores adaptable post-COVID strategies, advocating for resilient contingency plans and aligning with evolving risk landscapes. Significantly, this review surpasses previous examinations by accentuating emerging AI/ML techniques and their practical implications within SCRA. Furthermore, it highlights the contributions through a comprehensive bibliometric analysis, revealing publication trends, influential authors, and highly cited articles.
Authors: Dengxin Huang
This document presents a stock market analysis conducted on a dataset consisting of 750 instances and 16 attributes donated in 2014-10-23. The analysis includes an exploratory data analysis (EDA) section, feature engineering, data preparation, model selection, and insights from the analysis. The Fama French 3-factor model is also utilized in the analysis. The results of the analysis are presented, with linear regression being the best-performing model.
Authors: Pietro Talli, Federico Mason, Federico Chiariotti, Andrea Zanella
In Cyber Physical Systems (CPSs), two groups of actors interact toward the maximization of system performance: the sensors, observing and disseminating the system state, and the actuators, performing physical decisions based on the received information. While it is generally assumed that sensors periodically transmit updates, returning the feedback signal only when necessary, and consequently adapting the physical decisions to the communication policy, can significantly improve the efficiency of the system. In particular, the choice between push-based communication, in which updates are initiated autonomously by the sensors, and pull-based communication, in which they are requested by the actuators, is a key design step. In this work, we propose an analytical model for optimizing push- and pull-based communication in CPSs, observing that the policy optimality coincides with Value of Information (VoI) maximization. Our results also highlight that, despite providing a better optimal solution, implementable push-based communication strategies may underperform even in relatively simple scenarios.
Authors: Shuheng Zhou
In this paper, we consider the problem of partitioning a small data sample of size $n$ drawn from a mixture of $2$ sub-gaussian distributions. In particular, we analyze computational efficient algorithms proposed by the same author, to partition data into two groups approximately according to their population of origin given a small sample. This work is motivated by the application of clustering individuals according to their population of origin using $p$ markers, when the divergence between any two of the populations is small. We build upon the semidefinite relaxation of an integer quadratic program that is formulated essentially as finding the maximum cut on a graph, where edge weights in the cut represent dissimilarity scores between two nodes based on their $p$ features. Here we use $\Delta^2 :=p \gamma$ to denote the $\ell_2^2$ distance between two centers (mean vectors), namely, $\mu^{(1)}$, $\mu^{(2)}$ $\in$ $\mathbb{R}^p$. The goal is to allow a full range of tradeoffs between $n, p, \gamma$ in the sense that partial recovery (success rate $< 100\%$) is feasible once the signal to noise ratio $s^2 := \min\{np \gamma^2, \Delta^2\}$ is lower bounded by a constant. Importantly, we prove that the misclassification error decays exponentially with respect to the SNR $s^2$. This result was introduced earlier without a full proof. We therefore present the full proof in the present work. Finally, for balanced partitions, we consider a variant of the SDP1, and show that the new estimator has a superb debiasing property. This is novel to the best of our knowledge.
Authors: Sauren Gupta, Apoorva Hathi Katharaki, Yifan Xu, Bhaskar Krishnamachari, Rajarshi Gupta
This research explores a relatively unexplored area of predicting cryptocurrency staking rewards, offering potential insights to researchers and investors. We investigate two predictive methodologies: a) a straightforward sliding-window average, and b) linear regression models predicated on historical data. The findings reveal that ETH staking rewards can be forecasted with an RMSE within 0.7% and 1.1% of the mean value for 1-day and 7-day look-aheads respectively, using a 7-day sliding-window average approach. Additionally, we discern diverse prediction accuracies across various cryptocurrencies, including SOL, XTZ, ATOM, and MATIC. Linear regression is identified as superior to the moving-window average for perdicting in the short term for XTZ and ATOM. The results underscore the generally stable and predictable nature of staking rewards for most assets, with MATIC presenting a noteworthy exception.
Authors: Gianvincenzo Alfano, Sergio Greco, Domenico Mandaglio, Francesco Parisi, Reza Shahbazian, Irina Trubitsyna
EXplainable AI has received significant attention in recent years. Machine learning models often operate as black boxes, lacking explainability and transparency while supporting decision-making processes. Local post-hoc explainability queries attempt to answer why individual inputs are classified in a certain way by a given model. While there has been important work on counterfactual explanations, less attention has been devoted to semifactual ones. In this paper, we focus on local post-hoc explainability queries within the semifactual `even-if' thinking and their computational complexity among different classes of models, and show that both linear and tree-based models are strictly more interpretable than neural networks. After this, we introduce a preference-based framework that enables users to personalize explanations based on their preferences, both in the case of semifactuals and counterfactuals, enhancing interpretability and user-centricity. Finally, we explore the complexity of several interpretability problems in the proposed preference-based framework and provide algorithms for polynomial cases.
Authors: Majid Ramezani, Hamed Mohammad-Shahi, Mahshid Daliry, Soroor Rahmani, Amir-Hosein Asghari
In the era of information proliferation, discerning the credibility of news content poses an ever-growing challenge. This paper introduces RELIANCE, a pioneering ensemble learning system designed for robust information and fake news credibility evaluation. Comprising five diverse base models, including Support Vector Machine (SVM), naive Bayes, logistic regression, random forest, and Bidirectional Long Short Term Memory Networks (BiLSTMs), RELIANCE employs an innovative approach to integrate their strengths, harnessing the collective intelligence of the ensemble for enhanced accuracy. Experiments demonstrate the superiority of RELIANCE over individual models, indicating its efficacy in distinguishing between credible and non-credible information sources. RELIANCE, also surpasses baseline models in information and news credibility assessment, establishing itself as an effective solution for evaluating the reliability of information sources.
Authors: David Chhan, Ellen Novoseller, Vernon J. Lawhern
Preference-based reinforcement learning (RL) provides a framework to train agents using human feedback through pairwise preferences over pairs of behaviors, enabling agents to learn desired behaviors when it is difficult to specify a numerical reward function. While this paradigm leverages human feedback, it currently treats the feedback as given by a single human user. Meanwhile, incorporating preference feedback from crowds (i.e. ensembles of users) in a robust manner remains a challenge, and the problem of training RL agents using feedback from multiple human users remains understudied. In this work, we introduce Crowd-PrefRL, a framework for performing preference-based RL leveraging feedback from crowds. This work demonstrates the viability of learning reward functions from preference feedback provided by crowds of unknown expertise and reliability. Crowd-PrefRL not only robustly aggregates the crowd preference feedback, but also estimates the reliability of each user within the crowd using only the (noisy) crowdsourced preference comparisons. Most importantly, we show that agents trained with Crowd-PrefRL outperform agents trained with majority-vote preferences or preferences from any individual user in most cases, especially when the spread of user error rates among the crowd is large. Results further suggest that our method can identify minority viewpoints within the crowd.
Authors: Bhavika Sachdeva, Harshita Rathee, Sristi, Arun Sharma, Witold Wydmański
This review explores machine unlearning (MUL) in recommendation systems, addressing adaptability, personalization, privacy, and bias challenges. Unlike traditional models, MUL dynamically adjusts system knowledge based on shifts in user preferences and ethical considerations. The paper critically examines MUL's basics, real-world applications, and challenges like algorithmic transparency. It sifts through literature, offering insights into how MUL could transform recommendations, discussing user trust, and suggesting paths for future research in responsible and user-focused artificial intelligence (AI). The document guides researchers through challenges involving the trade-off between personalization and privacy, encouraging contributions to meet practical demands for targeted data removal. Emphasizing MUL's role in secure and adaptive machine learning, the paper proposes ways to push its boundaries. The novelty of this paper lies in its exploration of the limitations of the methods, which highlights exciting prospects for advancing the field.
Authors: Giacomo Delcaro, Federico Dettù, Simone Formentin, Sergio Matteo Savaresi
State-of-the-art vehicle dynamics estimation techniques usually share one common drawback: each variable to estimate is computed with an independent, simplified filtering module. These modules run in parallel and need to be calibrated separately. To solve this issue, a unified Twin-in-the-Loop (TiL) Observer architecture has recently been proposed: the classical simplified control-oriented vehicle model in the estimators is replaced by a full-fledged vehicle simulator, or digital twin (DT). The states of the DT are corrected in real time with a linear time invariant output error law. Since the simulator is a black-box, no explicit analytical formulation is available, hence classical filter tuning techniques cannot be used. Due to this reason, Bayesian Optimization will be used to solve a data-driven optimization problem to tune the filter. Due to the complexity of the DT, the optimization problem is high-dimensional. This paper aims to find a procedure to tune the high-complexity observer by lowering its dimensionality. In particular, in this work we will analyze both a supervised and an unsupervised learning approach. The strategies have been validated for speed and yaw-rate estimation on real-world data.
Authors: Ali Baheri, and Mykel J. Kochenderfer
This paper explores the integration of optimal transport (OT) theory with multi-agent reinforcement learning (MARL). This integration uses OT to handle distributions and transportation problems to enhance the efficiency, coordination, and adaptability of MARL. There are five key areas where OT can impact MARL: (1) policy alignment, where OT's Wasserstein metric is used to align divergent agent strategies towards unified goals; (2) distributed resource management, employing OT to optimize resource allocation among agents; (3) addressing non-stationarity, using OT to adapt to dynamic environmental shifts; (4) scalable multi-agent learning, harnessing OT for decomposing large-scale learning objectives into manageable tasks; and (5) enhancing energy efficiency, applying OT principles to develop sustainable MARL systems. This paper articulates how the synergy between OT and MARL can address scalability issues, optimize resource distribution, align agent policies in cooperative environments, and ensure adaptability in dynamically changing conditions.
Authors: Xiaolong Huang, Qiankun Li, Xueran Li, Xuesong Gao
Visual fine-tuning has garnered significant attention with the rise of pre-trained vision models. The current prevailing method, full fine-tuning, suffers from the issue of knowledge forgetting as it focuses solely on fitting the downstream training set. In this paper, we propose a novel weight rollback-based fine-tuning method called OLOR (One step Learning, One step Review). OLOR combines fine-tuning with optimizers, incorporating a weight rollback term into the weight update term at each step. This ensures consistency in the weight range of upstream and downstream models, effectively mitigating knowledge forgetting and enhancing fine-tuning performance. In addition, a layer-wise penalty is presented to employ penalty decay and the diversified decay rate to adjust the weight rollback levels of layers for adapting varying downstream tasks. Through extensive experiments on various tasks such as image classification, object detection, semantic segmentation, and instance segmentation, we demonstrate the general applicability and state-of-the-art performance of our proposed OLOR. Code is available at https://github.com/rainbow-xiao/OLOR-AAAI-2024.
Authors: Danzel Serrano, Jakub Szymkowiak, Przemyslaw Musialski
Recently proposed methods for implicitly representing signals such as images, scenes, or geometries using coordinate-based neural network architectures often do not leverage the choice of activation functions, or do so only to a limited extent. In this paper, we introduce the Hyperbolic Oscillation function (HOSC), a novel activation function with a controllable sharpness parameter. Unlike any previous activations, HOSC has been specifically designed to better capture sudden changes in the input signal, and hence sharp or acute features of the underlying data, as well as smooth low-frequency transitions. Due to its simplicity and modularity, HOSC offers a plug-and-play functionality that can be easily incorporated into any existing method employing a neural network as a way of implicitly representing a signal. We benchmark HOSC against other popular activations in an array of general tasks, empirically showing an improvement in the quality of obtained representations, provide the mathematical motivation behind the efficacy of HOSC, and discuss its limitations.
Authors: Paula Mercurio, Di Liu
In order to efficiently explore the chemical space of all possible small molecules, a common approach is to compress the dimension of the system to facilitate downstream machine learning tasks. Towards this end, we present a data driven approach for clustering potential energy landscapes of molecular structures by applying recently developed Network Embedding techniques, to obtain latent variables defined through the embedding function. To scale up the method, we also incorporate an entropy sensitive adaptive scheme for hierarchical sampling of the energy landscape, based on Metadynamics and Transition Path Theory. By taking into account the kinetic information implied by a system's energy landscape, we are able to interpret dynamical node-node relationships in reduced dimensions. We demonstrate the framework through Lennard-Jones (LJ) clusters and a human DNA sequence.
Authors: Chuxiong Sun, Zehua Zang, Jiabao Li, Jiangmeng Li, Xiao Xu, Rui Wang, Changwen Zheng
Communication stands as a potent mechanism to harmonize the behaviors of multiple agents. However, existing works primarily concentrate on broadcast communication, which not only lacks practicality, but also leads to information redundancy. This surplus, one-fits-all information could adversely impact the communication efficiency. Furthermore, existing works often resort to basic mechanisms to integrate observed and received information, impairing the learning process. To tackle these difficulties, we propose Targeted and Trusted Multi-Agent Communication (T2MAC), a straightforward yet effective method that enables agents to learn selective engagement and evidence-driven integration. With T2MAC, agents have the capability to craft individualized messages, pinpoint ideal communication windows, and engage with reliable partners, thereby refining communication efficiency. Following the reception of messages, the agents integrate information observed and received from different sources at an evidence level. This process enables agents to collectively use evidence garnered from multiple perspectives, fostering trusted and cooperative behaviors. We evaluate our method on a diverse set of cooperative multi-agent tasks, with varying difficulties, involving different scales and ranging from Hallway, MPE to SMAC. The experiments indicate that the proposed model not only surpasses the state-of-the-art methods in terms of cooperative performance and communication efficiency, but also exhibits impressive generalization.
Authors: Joohwan Ko, Kyurae Kim, Woo Chang Kim, Jacob R. Gardner
Variational families with full-rank covariance approximations are known not to work well in black-box variational inference (BBVI), both empirically and theoretically. In fact, recent computational complexity results for BBVI have established that full-rank variational families scale poorly with the dimensionality of the problem compared to e.g. mean field families. This is particularly critical to hierarchical Bayesian models with local variables; their dimensionality increases with the size of the datasets. Consequently, one gets an iteration complexity with an explicit $\mathcal{O}(N^2)$ dependence on the dataset size $N$. In this paper, we explore a theoretical middle ground between mean-field variational families and full-rank families: structured variational families. We rigorously prove that certain scale matrix structures can achieve a better iteration complexity of $\mathcal{O}(N)$, implying better scaling with respect to $N$. We empirically verify our theoretical results on large-scale hierarchical models.
Authors: Ben Aoki-Sherwood, Catherine Bregou, David Liben-Nowell, Kiran Tomlinson, Thomas Zeng
A common theory of choice posits that individuals make choices in a two-step process, first selecting some subset of the alternatives to consider before making a selection from the resulting consideration set. However, inferring unobserved consideration sets (or item consideration probabilities) in this "consider then choose" setting poses significant challenges, because even simple models of consideration with strong independence assumptions are not identifiable, even if item utilities are known. We consider a natural extension of consider-then-choose models to a top-$k$ ranking setting, where we assume rankings are constructed according to a Plackett-Luce model after sampling a consideration set. While item consideration probabilities remain non-identified in this setting, we prove that knowledge of item utilities allows us to infer bounds on the relative sizes of consideration probabilities. Additionally, given a condition on the expected consideration set size, we derive absolute upper and lower bounds on item consideration probabilities. We also provide algorithms to tighten those bounds on consideration probabilities by propagating inferred constraints. Thus, we show that we can learn useful information about consideration probabilities despite not being able to identify them precisely. We demonstrate our methods on a ranking dataset from a psychology experiment with two different ranking tasks (one with fixed consideration sets and one with unknown consideration sets). This combination of data allows us to estimate utilities and then learn about unknown consideration probabilities using our bounds.
Authors: Ismail Rasim Ulgen, Zongyang Du, Carlos Busso, Berrak Sisman
Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assumed that emotion information is indirectly embedded within speaker embeddings, leading to their under-utilization. Our study reveals a direct and useful link between emotion and state-of-the-art speaker embeddings in the form of intra-speaker clusters. By conducting a thorough clustering analysis, we demonstrate that emotion information can be readily extracted from speaker embeddings. In order to leverage this information, we introduce a novel contrastive pretraining approach applied to emotion-unlabeled data for speech emotion recognition. The proposed approach involves the sampling of positive and the negative examples based on the intra-speaker clusters of speaker embeddings. The proposed strategy, which leverages extensive emotion-unlabeled data, leads to a significant improvement in SER performance, whether employed as a standalone pretraining task or integrated into a multi-task pretraining setting.
Authors: Youming Tao, Cheng-Long Wang, Miao Pan, Dongxiao Yu, Xiuzhen Cheng, Di Wang
We study federated unlearning, a novel problem to eliminate the impact of specific clients or data points on the global model learned via federated learning (FL). This problem is driven by the right to be forgotten and the privacy challenges in FL. We introduce a new framework for exact federated unlearning that meets two essential criteria: \textit{communication efficiency} and \textit{exact unlearning provability}. To our knowledge, this is the first work to tackle both aspects coherently. We start by giving a rigorous definition of \textit{exact} federated unlearning, which guarantees that the unlearned model is statistically indistinguishable from the one trained without the deleted data. We then pinpoint the key property that enables fast exact federated unlearning: total variation (TV) stability, which measures the sensitivity of the model parameters to slight changes in the dataset. Leveraging this insight, we develop a TV-stable FL algorithm called \texttt{FATS}, which modifies the classical \texttt{\underline{F}ed\underline{A}vg} algorithm for \underline{T}V \underline{S}tability and employs local SGD with periodic averaging to lower the communication round. We also design efficient unlearning algorithms for \texttt{FATS} under two settings: client-level and sample-level unlearning. We provide theoretical guarantees for our learning and unlearning algorithms, proving that they achieve exact federated unlearning with reasonable convergence rates for both the original and unlearned models. We empirically validate our framework on 6 benchmark datasets, and show its superiority over state-of-the-art methods in terms of accuracy, communication cost, computation cost, and unlearning efficacy.
Authors: Shashwat Khandelwal, Shreejith Shanker
Vehicles today comprise intelligent systems like connected autonomous driving and advanced driving assistance systems (ADAS) to enhance the driving experience, which is enabled through increased connectivity to infrastructure and fusion of information from different sensing modes. However, the rising connectivity coupled with the legacy network architecture within vehicles can be exploited for launching active and passive attacks on critical vehicle systems and directly affecting the safety of passengers. Machine learning-based intrusion detection models have been shown to successfully detect multiple targeted attack vectors in recent literature, whose deployments are enabled through quantised neural networks targeting low-power platforms. Multiple models are often required to simultaneously detect multiple attack vectors, increasing the area, (resource) cost, and energy consumption. In this paper, we present a case for utilising custom-quantised MLP's (CQMLP) as a multi-class classification model, capable of detecting multiple attacks from the benign flow of controller area network (CAN) messages. The specific quantisation and neural architecture are determined through a joint design space exploration, resulting in our choice of the 2-bit precision and the n-layer MLP. Our 2-bit version is trained using Brevitas and optimised as a dataflow hardware model through the FINN toolflow from AMD/Xilinx, targeting an XCZU7EV device. We show that the 2-bit CQMLP model, when integrated as the IDS, can detect malicious attack messages (DoS, fuzzing, and spoofing attack) with a very high accuracy of 99.9%, on par with the state-of-the-art methods in the literature. Furthermore, the dataflow model can perform line rate detection at a latency of 0.11 ms from message reception while consuming 0.23 mJ/inference, making it ideally suited for integration with an ECU in critical CAN networks.
Authors: Minkai Xu, Jiaqi Han, Aaron Lou, Jean Kossaifi, Arvind Ramanathan, Kamyar Azizzadenesheli, Jure Leskovec, Stefano Ermon, Anima Anandkumar
Modeling the complex three-dimensional (3D) dynamics of relational systems is an important problem in the natural sciences, with applications ranging from molecular simulations to particle mechanics. Machine learning methods have achieved good success by learning graph neural networks to model spatial interactions. However, these approaches do not faithfully capture temporal correlations since they only model next-step predictions. In this work, we propose Equivariant Graph Neural Operator (EGNO), a novel and principled method that directly models dynamics as trajectories instead of just next-step prediction. Different from existing methods, EGNO explicitly learns the temporal evolution of 3D dynamics where we formulate the dynamics as a function over time and learn neural operators to approximate it. To capture the temporal correlations while keeping the intrinsic SE(3)-equivariance, we develop equivariant temporal convolutions parameterized in the Fourier space and build EGNO by stacking the Fourier layers over equivariant networks. EGNO is the first operator learning framework that is capable of modeling solution dynamics functions over time while retaining 3D equivariance. Comprehensive experiments in multiple domains, including particle simulations, human motion capture, and molecular dynamics, demonstrate the significantly superior performance of EGNO against existing methods, thanks to the equivariant temporal modeling.
Authors: Karol Capała, Paulina Tworek, Jose Sousa
The applicability of widely adopted machine learning (ML) methods to classification is circumscribed by the imperatives of explicability and uncertainty, particularly evident in domains such as healthcare, behavioural sciences, and finances, wherein accountability assumes priority. Recently, Small and Incomplete Dataset Analyser (SaNDA) has been proposed to enhance the ability to perform classification in such domains, by developing a data abstraction protocol using a ROC curve-based method. This paper focuses on column-wise data transformations called abstractions, which are crucial for SaNDA's classification process and explores alternative abstractions protocols, such as constant binning and quantiles. The best-performing methods have been compared against Random Forest as a baseline for explainable methods. The results suggests that SaNDA can be a viable substitute for Random Forest when data is incomplete, even with minimal missing values. It consistently maintains high accuracy even when half of the dataset is missing, unlike Random Forest which experiences a significant decline in accuracy under similar conditions.
Authors: Moshe Eliasof, Eldad Haber, Eran Treister, Carola-Bibiane Schönlieb
Graph Neural Networks (GNNs) have demonstrated remarkable success in modeling complex relationships in graph-structured data. A recent innovation in this field is the family of Differential Equation-Inspired Graph Neural Networks (DE-GNNs), which leverage principles from continuous dynamical systems to model information flow on graphs with built-in properties such as feature smoothing or preservation. However, existing DE-GNNs rely on first or second-order temporal dependencies. In this paper, we propose a neural extension to those pre-defined temporal dependencies. We show that our model, called TDE-GNN, can capture a wide range of temporal dynamics that go beyond typical first or second-order methods, and provide use cases where existing temporal models are challenged. We demonstrate the benefit of learning the temporal dependencies using our method rather than using pre-defined temporal dynamics on several graph benchmarks.
Authors: Adel Javanmard, Lin Chen, Vahab Mirrokni, Ashwinkumar Badanidiyuru, Gang Fu
Due to the rise of privacy concerns, in many practical applications the training data is aggregated before being shared with the learner, in order to protect privacy of users' sensitive responses. In an aggregate learning framework, the dataset is grouped into bags of samples, where each bag is available only with an aggregate response, providing a summary of individuals' responses in that bag. In this paper, we study two natural loss functions for learning from aggregate responses: bag-level loss and the instance-level loss. In the former, the model is learnt by minimizing a loss between aggregate responses and aggregate model predictions, while in the latter the model aims to fit individual predictions to the aggregate responses. In this work, we show that the instance-level loss can be perceived as a regularized form of the bag-level loss. This observation lets us compare the two approaches with respect to bias and variance of the resulting estimators, and introduce a novel interpolating estimator which combines the two approaches. For linear regression tasks, we provide a precise characterization of the risk of the interpolating estimator in an asymptotic regime where the size of the training set grows in proportion to the features dimension. Our analysis allows us to theoretically understand the effect of different factors, such as bag size on the model prediction risk. In addition, we propose a mechanism for differentially private learning from aggregate responses and derive the optimal bag size in terms of prediction risk-privacy trade-off. We also carry out thorough experiments to corroborate our theory and show the efficacy of the interpolating estimator.
Authors: Cong Lei, Yuxuan Du, Peng Mi, Jun Yu, Tongliang Liu
Quantum kernels hold great promise for offering computational advantages over classical learners, with the effectiveness of these kernels closely tied to the design of the quantum feature map. However, the challenge of designing effective quantum feature maps for real-world datasets, particularly in the absence of sufficient prior information, remains a significant obstacle. In this study, we present a data-driven approach that automates the design of problem-specific quantum feature maps. Our approach leverages feature-selection techniques to handle high-dimensional data on near-term quantum machines with limited qubits, and incorporates a deep neural predictor to efficiently evaluate the performance of various candidate quantum kernels. Through extensive numerical simulations on different datasets, we demonstrate the superiority of our proposal over prior methods, especially for the capability of eliminating the kernel concentration issue and identifying the feature map with prediction advantages. Our work not only unlocks the potential of quantum kernels for enhancing real-world tasks but also highlights the substantial role of deep learning in advancing quantum machine learning.
Authors: Jiachen T. Wang, Prateek Mittal, Ruoxi Jia
This work aims to address an open problem in data valuation literature concerning the efficient computation of Data Shapley for weighted $K$ nearest neighbor algorithm (WKNN-Shapley). By considering the accuracy of hard-label KNN with discretized weights as the utility function, we reframe the computation of WKNN-Shapley into a counting problem and introduce a quadratic-time algorithm, presenting a notable improvement from $O(N^K)$, the best result from existing literature. We develop a deterministic approximation algorithm that further improves computational efficiency while maintaining the key fairness properties of the Shapley value. Through extensive experiments, we demonstrate WKNN-Shapley's computational efficiency and its superior performance in discerning data quality compared to its unweighted counterpart.
Authors: Triet H. M. Le, Xiaoning Du, M. Ali Babar
Collecting relevant and high-quality data is integral to the development of effective Software Vulnerability (SV) prediction models. Most of the current SV datasets rely on SV-fixing commits to extract vulnerable functions and lines. However, none of these datasets have considered latent SVs existing between the introduction and fix of the collected SVs. There is also little known about the usefulness of these latent SVs for SV prediction. To bridge these gaps, we conduct a large-scale study on the latent vulnerable functions in two commonly used SV datasets and their utilization for function-level and line-level SV predictions. Leveraging the state-of-the-art SZZ algorithm, we identify more than 100k latent vulnerable functions in the studied datasets. We find that these latent functions can increase the number of SVs by 4x on average and correct up to 5k mislabeled functions, yet they have a noise level of around 6%. Despite the noise, we show that the state-of-the-art SV prediction model can significantly benefit from such latent SVs. The improvements are up to 24.5% in the performance (F1-Score) of function-level SV predictions and up to 67% in the effectiveness of localizing vulnerable lines. Overall, our study presents the first promising step toward the use of latent SVs to improve the quality of SV datasets and enhance the performance of SV prediction tasks.
Unsupervised video object learning seeks to decompose video scenes into structural object representations without any supervision from depth, optical flow, or segmentation. We present VONet, an innovative approach that is inspired by MONet. While utilizing a U-Net architecture, VONet employs an efficient and effective parallel attention inference process, generating attention masks for all slots simultaneously. Additionally, to enhance the temporal consistency of each mask across consecutive video frames, VONet develops an object-wise sequential VAE framework. The integration of these innovative encoder-side techniques, in conjunction with an expressive transformer-based decoder, establishes VONet as the leading unsupervised method for object learning across five MOVI datasets, encompassing videos of diverse complexities. Code is available at https://github.com/hnyu/vonet.
Authors: Maryam Khalid, Elizabeth B. Klerman, Andrew W. Mchill, Andrew J. K. Phillips, Akane Sano
Sleep behavior significantly impacts health and acts as an indicator of physical and mental well-being. Monitoring and predicting sleep behavior with ubiquitous sensors may therefore assist in both sleep management and tracking of related health conditions. While sleep behavior depends on, and is reflected in the physiology of a person, it is also impacted by external factors such as digital media usage, social network contagion, and the surrounding weather. In this work, we propose SPAND (Sleep Prediction Architecture using Network Dynamics), a system that exploits social contagion in sleep behavior through graph networks and integrates it with physiological and phone data extracted from ubiquitous mobile and wearable devices for predicting next-day sleep labels about sleep duration. Our architecture overcomes the limitations of large-scale graphs containing connections irrelevant to sleep behavior by devising an attention mechanism. The extensive experimental evaluation highlights the improvement provided by incorporating social networks in the model. Additionally, we conduct robustness analysis to demonstrate the system's performance in real-life conditions. The outcomes affirm the stability of SPAND against perturbations in input data. Further analyses emphasize the significance of network topology in prediction performance revealing that users with higher eigenvalue centrality are more vulnerable to data perturbations.
Authors: Marwan Dhuheir, Aiman Erbad, Ala Al-Fuqaha
In the past decade, Unmanned Aerial Vehicles (UAVs) have grabbed the attention of researchers in academia and industry for their potential use in critical emergency applications, such as providing wireless services to ground users and collecting data from areas affected by disasters, due to their advantages in terms of maneuverability and movement flexibility. The UAVs' limited resources, energy budget, and strict mission completion time have posed challenges in adopting UAVs for these applications. Our system model considers a UAV swarm that navigates an area collecting data from ground IoT devices focusing on providing better service for strategic locations and allowing UAVs to join and leave the swarm (e.g., for recharging) in a dynamic way. In this work, we introduce an optimization model with the aim of minimizing the total energy consumption and provide the optimal path planning of UAVs under the constraints of minimum completion time and transmit power. The formulated optimization is NP-hard making it not applicable for real-time decision making. Therefore, we introduce a light-weight meta-reinforcement learning solution that can also cope with sudden changes in the environment through fast convergence. We conduct extensive simulations and compare our approach to three state-of-the-art learning models. Our simulation results prove that our introduced approach is better than the three state-of-the-art algorithms in providing coverage to strategic locations with fast convergence.
Authors: Dimitrios Sinodinos, Narges Armanfard
Multitask learning (MTL) has gained prominence for its ability to jointly predict multiple tasks, achieving better per-task performance while using fewer per-task model parameters than single-task learning. More recently, decoder-focused architectures have considerably improved multitask performance by refining task predictions using the features of other related tasks. However, most of these refinement methods fail to simultaneously capture local and global task-specific representations, as well as cross-task patterns in a parameter-efficient manner. In this paper, we introduce the Efficient Multitask Affinity Learning Network (EMA-Net), which is a lightweight framework that enhances the task refinement capabilities of multitask networks. EMA-Net adeptly captures local, global, and cross-task interactions using our novel Cross-Task Affinity Learning (CTAL) module. The key innovation of CTAL lies in its ability to manipulate task affinity matrices in a manner that is optimally suited to apply parameter-efficient grouped convolutions without worrying about information loss. Our results show that we achieve state-of-the-art MTL performance for CNN-based decoder-focused models while using substantially fewer model parameters. Our code is publicly available at https://github.com/Armanfard-Lab/EMA-Net.
Authors: Hangsheng Zhang, Jiqiang Liu, Jinsong Dong
Ensemble defenses, are widely employed in various security-related applications to enhance model performance and robustness. The widespread adoption of these techniques also raises many questions: Are general ensembles defenses guaranteed to be more robust than individuals? Will stronger adaptive attacks defeat existing ensemble defense strategies as the cybersecurity arms race progresses? Can ensemble defenses achieve adversarial robustness to different types of attacks simultaneously and resist the continually adjusted adaptive attacks? Unfortunately, these critical questions remain unresolved as there are no platforms for comprehensive evaluation of ensemble adversarial attacks and defenses in the cybersecurity domain. In this paper, we propose a general Cybersecurity Adversarial Robustness Evaluation (CARE) platform aiming to bridge this gap.
Authors: Yuta Kawakami, Manabu Kuroki, Jin Tian
There has been considerable recent interest in estimating heterogeneous causal effects. In this paper, we introduce conditional average partial causal effects (CAPCE) to reveal the heterogeneity of causal effects with continuous treatment. We provide conditions for identifying CAPCE in an instrumental variable setting. We develop three families of CAPCE estimators: sieve, parametric, and reproducing kernel Hilbert space (RKHS)-based, and analyze their statistical properties. We illustrate the proposed CAPCE estimators on synthetic and real-world data.
Authors: Georgios Ioannides, Aman Chadha, Aaron Elkins
We propose the Multi-Head Gaussian Adaptive Attention Mechanism (GAAM), a novel probabilistic attention framework, and the Gaussian Adaptive Transformer (GAT), designed to enhance information aggregation across multiple modalities, including Speech, Text and Vision. GAAM integrates learnable mean and variance into its attention mechanism, implemented in a Multi-Headed framework enabling it to collectively model any Probability Distribution for dynamic recalibration of feature significance. This method demonstrates significant improvements, especially with highly non-stationary data, surpassing the state-of-the-art attention techniques in model performance (up to approximately +20% in accuracy) by identifying key elements within the feature space. GAAM's compatibility with dot-product-based attention models and relatively low number of parameters showcases its adaptability and potential to boost existing attention frameworks. Empirically, GAAM exhibits superior adaptability and efficacy across a diverse range of tasks, including emotion recognition in speech, image classification, and text classification, thereby establishing its robustness and versatility in handling multi-modal data. Furthermore, we introduce the Importance Factor (IF), a new learning-based metric that enhances the explainability of models trained with GAAM-based methods. Overall, GAAM represents an advancement towards development of better performing and more explainable attention models across multiple modalities.
Authors: Haiyang Zhang, Qiuyi Chen, Yuanjie Zou, Yushan Pan, Jia Wang, Mark Stevenson
Document set expansion aims to identify relevant documents from a large collection based on a small set of documents that are on a fine-grained topic. Previous work shows that PU learning is a promising method for this task. However, some serious issues remain unresolved, i.e. typical challenges that PU methods suffer such as unknown class prior and imbalanced data, and the need for transductive experimental settings. In this paper, we propose a novel PU learning framework based on density estimation, called puDE, that can handle the above issues. The advantage of puDE is that it neither constrained to the SCAR assumption and nor require any class prior knowledge. We demonstrate the effectiveness of the proposed method using a series of real-world datasets and conclude that our method is a better alternative for the DSE task.
Authors: Nicolás Ayobi, Santiago Rodríguez, Alejandra Pérez, Isabela Hernández, Nicolás Aparicio, Eugénie Dessevres, Sebastián Peña, Jessica Santander, Juan Ignacio Caicedo, Nicolás Fernández, Pablo Arbeláez
This paper presents the Holistic and Multi-Granular Surgical Scene Understanding of Prostatectomies (GraSP) dataset, a curated benchmark that models surgical scene understanding as a hierarchy of complementary tasks with varying levels of granularity. Our approach enables a multi-level comprehension of surgical activities, encompassing long-term tasks such as surgical phases and steps recognition and short-term tasks including surgical instrument segmentation and atomic visual actions detection. To exploit our proposed benchmark, we introduce the Transformers for Actions, Phases, Steps, and Instrument Segmentation (TAPIS) model, a general architecture that combines a global video feature extractor with localized region proposals from an instrument segmentation model to tackle the multi-granularity of our benchmark. Through extensive experimentation, we demonstrate the impact of including segmentation annotations in short-term recognition tasks, highlight the varying granularity requirements of each task, and establish TAPIS's superiority over previously proposed baselines and conventional CNN-based models. Additionally, we validate the robustness of our method across multiple public benchmarks, confirming the reliability and applicability of our dataset. This work represents a significant step forward in Endoscopic Vision, offering a novel and comprehensive framework for future research towards a holistic understanding of surgical procedures.
Authors: Shyam Venkatasubramanian, Sandeep Gogineni, Bosung Kang, Ali Pezeshki, Muralidhar Rangaswamy, Vahid Tarokh
In modern radar systems, precise target localization using azimuth and velocity estimation is paramount. Traditional unbiased estimation methods have leveraged gradient descent algorithms to reach the theoretical limits of the Cram\'er Rao Bound (CRB) for the error of the parameter estimates. In this study, we present a data-driven neural network approach that outperforms these traditional techniques, demonstrating improved accuracies in target azimuth and velocity estimation. Using a representative simulated scenario, we show that our proposed neural network model consistently achieves improved parameter estimates due to its inherently biased nature, yielding a diminished mean squared error (MSE). Our findings underscore the potential of employing deep learning methods in radar systems, paving the way for more accurate localization in cluttered and dynamic environments.
Authors: Randall Balestriero, Yann LeCun
One fruitful formulation of Deep Networks (DNs) enabling their theoretical study and providing practical guidelines to practitioners relies on Piecewise Affine Splines. In that realm, a DN's input-mapping is expressed as per-region affine mapping where those regions are implicitly determined by the model's architecture and form a partition of their input space. That partition -- which is involved in all the results spanned from this line of research -- has so far only been computed on $2/3$-dimensional slices of the DN's input space or estimated by random sampling. In this paper, we provide the first parallel algorithm that does exact enumeration of the DN's partition regions. The proposed algorithm enables one to finally assess the closeness of the commonly employed approximations methods, e.g. based on random sampling of the DN input space. One of our key finding is that if one is only interested in regions with ``large'' volume, then uniform sampling of the space is highly efficient, but that if one is also interested in discovering the ``small'' regions of the partition, then uniform sampling is exponentially costly with the DN's input space dimension. On the other hand, our proposed method has complexity scaling linearly with input dimension and the number of regions.
Authors: Soham Shanbhag, Dong Eui Chang
In this paper, a machine learning based observer for systems evolving on manifolds is designed such that the state of the observer is restricted to the Lie group on which the system evolves. Conventional techniques involving machine learning based observers on systems evolving on Lie groups involve designing charts for the Lie group, training a machine learning based observer for each chart, and switching between the trained models based on the state of the system. We propose a novel deep learning based technique whose predictions are restricted to a measure 0 subset of Euclidean space without using charts. Using this network, we design an observer ensuring that the state of the observer is restricted to the Lie group, and predicting the state using only one trained algorithm. The deep learning network predicts an ``error term'' on the Lie algebra of the Lie group, uses the map from the Lie algebra to the group, and uses the group action and the present state to estimate the state at the next epoch. This model being purely data driven does not require the model of the system. The proposed algorithm provides a novel framework for constraining the output of machine learning networks to a measure 0 subset of a Euclidean space without chart specific training and without requiring switching. We show the validity of this method using Monte Carlo simulations performed of the rigid body rotation and translation system.
Authors: Paul M. Baggenstoss, Kevin Wilkinghoff, Felix Govaers, Frank Kurth
The projected belief network (PBN) is a generative stochastic network with tractable likelihood function based on a feed-forward neural network (FFNN). The generative function operates by "backing up" through the FFNN. The PBN is two networks in one, a FFNN that operates in the forward direction, and a generative network that operates in the backward direction. Both networks co-exist based on the same parameter set, have their own cost functions, and can be separately or jointly trained. The PBN therefore has the potential to possess the best qualities of both discriminative and generative classifiers. To realize this potential, a separate PBN is trained on each class, maximizing the generative likelihood function for the given class, while minimizing the discriminative cost for the FFNN against "all other classes". This technique, called discriminative alignment (PBN-DA), aligns the contours of the likelihood function to the decision boundaries and attains vastly improved classification performance, rivaling that of state of the art discriminative networks. The method may be further improved using a hidden Markov model (HMM) as a component of the PBN, called PBN-DA-HMM. This paper provides a comprehensive treatment of PBN, PBN-DA, and PBN-DA-HMM. In addition, the results of two new classification experiments are provided. The first experiment uses air-acoustic events, and the second uses underwater acoustic data consisting of marine mammal calls. In both experiments, PBN-DA-HMM attains comparable or better performance as a state of the art CNN, and attain a factor of two error reduction when combined with the CNN.
Authors: Sami Alabed, Bart Chrzaszcz, Juliana Franco, Dominik Grewe, Dougal Maclaurin, James Molloy, Tom Natan, Tamara Norman, Xiaoyue Pan, Adam Paszke, Norman A. Rink, Michael Schaarschmidt, Timur Sitdikov, Agnieszka Swietlik, Dimitrios Vytiniotis, Joel Wee
Training of modern large neural networks (NN) requires a combination of parallelization strategies encompassing data, model, or optimizer sharding. When strategies increase in complexity, it becomes necessary for partitioning tools to be 1) expressive, allowing the composition of simpler strategies, and 2) predictable to estimate performance analytically. We present PartIR, our design for a NN partitioning system. PartIR is focused on an incremental approach to rewriting and is hardware-and-runtime agnostic. We present a simple but powerful API for composing sharding strategies and a simulator to validate them. The process is driven by high-level programmer-issued partitioning tactics, which can be both manual and automatic. Importantly, the tactics are specified separately from the model code, making them easy to change. We evaluate PartIR on several different models to demonstrate its predictability, expressibility, and ability to reach peak performance..
Authors: Yuval Lev Lubarsky, Jan Tönshoff, Martin Grohe, Benny Kimelfeld
Machinery for data analysis often requires a numeric representation of the input. Towards that, a common practice is to embed components of structured data into a high-dimensional vector space. We study the embedding of the tuples of a relational database, where existing techniques are often based on optimization tasks over a collection of random walks from the database. The focus of this paper is on the recent FoRWaRD algorithm that is designed for dynamic databases, where walks are sampled by following foreign keys between tuples. Importantly, different walks have different schemas, or "walk schemes", that are derived by listing the relations and attributes along the walk. Also importantly, different walk schemes describe relationships of different natures in the database. We show that by focusing on a few informative walk schemes, we can obtain tuple embedding significantly faster, while retaining the quality. We define the problem of scheme selection for tuple embedding, devise several approaches and strategies for scheme selection, and conduct a thorough empirical study of the performance over a collection of downstream tasks. Our results confirm that with effective strategies for scheme selection, we can obtain high-quality embeddings considerably (e.g., three times) faster, preserve the extensibility to newly inserted tuples, and even achieve an increase in the precision of some tasks.
Authors: Ece S. Koksal, Erdal Aydin
Constructing first principles models is a challenging task for nonlinear and complex systems such as a wastewater treatment unit. In recent years, data-driven models are widely used to overcome the complexity. However, they often suffer from issues such as missing, low quality or noisy data. Transfer learning is a solution for this issue where knowledge from another task is transferred to target one to increase the prediction performance. In this work, the objective is increasing the prediction performance of an industrial wastewater treatment plant by transferring the knowledge of (i) an open-source simulation model that captures the underlying physics of the process, albeit with dissimilarities to the target plant, (ii) another industrial plant characterized by noisy and limited data but located in the same refinery, and (iii) the model in (ii) and making the objective function of the training problem physics informed where the physics information derived from the open-source model in (ii). The results have shown that test and validation performance are improved up to 27% and 59%, respectively.
Authors: Chen Liu, Shibo He, Haoyu Liu, Shizhong Li
Time series anomaly detection (TSAD) plays a vital role in various domains such as healthcare, networks, and industry. Considering labels are crucial for detection but difficult to obtain, we turn to TSAD with inexact supervision: only series-level labels are provided during the training phase, while point-level anomalies are predicted during the testing phase. Previous works follow a traditional multi-instance learning (MIL) approach, which focuses on encouraging high anomaly scores at individual time steps. However, time series anomalies are not only limited to individual point anomalies, they can also be collective anomalies, typically exhibiting abnormal patterns over subsequences. To address the challenge of collective anomalies, in this paper, we propose a tree-based MIL framework (TreeMIL). We first adopt an N-ary tree structure to divide the entire series into multiple nodes, where nodes at different levels represent subsequences with different lengths. Then, the subsequence features are extracted to determine the presence of collective anomalies. Finally, we calculate point-level anomaly scores by aggregating features from nodes at different levels. Experiments conducted on seven public datasets and eight baselines demonstrate that TreeMIL achieves an average 32.3% improvement in F1- score compared to previous state-of-the-art methods. The code is available at https://github.com/fly-orange/TreeMIL.
Authors: Raj Ghugare, Matthieu Geist, Glen Berseth, Benjamin Eysenbach
Some reinforcement learning (RL) algorithms can stitch pieces of experience to solve a task never seen before during training. This oft-sought property is one of the few ways in which RL methods based on dynamic-programming differ from RL methods based on supervised-learning (SL). Yet, certain RL methods based on off-the-shelf SL algorithms achieve excellent results without an explicit mechanism for stitching; it remains unclear whether those methods forgo this important stitching property. This paper studies this question for the problems of achieving a target goal state and achieving a target return value. Our main result is to show that the stitching property corresponds to a form of combinatorial generalization: after training on a distribution of (state, goal) pairs, one would like to evaluate on (state, goal) pairs not seen together in the training data. Our analysis shows that this sort of generalization is different from i.i.d. generalization. This connection between stitching and generalisation reveals why we should not expect SL-based RL methods to perform stitching, even in the limit of large datasets and models. Based on this analysis, we construct new datasets to explicitly test for this property, revealing that SL-based methods lack this stitching property and hence fail to perform combinatorial generalization. Nonetheless, the connection between stitching and combinatorial generalisation also suggests a simple remedy for improving generalisation in SL: data augmentation. We propose a temporal data augmentation and demonstrate that adding it to SL-based methods enables them to successfully complete tasks not seen together during training. On a high level, this connection illustrates the importance of combinatorial generalization for data efficiency in time-series data beyond tasks beyond RL, like audio, video, or text.
Authors: Mehmet Y. Turali, Mehmet E. Lorasdagi, Ali T. Koc, Suleyman S. Kozat
We study the problem of feature selection in general machine learning (ML) context, which is one of the most critical subjects in the field. Although, there exist many feature selection methods, however, these methods face challenges such as scalability, managing high-dimensional data, dealing with correlated features, adapting to variable feature importance, and integrating domain knowledge. To this end, we introduce the ``Adaptive Feature Selection with Binary Masking" (AFS-BM) which remedies these problems. AFS-BM achieves this by joint optimization for simultaneous feature selection and model training. In particular, we do the joint optimization and binary masking to continuously adapt the set of features and model parameters during the training process. This approach leads to significant improvements in model accuracy and a reduction in computational requirements. We provide an extensive set of experiments where we compare AFS-BM with the established feature selection methods using well-known datasets from real-life competitions. Our results show that AFS-BM makes significant improvement in terms of accuracy and requires significantly less computational complexity. This is due to AFS-BM's ability to dynamically adjust to the changing importance of features during the training process, which an important contribution to the field. We openly share our code for the replicability of our results and to facilitate further research.
Authors: Suhan Cui, Jiaqi Wang, Yuan Zhong, Han Liu, Ting Wang, Fenglong Ma
The widespread adoption of Electronic Health Record (EHR) systems in healthcare institutes has generated vast amounts of medical data, offering significant opportunities for improving healthcare services through deep learning techniques. However, the complex and diverse modalities and feature structures in real-world EHR data pose great challenges for deep learning model design. To address the multi-modality challenge in EHR data, current approaches primarily rely on hand-crafted model architectures based on intuition and empirical experiences, leading to sub-optimal model architectures and limited performance. Therefore, to automate the process of model design for mining EHR data, we propose a novel neural architecture search (NAS) framework named AutoFM, which can automatically search for the optimal model architectures for encoding diverse input modalities and fusion strategies. We conduct thorough experiments on real-world multi-modal EHR data and prediction tasks, and the results demonstrate that our framework not only achieves significant performance improvement over existing state-of-the-art methods but also discovers meaningful network architectures effectively.
Authors: Weiguo Lu, Xuan Wu, Deng Ding, Jinqiao Duan, Jirong Zhuang, Gangnan Yuan
Diffusion models (DMs) are a type of generative model that has a huge impact on image synthesis and beyond. They achieve state-of-the-art generation results in various generative tasks. A great diversity of conditioning inputs, such as text or bounding boxes, are accessible to control the generation. In this work, we propose a conditioning mechanism utilizing Gaussian mixture models (GMMs) as feature conditioning to guide the denoising process. Based on set theory, we provide a comprehensive theoretical analysis that shows that conditional latent distribution based on features and classes is significantly different, so that conditional latent distribution on features produces fewer defect generations than conditioning on classes. Two diffusion models conditioned on the Gaussian mixture model are trained separately for comparison. Experiments support our findings. A novel gradient function called the negative Gaussian mixture gradient (NGMG) is proposed and applied in diffusion model training with an additional classifier. Training stability has improved. We also theoretically prove that NGMG shares the same benefit as the Earth Mover distance (Wasserstein) as a more sensible cost function when learning distributions supported by low-dimensional manifolds.
Authors: Lixu Wang, Shichao Xu, Xinyu Du, Qi Zhu
Anomaly detection in time-series data is crucial for identifying faults, failures, threats, and outliers across a range of applications. Recently, deep learning techniques have been applied to this topic, but they often struggle in real-world scenarios that are complex and highly dynamic, e.g., the normal data may consist of multiple distributions, and various types of anomalies may differ from the normal data to different degrees. In this work, to tackle these challenges, we propose Distribution-Augmented Contrastive Reconstruction (DACR). DACR generates extra data disjoint from the normal data distribution to compress the normal data's representation space, and enhances the feature extractor through contrastive learning to better capture the intrinsic semantics from time-series data. Furthermore, DACR employs an attention mechanism to model the semantic dependencies among multivariate time-series features, thereby achieving more robust reconstruction for anomaly detection. Extensive experiments conducted on nine benchmark datasets in various anomaly detection scenarios demonstrate the effectiveness of DACR in achieving new state-of-the-art time-series anomaly detection.
Authors: David W. Romero, Erik J. Bekkers, Jakub M. Tomczak, Mark Hoogendoorn
Leveraging the symmetries inherent to specific data domains for the construction of equivariant neural networks has lead to remarkable improvements in terms of data efficiency and generalization. However, most existing research focuses on symmetries arising from planar and volumetric data, leaving a crucial data source largely underexplored: time-series. In this work, we fill this gap by leveraging the symmetries inherent to time-series for the construction of equivariant neural network. We identify two core symmetries: *scale and translation*, and construct scale-translation equivariant neural networks for time-series learning. Intriguingly, we find that scale-translation equivariant mappings share strong resemblance with the wavelet transform. Inspired by this resemblance, we term our networks Wavelet Networks, and show that they perform nested non-linear wavelet-like time-frequency transforms. Empirical results show that Wavelet Networks outperform conventional CNNs on raw waveforms, and match strongly engineered spectrogram techniques across several tasks and time-series types, including audio, environmental sounds, and electrical signals. Our code is publicly available at https://github.com/dwromero/wavelet_networks.
Authors: Abdellah Aznag, Vineet Goyal, Noemie Perivier
We consider a dynamic assortment selection problem where a seller has a fixed inventory of $N$ substitutable products and faces an unknown demand that arrives sequentially over $T$ periods. In each period, the seller needs to decide on the assortment of products (of cardinality at most $K$) to offer to the customers. The customer's response follows an unknown multinomial logit model (MNL) with parameters $v$. The goal of the seller is to maximize the total expected revenue given the fixed initial inventory of $N$ products. We give a policy that achieves a regret of $\tilde O\Big(K \sqrt{KN T}\Big(\sqrt{v_{\text{max}}} + \frac{1}{q_{\text{min}}}\text{OPT}\Big)\Big)$, where $v_{\text{max}}\leq 1$ is the maximum utility for any product and $q_{\text{min}}$ the minimum inventory level, under a mild assumption on the model parameters. In particular, our policy achieves a near-optimal $\tilde O(\sqrt{T})$ regret in a large-inventory setting.
Our policy builds upon the UCB-based approach for MNL-bandit without inventory constraints in [1] and addresses the inventory constraints through an exponentially sized LP for which we present a tractable approximation while keeping the $\tilde O(\sqrt{T})$ regret bound.
Authors: Hadi Hojjati, Narges Armanfard
Semi-supervised anomaly detection aims to detect anomalies from normal samples using a model that is trained on normal data. With recent advancements in deep learning, researchers have designed efficient deep anomaly detection methods. Existing works commonly use neural networks to map the data into a more informative representation and then apply an anomaly detection algorithm. In this paper, we propose a method, DASVDD, that jointly learns the parameters of an autoencoder while minimizing the volume of an enclosing hyper-sphere on its latent representation. We propose an anomaly score which is a combination of autoencoder's reconstruction error and the distance from the center of the enclosing hypersphere in the latent representation. Minimizing this anomaly score aids us in learning the underlying distribution of the normal class during training. Including the reconstruction error in the anomaly score ensures that DASVDD does not suffer from the common hypersphere collapse issue since the DASVDD model does not converge to the trivial solution of mapping all inputs to a constant point in the latent representation. Experimental evaluations on several benchmark datasets show that the proposed method outperforms the commonly used state-of-the-art anomaly detection algorithms while maintaining robust performance across different anomaly classes.
Authors: Xin Chen, Qi Zhao, Xinyang Liu
With the fast development of Deep Learning techniques, Named Entity Recognition (NER) is becoming more and more important in the information extraction task. The greatest difficulty that the NER task faces is to keep the detectability even when types of NE and documents are unfamiliar. Realizing that the specificity information may contain potential meanings of a word and generate semantic-related features for word embedding, we develop a distribution-aware word embedding and implement three different methods to make use of the distribution information in a NER framework. And the result shows that the performance of NER will be improved if the word specificity is incorporated into existing NER methods.
Authors: Donghwan Lee, Han-Dong Lim, Jihoon Park, Okyong Choi
Sutton, Szepesv\'{a}ri and Maei introduced the first gradient temporal-difference (GTD) learning algorithms compatible with both linear function approximation and off-policy training. The goal of this paper is (a) to propose some variants of GTDs with extensive comparative analysis and (b) to establish new theoretical analysis frameworks for the GTDs. These variants are based on convex-concave saddle-point interpretations of GTDs, which effectively unify all the GTDs into a single framework, and provide simple stability analysis based on recent results on primal-dual gradient dynamics. Finally, numerical comparative analysis is given to evaluate these approaches.
Authors: Linfeng Ye, Shayan Mohajer Hamidi
The existing work shows that the neural network trained by naive gradient-based optimization method is prone to adversarial attacks, adds small malicious on the ordinary input is enough to make the neural network wrong. At the same time, the attack against a neural network is the key to improving its robustness. The training against adversarial examples can make neural networks resist some kinds of adversarial attacks. At the same time, the adversarial attack against a neural network can also reveal some characteristics of the neural network, a complex high-dimensional non-linear function, as discussed in previous work.
In This project, we develop a first-order method to attack the neural network. Compare with other first-order attacks, our method has a much higher success rate. Furthermore, it is much faster than second-order attacks and multi-steps first-order attacks.
Authors: Haoyu Wei, Xiaoyu Lei, Yixin Han, Huiming Zhang
Identifying important features linked to a response variable is a fundamental task in various scientific domains. This article explores statistical inference for simulated Markov random fields in high-dimensional settings. We introduce a methodology based on Markov Chain Monte Carlo Maximum Likelihood Estimation (MCMC-MLE) with Elastic-net regularization. Under mild conditions on the MCMC method, our penalized MCMC-MLE method achieves $\ell_{1}$-consistency. We propose a decorrelated score test, establishing both its asymptotic normality and that of a one-step estimator, along with the associated confidence interval. Furthermore, we construct two false discovery rate control procedures via the asymptotic behaviors for both p-values and e-values. Comprehensive numerical simulations confirm the theoretical validity of the proposed methods.
Authors: Abdallah Alabdallah, Mattias Ohlsson, Sepideh Pashami, Thorsteinn Rögnvaldsson
The Concordance Index (C-index) is a commonly used metric in Survival Analysis for evaluating the performance of a prediction model. In this paper, we propose a decomposition of the C-index into a weighted harmonic mean of two quantities: one for ranking observed events versus other observed events, and the other for ranking observed events versus censored cases. This decomposition enables a finer-grained analysis of the relative strengths and weaknesses between different survival prediction methods. The usefulness of this decomposition is demonstrated through benchmark comparisons against classical models and state-of-the-art methods, together with the new variational generative neural-network-based method (SurVED) proposed in this paper. The performance of the models is assessed using four publicly available datasets with varying levels of censoring. Using the C-index decomposition and synthetic censoring, the analysis shows that deep learning models utilize the observed events more effectively than other models. This allows them to keep a stable C-index in different censoring levels. In contrast to such deep learning methods, classical machine learning models deteriorate when the censoring level decreases due to their inability to improve on ranking the events versus other events.
Authors: Rishabh Dudeja, Daniel Hsu
Tensor PCA is a stylized statistical inference problem introduced by Montanari and Richard to study the computational difficulty of estimating an unknown parameter from higher-order moment tensors. Unlike its matrix counterpart, Tensor PCA exhibits a statistical-computational gap, i.e., a sample size regime where the problem is information-theoretically solvable but conjectured to be computationally hard. This paper derives computational lower bounds on the run-time of memory bounded algorithms for Tensor PCA using communication complexity. These lower bounds specify a trade-off among the number of passes through the data sample, the sample size, and the memory required by any algorithm that successfully solves Tensor PCA. While the lower bounds do not rule out polynomial-time algorithms, they do imply that many commonly-used algorithms, such as gradient descent and power method, must have a higher iteration count when the sample size is not large enough. Similar lower bounds are obtained for Non-Gaussian Component Analysis, a family of statistical estimation problems in which low-order moment tensors carry no information about the unknown parameter. Finally, stronger lower bounds are obtained for an asymmetric variant of Tensor PCA and related statistical estimation problems. These results explain why many estimators for these problems use a memory state that is significantly larger than the effective dimensionality of the parameter of interest.
Authors: Hadi Hojjati, Thi Kieu Khanh Ho, Narges Armanfard
Anomaly detection (AD) plays a crucial role in various domains, including cybersecurity, finance, and healthcare, by identifying patterns or events that deviate from normal behaviour. In recent years, significant progress has been made in this field due to the remarkable growth of deep learning models. Notably, the advent of self-supervised learning has sparked the development of novel AD algorithms that outperform the existing state-of-the-art approaches by a considerable margin. This paper aims to provide a comprehensive review of the current methodologies in self-supervised anomaly detection. We present technical details of the standard methods and discuss their strengths and drawbacks. We also compare the performance of these models against each other and other state-of-the-art anomaly detection models. Finally, the paper concludes with a discussion of future directions for self-supervised anomaly detection, including the development of more effective and efficient algorithms and the integration of these techniques with other related fields, such as multi-modal learning.
Authors: Pulkit Gopalani, Sayar Karmakar, Dibyakanti Kumar, Anirbit Mukherjee
In recent times machine learning methods have made significant advances in becoming a useful tool for analyzing physical systems. A particularly active area in this theme has been "physics-informed machine learning" which focuses on using neural nets for numerically solving differential equations. In this work, we aim to advance the theory of measuring out-of-sample error while training DeepONets -- which is among the most versatile ways to solve PDE systems in one-shot.
Firstly, for a class of DeepONets, we prove a bound on their Rademacher complexity which does not explicitly scale with the width of the nets involved. Secondly, we use this to show how the Huber loss can be chosen so that for these DeepONet classes generalization error bounds can be obtained that have no explicit dependence on the size of the nets. We note that our theoretical results apply to any PDE being targeted to be solved by DeepONets.
Authors: Feng Liang, Yangguang Li, Diana Marculescu
Recently, self-supervised Masked Autoencoders (MAE) have attracted unprecedented attention for their impressive representation learning ability. However, the pretext task, Masked Image Modeling (MIM), reconstructs the missing local patches, lacking the global understanding of the image. This paper extends MAE to a fully supervised setting by adding a supervised classification branch, thereby enabling MAE to learn global features from golden labels effectively. The proposed Supervised MAE (SupMAE) only exploits a visible subset of image patches for classification, unlike the standard supervised pre-training where all image patches are used. Through experiments, we demonstrate that SupMAE is not only more training efficient but it also learns more robust and transferable features. Specifically, SupMAE achieves comparable performance with MAE using only 30% of compute when evaluated on ImageNet with the ViT-B/16 model. SupMAE's robustness on ImageNet variants and transfer learning performance outperforms MAE and standard supervised pre-training counterparts. Codes are available at https://github.com/enyac-group/supmae.
Authors: Joyce Chew, Holly R. Steach, Siddharth Viswanath, Hau-Tieng Wu, Matthew Hirn, Deanna Needell, Smita Krishnaswamy, Michael Perlmutter
The manifold scattering transform is a deep feature extractor for data defined on a Riemannian manifold. It is one of the first examples of extending convolutional neural network-like operators to general manifolds. The initial work on this model focused primarily on its theoretical stability and invariance properties but did not provide methods for its numerical implementation except in the case of two-dimensional surfaces with predefined meshes. In this work, we present practical schemes, based on the theory of diffusion maps, for implementing the manifold scattering transform to datasets arising in naturalistic systems, such as single cell genetics, where the data is a high-dimensional point cloud modeled as lying on a low-dimensional manifold. We show that our methods are effective for signal classification and manifold classification tasks.
Authors: Yining Hua, Hang Jiang, Shixu Lin, Jie Yang, Joseph M. Plasek, David W. Bates, Li Zhou
Understanding public discourse on emergency use of unproven therapeutics is crucial for monitoring safe use and combating misinformation. We developed a natural language processing-based pipeline to comprehend public perceptions of and stances on coronavirus disease 2019 (COVID-19)-related drugs on Twitter over time. This retrospective study included 609,189 US-based tweets from January 29, 2020, to November 30, 2021, about four drugs that garnered significant public attention during the COVID-19 pandemic: (1) Hydroxychloroquine and Ivermectin, therapies with anecdotal evidence; and (2) Molnupiravir and Remdesivir, FDA-approved treatments for eligible patients. Time-trend analysis was employed to understand popularity trends and related events. Content and demographic analyses were conducted to explore potential rationales behind people's stances on each drug. Time-trend analysis indicated that Hydroxychloroquine and Ivermectin were discussed more than Molnupiravir and Remdesivir, particularly during COVID-19 surges. Hydroxychloroquine and Ivermectin discussions were highly politicized, related to conspiracy theories, hearsay, and celebrity influences. The distribution of stances between the two major US political parties was significantly different (P < .001); Republicans were more likely to support Hydroxychloroquine (55%) and Ivermectin (30%) than Democrats. People with healthcare backgrounds tended to oppose Hydroxychloroquine (7%) more than the general population, while the general population was more likely to support Ivermectin (14%). Our study found that social media users have varying perceptions and stances on off-label versus FDA-authorized drug use at different stages of COVID-19. This indicates that health systems, regulatory agencies, and policymakers should design tailored strategies to monitor and reduce misinformation to promote safe drug use.
Authors: Li Meng, Morten Goodwin, Anis Yazidi, Paal Engelstad
Transformers are neural network models that utilize multiple layers of self-attention heads and have exhibited enormous potential in natural language processing tasks. Meanwhile, there have been efforts to adapt transformers to visual tasks of machine learning, including Vision Transformers and Swin Transformers. Although some researchers use Vision Transformers for reinforcement learning tasks, their experiments remain at a small scale due to the high computational cost. This article presents the first online reinforcement learning scheme that is based on Swin Transformers: Swin DQN. In contrast to existing research, our novel approach demonstrate the superior performance with experiments on 49 games in the Arcade Learning Environment. The results show that our approach achieves significantly higher maximal evaluation scores than the baseline method in 45 of all the 49 games (92%), and higher mean evaluation scores than the baseline method in 40 of all the 49 games (82%).
Authors: Ke Xue, Yutong Wang, Cong Guan, Lei Yuan, Haobo Fu, Qiang Fu, Chao Qian, Yang Yu
Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL). Recently, some studies have made progress in ZSC by exposing the agents to diverse partners during the training process. They usually involve self-play when training the partners, implicitly assuming that the tasks are homogeneous. However, many real-world tasks are heterogeneous, and hence previous methods may be inefficient. In this paper, we study the heterogeneous ZSC problem for the first time and propose a general method based on coevolution, which coevolves two populations of agents and partners through three sub-processes: pairing, updating and selection. Experimental results on various heterogeneous tasks highlight the necessity of considering the heterogeneous setting and demonstrate that our proposed method is a promising solution for heterogeneous ZSC tasks.
Authors: Chentao Cao, Zhuo-Xu Cui, Yue Wang, Shaonan Liu, Taijin Chen, Hairong Zheng, Dong Liang, Yanjie Zhu
Diffusion models with continuous stochastic differential equations (SDEs) have shown superior performances in image generation. It can serve as a deep generative prior to solving the inverse problem in magnetic resonance (MR) reconstruction. However, low-frequency regions of $k$-space data are typically fully sampled in fast MR imaging, while existing diffusion models are performed throughout the entire image or $k$-space, inevitably introducing uncertainty in the reconstruction of low-frequency regions. Additionally, existing diffusion models often demand substantial iterations to converge, resulting in time-consuming reconstructions. To address these challenges, we propose a novel SDE tailored specifically for MR reconstruction with the diffusion process in high-frequency space (referred to as HFS-SDE). This approach ensures determinism in the fully sampled low-frequency regions and accelerates the sampling procedure of reverse diffusion. Experiments conducted on the publicly available fastMRI dataset demonstrate that the proposed HFS-SDE method outperforms traditional parallel imaging methods, supervised deep learning, and existing diffusion models in terms of reconstruction accuracy and stability. The fast convergence properties are also confirmed through theoretical and experimental validation. Our code and weights are available at https://github.com/Aboriginer/HFS-SDE.
Authors: Mavina Nikandrou, Lu Yu, Alessandro Suglia, Ioannis Konstas, Verena Rieser
Continual learning aims to train a model incrementally on a sequence of tasks without forgetting previous knowledge. Although continual learning has been widely studied in computer vision, its application to Vision+Language tasks is not that straightforward, as settings can be parameterized in multiple ways according to their input modalities. In this paper, we present a detailed study of how different settings affect performance for Visual Question Answering. We first propose three plausible task formulations and demonstrate their impact on the performance of continual learning algorithms. We break down several factors of task similarity, showing that performance and sensitivity to task order highly depend on the shift of the output distribution. We also investigate the potential of pretrained models and compare the robustness of transformer models with different visual embeddings. Finally, we provide an analysis interpreting model representations and their impact on forgetting. Our results highlight the importance of stabilizing visual representations in deeper layers.
Authors: Tim Clifford, Ilia Shumailov, Yiren Zhao, Ross Anderson, Robert Mullins
Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors in models or even remove them. These defences work by inspecting the training data, the model, or the integrity of the training procedure. In this work, we show that backdoors can be added during compilation, circumventing any safeguards in the data preparation and model training stages. The attacker can not only insert existing weight-based backdoors during compilation, but also a new class of weight-independent backdoors, such as ImpNet. These backdoors are impossible to detect during the training or data preparation processes, because they are not yet present. Next, we demonstrate that some backdoors, including ImpNet, can only be reliably detected at the stage where they are inserted and removing them anywhere else presents a significant challenge. We conclude that ML model security requires assurance of provenance along the entire technical pipeline, including the data, model architecture, compiler, and hardware specification.
Authors: Shunya Minami, Kenji Fukumizu, Yoshihiro Hayashi, Ryo Yoshida
Supervised transfer learning has received considerable attention due to its potential to boost the predictive power of machine learning in scenarios where data are scarce. Generally, a given set of source models and a dataset from a target domain are used to adapt the pre-trained models to a target domain by statistically learning domain shift and domain-specific factors. While such procedurally and intuitively plausible methods have achieved great success in a wide range of real-world applications, the lack of a theoretical basis hinders further methodological development. This paper presents a general class of transfer learning regression called affine model transfer, following the principle of expected-square loss minimization. It is shown that the affine model transfer broadly encompasses various existing methods, including the most common procedure based on neural feature extractors. Furthermore, the current paper clarifies theoretical properties of the affine model transfer such as generalization error and excess risk. Through several case studies, we demonstrate the practical benefits of modeling and estimating inter-domain commonality and domain-specific factors separately with the affine-type transfer models.
Authors: Lilian W. Bialokozowicz
We present the new Orthogonal Polynomials Approximation Algorithm (OPAA), a parallelizable algorithm that estimates probability distributions using functional analytic approach: first, it finds a smooth functional estimate of the probability distribution, whether it is normalized or not; second, the algorithm provides an estimate of the normalizing weight; and third, the algorithm proposes a new computation scheme to compute such estimates.
A core component of OPAA is a special transform of the square root of the joint distribution into a special functional space of our construct. Through this transform, the evidence is equated with the $L^2$ norm of the transformed function, squared. Hence, the evidence can be estimated by the sum of squares of the transform coefficients. Computations can be parallelized and completed in one pass.
OPAA can be applied broadly to the estimation of probability density functions. In Bayesian problems, it can be applied to estimating the normalizing weight of the posterior, which is also known as the evidence, serving as an alternative to existing optimization-based methods.
Authors: Amit Daniely, Elad Granot
We investigate the sample complexity of bounded two-layer neural networks using different activation functions.
In particular, we consider the class
$$ \mathcal{H} = \left\{\textbf{x}\mapsto \langle \textbf{v}, \sigma \circ W\textbf{b} + \textbf{b} \rangle : \textbf{b}\in\mathbb{R}^d, W \in \mathbb{R}^{\mathcal{T}\times d}, \textbf{v} \in \mathbb{R}^{\mathcal{T}}\right\} $$
where the spectral norm of $W$ and $\textbf{v}$ is bounded by $O(1)$, the Frobenius norm of $W$ is bounded from its initialization by $R > 0$, and $\sigma$ is a Lipschitz activation function.
We prove that if $\sigma$ is element-wise, then the sample complexity of $\mathcal{H}$ has only logarithmic dependency in width and that this complexity is tight, up to logarithmic factors.
We further show that the element-wise property of $\sigma$ is essential for a logarithmic dependency bound in width, in the sense that there exist non-element-wise activation functions whose sample complexity is linear in width, for widths that can be up to exponential in the input dimension.
For the upper bound, we use the recent approach for norm-based bounds named Approximate Description Length (ADL) by arXiv:1910.05697.
We further develop new techniques and tools for this approach that will hopefully inspire future works.
Authors: Pengyu Qiu, Xuhong Zhang, Shouling Ji, Chong Fu, Xing Yang, Ting Wang
Vertical Federated Learning (VFL) is a trending collaborative machine learning model training solution. Existing industrial frameworks employ secure multi-party computation techniques such as homomorphic encryption to ensure data security and privacy. Despite these efforts, studies have revealed that data leakage remains a risk in VFL due to the correlations between intermediate representations and raw data. Neural networks can accurately capture these correlations, allowing an adversary to reconstruct the data. This emphasizes the need for continued research into securing VFL systems.
Our work shows that hashing is a promising solution to counter data reconstruction attacks. The one-way nature of hashing makes it difficult for an adversary to recover data from hash codes. However, implementing hashing in VFL presents new challenges, including vanishing gradients and information loss. To address these issues, we propose HashVFL, which integrates hashing and simultaneously achieves learnability, bit balance, and consistency.
Experimental results indicate that HashVFL effectively maintains task performance while defending against data reconstruction attacks. It also brings additional benefits in reducing the degree of label leakage, mitigating adversarial attacks, and detecting abnormal inputs. We hope our work will inspire further research into the potential applications of HashVFL.
Authors: Yeongwoo Song, Hawoong Jeong
Recent advances in deep learning for physics have focused on discovering shared representations of target systems by incorporating physics priors or inductive biases into neural networks. While effective, these methods are limited to the system domain, where the type of system remains consistent and thus cannot ensure the adaptation to new, or unseen physical systems governed by different laws. For instance, a neural network trained on a mass-spring system cannot guarantee accurate predictions for the behavior of a two-body system or any other system with different physical laws. In this work, we take a significant leap forward by targeting cross domain generalization within the field of Hamiltonian dynamics. We model our system with a graph neural network and employ a meta learning algorithm to enable the model to gain experience over a distribution of tasks and make it adapt to new physics. Our approach aims to learn a unified Hamiltonian representation that is generalizable across multiple system domains, thereby overcoming the limitations of system-specific models. Our results demonstrate that the meta-trained model not only adapts effectively to new systems but also captures a generalized Hamiltonian representation that is consistent across different physical domains. Overall, through the use of meta learning, we offer a framework that achieves cross domain generalization, providing a step towards a unified model for understanding a wide array of dynamical systems via deep learning.
Authors: William Yik, Sam J. Silva, Andrew Geiss, Duncan Watson-Parris
Exploring the climate impacts of various anthropogenic emissions scenarios is key to making informed decisions for climate change mitigation and adaptation. State-of-the-art Earth system models can provide detailed insight into these impacts, but have a large associated computational cost on a per-scenario basis. This large computational burden has driven recent interest in developing cheap machine learning models for the task of climate model emulation. In this manuscript, we explore the efficacy of randomly wired neural networks for this task. We describe how they can be constructed and compare them to their standard feedforward counterparts using the ClimateBench dataset. Specifically, we replace the serially connected dense layers in multilayer perceptrons, convolutional neural networks, and convolutional long short-term memory networks with randomly wired dense layers and assess the impact on model performance for models with 1 million and 10 million parameters. We find that models with less complex architectures see the greatest performance improvement with the addition of random wiring (up to 30.4% for multilayer perceptrons). Furthermore, out of 24 different model architecture, parameter count, and prediction task combinations, only one saw a statistically significant performance deficit in randomly wired networks compared to their standard counterparts, with 14 cases showing statistically significant improvement. We also find no significant difference in prediction speed between networks with standard feedforward dense layers and those with randomly wired layers. These findings indicate that randomly wired neural networks may be suitable direct replacements for traditional dense layers in many standard models.
Authors: Parikshit Gopalan, Michael P. Kim, Omer Reingold
We introduce and study Swap Agnostic Learning. The problem can be phrased as a game between a predictor and an adversary: first, the predictor selects a hypothesis $h$; then, the adversary plays in response, and for each level set of the predictor $\{x \in \mathcal{X} : h(x) = v\}$ selects a (different) loss-minimizing hypothesis $c_v \in \mathcal{C}$; the predictor wins if $h$ competes with the adaptive adversary's loss. Despite the strength of the adversary, we demonstrate the feasibility Swap Agnostic Learning for any convex loss.
Somewhat surprisingly, the result follows through an investigation into the connections between Omniprediction and Multicalibration. Omniprediction is a new notion of optimality for predictors that strengthtens classical notions such as agnostic learning. It asks for loss minimization guarantees (relative to a hypothesis class) that apply not just for a specific loss function, but for any loss belonging to a rich family of losses. A recent line of work shows that omniprediction is implied by multicalibration and related multi-group fairness notions. This unexpected connection raises the question: is multi-group fairness necessary for omniprediction?
Our work gives the first affirmative answer to this question. We establish an equivalence between swap variants of omniprediction and multicalibration and swap agnostic learning. Further, swap multicalibration is essentially equivalent to the standard notion of multicalibration, so existing learning algorithms can be used to achieve any of the three notions. Building on this characterization, we paint a complete picture of the relationship between different variants of multi-group fairness, omniprediction, and Outcome Indistinguishability. This inquiry reveals a unified notion of OI that captures all existing notions of omniprediction and multicalibration.
Authors: Jun Lu
The sole aim of this book is to give a self-contained introduction to concepts and mathematical tools in Bayesian matrix decomposition in order to seamlessly introduce matrix decomposition techniques and their applications in subsequent sections. However, we clearly realize our inability to cover all the useful and interesting results concerning Bayesian matrix decomposition and given the paucity of scope to present this discussion, e.g., the separated analysis of variational inference for conducting the optimization. We refer the reader to literature in the field of Bayesian analysis for a more detailed introduction to the related fields.
This book is primarily a summary of purpose, significance of important Bayesian matrix decomposition methods, e.g., real-valued decomposition, nonnegative matrix factorization, Bayesian interpolative decomposition, and the origin and complexity of the methods which shed light on their applications. The mathematical prerequisite is a first course in statistics and linear algebra. Other than this modest background, the development is self-contained, with rigorous proof provided throughout.
Authors: Mitsuhiko Nakamoto, Yuexiang Zhai, Anikait Singh, Max Sobol Mark, Yi Ma, Chelsea Finn, Aviral Kumar, Sergey Levine
A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interaction. However, existing offline RL methods tend to behave poorly during fine-tuning. In this paper, we devise an approach for learning an effective initialization from offline data that also enables fast online fine-tuning capabilities. Our approach, calibrated Q-learning (Cal-QL), accomplishes this by learning a conservative value function initialization that underestimates the value of the learned policy from offline data, while also being calibrated, in the sense that the learned Q-values are at a reasonable scale. We refer to this property as calibration, and define it formally as providing a lower bound on the true value function of the learned policy and an upper bound on the value of some other (suboptimal) reference policy, which may simply be the behavior policy. We show that offline RL algorithms that learn such calibrated value functions lead to effective online fine-tuning, enabling us to take the benefits of offline initializations in online fine-tuning. In practice, Cal-QL can be implemented on top of the conservative Q learning (CQL) for offline RL within a one-line code change. Empirically, Cal-QL outperforms state-of-the-art methods on 9/11 fine-tuning benchmark tasks that we study in this paper. Code and video are available at https://nakamotoo.github.io/Cal-QL
Authors: Huiming Zhang, Haoyu Wei, Guang Cheng
In non-asymptotic learning, variance-type parameters of sub-Gaussian distributions are of paramount importance. However, directly estimating these parameters using the empirical moment generating function (MGF) is infeasible. To address this, we suggest using the sub-Gaussian intrinsic moment norm [Buldygin and Kozachenko (2000), Theorem 1.3] achieved by maximizing a sequence of normalized moments. Significantly, the suggested norm can not only reconstruct the exponential moment bounds of MGFs but also provide tighter sub-Gaussian concentration inequalities. In practice, we provide an intuitive method for assessing whether data with a finite sample size is sub-Gaussian, utilizing the sub-Gaussian plot. The intrinsic moment norm can be robustly estimated via a simple plug-in approach. Our theoretical findings are also applicable to reinforcement learning, including the multi-armed bandit scenario.
Authors: Yotam Alexander, Nimrod De La Vega, Noam Razin, Nadav Cohen
The question of what makes a data distribution suitable for deep learning is a fundamental open problem. Focusing on locally connected neural networks (a prevalent family of architectures that includes convolutional and recurrent neural networks as well as local self-attention models), we address this problem by adopting theoretical tools from quantum physics. Our main theoretical result states that a certain locally connected neural network is capable of accurate prediction over a data distribution if and only if the data distribution admits low quantum entanglement under certain canonical partitions of features. As a practical application of this result, we derive a preprocessing method for enhancing the suitability of a data distribution to locally connected neural networks. Experiments with widespread models over various datasets demonstrate our findings. We hope that our use of quantum entanglement will encourage further adoption of tools from physics for formally reasoning about the relation between deep learning and real-world data.
Authors: Mohammed Latif Siddiq, Joanna C. S. Santos, Ridwanul Hasan Tanvir, Noshin Ulfat, Fahmid Al Rifat, Vinicius Carvalho Lopes
A code generation model generates code by taking a prompt from a code comment, existing code, or a combination of both. Although code generation models (e.g., GitHub Copilot) are increasingly being adopted in practice, it is unclear whether they can successfully be used for unit test generation without fine-tuning for a strongly typed language like Java. To fill this gap, we investigated how well three models (Codex, GPT-3.5-Turbo, and StarCoder) can generate unit tests. We used two benchmarks (HumanEval and Evosuite SF110) to investigate the effect of context generation on the unit test generation process. We evaluated the models based on compilation rates, test correctness, test coverage, and test smells. We found that the Codex model achieved above 80% coverage for the HumanEval dataset, but no model had more than 2% coverage for the EvoSuite SF110 benchmark. The generated tests also suffered from test smells, such as Duplicated Asserts and Empty Tests.
Authors: Shripad Vilasrao Deshmukh, Arpan Dasgupta, Balaji Krishnamurthy, Nan Jiang, Chirag Agarwal, Georgios Theocharous, Jayakumar Subramanian
Explanation is a key component for the adoption of reinforcement learning (RL) in many real-world decision-making problems. In the literature, the explanation is often provided by saliency attribution to the features of the RL agent's state. In this work, we propose a complementary approach to these explanations, particularly for offline RL, where we attribute the policy decisions of a trained RL agent to the trajectories encountered by it during training. To do so, we encode trajectories in offline training data individually as well as collectively (encoding a set of trajectories). We then attribute policy decisions to a set of trajectories in this encoded space by estimating the sensitivity of the decision with respect to that set. Further, we demonstrate the effectiveness of the proposed approach in terms of quality of attributions as well as practical scalability in diverse environments that involve both discrete and continuous state and action spaces such as grid-worlds, video games (Atari) and continuous control (MuJoCo). We also conduct a human study on a simple navigation task to observe how their understanding of the task compares with data attributed for a trained RL policy. Keywords -- Explainable AI, Verifiability of AI Decisions, Explainable RL.
Authors: Zihao Wang, Lei Wu
In this paper, we provide a theoretical analysis of the inductive biases in convolutional neural networks (CNNs). We start by examining the universality of CNNs, i.e., the ability to approximate any continuous functions. We prove that a depth of $\mathcal{O}(\log d)$ suffices for deep CNNs to achieve this universality, where $d$ in the input dimension. Additionally, we establish that learning sparse functions with CNNs requires only $\widetilde{\mathcal{O}}(\log^2d)$ samples, indicating that deep CNNs can efficiently capture {\em long-range} sparse correlations. These results are made possible through a novel combination of the multichanneling and downsampling when increasing the network depth. We also delve into the distinct roles of weight sharing and locality in CNNs. To this end, we compare the performance of CNNs, locally-connected networks (LCNs), and fully-connected networks (FCNs) on a simple regression task, where LCNs can be viewed as CNNs without weight sharing. On the one hand, we prove that LCNs require ${\Omega}(d)$ samples while CNNs need only $\widetilde{\mathcal{O}}(\log^2d)$ samples, highlighting the critical role of weight sharing. On the other hand, we prove that FCNs require $\Omega(d^2)$ samples, whereas LCNs need only $\widetilde{\mathcal{O}}(d)$ samples, underscoring the importance of locality. These provable separations quantify the difference between the two biases, and the major observation behind our proof is that weight sharing and locality break different symmetries in the learning process.
Authors: Xinchi Qiu, Ilias Leontiadis, Luca Melis, Alex Sablayrolles, Pierre Stock
Privacy-Preserving machine learning (PPML) can help us train and deploy models that utilize private information. In particular, on-device machine learning allows us to avoid sharing raw data with a third-party server during inference. On-device models are typically less accurate when compared to their server counterparts due to the fact that (1) they typically only rely on a small set of on-device features and (2) they need to be small enough to run efficiently on end-user devices. Split Learning (SL) is a promising approach that can overcome these limitations. In SL, a large machine learning model is divided into two parts, with the bigger part residing on the server side and a smaller part executing on-device, aiming to incorporate the private features. However, end-to-end training of such models requires exchanging gradients at the cut layer, which might encode private features or labels. In this paper, we provide insights into potential privacy risks associated with SL. Furthermore, we also investigate the effectiveness of various mitigation strategies. Our results indicate that the gradients significantly improve the attackers' effectiveness in all tested datasets reaching almost perfect reconstruction accuracy for some features. However, a small amount of differential privacy (DP) can effectively mitigate this risk without causing significant training degradation.
Authors: Di Wu, Christof Monz
Using a vocabulary that is shared across languages is common practice in Multilingual Neural Machine Translation (MNMT). In addition to its simple design, shared tokens play an important role in positive knowledge transfer, assuming that shared tokens refer to similar meanings across languages. However, when word overlap is small, especially due to different writing systems, transfer is inhibited. In this paper, we define word-level information transfer pathways via word equivalence classes and rely on graph networks to fuse word embeddings across languages. Our experiments demonstrate the advantages of our approach: 1) embeddings of words with similar meanings are better aligned across languages, 2) our method achieves consistent BLEU improvements of up to 2.3 points for high- and low-resource MNMT, and 3) less than 1.0\% additional trainable parameters are required with a limited increase in computational costs, while inference time remains identical to the baseline. We release the codebase to the community.
Authors: Ahmed A. Elhag, Yuyang Wang, Joshua M. Susskind, Miguel Angel Bautista
We present Manifold Diffusion Fields (MDF), an approach that unlocks learning of diffusion models of data in general non-Euclidean geometries. Leveraging insights from spectral geometry analysis, we define an intrinsic coordinate system on the manifold via the eigen-functions of the Laplace-Beltrami Operator. MDF represents functions using an explicit parametrization formed by a set of multiple input-output pairs. Our approach allows to sample continuous functions on manifolds and is invariant with respect to rigid and isometric transformations of the manifold. In addition, we show that MDF generalizes to the case where the training set contains functions on different manifolds. Empirical results on multiple datasets and manifolds including challenging scientific problems like weather prediction or molecular conformation show that MDF can capture distributions of such functions with better diversity and fidelity than previous approaches.
Authors: Qingyu Chen, Jingcheng Du, Yan Hu, Vipina Kuttichi Keloth, Xueqing Peng, Kalpana Raja, Rui Zhang, Zhiyong Lu, Hua Xu
Biomedical literature is growing rapidly, making it challenging to curate and extract knowledge manually. Biomedical natural language processing (BioNLP) techniques that can automatically extract information from biomedical literature help alleviate this burden. Recently, large Language Models (LLMs), such as GPT-3 and GPT-4, have gained significant attention for their impressive performance. However, their effectiveness in BioNLP tasks and impact on method development and downstream users remain understudied. This pilot study (1) establishes the baseline performance of GPT-3 and GPT-4 at both zero-shot and one-shot settings in eight BioNLP datasets across four applications: named entity recognition, relation extraction, multi-label document classification, and semantic similarity and reasoning, (2) examines the errors produced by the LLMs and categorized the errors into three types: missingness, inconsistencies, and unwanted artificial content, and (3) provides suggestions for using LLMs in BioNLP applications. We make the datasets, baselines, and results publicly available to the community via https://github.com/qingyu-qc/gpt_bionlp_benchmark.
Authors: Xi Weng, Yunhao Ni, Tengwei Song, Jie Luo, Rao Muhammad Anwer, Salman Khan, Fahad Shahbaz Khan, Lei Huang
Whitening loss offers a theoretical guarantee against feature collapse in self-supervised learning (SSL) with joint embedding architectures. Typically, it involves a hard whitening approach, transforming the embedding and applying loss to the whitened output. In this work, we introduce Spectral Transformation (ST), a framework to modulate the spectrum of embedding and to seek for functions beyond whitening that can avoid dimensional collapse. We show that whitening is a special instance of ST by definition, and our empirical investigations unveil other ST instances capable of preventing collapse. Additionally, we propose a novel ST instance named IterNorm with trace loss (INTL). Theoretical analysis confirms INTL's efficacy in preventing collapse and modulating the spectrum of embedding toward equal-eigenvalues during optimization. Our experiments on ImageNet classification and COCO object detection demonstrate INTL's potential in learning superior representations. The code is available at https://github.com/winci-ai/INTL.
Authors: Sohyun An, Hayeon Lee, Jaehyeong Jo, Seanie Lee, Sung Ju Hwang
Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant architectures. To tackle such limitations of existing NAS methods, we propose a paradigm shift from NAS to a novel conditional Neural Architecture Generation (NAG) framework based on diffusion models, dubbed DiffusionNAG. Specifically, we consider the neural architectures as directed graphs and propose a graph diffusion model for generating them. Moreover, with the guidance of parameterized predictors, DiffusionNAG can flexibly generate task-optimal architectures with the desired properties for diverse tasks, by sampling from a region that is more likely to satisfy the properties. This conditional NAG scheme is significantly more efficient than previous NAS schemes which sample the architectures and filter them using the property predictors. We validate the effectiveness of DiffusionNAG through extensive experiments in two predictor-based NAS scenarios: Transferable NAS and Bayesian Optimization (BO)-based NAS. DiffusionNAG achieves superior performance with speedups of up to 20 times when compared to the baselines on Transferable NAS benchmarks. Furthermore, when integrated into a BO-based algorithm, DiffusionNAG outperforms existing BO-based NAS approaches, particularly in the large MobileNetV3 search space on the ImageNet 1K dataset.
Authors: Vincent Zhihao Zheng, Seongjin Choi, Lijun Sun
Deep probabilistic time series forecasting has gained significant attention due to its superior performance in nonlinear approximation and its ability to provide valuable uncertainty quantification for decision-making tasks. However, many existing models oversimplify the problem by assuming that the error process is time-independent, thereby overlooking the serial correlation in the error process. To overcome this limitation, we propose an innovative training method that incorporates error autocorrelation to further enhance the accuracy of probabilistic forecasting. Our method involves constructing a mini-batch as a collection of $D$ consecutive time series segments for model training and explicitly learning a time-varying covariance matrix over each mini-batch that encodes the error correlation among adjacent time steps. The learned covariance matrix can be used to improve prediction accuracy and enhance uncertainty quantification. We evaluate our method on two different neural forecasting models and multiple public datasets, and the experimental results confirm the effectiveness of the proposed approach in enhancing the performance of both models across a wide range of datasets, yielding notable improvements in predictive accuracy.
Authors: Matthias J. Ehrhardt, Silvia Gazzola, Sebastian J. Scott (Department of Mathematical Sciences, University of Bath, Bath, UK)
Variational regularization is commonly used to solve linear inverse problems, and involves augmenting a data fidelity by a regularizer. The regularizer is used to promote a priori information and is weighted by a regularization parameter. Selection of an appropriate regularization parameter is critical, with various choices leading to very different reconstructions. Classical strategies used to determine a suitable parameter value include the discrepancy principle and the L-curve criterion, and in recent years a supervised machine learning approach called bilevel learning has been employed. Bilevel learning is a powerful framework to determine optimal parameters and involves solving a nested optimization problem. While previous strategies enjoy various theoretical results, the well-posedness of bilevel learning in this setting is still an open question. In particular, a necessary property is positivity of the determined regularization parameter. In this work, we provide a new condition that better characterizes positivity of optimal regularization parameters than the existing theory. Numerical results verify and explore this new condition for both small and high-dimensional problems.
Authors: Sicen Liu, Xiaolong Wang, Xianbing Zhao, Hao Chen
Medication recommendation is a fundamental yet crucial branch of healthcare, which provides opportunities to support clinical physicians with more accurate medication prescriptions for patients with complex health conditions. Learning from electronic health records (EHR) to recommend medications is the most common way in previous studies. However, most of them neglect incorporating domain knowledge according to the clinical manifestations in the EHR of the patient. To address these issues, we propose a novel \textbf{D}omain \textbf{K}nowledge \textbf{I}nformed \textbf{Net}work (DKINet) to integrate domain knowledge with observable clinical manifestations of the patient, which is the first dynamic domain knowledge informed framework toward medication recommendation. In particular, we first design a knowledge-driven encoder to capture the domain information and then develop a data-driven encoder to integrate domain knowledge into the observable EHR. To endow the model with the capability of temporal decision, we design an explicit medication encoder for learning the longitudinal dependence of the patient. Extensive experiments on three publicly available datasets verify the superiority of our method. The code will be public upon acceptance.
Authors: John Falk, Luigi Bonati, Pietro Novelli, Michele Parrinello, Massimiliano Pontil
Interatomic potentials learned using machine learning methods have been successfully applied to atomistic simulations. However, accurate models require large training datasets, while generating reference calculations is computationally demanding. To bypass this difficulty, we propose a transfer learning algorithm that leverages the ability of graph neural networks (GNNs) to represent chemical environments together with kernel mean embeddings. We extract a feature map from GNNs pre-trained on the OC20 dataset and use it to learn the potential energy surface from system-specific datasets of catalytic processes. Our method is further enhanced by incorporating into the kernel the chemical species information, resulting in improved performance and interpretability. We test our approach on a series of realistic datasets of increasing complexity, showing excellent generalization and transferability performance, and improving on methods that rely on GNNs or ridge regression alone, as well as similar fine-tuning approaches.
Authors: Pengcheng Jiang, Cao Xiao, Tianfan Fu, Jimeng Sun
Molecule representation learning is crucial for various downstream applications, such as understanding and predicting molecular properties and side effects. In this paper, we propose a novel method called GODE, which takes into account the two-level structure of individual molecules. We recognize that molecules have an intrinsic graph structure as well as being a node in a larger molecule knowledge graph. GODE integrates graph representations of individual molecules with multidomain biochemical data from knowledge graphs. By pre-training two graph neural networks (GNNs) on different graph structures, combined with contrastive learning, GODE fuses molecular structures with their corresponding knowledge graph substructures. This fusion results in a more robust and informative representation, which enhances molecular property prediction by harnessing both chemical and biological information. When fine-tuned across 11 chemical property tasks, our model outperforms existing benchmarks, registering an average ROC-AUC uplift of 13.8% for classification tasks and an average RMSE/MAE enhancement of 35.1% for regression tasks. Impressively, it surpasses the current leading model in molecule property predictions with average advancements of 2.1% in classification and 6.4% in regression tasks.
Authors: Aldo Pacchiano, Christoph Dann, Claudio Gentile
We consider model selection for sequential decision making in stochastic environments with bandit feedback, where a meta-learner has at its disposal a pool of base learners, and decides on the fly which action to take based on the policies recommended by each base learner. Model selection is performed by regret balancing but, unlike the recent literature on this subject, we do not assume any prior knowledge about the base learners like candidate regret guarantees; instead, we uncover these quantities in a data-driven manner. The meta-learner is therefore able to leverage the realized regret incurred by each base learner for the learning environment at hand (as opposed to the expected regret), and single out the best such regret. We design two model selection algorithms operating with this more ambitious notion of regret and, besides proving model selection guarantees via regret balancing, we experimentally demonstrate the compelling practical benefits of dealing with actual regrets instead of candidate regret bounds.
Authors: Hien Dang, Tho Tran, Tan Nguyen, Nhat Ho
The posterior collapse phenomenon in variational autoencoder (VAE), where the variational posterior distribution closely matches the prior distribution, can hinder the quality of the learned latent variables. As a consequence of posterior collapse, the latent variables extracted by the encoder in VAE preserve less information from the input data and thus fail to produce meaningful representations as input to the reconstruction process in the decoder. While this phenomenon has been an actively addressed topic related to VAE performance, the theory for posterior collapse remains underdeveloped, especially beyond the standard VAE. In this work, we advance the theoretical understanding of posterior collapse to two important and prevalent yet less studied classes of VAE: conditional VAE and hierarchical VAE. Specifically, via a non-trivial theoretical analysis of linear conditional VAE and hierarchical VAE with two levels of latent, we prove that the cause of posterior collapses in these models includes the correlation between the input and output of the conditional VAE and the effect of learnable encoder variance in the hierarchical VAE. We empirically validate our theoretical findings for linear conditional and hierarchical VAE and demonstrate that these results are also predictive for non-linear cases with extensive experiments.
Authors: Dobrik Georgiev, Danilo Numeroso, Davide Bacciu, Pietro Liò
Solving NP-hard/complete combinatorial problems with neural networks is a challenging research area that aims to surpass classical approximate algorithms. The long-term objective is to outperform hand-designed heuristics for NP-hard/complete problems by learning to generate superior solutions solely from training data. Current neural-based methods for solving CO problems often overlook the inherent "algorithmic" nature of the problems. In contrast, heuristics designed for CO problems, e.g. TSP, frequently leverage well-established algorithms, such as those for finding the minimum spanning tree. In this paper, we propose leveraging recent advancements in neural algorithmic reasoning to improve the learning of CO problems. Specifically, we suggest pre-training our neural model on relevant algorithms before training it on CO instances. Our results demonstrate that by using this learning setup, we achieve superior performance compared to non-algorithmically informed deep learning models.
Authors: Sanyam Jain
This paper implements and investigates popular adversarial attacks on the YOLOv5 Object Detection algorithm. The paper explores the vulnerability of the YOLOv5 to adversarial attacks in the context of traffic and road sign detection. The paper investigates the impact of different types of attacks, including the Limited memory Broyden Fletcher Goldfarb Shanno (L-BFGS), the Fast Gradient Sign Method (FGSM) attack, the Carlini and Wagner (C&W) attack, the Basic Iterative Method (BIM) attack, the Projected Gradient Descent (PGD) attack, One Pixel Attack, and the Universal Adversarial Perturbations attack on the accuracy of YOLOv5 in detecting traffic and road signs. The results show that YOLOv5 is susceptible to these attacks, with misclassification rates increasing as the magnitude of the perturbations increases. We also explain the results using saliency maps. The findings of this paper have important implications for the safety and reliability of object detection algorithms used in traffic and transportation systems, highlighting the need for more robust and secure models to ensure their effectiveness in real-world applications.
Authors: Alexia Atsidakou, Branislav Kveton, Sumeet Katariya, Constantine Caramanis, Sujay Sanghavi
We derive the first finite-time logarithmic Bayes regret upper bounds for Bayesian bandits. In a multi-armed bandit, we obtain $O(c_\Delta \log n)$ and $O(c_h \log^2 n)$ upper bounds for an upper confidence bound algorithm, where $c_h$ and $c_\Delta$ are constants depending on the prior distribution and the gaps of bandit instances sampled from it, respectively. The latter bound asymptotically matches the lower bound of Lai (1987). Our proofs are a major technical departure from prior works, while being simple and general. To show the generality of our techniques, we apply them to linear bandits. Our results provide insights on the value of prior in the Bayesian setting, both in the objective and as a side information given to the learner. They significantly improve upon existing $\tilde{O}(\sqrt{n})$ bounds, which have become standard in the literature despite the logarithmic lower bound of Lai (1987).
Authors: Lucy L. Gao, Jane J. Ye, Haian Yin, Shangzhi Zeng, Jin Zhang
Bilevel programming has emerged as a valuable tool for hyperparameter selection, a central concern in machine learning. In a recent study by Ye et al. (2023), a value function-based difference of convex algorithm was introduced to address bilevel programs. This approach proves particularly powerful when dealing with scenarios where the lower-level problem exhibits convexity in both the upper-level and lower-level variables. Examples of such scenarios include support vector machines and $\ell_1$ and $\ell_2$ regularized regression. In this paper, we significantly expand the range of applications, now requiring convexity only in the lower-level variables of the lower-level program. We present an innovative single-level difference of weakly convex reformulation based on the Moreau envelope of the lower-level problem. We further develop a sequentially convergent Inexact Proximal Difference of Weakly Convex Algorithm (iP-DwCA). To evaluate the effectiveness of the proposed iP-DwCA, we conduct numerical experiments focused on tuning hyperparameters for kernel support vector machines on simulated data.
Authors: Apratim Bhattacharyya, Sunny Panchal, Mingu Lee, Reza Pourreza, Pulkit Madan, Roland Memisevic
Multi-modal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. However, existing methods still fall short in tasks like causal or compositional spatiotemporal reasoning over actions, in which model predictions need to be grounded in fine-grained low-level details, such as object motions and object interactions. In this work, we propose training an LM end-to-end on low-level surrogate tasks, including object detection, re-identification, and tracking, to endow the model with the required low-level visual capabilities. We show that a two-stream video encoder with spatiotemporal attention is effective at capturing the required static and motion-based cues in the video. By leveraging the LM's ability to perform the low-level surrogate tasks, we can cast reasoning in videos as the three-step process of Look, Remember, Reason wherein visual information is extracted using low-level visual skills step-by-step and then integrated to arrive at a final answer. We demonstrate the effectiveness of our framework on diverse visual reasoning tasks from the ACRE, CATER, Something-Else and STAR datasets. Our approach is trainable end-to-end and surpasses state-of-the-art task-specific methods across these tasks by a large margin.
Authors: Gerry Windiarto Mohamad Dunda, Shenghui Song
Federated learning (FL) has garnered considerable attention due to its privacy-preserving feature. Nonetheless, the lack of freedom in managing user data can lead to group fairness issues, where models are biased towards sensitive factors such as race or gender. To tackle this issue, this paper proposes a novel algorithm, fair federated averaging with augmented Lagrangian method (FFALM), designed explicitly to address group fairness issues in FL. Specifically, we impose a fairness constraint on the training objective and solve the minimax reformulation of the constrained optimization problem. Then, we derive the theoretical upper bound for the convergence rate of FFALM. The effectiveness of FFALM in improving fairness is shown empirically on CelebA and UTKFace datasets in the presence of severe statistical heterogeneity.
Authors: Mahmoud Shoush, Marlon Dumas
Prescriptive process monitoring methods seek to optimize the performance of business processes by triggering interventions at runtime, thereby increasing the probability of positive case outcomes. These interventions are triggered according to an intervention policy. Reinforcement learning has been put forward as an approach to learning intervention policies through trial and error. Existing approaches in this space assume that the number of resources available to perform interventions in a process is unlimited, an unrealistic assumption in practice. This paper argues that, in the presence of resource constraints, a key dilemma in the field of prescriptive process monitoring is to trigger interventions based not only on predictions of their necessity, timeliness, or effect but also on the uncertainty of these predictions and the level of resource utilization. Indeed, committing scarce resources to an intervention when the necessity or effects of this intervention are highly uncertain may intuitively lead to suboptimal intervention effects. Accordingly, the paper proposes a reinforcement learning approach for prescriptive process monitoring that leverages conformal prediction techniques to consider the uncertainty of the predictions upon which an intervention decision is based. An evaluation using real-life datasets demonstrates that explicitly modeling uncertainty using conformal predictions helps reinforcement learning agents converge towards policies with higher net intervention gain
Authors: Siqiao Xue, Xiaoming Shi, Zhixuan Chu, Yan Wang, Hongyan Hao, Fan Zhou, Caigao Jiang, Chen Pan, James Y. Zhang, Qingsong Wen, Jun Zhou, Hongyuan Mei
Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and competitive models, making a significant impact in both academic and application communities. Despite the emergence of many powerful models in recent years, there hasn't been a central benchmark for these models and future research endeavors. This lack of standardization impedes researchers and practitioners from comparing methods and reproducing results, potentially slowing down progress in this field. In this paper, we present EasyTPP, the first central repository of research assets (e.g., data, models, evaluation programs, documentations) in the area of event sequence modeling. Our EasyTPP makes several unique contributions to this area: a unified interface of using existing datasets and adding new datasets; a wide range of evaluation programs that are easy to use and extend as well as facilitate reproducible research; implementations of popular neural TPPs, together with a rich library of modules by composing which one could quickly build complex models. All the data and implementation can be found at \href{https://github.com/ant-research/EasyTemporalPointProcess}{\textcolor{blue}{Github repository}}. We will actively maintain this benchmark and welcome contributions from other researchers and practitioners. Our benchmark will help promote reproducible research in this field, thus accelerating research progress as well as making more significant real-world impacts.
Authors: Hai Duong, ThanhVu Nguyen, Matthew Dwyer
Deep Neural Networks (DNNs) have emerged as an effective approach to tackling real-world problems. However, like human-written software, DNNs can have bugs and can be attacked. To address this, research has explored a wide-range of algorithmic approaches to verify DNN behavior. In this work, we introduce NeuralSAT, a new verification approach that adapts the widely-used DPLL(T) algorithm used in modern SMT solvers. A key feature of SMT solvers is the use of conflict clause learning and search restart to scale verification. Unlike prior DNN verification approaches, NeuralSAT combines an abstraction-based deductive theory solver with clause learning and an evaluation clearly demonstrates the benefits of the approach on a set of challenging verification benchmarks.
Authors: Zijiang Yan, Wael Jaafar, Bassant Selim, Hina Tabassum
This paper presents a deep reinforcement learning solution for optimizing multi-UAV cell-association decisions and their moving velocity on a 3D aerial highway. The objective is to enhance transportation and communication performance, including collision avoidance, connectivity, and handovers. The problem is formulated as a Markov decision process (MDP) with UAVs' states defined by velocities and communication data rates. We propose a neural architecture with a shared decision module and multiple network branches, each dedicated to a specific action dimension in a 2D transportation-communication space. This design efficiently handles the multi-dimensional action space, allowing independence for individual action dimensions. We introduce two models, Branching Dueling Q-Network (BDQ) and Branching Dueling Double Deep Q-Network (Dueling DDQN), to demonstrate the approach. Simulation results show a significant improvement of 18.32% compared to existing benchmarks.
Authors: Leiming Chen, Cihao Dong, Sibo Qiao, Ziling Huang, Yuming Nie, Zhaoxiang Hou, Chee Wei Tan
Traditional federated learning uses the number of samples to calculate the weights of each client model and uses this fixed weight value to fusion the global model. However, in practical scenarios, each client's device and data heterogeneity leads to differences in the quality of each client's model. Thus the contribution to the global model is not wholly determined by the sample size. In addition, if clients intentionally upload low-quality or malicious models, using these models for aggregation will lead to a severe decrease in global model accuracy. Traditional federated learning algorithms do not address these issues. To solve this probelm, we propose FedDRL, a model fusion approach using reinforcement learning based on a two staged approach. In the first stage, Our method could filter out malicious models and selects trusted client models to participate in the model fusion. In the second stage, the FedDRL algorithm adaptively adjusts the weights of the trusted client models and aggregates the optimal global model. We also define five model fusion scenarios and compare our method with two baseline algorithms in those scenarios. The experimental results show that our algorithm has higher reliability than other algorithms while maintaining accuracy.
Authors: Ananth Raman, Vinod Raman, Unique Subedi, Idan Mehalel, Ambuj Tewari
We study online multiclass classification under bandit feedback. We extend the results of Daniely and Helbertal [2013] by showing that the finiteness of the Bandit Littlestone dimension is necessary and sufficient for bandit online learnability even when the label space is unbounded. Moreover, we show that, unlike the full-information setting, sequential uniform convergence is necessary but not sufficient for bandit online learnability. Our result complements the recent work by Hanneke, Moran, Raman, Subedi, and Tewari [2023] who show that the Littlestone dimension characterizes online multiclass learnability in the full-information setting even when the label space is unbounded.
Authors: Michael Y. Hu, Angelica Chen, Naomi Saphra, Kyunghyun Cho
The impact of randomness on model training is poorly understood. How do differences in data order and initialization actually manifest in the model, such that some training runs outperform others or converge faster? Furthermore, how can we interpret the resulting training dynamics and the phase transitions that characterize different trajectories? To understand the effect of randomness on the dynamics and outcomes of neural network training, we train models multiple times with different random seeds and compute a variety of metrics throughout training, such as the $L_2$ norm, mean, and variance of the neural network's weights. We then fit a hidden Markov model (HMM) over the resulting sequences of metrics. The HMM represents training as a stochastic process of transitions between latent states, providing an intuitive overview of significant changes during training. Using our method, we produce a low-dimensional, discrete representation of training dynamics on grokking tasks, image classification, and masked language modeling. We use the HMM representation to study phase transitions and identify latent "detour" states that slow down convergence.
Authors: Daniel Bethell, Simos Gerasimou, Radu Calinescu
Deploying deep learning models in safety-critical applications remains a very challenging task, mandating the provision of assurances for the dependable operation of these models. Uncertainty quantification (UQ) methods estimate the model's confidence per prediction, informing decision-making by considering the effect of randomness and model misspecification. Despite the advances of state-of-the-art UQ methods, they are computationally expensive or produce conservative prediction sets/intervals. We introduce MC-CP, a novel hybrid UQ method that combines a new adaptive Monte Carlo (MC) dropout method with conformal prediction (CP). MC-CP adaptively modulates the traditional MC dropout at runtime to save memory and computation resources, enabling predictions to be consumed by CP, yielding robust prediction sets/intervals. Throughout comprehensive experiments, we show that MC-CP delivers significant improvements over advanced UQ methods, like MC dropout, RAPS and CQR, both in classification and regression benchmarks. MC-CP can be easily added to existing models, making its deployment simple.
Authors: Jiacong Xu, Yi Zhang, Jiawei Peng, Wufei Ma, Artur Jesslen, Pengliang Ji, Qixin Hu, Jiehua Zhang, Qihao Liu, Jiahao Wang, Wei Ji, Chen Wang, Xiaoding Yuan, Prakhar Kaushik, Guofeng Zhang, Jie Liu, Yushan Xie, Yawen Cui, Alan Yuille, Adam Kortylewski
Accurately estimating the 3D pose and shape is an essential step towards understanding animal behavior, and can potentially benefit many downstream applications, such as wildlife conservation. However, research in this area is held back by the lack of a comprehensive and diverse dataset with high-quality 3D pose and shape annotations. In this paper, we propose Animal3D, the first comprehensive dataset for mammal animal 3D pose and shape estimation. Animal3D consists of 3379 images collected from 40 mammal species, high-quality annotations of 26 keypoints, and importantly the pose and shape parameters of the SMAL model. All annotations were labeled and checked manually in a multi-stage process to ensure highest quality results. Based on the Animal3D dataset, we benchmark representative shape and pose estimation models at: (1) supervised learning from only the Animal3D data, (2) synthetic to real transfer from synthetically generated images, and (3) fine-tuning human pose and shape estimation models. Our experimental results demonstrate that predicting the 3D shape and pose of animals across species remains a very challenging task, despite significant advances in human pose estimation. Our results further demonstrate that synthetic pre-training is a viable strategy to boost the model performance. Overall, Animal3D opens new directions for facilitating future research in animal 3D pose and shape estimation, and is publicly available.
Authors: Jie JW Wu
Large language models (LLMs) have significantly improved the ability to perform tasks in the field of code generation. However, there is still a gap between LLMs being capable coders and being top-tier software engineers. Based on the observation that toplevel software engineers often ask clarifying questions to reduce ambiguity in both requirements and coding solutions, I argue that the same should be applied to LLMs for code generation tasks. By asking probing questions in various topics before generating the final code, the challenges of programming with LLMs, such as unclear intent specification, lack of computational thinking, and undesired code quality, may be alleviated. This, in turn, increases confidence in the generated code. In this work, I explore how to leverage better communication skills to achieve greater confidence in generated code. I propose a communication-centered process that uses an LLM-generated communicator to identify issues with high ambiguity or low confidence in problem descriptions and generated code. I then ask clarifying questions to obtain responses from users for refining the code.
Authors: Mengwei Xu, Dongqi Cai, Yaozong Wu, Xiang Li, Shangguang Wang
Large Language Models (LLMs) are transforming the landscape of mobile intelligence. Federated Learning (FL), a method to preserve user data privacy, is often employed in fine-tuning LLMs to downstream mobile tasks, an approach known as FedLLM. Though recent efforts have addressed the network issue induced by the vast model size, they have not practically mitigated vital challenges concerning integration with mobile devices, such as significant memory consumption and sluggish model convergence.
In response to these challenges, this work introduces FwdLLM, an innovative FL protocol designed to enhance the FedLLM efficiency. The key idea of FwdLLM to employ backpropagation (BP)-free training methods, requiring devices only to execute ``perturbed inferences''. Consequently, FwdLLM delivers way better memory efficiency and time efficiency (expedited by mobile NPUs and an expanded array of participant devices). FwdLLM centers around three key designs: (1) it combines BP-free training with parameter-efficient training methods, an essential way to scale the approach to the LLM era; (2) it systematically and adaptively allocates computational loads across devices, striking a careful balance between convergence speed and accuracy; (3) it discriminatively samples perturbed predictions that are more valuable to model convergence. Comprehensive experiments with five LLMs and three NLP tasks illustrate FwdLLM's significant advantages over conventional methods, including up to three orders of magnitude faster convergence and a 14.6x reduction in memory footprint. Uniquely, FwdLLM paves the way for federated learning of billion-parameter LLMs such as LLaMA on COTS mobile devices -- a feat previously unattained.
Authors: Saeid Asgari Taghanaki, Aliasghar Khani, Amir Khasahmadi, Aditya Sanghi, Karl D.D. Willis, Ali Mahdavi-Amiri
Interpreting the learned features of vision models has posed a longstanding challenge in the field of machine learning. To address this issue, we propose a novel method that leverages the capabilities of language models to interpret the learned features of pre-trained image classifiers. Our method, called TExplain, tackles this task by training a neural network to establish a connection between the feature space of image classifiers and language models. Then, during inference, our approach generates a vast number of sentences to explain the features learned by the classifier for a given image. These sentences are then used to extract the most frequent words, providing a comprehensive understanding of the learned features and patterns within the classifier. Our method, for the first time, utilizes these frequent words corresponding to a visual representation to provide insights into the decision-making process of the independently trained classifier, enabling the detection of spurious correlations, biases, and a deeper comprehension of its behavior. To validate the effectiveness of our approach, we conduct experiments on diverse datasets, including ImageNet-9L and Waterbirds. The results demonstrate the potential of our method to enhance the interpretability and robustness of image classifiers.
Authors: Xuanming Zhang, Xiaoxue Wang, Yonghang Chen
This study preprocessed 2000-2019 energy consumption data for 46 key Sichuan industries using matrix normalization. DBSCAN clustering identified 16 feature classes to objectively group industries. Penalized regression models were then applied for their advantages in overfitting control, high-dimensional data processing, and feature selection - well-suited for the complex energy data. Results showed the second cluster around coal had highest emissions due to production needs. Emissions from gasoline-focused and coke-focused clusters were also significant. Based on this, emission reduction suggestions included clean coal technologies, transportation management, coal-electricity replacement in steel, and industry standardization. The research introduced unsupervised learning to objectively select factors and aimed to explore new emission reduction avenues. In summary, the study identified industry groupings, assessed emissions drivers, and proposed scientific reduction strategies to better inform decision-making using algorithms like DBSCAN and penalized regression models.
Authors: Ishan S. Khare, Tarun K. Martheswaran, Akshana Dassanaike-Perera
This work seeks to answer key research questions regarding the viability of reinforcement learning over the S&P 500 index. The on-policy techniques of Value Iteration (VI) and State-action-reward-state-action (SARSA) are implemented along with the off-policy technique of Q-Learning. The models are trained and tested on a dataset comprising multiple years of stock market data from 2000-2023. The analysis presents the results and findings from training and testing the models using two different time periods: one including the COVID-19 pandemic years and one excluding them. The results indicate that including market data from the COVID-19 period in the training dataset leads to superior performance compared to the baseline strategies. During testing, the on-policy approaches (VI and SARSA) outperform Q-learning, highlighting the influence of bias-variance tradeoff and the generalization capabilities of simpler policies. However, it is noted that the performance of Q-learning may vary depending on the stability of future market conditions. Future work is suggested, including experiments with updated Q-learning policies during testing and trading diverse individual stocks. Additionally, the exploration of alternative economic indicators for training the models is proposed.
Authors: Zhengxiang Shi, Aldo Lipani
Prompt tuning (PT), where a small amount of trainable soft (continuous) prompt vectors is affixed to the input of language models (LM), has shown promising results across various tasks and models for parameter-efficient fine-tuning (PEFT). PT stands out from other PEFT approaches because it maintains competitive performance with fewer trainable parameters and does not drastically scale up its parameters as the model size expands. However, PT introduces additional soft prompt tokens, leading to longer input sequences, which significantly impacts training and inference time and memory usage due to the Transformer's quadratic complexity. Particularly concerning for Large Language Models (LLMs) that face heavy daily querying. To address this issue, we propose Decomposed Prompt Tuning (DePT), which decomposes the soft prompt into a shorter soft prompt and a pair of low-rank matrices that are then optimised with two different learning rates. This allows DePT to achieve better performance while saving substantial memory and time costs compared to vanilla PT and its variants, without changing trainable parameter sizes. Through extensive experiments on 23 natural language processing (NLP) and vision-language (VL) tasks, we demonstrate that DePT outperforms state-of-the-art PEFT approaches, including the full fine-tuning baseline, in some scenarios. Additionally, we empirically show that DEPT grows more efficient as the model size increases. Our further study reveals that DePT integrates seamlessly with parameter-efficient transfer learning in the few-shot learning setting and highlights its adaptability to various model architectures and sizes.
Authors: Antonio Sclocchi, Matthieu Wyart
Modern deep networks are trained with stochastic gradient descent (SGD) whose key hyperparameters are the number of data considered at each step or batch size $B$, and the step size or learning rate $\eta$. For small $B$ and large $\eta$, SGD corresponds to a stochastic evolution of the parameters, whose noise amplitude is governed by the `temperature' $T\equiv \eta/B$. Yet this description is observed to break down for sufficiently large batches $B\geq B^*$, or simplifies to gradient descent (GD) when the temperature is sufficiently small. Understanding where these cross-overs take place remains a central challenge. Here, we resolve these questions for a teacher-student perceptron classification model and show empirically that our key predictions still apply to deep networks. Specifically, we obtain a phase diagram in the $B$-$\eta$ plane that separates three dynamical phases: \textit{(i)} a noise-dominated SGD governed by temperature, \textit{(ii)} a large-first-step-dominated SGD and \textit{(iii)} GD. These different phases also correspond to different regimes of generalization error. Remarkably, our analysis reveals that the batch size $B^*$ separating regimes \textit{(i)} and \textit{(ii)} scale with the size $P$ of the training set, with an exponent that characterizes the hardness of the classification problem.
Authors: Urszula Chajewska, Harsh Shrivastava
Federated Learning (FL) addresses the need to create models based on proprietary data in such a way that multiple clients retain exclusive control over their data, while all benefit from improved model accuracy due to pooled resources. Recently proposed Neural Graphical Models (NGMs) are Probabilistic Graphical models that utilize the expressive power of neural networks to learn complex non-linear dependencies between the input features. They learn to capture the underlying data distribution and have efficient algorithms for inference and sampling. We develop a FL framework which maintains a global NGM model that learns the averaged information from the local NGM models while keeping the training data within the client's environment. Our design, FedNGMs, avoids the pitfalls and shortcomings of neuron matching frameworks like Federated Matched Averaging that suffers from model parameter explosion. Our global model size remains constant throughout the process. In the cases where clients have local variables that are not part of the combined global distribution, we propose a `Stitching' algorithm, which personalizes the global NGM models by merging the additional variables using the client's data. FedNGM is robust to data heterogeneity, large number of participants, and limited communication bandwidth.
Authors: Hector Kohler, Riad Akrour, Philippe Preux
Finding an optimal decision tree for a supervised learning task is a challenging combinatorial problem to solve at scale. It was recently proposed to frame the problem as a Markov Decision Problem (MDP) and use deep reinforcement learning to tackle scaling. Unfortunately, these methods are not competitive with the current branch-and-bound state-of-the-art. We propose instead to scale the resolution of such MDPs using an information-theoretic tests generating function that heuristically, and dynamically for every state, limits the set of admissible test actions to a few good candidates. As a solver, we show empirically that our algorithm is at the very least competitive with branch-and-bound alternatives. As a machine learning tool, a key advantage of our approach is to solve for multiple complexity-performance trade-offs at virtually no additional cost. With such a set of solutions, a user can then select the tree that generalizes best and which has the interpretability level that best suits their needs, which no current branch-and-bound method allows.
Authors: Hector Kohler, Riad Akrour, Philippe Preux
Interpretability of AI models allows for user safety checks to build trust in such AIs. In particular, Decision Trees (DTs) provide a global look at the learned model and transparently reveal which features of the input are critical for making a decision. However, interpretability is hindered if the DT is too large. To learn compact trees, a recent Reinforcement Learning (RL) framework has been proposed to explore the space of DTs using deep RL. This framework augments a decision problem (e.g. a supervised classification task) with additional actions that gather information about the features of an otherwise hidden input. By appropriately penalizing these actions, the agent learns to optimally trade-off size and performance of DTs. In practice, a reactive policy for a partially observable Markov decision process (MDP) needs to be learned, which is still an open problem. We show in this paper that deep RL can fail even on simple toy tasks of this class. However, when the underlying decision problem is a supervised classification task, we show that finding the optimal tree can be cast as a fully observable Markov decision problem and be solved efficiently, giving rise to a new family of algorithms for learning DTs that go beyond the classical greedy maximization ones.
Authors: Fabian Jenelten, Junzhe He, Farbod Farshidian, Marco Hutter
Legged locomotion is a complex control problem that requires both accuracy and robustness to cope with real-world challenges. Legged systems have traditionally been controlled using trajectory optimization with inverse dynamics. Such hierarchical model-based methods are appealing due to intuitive cost function tuning, accurate planning, generalization, and most importantly, the insightful understanding gained from more than one decade of extensive research. However, model mismatch and violation of assumptions are common sources of faulty operation. Simulation-based reinforcement learning, on the other hand, results in locomotion policies with unprecedented robustness and recovery skills. Yet, all learning algorithms struggle with sparse rewards emerging from environments where valid footholds are rare, such as gaps or stepping stones. In this work, we propose a hybrid control architecture that combines the advantages of both worlds to simultaneously achieve greater robustness, foot-placement accuracy, and terrain generalization. Our approach utilizes a model-based planner to roll out a reference motion during training. A deep neural network policy is trained in simulation, aiming to track the optimized footholds. We evaluate the accuracy of our locomotion pipeline on sparse terrains, where pure data-driven methods are prone to fail. Furthermore, we demonstrate superior robustness in the presence of slippery or deformable ground when compared to model-based counterparts. Finally, we show that our proposed tracking controller generalizes across different trajectory optimization methods not seen during training. In conclusion, our work unites the predictive capabilities and optimality guarantees of online planning with the inherent robustness attributed to offline learning.
Authors: Guillem Pascual, Filip Lemic, Carmen Delgado, Xavier Costa-Perez
Advancements in nanotechnology and material science are paving the way toward nanoscale devices that combine sensing, computing, data and energy storage, and wireless communication. In precision medicine, these nanodevices show promise for disease diagnostics, treatment, and monitoring from within the patients' bloodstreams. Assigning the location of a sensed biological event with the event itself, which is the main proposition of flow-guided in-body nanoscale localization, would be immensely beneficial from the perspective of precision medicine. The nanoscale nature of the nanodevices and the challenging environment that the bloodstream represents, result in current flow-guided localization approaches being constrained in their communication and energy-related capabilities. The communication and energy constraints of the nanodevices result in different features of raw data for flow-guided localization, in turn affecting its performance. An analytical modeling of the effects of imperfect communication and constrained energy causing intermittent operation of the nanodevices on the raw data produced by the nanodevices would be beneficial. Hence, we propose an analytical model of raw data for flow-guided localization, where the raw data is modeled as a function of communication and energy-related capabilities of the nanodevice. We evaluate the model by comparing its output with the one obtained through the utilization of a simulator for objective evaluation of flow-guided localization, featuring comparably higher level of realism. Our results across a number of scenarios and heterogeneous performance metrics indicate high similarity between the model and simulator-generated raw datasets.
Authors: Nils Lukas, Abdulrahman Diaa, Lucas Fenaux, Florian Kerschbaum
Untrustworthy users can misuse image generators to synthesize high-quality deepfakes and engage in unethical activities. Watermarking deters misuse by marking generated content with a hidden message, enabling its detection using a secret watermarking key. A core security property of watermarking is robustness, which states that an attacker can only evade detection by substantially degrading image quality. Assessing robustness requires designing an adaptive attack for the specific watermarking algorithm. When evaluating watermarking algorithms and their (adaptive) attacks, it is challenging to determine whether an adaptive attack is optimal, i.e., the best possible attack. We solve this problem by defining an objective function and then approach adaptive attacks as an optimization problem. The core idea of our adaptive attacks is to replicate secret watermarking keys locally by creating surrogate keys that are differentiable and can be used to optimize the attack's parameters. We demonstrate for Stable Diffusion models that such an attacker can break all five surveyed watermarking methods at no visible degradation in image quality. Optimizing our attacks is efficient and requires less than 1 GPU hour to reduce the detection accuracy to 6.3% or less. Our findings emphasize the need for more rigorous robustness testing against adaptive, learnable attackers.
Authors: Lirui Wang, Yiyang Ling, Zhecheng Yuan, Mohit Shridhar, Chen Bao, Yuzhe Qin, Bailin Wang, Huazhe Xu, Xiaolong Wang
Collecting large amounts of real-world interaction data to train general robotic policies is often prohibitively expensive, thus motivating the use of simulation data. However, existing methods for data generation have generally focused on scene-level diversity (e.g., object instances and poses) rather than task-level diversity, due to the human effort required to come up with and verify novel tasks. This has made it challenging for policies trained on simulation data to demonstrate significant task-level generalization. In this paper, we propose to automatically generate rich simulation environments and expert demonstrations by exploiting a large language models' (LLM) grounding and coding ability. Our approach, dubbed GenSim, has two modes: goal-directed generation, wherein a target task is given to the LLM and the LLM proposes a task curriculum to solve the target task, and exploratory generation, wherein the LLM bootstraps from previous tasks and iteratively proposes novel tasks that would be helpful in solving more complex tasks. We use GPT4 to expand the existing benchmark by ten times to over 100 tasks, on which we conduct supervised finetuning and evaluate several LLMs including finetuned GPTs and Code Llama on code generation for robotic simulation tasks. Furthermore, we observe that LLMs-generated simulation programs can enhance task-level generalization significantly when used for multitask policy training. We further find that with minimal sim-to-real adaptation, the multitask policies pretrained on GPT4-generated simulation tasks exhibit stronger transfer to unseen long-horizon tasks in the real world and outperform baselines by 25%. See the project website (https://liruiw.github.io/gensim) for code, demos, and videos.
Authors: Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, Jianfeng Gao
Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit impressive problem-solving skills in many tasks and domains, but their ability in mathematical reasoning in visual contexts has not been systematically studied. To bridge this gap, we present MathVista, a benchmark designed to combine challenges from diverse mathematical and visual tasks. It consists of 6,141 examples, derived from 28 existing multimodal datasets involving mathematics and 3 newly created datasets (i.e., IQTest, FunctionQA, and PaperQA). Completing these tasks requires fine-grained, deep visual understanding and compositional reasoning, which all state-of-the-art foundation models find challenging. With MathVista, we have conducted a comprehensive, quantitative evaluation of 12 prominent foundation models. The best-performing GPT-4V model achieves an overall accuracy of 49.9%, substantially outperforming Bard, the second-best performer, by 15.1%. Our in-depth analysis reveals that the superiority of GPT-4V is mainly attributed to its enhanced visual perception and mathematical reasoning. However, GPT-4V still falls short of human performance by 10.4%, as it often struggles to understand complex figures and perform rigorous reasoning. This significant gap underscores the critical role that MathVista will play in the development of general-purpose AI agents capable of tackling mathematically intensive and visually rich real-world tasks. We further explore the new ability of self-verification, the application of self-consistency, and the interactive chatbot capabilities of GPT-4V, highlighting its promising potential for future research. The project is available at https://mathvista.github.io/.
Authors: Yi-Ping Chen, Liwei Wang, Yigitcan Comlek, Wei Chen
Multi-fidelity (MF) methods are gaining popularity for enhancing surrogate modeling and design optimization by incorporating data from various low-fidelity (LF) models. While most existing MF methods assume a fixed dataset, adaptive sampling methods that dynamically allocate resources among fidelity models can achieve higher efficiency in the exploring and exploiting the design space. However, most existing MF methods rely on the hierarchical assumption of fidelity levels or fail to capture the intercorrelation between multiple fidelity levels and utilize it to quantify the value of the future samples and navigate the adaptive sampling. To address this hurdle, we propose a framework hinged on a latent embedding for different fidelity models and the associated pre-posterior analysis to explicitly utilize their correlation for adaptive sampling. In this framework, each infill sampling iteration includes two steps: We first identify the location of interest with the greatest potential improvement using the high-fidelity (HF) model, then we search for the next sample across all fidelity levels that maximize the improvement per unit cost at the location identified in the first step. This is made possible by a single Latent Variable Gaussian Process (LVGP) model that maps different fidelity models into an interpretable latent space to capture their correlations without assuming hierarchical fidelity levels. The LVGP enables us to assess how LF sampling candidates will affect HF response with pre-posterior analysis and determine the next sample with the best benefit-to-cost ratio. Through test cases, we demonstrate that the proposed method outperforms the benchmark methods in both MF global fitting (GF) and Bayesian Optimization (BO) problems in convergence rate and robustness. Moreover, the method offers the flexibility to switch between GF and BO by simply changing the acquisition function.
Authors: Davin Choo, Joy Qiping Yang, Arnab Bhattacharyya, Clément L. Canonne
We establish finite-sample guarantees for efficient proper learning of bounded-degree polytrees, a rich class of high-dimensional probability distributions and a subclass of Bayesian networks, a widely-studied type of graphical model. Recently, Bhattacharyya et al. (2021) obtained finite-sample guarantees for recovering tree-structured Bayesian networks, i.e., 1-polytrees. We extend their results by providing an efficient algorithm which learns $d$-polytrees in polynomial time and sample complexity for any bounded $d$ when the underlying undirected graph (skeleton) is known. We complement our algorithm with an information-theoretic sample complexity lower bound, showing that the dependence on the dimension and target accuracy parameters are nearly tight.
Authors: Hansen Feng, Lizhi Wang, Yiqi Huang, Yuzhi Wang, Lin Zhu, Hua Huang
Recently, the mainstream practice for training low-light raw image denoising methods has shifted towards employing synthetic data. Noise modeling, which focuses on characterizing the noise distribution of real-world sensors, profoundly influences the effectiveness and practicality of synthetic data. Currently, physics-based noise modeling struggles to characterize the entire real noise distribution, while learning-based noise modeling impractically depends on paired real data. In this paper, we propose a novel strategy: learning the noise model from dark frames instead of paired real data, to break down the data dependency. Based on this strategy, we introduce an efficient physics-guided noise neural proxy (PNNP) to approximate the real-world sensor noise model. Specifically, we integrate physical priors into neural proxies and introduce three efficient techniques: physics-guided noise decoupling (PND), physics-guided proxy model (PPM), and differentiable distribution loss (DDL). PND decouples the dark frame into different components and handles different levels of noise flexibly, which reduces the complexity of noise modeling. PPM incorporates physical priors to constrain the generated noise, which promotes the accuracy of noise modeling. DDL provides explicit and reliable supervision for noise distribution, which promotes the precision of noise modeling. PNNP exhibits powerful potential in characterizing the real noise distribution. Extensive experiments on public datasets demonstrate superior performance in practical low-light raw image denoising. The code will be available at \url{https://github.com/fenghansen/PNNP}.
Authors: Cheng-Kun Yang, Min-Hung Chen, Yung-Yu Chuang, Yen-Yu Lin
We present a Multimodal Interlaced Transformer (MIT) that jointly considers 2D and 3D data for weakly supervised point cloud segmentation. Research studies have shown that 2D and 3D features are complementary for point cloud segmentation. However, existing methods require extra 2D annotations to achieve 2D-3D information fusion. Considering the high annotation cost of point clouds, effective 2D and 3D feature fusion based on weakly supervised learning is in great demand. To this end, we propose a transformer model with two encoders and one decoder for weakly supervised point cloud segmentation using only scene-level class tags. Specifically, the two encoders compute the self-attended features for 3D point clouds and 2D multi-view images, respectively. The decoder implements interlaced 2D-3D cross-attention and carries out implicit 2D and 3D feature fusion. We alternately switch the roles of queries and key-value pairs in the decoder layers. It turns out that the 2D and 3D features are iteratively enriched by each other. Experiments show that it performs favorably against existing weakly supervised point cloud segmentation methods by a large margin on the S3DIS and ScanNet benchmarks. The project page will be available at https://jimmy15923.github.io/mit_web/.
Authors: Sohrab Andaz, Carson Eisenach, Dhruv Madeka, Kari Torkkola, Randy Jia, Dean Foster, Sham Kakade
In this paper we address the problem of learning and backtesting inventory control policies in the presence of general arrival dynamics -- which we term as a quantity-over-time arrivals model (QOT). We also allow for order quantities to be modified as a post-processing step to meet vendor constraints such as order minimum and batch size constraints -- a common practice in real supply chains. To the best of our knowledge this is the first work to handle either arbitrary arrival dynamics or an arbitrary downstream post-processing of order quantities. Building upon recent work (Madeka et al., 2022) we similarly formulate the periodic review inventory control problem as an exogenous decision process, where most of the state is outside the control of the agent. Madeka et al., 2022 show how to construct a simulator that replays historic data to solve this class of problem. In our case, we incorporate a deep generative model for the arrivals process as part of the history replay. By formulating the problem as an exogenous decision process, we can apply results from Madeka et al., 2022 to obtain a reduction to supervised learning. Via simulation studies we show that this approach yields statistically significant improvements in profitability over production baselines. Using data from a real-world A/B test, we show that Gen-QOT generalizes well to off-policy data and that the resulting buying policy outperforms traditional inventory management systems in real world settings.
Authors: Aysin Tumay, Mustafa E. Aydin, Ali T. Koc, Suleyman S. Kozat
We introduce a novel ensemble approach for feature selection based on hierarchical stacking for non-stationarity and/or a limited number of samples with a large number of features. Our approach exploits the co-dependency between features using a hierarchical structure. Initially, a machine learning model is trained using a subset of features, and then the output of the model is updated using other algorithms in a hierarchical manner with the remaining features to minimize the target loss. This hierarchical structure allows for flexible depth and feature selection. By exploiting feature co-dependency hierarchically, our proposed approach overcomes the limitations of traditional feature selection methods and feature importance scores. The effectiveness of the approach is demonstrated on synthetic and well-known real-life datasets, providing significant scalable and stable performance improvements compared to the traditional methods and the state-of-the-art approaches. We also provide the source code of our approach to facilitate further research and replicability of our results.
Authors: Yuanyuan Wang, Xi Geng, Wei Huang, Biwei Huang, Mingming Gong
In this paper, we present conditions for identifying the generator of a linear stochastic differential equation (SDE) from the distribution of its solution process with a given fixed initial state. These identifiability conditions are crucial in causal inference using linear SDEs as they enable the identification of the post-intervention distributions from its observational distribution. Specifically, we derive a sufficient and necessary condition for identifying the generator of linear SDEs with additive noise, as well as a sufficient condition for identifying the generator of linear SDEs with multiplicative noise. We show that the conditions derived for both types of SDEs are generic. Moreover, we offer geometric interpretations of the derived identifiability conditions to enhance their understanding. To validate our theoretical results, we perform a series of simulations, which support and substantiate the established findings.
Authors: Kamel Alrashedy, Vincent J. Hellendoorn, Alessandro Orso
Pretrained models of code, such as CodeBERT and CodeT5, have become popular choices for code understanding and generation tasks. Such models tend to be large and require commensurate volumes of training data, which are rarely available for downstream tasks. Instead, it has become popular to train models with far larger but less realistic datasets, such as functions with artificially injected bugs. Models trained on such data, however, tend to only perform well on similar data, while underperforming on real world programs. In this paper, we conjecture that this discrepancy stems from the presence of distracting samples that steer the model away from the real-world task distribution. To investigate this conjecture, we propose an approach for identifying the subsets of these large yet unrealistic datasets that are most similar to examples in real-world datasets based on their learned representations. Our approach extracts high-dimensional embeddings of both real-world and artificial programs using a neural model and scores artificial samples based on their distance to the nearest real-world sample. We show that training on only the nearest, representationally most similar samples while discarding samples that are not at all similar in representations yields consistent improvements across two popular pretrained models of code on two code understanding tasks. Our results are promising, in that they show that training models on a representative subset of an unrealistic dataset can help us harness the power of large-scale synthetic data generation while preserving downstream task performance. Finally, we highlight the limitations of applying AI models for predicting vulnerabilities and bugs in real-world applications
Authors: Elisa Warner, Joonsang Lee, William Hsu, Tanveer Syeda-Mahmood, Charles Kahn, Olivier Gevaert, Arvind Rao
Machine learning (ML) applications in medical artificial intelligence (AI) systems have shifted from traditional and statistical methods to increasing application of deep learning models. This survey navigates the current landscape of multimodal ML, focusing on its profound impact on medical image analysis and clinical decision support systems. Emphasizing challenges and innovations in addressing multimodal representation, fusion, translation, alignment, and co-learning, the paper explores the transformative potential of multimodal models for clinical predictions. It also highlights the need for principled assessments and practical implementation of such models, bringing attention to the dynamics between decision support systems and healthcare providers and personnel. Despite advancements, challenges such as data biases and the scarcity of "big data" in many biomedical domains persist. We conclude with a discussion on principled innovation and collaborative efforts to further the mission of seamless integration of multimodal ML models into biomedical practice.
Authors: Charles Miranda, Janina Schütte, David Sommer, Martin Eigel
We sample from a given target distribution by constructing a neural network which maps samples from a simple reference, e.g. the standard normal distribution, to samples from the target. To that end, we propose using a neural network architecture inspired by the Langevin Monte Carlo (LMC) algorithm. Based on LMC perturbation results, we show approximation rates of the proposed architecture for smooth, log-concave target distributions measured in the Wasserstein-$2$ distance. The analysis heavily relies on the notion of sub-Gaussianity of the intermediate measures of the perturbed LMC process. In particular, we derive bounds on the growth of the intermediate variance proxies under different assumptions on the perturbations. Moreover, we propose an architecture similar to deep residual neural networks and derive expressivity results for approximating the sample to target distribution map.
Authors: Javier Marin
In recent years, significant progress in generative AI has highlighted the important role of physics-inspired models that utilize advanced mathematical concepts based on fundamental physics principles to enhance artificial intelligence capabilities. Among these models, those based on diffusion equations have greatly improved image quality. This study aims to explore the potential uses of Maxwell-Boltzmann equation, which forms the basis of the kinetic theory of gases, and the Michaelis-Menten model in Marketing Mix Modelling (MMM) applications. We propose incorporating these equations into Hierarchical Bayesian models to analyse consumer behaviour in the context of advertising. These equation sets excel in accurately describing the random dynamics in complex systems like social interactions and consumer-advertising interactions.
Authors: Matteo Zecchin, Kai Yu, Osvaldo Simeone
Large pre-trained sequence models, such as transformer-based architectures, have been recently shown to have the capacity to carry out in-context learning (ICL). In ICL, a decision on a new input is made via a direct mapping of the input and of a few examples from the given task, serving as the task's context, to the output variable. No explicit updates of the model parameters are needed to tailor the decision to a new task. Pre-training, which amounts to a form of meta-learning, is based on the observation of examples from several related tasks. Prior work has shown ICL capabilities for linear regression. In this study, we leverage ICL to address the inverse problem of multiple-input and multiple-output (MIMO) equalization based on a context given by pilot symbols. A task is defined by the unknown fading channel and by the signal-to-noise ratio (SNR) level, which may be known. To highlight the practical potential of the approach, we allow the presence of quantization of the received signals. We demonstrate via numerical results that transformer-based ICL has a threshold behavior, whereby, as the number of pre-training tasks grows, the performance switches from that of a minimum mean squared error (MMSE) equalizer with a prior determined by the pre-trained tasks to that of an MMSE equalizer with the true data-generating prior.
Authors: Deborah Pelacani Cruz, George Strong, Oscar Bates, Carlos Cueto, Jiashun Yao, Lluis Guasch
Quantitative evaluations of differences and/or similarities between data samples define and shape optimisation problems associated with learning data distributions. Current methods to compare data often suffer from limitations in capturing such distributions or lack desirable mathematical properties for optimisation (e.g. smoothness, differentiability, or convexity). In this paper, we introduce a new method to measure (dis)similarities between paired samples inspired by Wiener-filter theory. The convolutional nature of Wiener filters allows us to comprehensively compare data samples in a globally correlated way. We validate our approach in four machine learning applications: data compression, medical imaging imputation, translated classification, and non-parametric generative modelling. Our results demonstrate increased resolution in reconstructed images with better perceptual quality and higher data fidelity, as well as robustness against translations, compared to conventional mean-squared-error analogue implementations.
Authors: Shengbo Wang, Nian Si, Jose Blanchet, Zhengyuan Zhou
Motivated by the need for a robust policy in the face of environment shifts between training and the deployment, we contribute to the theoretical foundation of distributionally robust reinforcement learning (DRRL). This is accomplished through a comprehensive modeling framework centered around distributionally robust Markov decision processes (DRMDPs). This framework obliges the decision maker to choose an optimal policy under the worst-case distributional shift orchestrated by an adversary. By unifying and extending existing formulations, we rigorously construct DRMDPs that embraces various modeling attributes for both the decision maker and the adversary. These attributes include adaptability granularity, exploring history-dependent, Markov, and Markov time-homogeneous decision maker and adversary dynamics. Additionally, we delve into the flexibility of shifts induced by the adversary, examining SA and S-rectangularity. Within this DRMDP framework, we investigate conditions for the existence or absence of the dynamic programming principle (DPP). From an algorithmic standpoint, the existence of DPP holds significant implications, as the vast majority of existing data and computationally efficiency RL algorithms are reliant on the DPP. To study its existence, we comprehensively examine combinations of controller and adversary attributes, providing streamlined proofs grounded in a unified methodology. We also offer counterexamples for settings in which a DPP with full generality is absent.
Authors: Yuanwei Wu, Xiang Li, Yixin Liu, Pan Zhou, Lichao Sun
Existing work on jailbreak Multimodal Large Language Models (MLLMs) has focused primarily on adversarial examples in model inputs, with less attention to vulnerabilities, especially in model API. To fill the research gap, we carry out the following work: 1) We discover a system prompt leakage vulnerability in GPT-4V. Through carefully designed dialogue, we successfully extract the internal system prompts of GPT-4V. This finding indicates potential exploitable security risks in MLLMs; 2) Based on the acquired system prompts, we propose a novel MLLM jailbreaking attack method termed SASP (Self-Adversarial Attack via System Prompt). By employing GPT-4 as a red teaming tool against itself, we aim to search for potential jailbreak prompts leveraging stolen system prompts. Furthermore, in pursuit of better performance, we also add human modification based on GPT-4's analysis, which further improves the attack success rate to 98.7\%; 3) We evaluated the effect of modifying system prompts to defend against jailbreaking attacks. Results show that appropriately designed system prompts can significantly reduce jailbreak success rates. Overall, our work provides new insights into enhancing MLLM security, demonstrating the important role of system prompts in jailbreaking. This finding could be leveraged to greatly facilitate jailbreak success rates while also holding the potential for defending against jailbreaks.
Authors: Guang Yang, Yuan-Bin Liu, Lei Yang, Bing-Yang Cao
Using the atomic cluster expansion (ACE) framework, we develop a machine learning interatomic potential for fast and accurately modelling the phonon transport properties of wurtzite aluminum nitride. The predictive power of the ACE potential against density functional theory (DFT) is demonstrated across a broad range of properties of w-AlN, including ground-state lattice parameters, specific heat capacity, coefficients of thermal expansion, bulk modulus, and harmonic phonon dispersions. Validation of lattice thermal conductivity is further carried out by comparing the ACE-predicted values to the DFT calculations and experiments, exhibiting the overall capability of our ACE potential in sufficiently describing anharmonic phonon interactions. As a practical application, we perform a lattice dynamics analysis using the potential to unravel the effects of biaxial strains on thermal conductivity and phonon properties of w-AlN, which is identified as a significant tuning factor for near-junction thermal design of w-AlN-based electronics.
Authors: Christoph Kern, Stephanie Eckman, Jacob Beck, Rob Chew, Bolei Ma, Frauke Kreuter
When training data are collected from human annotators, the design of the annotation instrument, the instructions given to annotators, the characteristics of the annotators, and their interactions can impact training data. This study demonstrates that design choices made when creating an annotation instrument also impact the models trained on the resulting annotations. We introduce the term annotation sensitivity to refer to the impact of annotation data collection methods on the annotations themselves and on downstream model performance and predictions. We collect annotations of hate speech and offensive language in five experimental conditions of an annotation instrument, randomly assigning annotators to conditions. We then fine-tune BERT models on each of the five resulting datasets and evaluate model performance on a holdout portion of each condition. We find considerable differences between the conditions for 1) the share of hate speech/offensive language annotations, 2) model performance, 3) model predictions, and 4) model learning curves. Our results emphasize the crucial role played by the annotation instrument which has received little attention in the machine learning literature. We call for additional research into how and why the instrument impacts the annotations to inform the development of best practices in instrument design.
Authors: Shuo Chen, Boxiao Liu, Haihang You
Spiking Neural Networks (SNNs) have gained considerable attention due to the energy-efficient and multiplication-free characteristics. The continuous growth in scale of deep SNNs poses challenges for model deployment. Network pruning reduces hardware resource requirements of model deployment by compressing the network scale. However, existing SNN pruning methods cause high pruning costs and performance loss because the pruning iterations amplify the training difficulty of SNNs. In this paper, inspired by the critical brain hypothesis in neuroscience, we propose a regeneration mechanism based on the neuron criticality for SNN pruning to enhance feature extraction and accelerate the pruning process. Firstly, we propose a low-cost metric for the criticality in SNNs. Then, we re-rank the pruned structures after pruning and regenerate those with higher criticality to obtain the critical network. Our method achieves higher performance than the current state-of-the-art (SOTA) method with up to 95.26% reduction of pruning cost. Moreover, we investigate the underlying mechanism of our method and find that it efficiently selects potential structures and learns the consistent feature representation.
Authors: Benjamin Schneider, Nils Lukas, Florian Kerschbaum
Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike adversarial examples, backdoor attacks often target specific classes rather than any class learned by the model. One might expect that targeting many classes through a naive composition of attacks vastly increases the number of poison samples. We show this is not necessarily true and more efficient, universal data poisoning attacks exist that allow controlling misclassifications from any source class into any target class with a small increase in poison samples. Our idea is to generate triggers with salient characteristics that the model can learn. The triggers we craft exploit a phenomenon we call inter-class poison transferability, where learning a trigger from one class makes the model more vulnerable to learning triggers for other classes. We demonstrate the effectiveness and robustness of our universal backdoor attacks by controlling models with up to 6,000 classes while poisoning only 0.15% of the training dataset. Our source code is available at https://github.com/Ben-Schneider-code/Universal-Backdoor-Attacks.
Authors: Kaitlyn Wang, Jian Ge, Kevin Willis, Kevin Wang, Yinan Zhao
This paper presents GPFC, a novel Graphics Processing Unit (GPU) Phase Folding and Convolutional Neural Network (CNN) system to detect exoplanets using the transit method. We devise a fast folding algorithm parallelized on a GPU to amplify low signal-to-noise ratio transit signals, allowing a search at high precision and speed. A CNN trained on two million synthetic light curves reports a score indicating the likelihood of a planetary signal at each period. While the GPFC method has broad applicability across period ranges, this research specifically focuses on detecting ultra-short-period planets with orbital periods less than one day. GPFC improves on speed by three orders of magnitude over the predominant Box-fitting Least Squares (BLS) method. Our simulation results show GPFC achieves $97%$ training accuracy, higher true positive rate at the same false positive rate of detection, and higher precision at the same recall rate when compared to BLS. GPFC recovers $100\%$ of known ultra-short-period planets in $\textit{Kepler}$ light curves from a blind search. These results highlight the promise of GPFC as an alternative approach to the traditional BLS algorithm for finding new transiting exoplanets in data taken with $\textit{Kepler}$ and other space transit missions such as K2, TESS and future PLATO and Earth 2.0.
Authors: Bokun Wang, Tianbao Yang
This paper revisits a class of convex Finite-Sum Coupled Compositional Stochastic Optimization (cFCCO) problems with many applications, including group distributionally robust optimization (GDRO), learning with imbalanced data, reinforcement learning, and learning to rank. To better solve these problems, we introduce an efficient single-loop primal-dual block-coordinate proximal algorithm, dubbed ALEXR. This algorithm leverages block-coordinate stochastic mirror ascent updates for the dual variable and stochastic proximal gradient descent updates for the primal variable. We establish the convergence rates of ALEXR in both convex and strongly convex cases under smoothness and non-smoothness conditions of involved functions, which not only improve the best rates in previous works on smooth cFCCO problems but also expand the realm of cFCCO for solving more challenging non-smooth problems such as the dual form of GDRO. Finally, we present lower complexity bounds to demonstrate that the convergence rates of ALEXR are optimal among first-order block-coordinate stochastic algorithms for the considered class of cFCCO problems.
Authors: Zhongyuan Zhao, Jake Perazzone, Gunjan Verma, Santiago Segarra
Computational offloading has become an enabling component for edge intelligence in mobile and smart devices. Existing offloading schemes mainly focus on mobile devices and servers, while ignoring the potential network congestion caused by tasks from multiple mobile devices, especially in wireless multi-hop networks. To fill this gap, we propose a low-overhead, congestion-aware distributed task offloading scheme by augmenting a distributed greedy framework with graph-based machine learning. In simulated wireless multi-hop networks with 20-110 nodes and a resource allocation scheme based on shortest path routing and contention-based link scheduling, our approach is demonstrated to be effective in reducing congestion or unstable queues under the context-agnostic baseline, while improving the execution latency over local computing.
Authors: Amirhesam Abedsoltan, Mikhail Belkin, Parthe Pandit, Luis Rademacher
Kernel methods are a popular class of nonlinear predictive models in machine learning. Scalable algorithms for learning kernel models need to be iterative in nature, but convergence can be slow due to poor conditioning. Spectral preconditioning is an important tool to speed-up the convergence of such iterative algorithms for training kernel models. However computing and storing a spectral preconditioner can be expensive which can lead to large computational and storage overheads, precluding the application of kernel methods to problems with large datasets. A Nystrom approximation of the spectral preconditioner is often cheaper to compute and store, and has demonstrated success in practical applications. In this paper we analyze the trade-offs of using such an approximated preconditioner. Specifically, we show that a sample of logarithmic size (as a function of the size of the dataset) enables the Nystrom-based approximated preconditioner to accelerate gradient descent nearly as well as the exact preconditioner, while also reducing the computational and storage overheads.
Authors: Zihan Zhang, Wenhao Zhan, Yuxin Chen, Simon S. Du, Jason D. Lee
Multi-distribution learning (MDL), which seeks to learn a shared model that minimizes the worst-case risk across $k$ distinct data distributions, has emerged as a unified framework in response to the evolving demand for robustness, fairness, multi-group collaboration, etc. Achieving data-efficient MDL necessitates adaptive sampling, also called on-demand sampling, throughout the learning process. However, there exist substantial gaps between the state-of-the-art upper and lower bounds on the optimal sample complexity. Focusing on a hypothesis class of Vapnik-Chervonenkis (VC) dimension $d$, we propose a novel algorithm that yields an $varepsilon$-optimal randomized hypothesis with a sample complexity on the order of $(d+k)/\varepsilon^2$ (modulo some logarithmic factor), matching the best-known lower bound. Our algorithmic ideas and theory have been further extended to accommodate Rademacher classes. The proposed algorithms are oracle-efficient, which access the hypothesis class solely through an empirical risk minimization oracle. Additionally, we establish the necessity of randomization, unveiling a large sample size barrier when only deterministic hypotheses are permitted. These findings successfully resolve three open problems presented in COLT 2023 (i.e., Awasthi et al., (2023, Problem 1, 3 and 4)).
Authors: Manon Flageat, Bryan Lim, Antoine Cully
Many applications in Reinforcement Learning (RL) usually have noise or stochasticity present in the environment. Beyond their impact on learning, these uncertainties lead the exact same policy to perform differently, i.e. yield different return, from one roll-out to another. Common evaluation procedures in RL summarise the consequent return distributions using solely the expected return, which does not account for the spread of the distribution. Our work defines this spread as the policy reproducibility: the ability of a policy to obtain similar performance when rolled out many times, a crucial property in some real-world applications. We highlight that existing procedures that only use the expected return are limited on two fronts: first an infinite number of return distributions with a wide range of performance-reproducibility trade-offs can have the same expected return, limiting its effectiveness when used for comparing policies; second, the expected return metric does not leave any room for practitioners to choose the best trade-off value for considered applications. In this work, we address these limitations by recommending the use of Lower Confidence Bound, a metric taken from Bayesian optimisation that provides the user with a preference parameter to choose a desired performance-reproducibility trade-off. We also formalise and quantify policy reproducibility, and demonstrate the benefit of our metrics using extensive experiments of popular RL algorithms on common uncertain RL tasks.
Authors: Baihe Huang, Banghua Zhu, Hanlin Zhu, Jason D. Lee, Jiantao Jiao, Michael I. Jordan
We study statistical watermarking by formulating it as a hypothesis testing problem, a general framework which subsumes all previous statistical watermarking methods. Key to our formulation is a coupling of the output tokens and the rejection region, realized by pseudo-random generators in practice, that allows non-trivial trade-off between the Type I error and Type II error. We characterize the Uniformly Most Powerful (UMP) watermark in the general hypothesis testing setting and the minimax Type II error in the model-agnostic setting. In the common scenario where the output is a sequence of $n$ tokens, we establish nearly matching upper and lower bounds on the number of i.i.d. tokens required to guarantee small Type I and Type II errors. Our rate of $\Theta(h^{-1} \log (1/h))$ with respect to the average entropy per token $h$ highlights potentials for improvement from the rate of $h^{-2}$ in the previous works. Moreover, we formulate the robust watermarking problem where users are allowed to perform a class of perturbations on the generated texts, and characterize the optimal type II error of robust UMP tests via a linear programming problem. To the best of our knowledge, this is the first systematic statistical treatment on the watermarking problem with near-optimal rates in the i.i.d. setting, which might be of interest for future works.
Authors: Zhaoxi Mu, Xinyu Yang, Sining Sun, Qing Yang
Speech signals are inherently complex as they encompass both global acoustic characteristics and local semantic information. However, in the task of target speech extraction, certain elements of global and local semantic information in the reference speech, which are irrelevant to speaker identity, can lead to speaker confusion within the speech extraction network. To overcome this challenge, we propose a self-supervised disentangled representation learning method. Our approach tackles this issue through a two-phase process, utilizing a reference speech encoding network and a global information disentanglement network to gradually disentangle the speaker identity information from other irrelevant factors. We exclusively employ the disentangled speaker identity information to guide the speech extraction network. Moreover, we introduce the adaptive modulation Transformer to ensure that the acoustic representation of the mixed signal remains undisturbed by the speaker embeddings. This component incorporates speaker embeddings as conditional information, facilitating natural and efficient guidance for the speech extraction network. Experimental results substantiate the effectiveness of our meticulously crafted approach, showcasing a substantial reduction in the likelihood of speaker confusion.
Authors: Xiao Tian, Rachael Hwee Ling Sim, Jue Fan, Bryan Kian Hsiang Low
Data valuation is concerned with determining a fair valuation of data from data sources to compensate them or to identify training examples that are the most or least useful for predictions. With the rising interest in personal data ownership and data protection regulations, model owners will likely have to fulfil more data deletion requests. This raises issues that have not been addressed by existing works: Are the data valuation scores still fair with deletions? Must the scores be expensively recomputed? The answer is no. To avoid recomputations, we propose using our data valuation framework DeRDaVa upfront for valuing each data source's contribution to preserving robust model performance after anticipated data deletions. DeRDaVa can be efficiently approximated and will assign higher values to data that are more useful or less likely to be deleted. We further generalize DeRDaVa to Risk-DeRDaVa to cater to risk-averse/seeking model owners who are concerned with the worst/best-cases model utility. We also empirically demonstrate the practicality of our solutions.
Authors: YoungJoon Yoo, Jongwon Choi
This paper introduces a novel approach for topic modeling utilizing latent codebooks from Vector-Quantized Variational Auto-Encoder~(VQ-VAE), discretely encapsulating the rich information of the pre-trained embeddings such as the pre-trained language model. From the novel interpretation of the latent codebooks and embeddings as conceptual bag-of-words, we propose a new generative topic model called Topic-VQ-VAE~(TVQ-VAE) which inversely generates the original documents related to the respective latent codebook. The TVQ-VAE can visualize the topics with various generative distributions including the traditional BoW distribution and the autoregressive image generation. Our experimental results on document analysis and image generation demonstrate that TVQ-VAE effectively captures the topic context which reveals the underlying structures of the dataset and supports flexible forms of document generation. Official implementation of the proposed TVQ-VAE is available at https://github.com/clovaai/TVQ-VAE.
Authors: Yang Jiao, Kai Yang, Tiancheng Wu, Chengtao Jian, Jianwei Huang
Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach; 2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes $\mu$-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed $\mu$-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the $\mu$-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain $\epsilon$-stationary point is upper bounded by $\mathcal{O}(\frac{1}{\epsilon^2})$. Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80$\%$.
Authors: Dongmin Kim, Sunghyun Park, Jaegul Choo
Time-series anomaly detection deals with the problem of detecting anomalous timesteps by learning normality from the sequence of observations. However, the concept of normality evolves over time, leading to a "new normal problem", where the distribution of normality can be changed due to the distribution shifts between training and test data. This paper highlights the prevalence of the new normal problem in unsupervised time-series anomaly detection studies. To tackle this issue, we propose a simple yet effective test-time adaptation strategy based on trend estimation and a self-supervised approach to learning new normalities during inference. Extensive experiments on real-world benchmarks demonstrate that incorporating the proposed strategy into the anomaly detector consistently improves the model's performance compared to the baselines, leading to robustness to the distribution shifts.
Authors: Tao Wu, Tie Luo, Donald C. Wunsch
The transferability of adversarial examples is of central importance to transfer-based black-box adversarial attacks. Previous works for generating transferable adversarial examples focus on attacking \emph{given} pretrained surrogate models while the connections between surrogate models and adversarial trasferability have been overlooked. In this paper, we propose {\em Lipschitz Regularized Surrogate} (LRS) for transfer-based black-box attacks, a novel approach that transforms surrogate models towards favorable adversarial transferability. Using such transformed surrogate models, any existing transfer-based black-box attack can run without any change, yet achieving much better performance. Specifically, we impose Lipschitz regularization on the loss landscape of surrogate models to enable a smoother and more controlled optimization process for generating more transferable adversarial examples. In addition, this paper also sheds light on the connection between the inner properties of surrogate models and adversarial transferability, where three factors are identified: smaller local Lipschitz constant, smoother loss landscape, and stronger adversarial robustness. We evaluate our proposed LRS approach by attacking state-of-the-art standard deep neural networks and defense models. The results demonstrate significant improvement on the attack success rates and transferability. Our code is available at https://github.com/TrustAIoT/LRS.
Authors: Yousef El-Laham, Elizabeth Fons, Dillon Daudert, Svitlana Vyetrenko
Data augmentation techniques play an important role in enhancing the performance of deep learning models. Despite their proven benefits in computer vision tasks, their application in the other domains remains limited. This paper proposes a Mixup regularization scheme, referred to as UMAP Mixup, designed for ``on-manifold" automated data augmentation for deep learning predictive models. The proposed approach ensures that the Mixup operations result in synthesized samples that lie on the data manifold of the features and labels by utilizing a dimensionality reduction technique known as uniform manifold approximation and projection. Evaluations across diverse regression tasks show that UMAP Mixup is competitive with or outperforms other Mixup variants, show promise for its potential as an effective tool for enhancing the generalization performance of deep learning models.
Authors: Zhongchang Sun, Yousef El-Laham, Svitlana Vyetrenko
Stochastic differential equations (SDEs) have been widely used to model real world random phenomena. Existing works mainly focus on the case where the time series is modeled by a single SDE, which might be restrictive for modeling time series with distributional shift. In this work, we propose a change point detection algorithm for time series modeled as neural SDEs. Given a time series dataset, the proposed method jointly learns the unknown change points and the parameters of distinct neural SDE models corresponding to each change point. Specifically, the SDEs are learned under the framework of generative adversarial networks (GANs) and the change points are detected based on the output of the GAN discriminator in a forward pass. At each step of the proposed algorithm, the change points and the SDE model parameters are updated in an alternating fashion. Numerical results on both synthetic and real datasets are provided to validate the performance of our algorithm in comparison to classical change point detection benchmarks, standard GAN-based neural SDEs, and other state-of-the-art deep generative models for time series data.
Authors: Zhixuan Chu, Mengxuan Hu, Qing Cui, Longfei Li, Sheng Li
Since artificial intelligence has seen tremendous recent successes in many areas, it has sparked great interest in its potential for trustworthy and interpretable risk prediction. However, most models lack causal reasoning and struggle with class imbalance, leading to poor precision and recall. To address this, we propose a Task-Driven Causal Feature Distillation model (TDCFD) to transform original feature values into causal feature attributions for the specific risk prediction task. The causal feature attribution helps describe how much contribution the value of this feature can make to the risk prediction result. After the causal feature distillation, a deep neural network is applied to produce trustworthy prediction results with causal interpretability and high precision/recall. We evaluate the performance of our TDCFD method on several synthetic and real datasets, and the results demonstrate its superiority over the state-of-the-art methods regarding precision, recall, interpretability, and causality.
Authors: Harold Benoit, Liangze Jiang, Andrei Atanov, Oğuzhan Fatih Kar, Mattia Rigotti, Amir Zamir
Supervised learning datasets may contain multiple cues that explain the training set equally well, i.e., learning any of them would lead to the correct predictions on the training data. However, many of them can be spurious, i.e., lose their predictive power under a distribution shift and consequently fail to generalize to out-of-distribution (OOD) data. Recently developed "diversification" methods (Lee et al., 2023; Pagliardini et al., 2023) approach this problem by finding multiple diverse hypotheses that rely on different features. This paper aims to study this class of methods and identify the key components contributing to their OOD generalization abilities.
We show that (1) diversification methods are highly sensitive to the distribution of the unlabeled data used for diversification and can underperform significantly when away from a method-specific sweet spot. (2) Diversification alone is insufficient for OOD generalization. The choice of the used learning algorithm, e.g., the model's architecture and pretraining, is crucial. In standard experiments (classification on Waterbirds and Office-Home datasets), using the second-best choice leads to an up to 20\% absolute drop in accuracy. (3) The optimal choice of learning algorithm depends on the unlabeled data and vice versa i.e. they are co-dependent. (4) Finally, we show that, in practice, the above pitfalls cannot be alleviated by increasing the number of diverse hypotheses, the major feature of diversification methods.
These findings provide a clearer understanding of the critical design factors influencing the OOD generalization abilities of diversification methods. They can guide practitioners in how to use the existing methods best and guide researchers in developing new, better ones.
Authors: Daniel Huttenlocher, Hannah Li, Liang Lyu, Asuman Ozdaglar, James Siderius
Many online platforms of today, including social media sites, are two-sided markets bridging content creators and users. Most of the existing literature on platform recommendation algorithms largely focuses on user preferences and decisions, and does not simultaneously address creator incentives. We propose a model of content recommendation that explicitly focuses on the dynamics of user-content matching, with the novel property that both users and creators may leave the platform permanently if they do not experience sufficient engagement. In our model, each player decides to participate at each time step based on utilities derived from the current match: users based on alignment of the recommended content with their preferences, and creators based on their audience size. We show that a user-centric greedy algorithm that does not consider creator departures can result in arbitrarily poor total engagement, relative to an algorithm that maximizes total engagement while accounting for two-sided departures. Moreover, in stark contrast to the case where only users or only creators leave the platform, we prove that with two-sided departures, approximating maximum total engagement within any constant factor is NP-hard. We present two practical algorithms, one with performance guarantees under mild assumptions on user preferences, and another that tends to outperform algorithms that ignore two-sided departures in practice.
Authors: Sebastian-Vasile Echim, Iulian-Marius Tăiatu, Dumitru-Clementin Cercel, Florin Pop
This work focuses on plant leaf disease classification and explores three crucial aspects: adversarial training, model explainability, and model compression. The models' robustness against adversarial attacks is enhanced through adversarial training, ensuring accurate classification even in the presence of threats. Leveraging explainability techniques, we gain insights into the model's decision-making process, improving trust and transparency. Additionally, we explore model compression techniques to optimize computational efficiency while maintaining classification performance. Through our experiments, we determine that on a benchmark dataset, the robustness can be the price of the classification accuracy with performance reductions of 3%-20% for regular tests and gains of 50%-70% for adversarial attack tests. We also demonstrate that a student model can be 15-25 times more computationally efficient for a slight performance reduction, distilling the knowledge of more complex models.
Authors: Jie Feng, Ke Wei, Jinchi Chen
Natural policy gradient (NPG) and its variants are widely-used policy search methods in reinforcement learning. Inspired by prior work, a new NPG variant coined NPG-HM is developed in this paper, which utilizes the Hessian-aided momentum technique for variance reduction, while the sub-problem is solved via the stochastic gradient descent method. It is shown that NPG-HM can achieve the global last iterate $\epsilon$-optimality with a sample complexity of $\mathcal{O}(\epsilon^{-2})$, which is the best known result for natural policy gradient type methods under the generic Fisher non-degenerate policy parameterizations. The convergence analysis is built upon a relaxed weak gradient dominance property tailored for NPG under the compatible function approximation framework, as well as a neat way to decompose the error when handling the sub-problem. Moreover, numerical experiments on Mujoco-based environments demonstrate the superior performance of NPG-HM over other state-of-the-art policy gradient methods.
Authors: Baiting Luo, Yunuo Zhang, Abhishek Dubey, Ayan Mukhopadhyay
A fundamental (and largely open) challenge in sequential decision-making is dealing with non-stationary environments, where exogenous environmental conditions change over time. Such problems are traditionally modeled as non-stationary Markov decision processes (NSMDP). However, existing approaches for decision-making in NSMDPs have two major shortcomings: first, they assume that the updated environmental dynamics at the current time are known (although future dynamics can change); and second, planning is largely pessimistic, i.e., the agent acts ``safely'' to account for the non-stationary evolution of the environment. We argue that both these assumptions are invalid in practice -- updated environmental conditions are rarely known, and as the agent interacts with the environment, it can learn about the updated dynamics and avoid being pessimistic, at least in states whose dynamics it is confident about. We present a heuristic search algorithm called \textit{Adaptive Monte Carlo Tree Search (ADA-MCTS)} that addresses these challenges. We show that the agent can learn the updated dynamics of the environment over time and then act as it learns, i.e., if the agent is in a region of the state space about which it has updated knowledge, it can avoid being pessimistic. To quantify ``updated knowledge,'' we disintegrate the aleatoric and epistemic uncertainty in the agent's updated belief and show how the agent can use these estimates for decision-making. We compare the proposed approach with the multiple state-of-the-art approaches in decision-making across multiple well-established open-source problems and empirically show that our approach is faster and highly adaptive without sacrificing safety.
Authors: Ava Pettet, Yunuo Zhang, Baiting Luo, Kyle Wray, Hendrik Baier, Aron Laszka, Abhishek Dubey, Ayan Mukhopadhyay
Sequential decision-making under uncertainty is present in many important problems. Two popular approaches for tackling such problems are reinforcement learning and online search (e.g., Monte Carlo tree search). While the former learns a policy by interacting with the environment (typically done before execution), the latter uses a generative model of the environment to sample promising action trajectories at decision time. Decision-making is particularly challenging in non-stationary environments, where the environment in which an agent operates can change over time. Both approaches have shortcomings in such settings -- on the one hand, policies learned before execution become stale when the environment changes and relearning takes both time and computational effort. Online search, on the other hand, can return sub-optimal actions when there are limitations on allowed runtime. In this paper, we introduce \textit{Policy-Augmented Monte Carlo tree search} (PA-MCTS), which combines action-value estimates from an out-of-date policy with an online search using an up-to-date model of the environment. We prove theoretical results showing conditions under which PA-MCTS selects the one-step optimal action and also bound the error accrued while following PA-MCTS as a policy. We compare and contrast our approach with AlphaZero, another hybrid planning approach, and Deep Q Learning on several OpenAI Gym environments. Through extensive experiments, we show that under non-stationary settings with limited time constraints, PA-MCTS outperforms these baselines.
Authors: Quan Wang, Yiling Huang, Guanlong Zhao, Evan Clark, Wei Xia, Hank Liao
In this paper, we introduce DiarizationLM, a framework to leverage large language models (LLM) to post-process the outputs from a speaker diarization system. Various goals can be achieved with the proposed framework, such as improving the readability of the diarized transcript, or reducing the word diarization error rate (WDER). In this framework, the outputs of the automatic speech recognition (ASR) and speaker diarization systems are represented as a compact textual format, which is included in the prompt to an optionally finetuned LLM. The outputs of the LLM can be used as the refined diarization results with the desired enhancement. As a post-processing step, this framework can be easily applied to any off-the-shelf ASR and speaker diarization systems without retraining existing components. Our experiments show that a finetuned PaLM 2-S model can reduce the WDER by rel. 55.5% on the Fisher telephone conversation dataset, and rel. 44.9% on the Callhome English dataset.
Authors: Alex Havrilla, Kevin Rojas, Wenjing Liao, Molei Tao
Diffusion generative models have achieved remarkable success in generating images with a fixed resolution. However, existing models have limited ability to generalize to different resolutions when training data at those resolutions are not available. Leveraging techniques from operator learning, we present a novel deep-learning architecture, Dual-FNO UNet (DFU), which approximates the score operator by combining both spatial and spectral information at multiple resolutions. Comparisons of DFU to baselines demonstrate its scalability: 1) simultaneously training on multiple resolutions improves FID over training at any single fixed resolution; 2) DFU generalizes beyond its training resolutions, allowing for coherent, high-fidelity generation at higher-resolutions with the same model, i.e. zero-shot super-resolution image-generation; 3) we propose a fine-tuning strategy to further enhance the zero-shot super-resolution image-generation capability of our model, leading to a FID of 11.3 at 1.66 times the maximum training resolution on FFHQ, which no other method can come close to achieving.
Authors: Liu Yang, Stanley J. Osher
Can we build a single large model for a wide range of PDE-related scientific learning tasks? Can this model generalize to new PDEs, even of new forms, without any fine-tuning? In-context operator learning and the corresponding model In-Context Operator Networks (ICON) represent an initial exploration of these questions. The capability of ICON regarding the first question has been demonstrated previously. In this paper, we present a detailed methodology for solving PDE problems with ICON, and show how a single ICON model can make forward and reverse predictions for different equations with different strides, provided with appropriately designed data prompts. We show the positive evidence to the second question, i.e., ICON can generalize well to some PDEs with new forms without any fine-tuning. This is exemplified through a study on 1D scalar nonlinear conservation laws, a family of PDEs with temporal evolution. We also show how to broaden the range of problems that an ICON model can address, by transforming functions and equations to ICON's capability scope. We believe that the progress in this paper is a significant step towards the goal of training a foundation model for PDE-related tasks under the in-context operator learning framework.
Authors: Alexander Bork, Debraj Chakraborty, Kush Grover, Jan Kretinsky, Stefanie Mohr
Strategies for partially observable Markov decision processes (POMDP) typically require memory. One way to represent this memory is via automata. We present a method to learn an automaton representation of a strategy using a modification of the L*-algorithm. Compared to the tabular representation of a strategy, the resulting automaton is dramatically smaller and thus also more explainable. Moreover, in the learning process, our heuristics may even improve the strategy's performance. In contrast to approaches that synthesize an automaton directly from the POMDP thereby solving it, our approach is incomparably more scalable.
Authors: Shayan Mohajer Hamidi, Linfeng Ye
Deep neural networks (DNNs) could be deceived by generating human-imperceptible perturbations of clean samples. Therefore, enhancing the robustness of DNNs against adversarial attacks is a crucial task. In this paper, we aim to train robust DNNs by limiting the set of outputs reachable via a norm-bounded perturbation added to a clean sample. We refer to this set as adversarial polytope, and each clean sample has a respective adversarial polytope. Indeed, if the respective polytopes for all the samples are compact such that they do not intersect the decision boundaries of the DNN, then the DNN is robust against adversarial samples. Hence, the inner-working of our algorithm is based on learning \textbf{c}onfined \textbf{a}dversarial \textbf{p}olytopes (CAP). By conducting a thorough set of experiments, we demonstrate the effectiveness of CAP over existing adversarial robustness methods in improving the robustness of models against state-of-the-art attacks including AutoAttack.
Authors: Bang An, Mucong Ding, Tahseen Rabbani, Aakriti Agrawal, Yuancheng Xu, Chenghao Deng, Sicheng Zhu, Abdirisak Mohamed, Yuxin Wen, Tom Goldstein, Furong Huang
This paper investigates the weaknesses of image watermarking techniques. We present WAVES (Watermark Analysis Via Enhanced Stress-testing), a novel benchmark for assessing watermark robustness, overcoming the limitations of current evaluation methods.WAVES integrates detection and identification tasks, and establishes a standardized evaluation protocol comprised of a diverse range of stress tests. The attacks in WAVES range from traditional image distortions to advanced and novel variations of diffusive, and adversarial attacks. Our evaluation examines two pivotal dimensions: the degree of image quality degradation and the efficacy of watermark detection after attacks. We develop a series of Performance vs. Quality 2D plots, varying over several prominent image similarity metrics, which are then aggregated in a heuristically novel manner to paint an overall picture of watermark robustness and attack potency. Our comprehensive evaluation reveals previously undetected vulnerabilities of several modern watermarking algorithms. We envision WAVES as a toolkit for the future development of robust watermarking systems. The project is available at https://wavesbench.github.io/
Authors: Mostafa Rezapour, Muhammad Khalid Khan Niazi, Hao Lu, Aarthi Narayanan, Metin Nafi Gurcan
This study introduces the Supervised Magnitude-Altitude Scoring (SMAS) methodology, a machine learning-based approach, for analyzing gene expression data obtained from nonhuman primates (NHPs) infected with Ebola virus (EBOV). We utilize a comprehensive dataset of NanoString gene expression profiles from Ebola-infected NHPs, deploying the SMAS system for nuanced host-pathogen interaction analysis. SMAS effectively combines gene selection based on statistical significance and expression changes, employing linear classifiers such as logistic regression to accurately differentiate between RT-qPCR positive and negative NHP samples. A key finding of our research is the identification of IFI6 and IFI27 as critical biomarkers, demonstrating exceptional predictive performance with 100% accuracy and Area Under the Curve (AUC) metrics in classifying various stages of Ebola infection. Alongside IFI6 and IFI27, genes, including MX1, OAS1, and ISG15, were significantly upregulated, highlighting their essential roles in the immune response to EBOV. Our results underscore the efficacy of the SMAS method in revealing complex genetic interactions and response mechanisms during EBOV infection. This research provides valuable insights into EBOV pathogenesis and aids in developing more precise diagnostic tools and therapeutic strategies to address EBOV infection in particular and viral infection in general.
Authors: Nicholas Konz, Maciej A. Mazurowski
This paper investigates discrepancies in how neural networks learn from different imaging domains, which are commonly overlooked when adopting computer vision techniques from the domain of natural images to other specialized domains such as medical images. Recent works have found that the generalization error of a trained network typically increases with the intrinsic dimension ($d_{data}$) of its training set. Yet, the steepness of this relationship varies significantly between medical (radiological) and natural imaging domains, with no existing theoretical explanation. We address this gap in knowledge by establishing and empirically validating a generalization scaling law with respect to $d_{data}$, and propose that the substantial scaling discrepancy between the two considered domains may be at least partially attributed to the higher intrinsic "label sharpness" ($K_F$) of medical imaging datasets, a metric which we propose. Next, we demonstrate an additional benefit of measuring the label sharpness of a training set: it is negatively correlated with the trained model's adversarial robustness, which notably leads to models for medical images having a substantially higher vulnerability to adversarial attack. Finally, we extend our $d_{data}$ formalism to the related metric of learned representation intrinsic dimension ($d_{repr}$), derive a generalization scaling law with respect to $d_{repr}$, and show that $d_{data}$ serves as an upper bound for $d_{repr}$. Our theoretical results are supported by thorough experiments with six models and eleven natural and medical imaging datasets over a range of training set sizes. Our findings offer insights into the influence of intrinsic dataset properties on generalization, representation learning, and robustness in deep neural networks.
Authors: Saba Aslam, Hafsa Aslam, Arslan Manzoor, Chen Hui, Abdur Rasool
The escalating reliance on revolutionary online web services has introduced heightened security risks, with persistent challenges posed by phishing despite extensive security measures. Traditional phishing systems, reliant on machine learning and manual features, struggle with evolving tactics. Recent advances in deep learning offer promising avenues for tackling novel phishing challenges and malicious URLs. This paper introduces a two-phase stack generalized model named AntiPhishStack, designed to detect phishing sites. The model leverages the learning of URLs and character-level TF-IDF features symmetrically, enhancing its ability to combat emerging phishing threats. In Phase I, features are trained on a base machine learning classifier, employing K-fold cross-validation for robust mean prediction. Phase II employs a two-layered stacked-based LSTM network with five adaptive optimizers for dynamic compilation, ensuring premier prediction on these features. Additionally, the symmetrical predictions from both phases are optimized and integrated to train a meta-XGBoost classifier, contributing to a final robust prediction. The significance of this work lies in advancing phishing detection with AntiPhishStack, operating without prior phishing-specific feature knowledge. Experimental validation on two benchmark datasets, comprising benign and phishing or malicious URLs, demonstrates the model's exceptional performance, achieving a notable 96.04% accuracy compared to existing studies. This research adds value to the ongoing discourse on symmetry and asymmetry in information security and provides a forward-thinking solution for enhancing network security in the face of evolving cyber threats.
Authors: Haoxiong Liu, Andrew Chi-Chih Yao
Despite recent progress in improving the mathematical reasoning ability of large language models(LLMs), solving competition-level math problems without the use of external tools remains challenging for open-source LLMs. In this work, we introduce the MMIQC dataset, a mixture of processed web data and synthetic question-response pairs, to equip base models with better mathematical reasoning skills. In different model sizes, the models fine-tuned on MMIQC consistently outperform their counterparts by a clear margin on MATH test set. Notably, DeepSeek-67B-MMIQC achieves a 41.0% accuracy, 4.2% higher than the previous open-source SOTA. Our experiments also show that a large part of the improvement can be attributed to our novel augmentation method IQC(Iterative Question Composing), where we iteratively ask an LLM to compose new questions from the given seed problems and do rejection sampling from another LLM. MMIQC has now been released on https://huggingface.co/datasets/Vivacem/MMIQC.
Authors: Tong Xie, Haoyu Li, Andrew Bai, Cho-Jui Hsieh
Data attribution methods trace model behavior back to its training dataset, offering an effective approach to better understand ''black-box'' neural networks. While prior research has established quantifiable links between model output and training data in diverse settings, interpreting diffusion model outputs in relation to training samples remains underexplored. In particular, diffusion models operate over a sequence of timesteps instead of instantaneous input-output relationships in previous contexts, posing a significant challenge to extend existing frameworks to diffusion models directly. Notably, we present Diffusion-TracIn that incorporates this temporal dynamics and observe that samples' loss gradient norms are highly dependent on timestep. This trend leads to a prominent bias in influence estimation, and is particularly noticeable for samples trained on large-norm-inducing timesteps, causing them to be generally influential. To mitigate this effect, we introduce Diffusion-ReTrac as a re-normalized adaptation that enables the retrieval of training samples more targeted to the test sample of interest, facilitating a localized measurement of influence and considerably more intuitive visualization. We demonstrate the efficacy of our approach through various evaluation metrics and auxiliary tasks, reducing the amount of generally influential samples to $\frac{1}{3}$ of its original quantity.
Authors: Emanuele La Malfa, Christoph Weinhuber, Orazio Torre, Fangru Lin, Anthony Cohn, Nigel Shadbolt, Michael Wooldridge
We investigate the extent to which Large Language Models (LLMs) can simulate the execution of computer code and algorithms. We begin by looking at straight line programs, and show that current LLMs demonstrate poor performance even with such simple programs -- performance rapidly degrades with the length of code. We then investigate the ability of LLMs to simulate programs that contain critical paths and redundant instructions. We also go beyond straight line program simulation with sorting algorithms and nested loops, and we show the computational complexity of a routine directly affects the ability of an LLM to simulate its execution. We observe that LLMs execute instructions sequentially and with a low error margin only for short programs or standard procedures. LLMs' code simulation is in tension with their pattern recognition and memorisation capabilities: on tasks where memorisation is detrimental, we propose a novel prompting method to simulate code execution line by line. Empirically, our new Chain of Simulation (CoSm) method improves on the standard Chain of Thought prompting approach by avoiding the pitfalls of memorisation.
Authors: Diana Davila Gordillo, Joan Timoneda, Sebastian Vallejo Vera
Current methods to identify and classify racist language in text rely on small-n qualitative approaches or large-n approaches focusing exclusively on overt forms of racist discourse. This article provides a step-by-step generalizable guideline to identify and classify different forms of racist discourse in large corpora. In our approach, we start by conceptualizing racism and its different manifestations. We then contextualize these racist manifestations to the time and place of interest, which allows researchers to identify their discursive form. Finally, we apply XLM-RoBERTa (XLM-R), a cross-lingual model for supervised text classification with a cutting-edge contextual understanding of text. We show that XLM-R and XLM-R-Racismo, our pretrained model, outperform other state-of-the-art approaches in classifying racism in large corpora. We illustrate our approach using a corpus of tweets relating to the Ecuadorian ind\'igena community between 2018 and 2021.
Authors: Bobin Yang, Jie Deng, Zhenghan Chen, Ruoxue Wu
The task of deducing three-dimensional molecular configurations from their two-dimensional graph representations holds paramount importance in the fields of computational chemistry and pharmaceutical development. The rapid advancement of machine learning, particularly within the domain of deep generative networks, has revolutionized the precision of predictive modeling in this context. Traditional approaches often adopt a two-step strategy: initially estimating interatomic distances and subsequently refining the spatial molecular structure by solving a distance geometry problem. However, this sequential approach occasionally falls short in accurately capturing the intricacies of local atomic arrangements, thereby compromising the fidelity of the resulting structural models. Addressing these limitations, this research introduces a cutting-edge generative framework named \method{}. This framework is grounded in the principles of diffusion observed in classical non-equilibrium thermodynamics. \method{} views atoms as discrete entities and excels in guiding the reversal of diffusion, transforming a distribution of stochastic noise back into coherent molecular structures through a process akin to a Markov chain. This transformation commences with the initial representation of a molecular graph in an abstract latent space, culminating in the realization of three-dimensional structures via a sophisticated bilevel optimization scheme meticulously tailored to meet the specific requirements of the task. One of the formidable challenges in this modeling endeavor involves preserving roto-translational invariance to ensure that the generated molecular conformations adhere to the laws of physics. Extensive experimental evaluations confirm the efficacy of the proposed \method{} in comparison to state-of-the-art methods.
Authors: Sagar Shrestha, Xiao Fu
Unsupervised domain translation (UDT) aims to find functions that convert samples from one domain (e.g., sketches) to another domain (e.g., photos) without changing the high-level semantic meaning (also referred to as ``content''). The translation functions are often sought by probability distribution matching of the transformed source domain and target domain. CycleGAN stands as arguably the most representative approach among this line of work. However, it was noticed in the literature that CycleGAN and variants could fail to identify the desired translation functions and produce content-misaligned translations. This limitation arises due to the presence of multiple translation functions -- referred to as ``measure-preserving automorphism" (MPA) -- in the solution space of the learning criteria. Despite awareness of such identifiability issues, solutions have remained elusive. This study delves into the core identifiability inquiry and introduces an MPA elimination theory. Our analysis shows that MPA is unlikely to exist, if multiple pairs of diverse cross-domain conditional distributions are matched by the learning function. Our theory leads to a UDT learner using distribution matching over auxiliary variable-induced subsets of the domains -- other than over the entire data domains as in the classical approaches. The proposed framework is the first to rigorously establish translation identifiability under reasonable UDT settings, to our best knowledge. Experiments corroborate with our theoretical claims.
Authors: Zhijie Zhong, Zhiwen Yu, Yiyuan Yang, Weizheng Wang, Kaixiang Yang
Anomaly detection stands as a crucial aspect of time series analysis, aiming to identify abnormal events in time series samples. The central challenge of this task lies in effectively learning the representations of normal and abnormal patterns in a label-lacking scenario. Previous research mostly relied on reconstruction-based approaches, restricting the representational abilities of the models. In addition, most of the current deep learning-based methods are not lightweight enough, which prompts us to design a more efficient framework for anomaly detection. In this study, we introduce PatchAD, a novel multi-scale patch-based MLP-Mixer architecture that leverages contrastive learning for representational extraction and anomaly detection. Specifically, PatchAD is composed of four distinct MLP Mixers, exclusively utilizing the MLP architecture for high efficiency and lightweight architecture. Additionally, we also innovatively crafted a dual project constraint module to mitigate potential model degradation. Comprehensive experiments demonstrate that PatchAD achieves state-of-the-art results across multiple real-world multivariate time series datasets. Our code is publicly available.\footnote{\url{https://github.com/EmorZz1G/PatchAD}}
Authors: Yutong Xia, Runpeng Yu, Yuxuan Liang, Xavier Bresson, Xinchao Wang, Roger Zimmermann
Graph Neural Networks (GNNs) have become the preferred tool to process graph data, with their efficacy being boosted through graph data augmentation techniques. Despite the evolution of augmentation methods, issues like graph property distortions and restricted structural changes persist. This leads to the question: Is it possible to develop more property-conserving and structure-sensitive augmentation methods? Through a spectral lens, we investigate the interplay between graph properties, their augmentation, and their spectral behavior, and found that keeping the low-frequency eigenvalues unchanged can preserve the critical properties at a large scale when generating augmented graphs. These observations inform our introduction of the Dual-Prism (DP) augmentation method, comprising DP-Noise and DP-Mask, which adeptly retains essential graph properties while diversifying augmented graphs. Extensive experiments validate the efficiency of our approach, providing a new and promising direction for graph data augmentation.
Authors: Gianpaolo Palo, Luigi Fiorillo, Giuliana Monachino, Michal Bechny, Mark Melnykowycz, Athina Tzovara, Valentina Agostini, Francesca Dalia Faraci
Study Objectives: Polysomnography (PSG) currently serves as the benchmark for evaluating sleep disorders. Its discomfort, impracticality for home-use, and introduction of bias in sleep quality assessment necessitate the exploration of less invasive, cost-effective, and portable alternatives. One promising contender is the in-ear-EEG sensor, which offers advantages in terms of comfort, fixed electrode positions, resistance to electromagnetic interference, and user-friendliness. This study aims to establish a methodology to assess the similarity between the in-ear-EEG signal and standard PSG.
Methods: We assess the agreement between the PSG and in-ear-EEG derived hypnograms. We extract features in the time- and frequency- domain from PSG and in-ear-EEG 30-second epochs. We only consider the epochs where the PSG-scorers and the in-ear-EEG-scorers were in agreement. We introduce a methodology to quantify the similarity between PSG derivations and the single-channel in-ear-EEG. The approach relies on a comparison of distributions of selected features -- extracted for each sleep stage and subject on both PSG and the in-ear-EEG signals -- via a Jensen-Shannon Divergence Feature-based Similarity Index (JSD-FSI).
Results: We found a high intra-scorer variability, mainly due to the uncertainty the scorers had in evaluating the in-ear-EEG signals. We show that the similarity between PSG and in-ear-EEG signals is high (JSD-FSI: 0.61 +/- 0.06 in awake, 0.60 +/- 0.07 in NREM and 0.51 +/- 0.08 in REM), and in line with the similarity values computed independently on standard PSG-channel-combinations.
Conclusions: In-ear-EEG is a valuable solution for home-based sleep monitoring, however further studies with a larger and more heterogeneous dataset are needed.
Authors: Ben Ao Dai, Bao-Lin Ye
Real-time and accurate traffic flow prediction is the foundation for ensuring the efficient operation of intelligent transportation systems.In existing traffic flow prediction methods based on graph neural networks (GNNs), pre-defined graphs were usually used to describe the spatial correlations of different traffic nodes in urban road networks. However, the ability of pre-defined graphs used to describe spatial correlation was limited by prior knowledge and graph generation methods. Although time-varying graphs based on data-driven learning can partially overcome the drawbacks of pre-defined graphs, the learning ability of existing adaptive graphs was limited. For example, time-varying graphs cannot adequately capture the inherent spatial correlations in traffic flow data.In order to solve these problems, we have proposed a hybrid time-varying graph neural network (HTVGNN) for traffic flow prediction.
Authors: Qingyun Wang, Zixuan Zhang, Hongxiang Li, Xuan Liu, Jiawei Han, Heng Ji, Huimin Zhao
Fine-grained few-shot entity extraction in the chemical domain faces two unique challenges. First, compared with entity extraction tasks in the general domain, sentences from chemical papers usually contain more entities. Moreover, entity extraction models usually have difficulty extracting entities of long-tailed types. In this paper, we propose Chem-FINESE, a novel sequence-to-sequence (seq2seq) based few-shot entity extraction approach, to address these two challenges. Our Chem-FINESE has two components: a seq2seq entity extractor to extract named entities from the input sentence and a seq2seq self-validation module to reconstruct the original input sentence from extracted entities. Inspired by the fact that a good entity extraction system needs to extract entities faithfully, our new self-validation module leverages entity extraction results to reconstruct the original input sentence. Besides, we design a new contrastive loss to reduce excessive copying during the extraction process. Finally, we release ChemNER+, a new fine-grained chemical entity extraction dataset that is annotated by domain experts with the ChemNER schema. Experiments in few-shot settings with both ChemNER+ and CHEMET datasets show that our newly proposed framework has contributed up to 8.26% and 6.84% absolute F1-score gains respectively.
Authors: Wun Yung Shaney Sze, Maryglen Pearl Herrero, Roger Garriga
This study provides evidence that personality can be reliably predicted from activity data collected through mobile phone sensors. Employing a set of well informed indicators calculable from accelerometer records and movement patterns, we were able to predict users' personality up to a 0.78 F1 score on a two class problem. Given the fast growing number of data collected from mobile phones, our novel personality indicators open the door to exciting avenues for future research in social sciences. Our results reveal distinct behavioral patterns that proved to be differentially predictive of big five personality traits. They potentially enable cost effective, questionnaire free investigation of personality related questions at an unprecedented scale. We show how a combination of rich behavioral data obtained with smartphone sensing and the use of machine learning techniques can help to advance personality research and can inform both practitioners and researchers about the different behavioral patterns of personality. These findings have practical implications for organizations harnessing mobile sensor data for personality assessment, guiding the refinement of more precise and efficient prediction models in the future.
Authors: Tu Nguyen, Nedim Srndic, Alexander Neth
Tactics, Techniques and Procedures (TTPs) represent sophisticated attack patterns in the cybersecurity domain, described encyclopedically in textual knowledge bases. Identifying TTPs in cybersecurity writing, often called TTP mapping, is an important and challenging task. Conventional learning approaches often target the problem in the classical multi-class or multilabel classification setting. This setting hinders the learning ability of the model due to a large number of classes (i.e., TTPs), the inevitable skewness of the label distribution and the complex hierarchical structure of the label space. We formulate the problem in a different learning paradigm, where the assignment of a text to a TTP label is decided by the direct semantic similarity between the two, thus reducing the complexity of competing solely over the large labeling space. To that end, we propose a neural matching architecture with an effective sampling-based learn-to-compare mechanism, facilitating the learning process of the matching model despite constrained resources.
Authors: Eli Chien, Haoyu Wang, Ziang Chen, Pan Li
Machine unlearning has raised significant interest with the adoption of laws ensuring the ``right to be forgotten''. Researchers have provided a probabilistic notion of approximate unlearning under a similar definition of Differential Privacy (DP), where privacy is defined as statistical indistinguishability to retraining from scratch. We propose Langevin unlearning, an unlearning framework based on noisy gradient descent with privacy guarantees for approximate unlearning problems. Langevin unlearning unifies the DP learning process and the privacy-certified unlearning process with many algorithmic benefits. These include approximate certified unlearning for non-convex problems, complexity saving compared to retraining, sequential and batch unlearning for multiple unlearning requests. We verify the practicality of Langevin unlearning by studying its privacy-utility-complexity trade-off via experiments on benchmark datasets, and also demonstrate its superiority against gradient-decent-plus-output-perturbation based approximate unlearning.
Authors: Atith Gandhi, Raj Sanjay Shah, Vijay Marupudi, Sashank Varma
Neural networks often suffer from catastrophic interference (CI): performance on previously learned tasks drops off significantly when learning a new task. This contrasts strongly with humans, who can sequentially learn new tasks without appreciably forgetting previous tasks. Prior work has explored various techniques for mitigating CI such as regularization, rehearsal, generative replay, and distillation methods. The current work takes a different approach, one guided by cognitive science research showing that in naturalistic environments, the probability of encountering a task decreases as a power-law of the time since it was last performed. We argue that a realistic evaluation of techniques for the mitigation of CI should be performed in simulated naturalistic learning environments. Thus, we evaluate the extent of mitigation of CI when training simple rehearsal-based methods in power-law environments similar to the ones humans face. Our work explores this novel rehearsal-based approach for a domain-incremental task: learning permutations in the MNIST task. We compare our rehearsal environment with other baselines to show its efficacy in promoting continual learning. Additionally, we investigate whether this environment shows forward facilitation, i.e., faster learning of later tasks. Next, we explore the robustness of our learning environment to the number of tasks, model size, and amount of data rehearsed after each task. Notably, our results show that the performance is comparable or superior to that of models trained using popular regularization methods and also to rehearsals in non-power-law environments. The benefits of this training paradigm include simplicity and the lack of a need for extra neural circuitry. In addition, because our method is orthogonal to other methods, future research can combine training in power-law environments with other continual learning mechanisms.
Authors: Aron Brenner, Rahman Khorramfar, Dharik Mallapragada, Saurabh Amin
Solving large-scale capacity expansion problems (CEPs) is central to cost-effective decarbonization of regional-scale energy systems. To ensure the intended outcomes of CEPs, modeling uncertainty due to weather-dependent variable renewable energy (VRE) supply and energy demand becomes crucially important. However, the resulting stochastic optimization models are often less computationally tractable than their deterministic counterparts. Here, we propose a learning-assisted approximate solution method to tractably solve two-stage stochastic CEPs. Our method identifies low-cost planning decisions by constructing and solving a sequence of tractable temporally aggregated surrogate problems. We adopt a Bayesian optimization approach to searching the space of time series aggregation hyperparameters and compute approximate solutions that minimize costs on a validation set of supply-demand projections. Importantly, we evaluate solved planning outcomes on a held-out set of test projections. We apply our approach to generation and transmission expansion planning for a joint power-gas system spanning New England. We show that our approach yields an estimated cost savings of up to 3.8% in comparison to benchmark time series aggregation approaches.
Authors: Aydin Abadi, Bradley Doyle, Francesco Gini, Kieron Guinamard, Sasi Kumar Murakonda, Jack Liddell, Paul Mellor, Steven J. Murdoch, Mohammad Naseri, Hector Page, George Theodorakopoulos, Suzanne Weller
Federated Learning (FL) is a data-minimization approach enabling collaborative model training across diverse clients with local data, avoiding direct data exchange. However, state-of-the-art FL solutions to identify fraudulent financial transactions exhibit a subset of the following limitations. They (1) lack a formal security definition and proof, (2) assume prior freezing of suspicious customers' accounts by financial institutions (limiting the solutions' adoption), (3) scale poorly, involving either $O(n^2)$ computationally expensive modular exponentiation (where $n$ is the total number of financial institutions) or highly inefficient fully homomorphic encryption, (4) assume the parties have already completed the identity alignment phase, hence excluding it from the implementation, performance evaluation, and security analysis, and (5) struggle to resist clients' dropouts. This work introduces Starlit, a novel scalable privacy-preserving FL mechanism that overcomes these limitations. It has various applications, such as enhancing financial fraud detection, mitigating terrorism, and enhancing digital health. We implemented Starlit and conducted a thorough performance analysis using synthetic data from a key player in global financial transactions. The evaluation indicates Starlit's scalability, efficiency, and accuracy.
Authors: Ling Yang, Jingwei Liu, Shenda Hong, Zhilong Zhang, Zhilin Huang, Zheming Cai, Wentao Zhang, Bin Cui
Diffusion models are a new class of generative models, and have dramatically promoted image generation with unprecedented quality and diversity. Existing diffusion models mainly try to reconstruct input image from a corrupted one with a pixel-wise or feature-wise constraint along spatial axes. However, such point-based reconstruction may fail to make each predicted pixel/feature fully preserve its neighborhood context, impairing diffusion-based image synthesis. As a powerful source of automatic supervisory signal, context has been well studied for learning representations. Inspired by this, we for the first time propose ConPreDiff to improve diffusion-based image synthesis with context prediction. We explicitly reinforce each point to predict its neighborhood context (i.e., multi-stride features/tokens/pixels) with a context decoder at the end of diffusion denoising blocks in training stage, and remove the decoder for inference. In this way, each point can better reconstruct itself by preserving its semantic connections with neighborhood context. This new paradigm of ConPreDiff can generalize to arbitrary discrete and continuous diffusion backbones without introducing extra parameters in sampling procedure. Extensive experiments are conducted on unconditional image generation, text-to-image generation and image inpainting tasks. Our ConPreDiff consistently outperforms previous methods and achieves a new SOTA text-to-image generation results on MS-COCO, with a zero-shot FID score of 6.21.
Authors: Weizheng Wang, Le Mao, Baijian Yang, Guohua Chen, Byung-Cheol Min
Predicting crowded intents and trajectories is crucial in varouls real-world applications, including service robots and autonomous vehicles. Understanding environmental dynamics is challenging, not only due to the complexities of modeling pair-wise spatial and temporal interactions but also the diverse influence of group-wise interactions. To decode the comprehensive pair-wise and group-wise interactions in crowded scenarios, we introduce Hyper-STTN, a Hypergraph-based Spatial-Temporal Transformer Network for crowd trajectory prediction. In Hyper-STTN, crowded group-wise correlations are constructed using a set of multi-scale hypergraphs with varying group sizes, captured through random-walk robability-based hypergraph spectral convolution. Additionally, a spatial-temporal transformer is adapted to capture pedestrians' pair-wise latent interactions in spatial-temporal dimensions. These heterogeneous group-wise and pair-wise are then fused and aligned though a multimodal transformer network. Hyper-STTN outperformes other state-of-the-art baselines and ablation models on 5 real-world pedestrian motion datasets.
Authors: Ping Guo, Zhiyuan Yang, Xi Lin, Qingchuan Zhao, Qingfu Zhang
Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model's architecture and parameters. Traditional defense mechanisms, such as adversarial training, gradient masking, and input transformations, either impose substantial computational costs or compromise the test accuracy of non-adversarial inputs. To address these challenges, we propose an efficient defense mechanism, PuriDefense, that employs random patch-wise purifications with an ensemble of lightweight purification models at a low level of inference cost. These models leverage the local implicit function and rebuild the natural image manifold. Our theoretical analysis suggests that this approach slows down the convergence of query-based attacks by incorporating randomness into purifications. Extensive experiments on CIFAR-10 and ImageNet validate the effectiveness of our proposed purifier-based defense mechanism, demonstrating significant improvements in robustness against query-based attacks.