Authors: Rithwik Gupta, Daniel Muthukrishna, Michelle Lochner
Abstract: Automating anomaly detection is an open problem in many scientific fields, particularly in time-domain astronomy, where modern telescopes generate millions of alerts per night. Currently, most anomaly detection algorithms for astronomical time-series rely either on hand-crafted features or on features generated through unsupervised representation learning, coupled with standard anomaly detection algorithms. In this work, we introduce a novel approach that leverages the latent space of a neural network classifier for anomaly detection. We then propose a new method called Multi-Class Isolation Forests (MCIF), which trains separate isolation forests for each class to derive an anomaly score for an object based on its latent space representation. This approach significantly outperforms a standard isolation forest when distinct clusters exist in the latent space. Using a simulated dataset emulating the Zwicky Transient Facility (54 anomalies and 12,040 common), our anomaly detection pipeline discovered $46\pm3$ anomalies ($\sim 85\%$ recall) after following up the top 2,000 ($\sim 15\%$) ranked objects. Furthermore, our classifier-based approach outperforms or approaches the performance of other state-of-the-art anomaly detection pipelines. Our novel method demonstrates that existing and new classifiers can be effectively repurposed for real-time anomaly detection. The code used in this work, including a Python package, is publicly available, https://github.com/Rithwik-G/AstroMCAD.
Authors: Kenzo Clauw, Sebastiano Stramaglia, Daniele Marinazzo
Abstract: This paper studies emergent phenomena in neural networks by focusing on grokking where models suddenly generalize after delayed memorization. To understand this phase transition, we utilize higher-order mutual information to analyze the collective behavior (synergy) and shared properties (redundancy) between neurons during training. We identify distinct phases before grokking allowing us to anticipate when it occurs. We attribute grokking to an emergent phase transition caused by the synergistic interactions between neurons as a whole. We show that weight decay and weight initialization can enhance the emergent phase.
Authors: Minheng Xiao, Shi Bo
Abstract: Imbalanced datasets pose significant challenges in areas including neuroscience, cognitive science, and medical diagnostics, where accurately detecting minority classes is essential for robust model performance. This study addresses the issue of class imbalance, using the `Liking' label in the DEAP dataset as an example. Such imbalances are often overlooked by prior research, which typically focuses on the more balanced arousal and valence labels and predominantly uses accuracy metrics to measure model performance. To tackle this issue, we adopt numerical optimization techniques aimed at maximizing the area under the curve (AUC), thus enhancing the detection of underrepresented classes. Our approach, which begins with a linear classifier, is compared against traditional linear classifiers, including logistic regression and support vector machines (SVM). Our method significantly outperforms these models, increasing recall from 41.6\% to 79.7\% and improving the F1-score from 0.506 to 0.632. These results highlight the efficacy of AUC maximization via numerical optimization in managing imbalanced datasets, providing an effective solution for enhancing predictive accuracy in detecting minority but crucial classes in out-of-sample datasets.
Authors: Zhiyong Wang, Dongruo Zhou, John C. S. Lui, Wen Sun
Abstract: Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning inside the learned model is perhaps the most standard and simplest Model-based Reinforcement Learning (RL) framework. In this work, we show that such a simple Model-based RL scheme, when equipped with optimistic and pessimistic planning procedures, achieves strong regret and sample complexity bounds in online and offline RL settings. Particularly, we demonstrate that under the conditions where the trajectory-wise reward is normalized between zero and one and the transition is time-homogenous, it achieves horizon-free and second-order bounds. Horizon-free means that our bounds have no polynomial dependence on the horizon of the Markov Decision Process. A second-order bound is a type of instance-dependent bound that scales with respect to the variances of the returns of the policies which can be small when the system is nearly deterministic and (or) the optimal policy has small values. We highlight that our algorithms are simple, fairly standard, and indeed have been extensively studied in the RL literature: they learn a model via MLE, build a version space around the MLE solution, and perform optimistic or pessimistic planning depending on whether operating in the online or offline mode. These algorithms do not rely on additional specialized algorithmic designs such as learning variances and performing variance-weighted learning and thus can leverage rich function approximations that are significantly beyond linear or tabular structures. The simplicity of the algorithms also implies that our horizon-free and second-order regret analysis is actually standard and mainly follows the general framework of optimism/pessimism in the face of uncertainty.
Authors: Arwen Bradley, Preetum Nakkiran
Abstract: We investigate the theoretical foundations of classifier-free guidance (CFG). CFG is the dominant method of conditional sampling for text-to-image diffusion models, yet unlike other aspects of diffusion, it remains on shaky theoretical footing. In this paper, we disprove common misconceptions, by showing that CFG interacts differently with DDPM (Ho et al., 2020) and DDIM (Song et al., 2021), and neither sampler with CFG generates the gamma-powered distribution $p(x|c)^\gamma p(x)^{1-\gamma}$. Then, we clarify the behavior of CFG by showing that it is a kind of predictor-corrector method (Song et al., 2020) that alternates between denoising and sharpening, which we call predictor-corrector guidance (PCG). We prove that in the SDE limit, CFG is actually equivalent to combining a DDIM predictor for the conditional distribution together with a Langevin dynamics corrector for a gamma-powered distribution (with a carefully chosen gamma). Our work thus provides a lens to theoretically understand CFG by embedding it in a broader design space of principled sampling methods.
Authors: Youdong Guo, Timothy E. Holy
Abstract: Non-negative matrix factorization (NMF) is a key technique for feature extraction and widely used in source separation. However, existing algorithms may converge to poor local minima, or to one of several minima with similar objective value but differing feature parametrizations. Additionally, the performance of NMF greatly depends on the number of components, but choosing the optimal count remains a challenge. Here we show that some of these weaknesses may be mitigated by performing NMF in a higher-dimensional feature space and then iteratively combining components with an analytically-solvable pairwise merge strategy. Experimental results demonstrate our method helps NMF achieve better local optima and greater consistency of the solutions. Iterative merging also provides an efficient and informative framework for choosing the number of components. Surprisingly, despite these extra steps, our approach often improves computational performance by reducing the occurrence of ``convergence stalling'' near saddle points. This can be recommended as a preferred approach for most applications of NMF.
Authors: Yihe Dong
Abstract: With the rise of language and multimodal models of ever-increasing size, pretraining a general-purpose foundational model and adapting it to downstream tasks has become common practice. To this end, adaptation efficiency can be a critical bottleneck given the large model sizes, hence efficient finetuning methods such as LoRA have become prevalent. However, LoRA is typically applied with the same rank across all model layers, despite mounting evidence from transfer learning literature that during finetuning, later layers diverge more from pretrained weights. Inspired by the theory and observations around feature learning and module criticality, we develop a simple model disagreement based technique to predict the rank of a given module relative to the other modules. Empirically, AdaRank generalizes notably better on unseen data than using uniform ranks with the same number of parameters. Compared to prior work, AdaRank has the unique advantage of leaving the pretraining and adaptation stages completely intact: no need for any additional objectives or regularizers, which can hinder adaptation accuracy and performance. Our code is publicly available at https://github.com/google-research/google-research/tree/master/adaptive_low_rank.
URLs: https://github.com/google-research/google-research/tree/master/adaptive_low_rank.
Authors: Robert Reed, Luca Laurenti, Morteza Lahijanian
Abstract: Gaussian Process Regression (GPR) is a powerful and elegant method for learning complex functions from noisy data with a wide range of applications, including in safety-critical domains. Such applications have two key features: (i) they require rigorous error quantification, and (ii) the noise is often bounded and non-Gaussian due to, e.g., physical constraints. While error bounds for applying GPR in the presence of non-Gaussian noise exist, they tend to be overly restrictive and conservative in practice. In this paper, we provide novel error bounds for GPR under bounded support noise. Specifically, by relying on concentration inequalities and assuming that the latent function has low complexity in the reproducing kernel Hilbert space (RKHS) corresponding to the GP kernel, we derive both probabilistic and deterministic bounds on the error of the GPR. We show that these errors are substantially tighter than existing state-of-the-art bounds and are particularly well-suited for GPR with neural network kernels, i.e., Deep Kernel Learning (DKL). Furthermore, motivated by applications in safety-critical domains, we illustrate how these bounds can be combined with stochastic barrier functions to successfully quantify the safety probability of an unknown dynamical system from finite data. We validate the efficacy of our approach through several benchmarks and comparisons against existing bounds. The results show that our bounds are consistently smaller, and that DKLs can produce error bounds tighter than sample noise, significantly improving the safety probability of control systems.
Authors: Jamie Deng, Yusen Wu, Yelena Yesha, Phuong Nguyen
Abstract: Venous thromboembolism (VTE) is a critical cardiovascular condition, encompassing deep vein thrombosis (DVT) and pulmonary embolism (PE). Accurate and timely identification of VTE is essential for effective medical care. This study builds upon our previous work, which addressed VTE detection using deep learning methods for DVT and a hybrid approach combining deep learning and rule-based classification for PE. Our earlier approaches, while effective, had two major limitations: they were complex and required expert involvement for feature engineering of the rule set. To overcome these challenges, we utilize the Mamba architecture-based classifier. This model achieves remarkable results, with a 97\% accuracy and F1 score on the DVT dataset and a 98\% accuracy and F1 score on the PE dataset. In contrast to the previous hybrid method on PE identification, the Mamba classifier eliminates the need for hand-engineered rules, significantly reducing model complexity while maintaining comparable performance. Additionally, we evaluated a lightweight Large Language Model (LLM), Phi-3 Mini, in detecting VTE. While this model delivers competitive results, outperforming the baseline BERT models, it proves to be computationally intensive due to its larger parameter set. Our evaluation shows that the Mamba-based model demonstrates superior performance and efficiency in VTE identification, offering an effective solution to the limitations of previous approaches.
Authors: Vladimir Araujo, Marie-Francine Moens, Tinne Tuytelaars
Abstract: Parameter-efficient fine-tuning (PEFT) methods are increasingly used with pre-trained language models (PLMs) for continual learning (CL). These methods involve training a PEFT module for each new task and using similarity-based selection to route modules during inference. However, they face two major limitations: 1) interference with already learned modules and 2) suboptimal routing when composing modules. In this paper, we introduce a method that isolates the training of PEFT modules for task specialization. Then, before evaluation, it learns to compose the previously learned modules by training a router that leverages samples from a small memory. We evaluate our method in two CL setups using several benchmarks. Our results show that our method provides a better composition of PEFT modules, leading to better generalization and performance compared to previous methods.
Authors: Yan-Feng Xie, Peng Zhao, Zhi-Hua Zhou
Abstract: Gradient-variation online learning aims to achieve regret guarantees that scale with the variations in the gradients of online functions, which has been shown to be crucial for attaining fast convergence in games and robustness in stochastic optimization, hence receiving increased attention. Existing results often require the smoothness condition by imposing a fixed bound on the gradient Lipschitzness, but this may not hold in practice. Recent efforts in neural network optimization suggest a generalized smoothness condition, allowing smoothness to correlate with gradient norms. In this paper, we systematically study gradient-variation online learning under generalized smoothness. To this end, we extend the classic optimistic mirror descent algorithm to derive gradient-variation bounds by conducting stability analysis over the optimization trajectory and exploiting smoothness locally. Furthermore, we explore universal online learning, designing a single algorithm enjoying optimal gradient-variation regrets for convex and strongly convex functions simultaneously without knowing curvature information. The algorithm adopts a two-layer structure with a meta-algorithm running over a group of base-learners. To ensure favorable guarantees, we have designed a new meta-algorithm that is Lipschitz-adaptive to handle potentially unbounded gradients and meanwhile ensures second-order regret to cooperate with base-learners. Finally, we provide implications of our findings and obtain new results in fast-rate games and stochastic extended adversarial optimization.
Authors: Rung-Hung Gau, Ting-Yu Wang, Chun-Hung Liu
Abstract: In this paper, we study user association and wireless bandwidth allocation for a hierarchical federated learning system that consists of mobile users, edge servers, and a cloud server. To minimize the length of a global round in hierarchical federated learning with equal bandwidth allocation, we formulate a combinatorial optimization problem. We design the twin sorting dynamic programming (TSDP) algorithm that obtains a globally optimal solution in polynomial time when there are two edge servers. In addition, we put forward the TSDP-assisted algorithm for user association when there are three or more edge servers. Furthermore, given a user association matrix, we formulate and solve a convex optimization problem for optimal wireless bandwidth allocation. Simulation results show that the proposed approach outperforms a number of alternative schemes.
Authors: Mingxuan Xie, Tao Zou, Junchen Ye, Bowen Du, Runhe Huang
Abstract: Passenger behavior prediction aims to track passenger travel patterns through historical boarding and alighting data, enabling the analysis of urban station passenger flow and timely risk management. This is crucial for smart city development and public transportation planning. Existing research primarily relies on statistical methods and sequential models to learn from individual historical interactions, which ignores the correlations between passengers and stations. To address these issues, this paper proposes DyGPP, which leverages dynamic graphs to capture the intricate evolution of passenger behavior. First, we formalize passengers and stations as heterogeneous vertices in a dynamic graph, with connections between vertices representing interactions between passengers and stations. Then, we sample the historical interaction sequences for passengers and stations separately. We capture the temporal patterns from individual sequences and correlate the temporal behavior between the two sequences. Finally, we use an MLP-based encoder to learn the temporal patterns in the interactions and generate real-time representations of passengers and stations. Experiments on real-world datasets confirmed that DyGPP outperformed current models in the behavior prediction task, demonstrating the superiority of our model.
Authors: Manuel Wendl, Lukas Koller, Tobias Ladner, Matthias Althoff
Abstract: Reinforcement learning often uses neural networks to solve complex control tasks. However, neural networks are sensitive to input perturbations, which makes their deployment in safety-critical environments challenging. This work lifts recent results from formally verifying neural networks against such disturbances to reinforcement learning in continuous state and action spaces using reachability analysis. While previous work mainly focuses on adversarial attacks for robust reinforcement learning, we train neural networks utilizing entire sets of perturbed inputs and maximize the worst-case reward. The obtained agents are verifiably more robust than agents obtained by related work, making them more applicable in safety-critical environments. This is demonstrated with an extensive empirical evaluation of four different benchmarks.
Authors: Yuan Tian, Tianyi Zhang
Abstract: Recent advances in large language models (LLMs) such as Copilot and ChatGPT have transformed software development by automating coding tasks. Despite these advancements, challenges remain in reducing error rates and fully meeting user expectations. Our empirical study reveals LLMs tend to dilute their self-attention on the initial prompt as more code tokens are generated. We hypothesize this self-attention dilution issue is one of the root causes of inaccuracies in LLM-generated code. To mitigate this issue, we propose Selective Prompt Anchoring (SPA). SPA amplifies the influence of the selected parts in the initial prompt, which we refer to as ``anchored text'', during code generation. Specifically, SPA calculates the logit distribution difference with and without the anchored text. We prove this difference approximates the anchored text's contextual contribution to the output logits. SPA creates an augmented logit distribution by linearly combining the original logit distribution and the logit difference. We evaluate SPA with five LLMs on four benchmarks. Our results demonstrate that using SPA can consistently improve Pass@1 rates by up to 9.7% in all settings. Notably, with selective text anchoring, a small version of DeepSeek-Coder (6.7B) can achieve better performance than an original much larger version (33B). Our code is available at https://github.com/magic-YuanTian/Selective-Prompt-Anchoring.
URLs: https://github.com/magic-YuanTian/Selective-Prompt-Anchoring.
Authors: Hao Li, Hao Jiang, Jiajun Fan, Dongsheng Ye, Liang Du
Abstract: Persistent homology, a fundamental technique within Topological Data Analysis (TDA), captures structural and shape characteristics of graphs, yet encounters computational difficulties when applied to dynamic directed graphs. This paper introduces the Dynamic Neural Dowker Network (DNDN), a novel framework specifically designed to approximate the results of dynamic Dowker filtration, aiming to capture the high-order topological features of dynamic directed graphs. Our approach creatively uses line graph transformations to produce both source and sink line graphs, highlighting the shared neighbor structures that Dowker complexes focus on. The DNDN incorporates a Source-Sink Line Graph Neural Network (SSLGNN) layer to effectively capture the neighborhood relationships among dynamic edges. Additionally, we introduce an innovative duality edge fusion mechanism, ensuring that the results for both the sink and source line graphs adhere to the duality principle intrinsic to Dowker complexes. Our approach is validated through comprehensive experiments on real-world datasets, demonstrating DNDN's capability not only to effectively approximate dynamic Dowker filtration results but also to perform exceptionally in dynamic graph classification tasks.
Authors: Rishabh Agrawal, Nathan Dahlin, Rahul Jain, Ashutosh Nayyar
Abstract: Imitation learning (IL) is notably effective for robotic tasks where directly programming behaviors or defining optimal control costs is challenging. In this work, we address a scenario where the imitator relies solely on observed behavior and cannot make environmental interactions during learning. It does not have additional supplementary datasets beyond the expert's dataset nor any information about the transition dynamics. Unlike state-of-the-art (SOTA) IL methods, this approach tackles the limitations of conventional IL by operating in a more constrained and realistic setting. Our method uses the Markov balance equation and introduces a novel conditional density estimation-based imitation learning framework. It employs conditional normalizing flows for transition dynamics estimation and aims at satisfying a balance equation for the environment. Through a series of numerical experiments on Classic Control and MuJoCo environments, we demonstrate consistently superior empirical performance compared to many SOTA IL algorithms.
Authors: Subrat Prasad Panda, Blaise Genest, Arvind Easwaran, Ponnuthurai Nagaratnam Suganthan
Abstract: Decision Trees (DTs) constitute one of the major highly non-linear AI models, valued, e.g., for their efficiency on tabular data. Learning accurate DTs is, however, complicated, especially for oblique DTs, and does take a significant training time. Further, DTs suffer from overfitting, e.g., they proverbially "do not generalize" in regression tasks. Recently, some works proposed ways to make (oblique) DTs differentiable. This enables highly efficient gradient-descent algorithms to be used to learn DTs. It also enables generalizing capabilities by learning regressors at the leaves simultaneously with the decisions in the tree. Prior approaches to making DTs differentiable rely either on probabilistic approximations at the tree's internal nodes (soft DTs) or on approximations in gradient computation at the internal node (quantized gradient descent). In this work, we propose \textit{DTSemNet}, a novel \textit{sem}antically equivalent and invertible encoding for (hard, oblique) DTs as Neural \textit{Net}works (NNs), that uses standard vanilla gradient descent. Experiments across various classification and regression benchmarks show that oblique DTs learned using \textit{DTSemNet} are more accurate than oblique DTs of similar size learned using state-of-the-art techniques. Further, DT training time is significantly reduced. We also experimentally demonstrate that \textit{DTSemNet} can learn DT policies as efficiently as NN policies in the Reinforcement Learning (RL) setup with physical inputs (dimensions $\leq32$). The code is available at {\color{blue}\textit{\url{https://github.com/CPS-research-group/dtsemnet}}}.
Authors: SeungHyun Kim, Seohyeon Jung, Seonghyeon Kim, Juho Lee
Abstract: Bayesian Neural Networks(BNNs) with high-dimensional parameters pose a challenge for posterior inference due to the multi-modality of the posterior distributions. Stochastic Gradient MCMC(SGMCMC) with cyclical learning rate scheduling is a promising solution, but it requires a large number of sampling steps to explore high-dimensional multi-modal posteriors, making it computationally expensive. In this paper, we propose a meta-learning strategy to build \gls{sgmcmc} which can efficiently explore the multi-modal target distributions. Our algorithm allows the learned SGMCMC to quickly explore the high-density region of the posterior landscape. Also, we show that this exploration property is transferrable to various tasks, even for the ones unseen during a meta-training stage. Using popular image classification benchmarks and a variety of downstream tasks, we demonstrate that our method significantly improves the sampling efficiency, achieving better performance than vanilla \gls{sgmcmc} without incurring significant computational overhead.
Authors: Haojie Yan, Minglong Zhou, Jiayi Guo
Abstract: Empirical risk minimization, a cornerstone in machine learning, is often hindered by the Optimizer's Curse stemming from discrepancies between the empirical and true data-generating distributions.To address this challenge, the robust satisficing framework has emerged recently to mitigate ambiguity in the true distribution. Distinguished by its interpretable hyperparameter and enhanced performance guarantees, this approach has attracted increasing attention from academia. However, its applicability in tackling general machine learning problems, notably deep neural networks, remains largely unexplored due to the computational challenges in solving this model efficiently across general loss functions. In this study, we delve into the Kullback Leibler divergence based robust satisficing model under a general loss function, presenting analytical interpretations, diverse performance guarantees, efficient and stable numerical methods, convergence analysis, and an extension tailored for hierarchical data structures. Through extensive numerical experiments across three distinct machine learning tasks, we demonstrate the superior performance of our model compared to state-of-the-art benchmarks.
Authors: Xinyu Ning
Abstract: As the most representative scenario of spatial-temporal forecasting tasks, the traffic forecasting task attracted numerous attention from machine learning community due to its intricate correlation both in space and time dimension. Existing methods often treat road networks over time as spatial-temporal graphs, addressing spatial and temporal representations independently. However, these approaches struggle to capture the dynamic topology of road networks, encounter issues with message passing mechanisms and over-smoothing, and face challenges in learning spatial and temporal relationships separately. To address these limitations, we propose treating nodes in road networks at different time steps as independent spatial-temporal tokens and feeding them into a vanilla Transformer to learn complex spatial-temporal patterns, design STformer achieving SOTA. Given its quadratic complexity, we introduce a variant NSTformer based on Nystr$\ddot{o}$m method to approximate self-attention with linear complexity but even slightly better than former in a few cases astonishingly. Extensive experimental results on traffic datasets demonstrate that the proposed method achieves state-of-the-art performance at an affordable computational cost. Our code will be made available.
Authors: Jinhui Pang, Zixuan Wang, Jiliang Tang, Mingyan Xiao, Nan Yin
Abstract: Graph neural networks (GNNs) have achieved impressive impressions for graph-related tasks. However, most GNNs are primarily studied under the cases of signal domain with supervised training, which requires abundant task-specific labels and is difficult to transfer to other domains. There are few works focused on domain adaptation for graph node classification. They mainly focused on aligning the feature space of the source and target domains, without considering the feature alignment between different categories, which may lead to confusion of classification in the target domain. However, due to the scarcity of labels of the target domain, we cannot directly perform effective alignment of categories from different domains, which makes the problem more challenging. In this paper, we present the \textit{Spectral Augmentation for Graph Domain Adaptation (\method{})} for graph node classification. First, we observe that nodes with the same category in different domains exhibit similar characteristics in the spectral domain, while different classes are quite different. Following the observation, we align the category feature space of different domains in the spectral domain instead of aligning the whole features space, and we theoretical proof the stability of proposed \method{}. Then, we develop a dual graph convolutional network to jointly exploits local and global consistency for feature aggregation. Last, we utilize a domain classifier with an adversarial learning submodule to facilitate knowledge transfer between different domain graphs. Experimental results on a variety of publicly available datasets reveal the effectiveness of our \method{}.
Authors: Housen Wang, Yuxing Chen, Sirong Cao, Xiaoli Wang, Qiang Liu
Abstract: This article proposes a solution framework for delay differential equations (DDEs) based on deep neural networks (DNNs) - the neural delay differential equations (NDDEs), aimed at solving the forward and inverse problems of delay differential equations. This framework embeds the delay differential equations into the neural networks to accommodate the diverse requirements of DDEs in terms of initial conditions, control equations, and known data. NDDEs adjust the network parameters through automatic differentiation and optimization algorithms to minimize the loss function, thereby obtaining numerical solutions to the delay differential equations without the grid dependence and discretization errors typical of traditional numerical methods. In addressing inverse problems, the NDDE framework can utilize observational data to perform precise estimation of single or multiple delay parameters. The results of multiple numerical experiments have shown that NDDEs demonstrate high precision in both forward and inverse problems, proving their effectiveness and promising potential in dealing with delayed differential equation issues.
Authors: Erik B. Terres-Escudero, Javier Del Ser, Pablo Garcia-Bringas
Abstract: Forward-only learning algorithms have recently gained attention as alternatives to gradient backpropagation, replacing the backward step of this latter solver with an additional contrastive forward pass. Among these approaches, the so-called Forward-Forward Algorithm (FFA) has been shown to achieve competitive levels of performance in terms of generalization and complexity. Networks trained using FFA learn to contrastively maximize a layer-wise defined goodness score when presented with real data (denoted as positive samples) and to minimize it when processing synthetic data (corr. negative samples). However, this algorithm still faces weaknesses that negatively affect the model accuracy and training stability, primarily due to a gradient imbalance between positive and negative samples. To overcome this issue, in this work we propose a novel implementation of the FFA algorithm, denoted as Polar-FFA, which extends the original formulation by introducing a neural division (\emph{polarization}) between positive and negative instances. Neurons in each of these groups aim to maximize their goodness when presented with their respective data type, thereby creating a symmetric gradient behavior. To empirically gauge the improved learning capabilities of our proposed Polar-FFA, we perform several systematic experiments using different activation and goodness functions over image classification datasets. Our results demonstrate that Polar-FFA outperforms FFA in terms of accuracy and convergence speed. Furthermore, its lower reliance on hyperparameters reduces the need for hyperparameter tuning to guarantee optimal generalization capabilities, thereby allowing for a broader range of neural network configurations.
Authors: Lu Yi, Zhewei Wei
Abstract: With the recent adoption of laws supporting the ``right to be forgotten'' and the widespread use of Graph Neural Networks for modeling graph-structured data, graph unlearning has emerged as a crucial research area. Current studies focus on the efficient update of model parameters. However, they often overlook the time-consuming re-computation of graph propagation required for each removal, significantly limiting their scalability on large graphs. In this paper, we present ScaleGUN, the first certifiable graph unlearning mechanism that scales to billion-edge graphs. ScaleGUN employs a lazy local propagation method to facilitate efficient updates of the embedding matrix during data removal. Such lazy local propagation can be proven to ensure certified unlearning under all three graph unlearning scenarios, including node feature, edge, and node unlearning. Extensive experiments on real-world datasets demonstrate the efficiency and efficacy of ScaleGUN. Remarkably, ScaleGUN accomplishes $(\epsilon,\delta)=(1,10^{-4})$ certified unlearning on the billion-edge graph ogbn-papers100M in 20 seconds for a $5K$-random-edge removal request -- of which only 5 seconds are required for updating the embedding matrix -- compared to 1.91 hours for retraining and 1.89 hours for re-propagation. Our code is available online.
Authors: Xiyue Zhang, Benjie Wang, Marta Kwiatkowska, Huan Zhang
Abstract: Most methods for neural network verification focus on bounding the image, i.e., set of outputs for a given input set. This can be used to, for example, check the robustness of neural network predictions to bounded perturbations of an input. However, verifying properties concerning the preimage, i.e., the set of inputs satisfying an output property, requires abstractions in the input space. We present a general framework for preimage abstraction that produces under- and over-approximations of any polyhedral output set. Our framework employs cheap parameterised linear relaxations of the neural network, together with an anytime refinement procedure that iteratively partitions the input region by splitting on input features and neurons. The effectiveness of our approach relies on carefully designed heuristics and optimization objectives to achieve rapid improvements in the approximation volume. We evaluate our method on a range of tasks, demonstrating significant improvement in efficiency and scalability to high-input-dimensional image classification tasks compared to state-of-the-art techniques. Further, we showcase the application to quantitative verification and robustness analysis, presenting a sound and complete algorithm for the former and providing sound quantitative results for the latter.
Authors: P. Krishna Kumar a, Harish G. Ramaswamy
Abstract: Theoretical studies on the representation power of GNNs have been centered around understanding the equivalence of GNNs, using WL-Tests for detecting graph isomorphism. In this paper, we argue that such equivalence ignores the accompanying optimization issues and does not provide a holistic view of the GNN learning process. We illustrate these gaps between representation and optimization with examples and experiments. We also explore the existence of an implicit inductive bias (e.g. fully connected networks prefer to learn low frequency functions in their input space) in GNNs, in the context of graph classification tasks. We further prove theoretically that the message-passing layers in the graph, have a tendency to search for either discriminative subgraphs, or a collection of discriminative nodes dispersed across the graph, depending on the different global pooling layers used. We empirically verify this bias through experiments over real-world and synthetic datasets. Finally, we show how our work can help in incorporating domain knowledge via attention based architectures, and can evince their capability to discriminate coherent subgraphs.
Authors: Vamsi Krishna Pendyala, Hessam S. Sarjoughian, Bala Potineni, Edward J. Yellig
Abstract: Advancements in high-computing devices increase the necessity for improved and new understanding and development of smart manufacturing factories. Discrete-event models with simulators have been shown to be critical to architect, designing, building, and operating the manufacturing of semiconductor chips. The diffusion, implantation, and lithography machines have intricate processes due to their feedforward and feedback connectivity. The dataset collected from simulations of the factory models holds the promise of generating valuable machine-learning models. As surrogate data-based models, their executions are highly efficient compared to the physics-based counterpart models. For the development of surrogate models, it is beneficial to have publicly available benchmark simulation models that are grounded in factory models that have concise structures and accurate behaviors. Hence, in this research, a dataset is devised and constructed based on a benchmark model of an Intel semiconductor fabrication factory. The model is formalized using the Parallel Discrete-Event System Specification and executed using the DEVS-Suite simulator. The time series dataset is constructed using discrete-event time trajectories. This dataset is further analyzed and used to develop baseline univariate and multivariate machine learning models. The dataset can also be utilized in the machine learning community for behavioral analysis based on formalized and scalable component-based discrete-event models and simulations.
Authors: Gus Kristiansen, Mark Sandler, Andrey Zhmoginov, Nolan Miller, Anirudh Goyal, Jihwan Lee, Max Vladymyrov
Abstract: In modern deep learning, the models are learned by applying gradient updates using an optimizer, which transforms the updates based on various statistics. Optimizers are often hand-designed and tuning their hyperparameters is a big part of the training process. Learned optimizers have shown some initial promise, but are generally unsuccessful as a general optimization mechanism applicable to every problem. In this work we explore a different direction: instead of learning general optimizers, we instead specialize them to a specific training environment. We propose a novel optimizer technique that learns a layer-specific linear combination of update directions provided by a set of base optimizers, effectively adapting its strategy to the specific model and dataset. When evaluated on image classification tasks, this specialized optimizer significantly outperforms both traditional off-the-shelf methods such as Adam, as well as existing general learned optimizers. Moreover, it demonstrates robust generalization with respect to model initialization, evaluating on unseen datasets, and training durations beyond its meta-training horizon.
Authors: Dong Li, Chen Zhao, Minglai Shao, Wenjun Wang
Abstract: Achieving the generalization of an invariant classifier from training domains to shifted test domains while simultaneously considering model fairness is a substantial and complex challenge in machine learning. Existing methods address the problem of fairness-aware domain generalization, focusing on either covariate shift or correlation shift, but rarely consider both at the same time. In this paper, we introduce a novel approach that focuses on learning a fairness-aware domain-invariant predictor within a framework addressing both covariate and correlation shifts simultaneously, ensuring its generalization to unknown test domains inaccessible during training. In our approach, data are first disentangled into content and style factors in latent spaces. Furthermore, fairness-aware domain-invariant content representations can be learned by mitigating sensitive information and retaining as much other information as possible. Extensive empirical studies on benchmark datasets demonstrate that our approach surpasses state-of-the-art methods with respect to model accuracy as well as both group and individual fairness.
Authors: Ali Behroozi, Ali Edrisi
Abstract: Public transportation systems play a crucial role in daily commutes, business operations, and leisure activities, emphasizing the need for effective management to meet public demands. One approach to achieve this goal is by predicting demand at the station level. Bike-sharing systems, as a form of transit service, contribute to the reduction of air and noise pollution, as well as traffic congestion. This study focuses on predicting travel demand within a bike-sharing system. A novel hybrid deep learning model called the gate graph convolutional neural network is introduced. This model enables prediction of the travel demand at station level. By integrating trajectory data, weather data, access data, and leveraging gate graph convolution networks, the accuracy of travel demand forecasting is significantly improved. Chicago City bike-sharing system is chosen as the case study. In this investigation, the proposed model is compared to the base models used in previous literature to evaluate their performance, demonstrating that the main model exhibits better performance than the base models. By utilizing this framework, transportation planners can make informed decisions on resource allocation and rebalancing management.
Authors: Ben Halstead, Yun Sing Koh, Patricia Riddle, Mykola Pechenizkiy, Albert Bifet
Abstract: The distribution of streaming data often changes over time as conditions change, a phenomenon known as concept drift. Only a subset of previous experience, collected in similar conditions, is relevant to learning an accurate classifier for current data. Learning from irrelevant experience describing a different concept can degrade performance. A system learning from streaming data must identify which recent experience is irrelevant when conditions change and which past experience is relevant when concepts reoccur, \textit{e.g.,} when weather events or financial patterns repeat. Existing streaming approaches either do not consider experience to change in relevance over time and thus cannot handle concept drift, or only consider the recency of experience and thus cannot handle recurring concepts, or only sparsely evaluate relevance and thus fail when concept drift is missed. To enable learning in changing conditions, we propose SELeCT, a probabilistic method for continuously evaluating the relevance of past experience. SELeCT maintains a distinct internal state for each concept, representing relevant experience with a unique classifier. We propose a Bayesian algorithm for estimating state relevance, combining the likelihood of drawing recent observations from a given state with a transition pattern prior based on the system's current state.
Authors: Jiancheng Dong, Lei Jiang, Wei Jin, Lu Cheng
Abstract: Packing for Supervised Fine-Tuning (SFT) in autoregressive models involves concatenating data points of varying lengths until reaching the designed maximum length to facilitate GPU processing. However, randomly concatenating data points and feeding them into an autoregressive transformer can lead to cross-contamination of sequences due to the significant difference in their subject matter. The mainstream approaches in SFT ensure that each token in the attention calculation phase only focuses on tokens within its own short sequence, without providing additional learning signals for the preceding context. To address these challenges, we introduce Threshold Filtering Packing (TFP), a method that selects samples with related context while maintaining sufficient diversity within the same pack. Our experiments show that TFP offers a simple-to-implement and scalable approach that significantly enhances SFT performance, with observed improvements of up to 7\% on GSM8K, 4\% on HumanEval, and 15\% on the adult-census-income dataset.
Authors: Yilong Hou, Xi'an Li, Jinran Wu
Abstract: Bayesian Physics Informed Neural Networks (BPINN) have received considerable attention for inferring differential equations' system states and physical parameters according to noisy observations. However, in practice, Hamiltonian Monte Carlo (HMC) used to estimate the internal parameters of BPINN often encounters troubles, including poor performance and awful convergence for a given step size used to adjust the momentum of those parameters. To improve the efficacy of HMC convergence for the BPINN method and extend its application scope to multi-scale partial differential equations (PDE), we developed a robust multi-scale Bayesian PINN (dubbed MBPINN) method by integrating multi-scale deep neural networks (MscaleDNN) and Bayesian inference. In this newly proposed MBPINN method, we reframe HMC with Stochastic Gradient Descent (SGD) to ensure the most ``likely'' estimation is always provided, and we configure its solver as a Fourier feature mapping-induced MscaleDNN. The MBPINN method offers several key advantages: (1) it is more robust than HMC, (2) it incurs less computational cost than HMC, and (3) it is more flexible for complex problems. We demonstrate the applicability and performance of the proposed method through general Poisson and multi-scale elliptic problems in one- to three-dimensional spaces. Our findings indicate that the proposed method can avoid HMC failures and provide valid results. Additionally, our method can handle complex PDE and produce comparable results for general PDE. These findings suggest that our proposed approach has excellent potential for physics-informed machine learning for parameter estimation and solution recovery in the case of ill-posed problems.
Authors: Jianhao Guo, Zixuan Ni, Yun Zhu, Siliang Tang
Abstract: Continual learning has emerged as a crucial paradigm for learning from sequential data while preserving previous knowledge. In the realm of continual graph learning, where graphs continuously evolve based on streaming graph data, continual graph learning presents unique challenges that require adaptive and efficient graph learning methods in addition to the problem of catastrophic forgetting. The first challenge arises from the interdependencies between different graph data, where previous graphs can influence new data distributions. The second challenge lies in the efficiency concern when dealing with large graphs. To addresses these two problems, we produce an Efficient Continual Graph Learner (E-CGL) in this paper. We tackle the interdependencies issue by demonstrating the effectiveness of replay strategies and introducing a combined sampling strategy that considers both node importance and diversity. To overcome the limitation of efficiency, E-CGL leverages a simple yet effective MLP model that shares weights with a GCN during training, achieving acceleration by circumventing the computationally expensive message passing process. Our method comprehensively surpasses nine baselines on four graph continual learning datasets under two settings, meanwhile E-CGL largely reduces the catastrophic forgetting problem down to an average of -1.1%. Additionally, E-CGL achieves an average of 15.83x training time acceleration and 4.89x inference time acceleration across the four datasets. These results indicate that E-CGL not only effectively manages the correlation between different graph data during continual training but also enhances the efficiency of continual learning on large graphs. The code is publicly available at https://github.com/aubreygjh/E-CGL.
Authors: Yanzhi Chen, Zijing Ou, Adrian Weller, Yingzhen Li
Abstract: Estimating mutual information (MI) is a fundamental yet challenging task in data science and machine learning. This work proposes a new estimator for mutual information. Our main discovery is that a preliminary estimate of the data distribution can dramatically help estimate. This preliminary estimate serves as a bridge between the joint and the marginal distribution, and by comparing with this bridge distribution we can easily obtain the true difference between the joint distributions and the marginal distributions. Experiments on diverse tasks including non-Gaussian synthetic problems with known ground-truth and real-world applications demonstrate the advantages of our method.
Authors: Xingbo Fu, Zihan Chen, Binchi Zhang, Chen Chen, Jundong Li
Abstract: Federated Graph Learning (FGL) aims to learn graph learning models over graph data distributed in multiple data owners, which has been applied in various applications such as social recommendation and financial fraud detection. Inherited from generic Federated Learning (FL), FGL similarly has the data heterogeneity issue where the label distribution may vary significantly for distributed graph data across clients. For instance, a client can have the majority of nodes from a class, while another client may have only a few nodes from the same class. This issue results in divergent local objectives and impairs FGL convergence for node-level tasks, especially for node classification. Moreover, FGL also encounters a unique challenge for the node classification task: the nodes from a minority class in a client are more likely to have biased neighboring information, which prevents FGL from learning expressive node embeddings with Graph Neural Networks (GNNs). To grapple with the challenge, we propose FedSpray, a novel FGL framework that learns local class-wise structure proxies in the latent space and aligns them to obtain global structure proxies in the server. Our goal is to obtain the aligned structure proxies that can serve as reliable, unbiased neighboring information for node classification. To achieve this, FedSpray trains a global feature-structure encoder and generates unbiased soft targets with structure proxies to regularize local training of GNN models in a personalized way. We conduct extensive experiments over four datasets, and experiment results validate the superiority of FedSpray compared with other baselines. Our code is available at https://github.com/xbfu/FedSpray.
Authors: Tiberiu Musat
Abstract: Recent studies have revealed that neural networks learn interpretable algorithms for many simple problems. However, little is known about how these algorithms emerge during training. In this article, we study the training dynamics of a simplified transformer with 2-dimensional embeddings on the problem of modular addition. We observe that embedding vectors tend to organize into two types of structures: grids and circles. We study these structures and explain their emergence as a result of two simple tendencies exhibited by pairs of embeddings: clustering and alignment. We propose explicit formulae for these tendencies as interaction forces between different pairs of embeddings. To show that our formulae can fully account for the emergence of these structures, we construct an equivalent particle simulation where we find that identical structures emerge. We use our insights to discuss the role of weight decay and reveal a new mechanism that links regularization and training dynamics. We also release an interactive demo to support our findings: https://modular-addition.vercel.app/.
Authors: Kening Zheng, Junkai Chen, Yibo Yan, Xin Zou, Xuming Hu
Abstract: Hallucination issues persistently plagued current multimodal large language models (MLLMs). While existing research primarily focuses on object-level or attribute-level hallucinations, sidelining the more sophisticated relation hallucinations that necessitate advanced reasoning abilities from MLLMs. Besides, recent benchmarks regarding relation hallucinations lack in-depth evaluation and effective mitigation. Moreover, their datasets are typically derived from a systematic annotation process, which could introduce inherent biases due to the predefined process. To handle the aforementioned challenges, we introduce Reefknot, a comprehensive benchmark specifically targeting relation hallucinations, consisting of over 20,000 samples derived from real-world scenarios. Specifically, we first provide a systematic definition of relation hallucinations, integrating perspectives from perceptive and cognitive domains. Furthermore, we construct the relation-based corpus utilizing the representative scene graph dataset Visual Genome (VG), from which semantic triplets follow real-world distributions. Our comparative evaluation across three distinct tasks revealed a substantial shortcoming in the capabilities of current MLLMs to mitigate relation hallucinations. Finally, we advance a novel confidence-based mitigation strategy tailored to tackle the relation hallucinations problem. Across three datasets, including Reefknot, we observed an average reduction of 9.75% in the hallucination rate. We believe our paper sheds valuable insights into achieving trustworthy multimodal intelligence. Our dataset and code will be released upon paper acceptance.
Authors: Woojin Cho, Minju Jo, Haksoo Lim, Kookjin Lee, Dongeun Lee, Sanghyun Hong, Noseong Park
Abstract: Complex physical systems are often described by partial differential equations (PDEs) that depend on parameters such as the Reynolds number in fluid mechanics. In applications such as design optimization or uncertainty quantification, solutions of those PDEs need to be evaluated at numerous points in the parameter space. While physics-informed neural networks (PINNs) have emerged as a new strong competitor as a surrogate, their usage in this scenario remains underexplored due to the inherent need for repetitive and time-consuming training. In this paper, we address this problem by proposing a novel extension, parameterized physics-informed neural networks (P$^2$INNs). P$^2$INNs enable modeling the solutions of parameterized PDEs via explicitly encoding a latent representation of PDE parameters. With the extensive empirical evaluation, we demonstrate that P$^2$INNs outperform the baselines both in accuracy and parameter efficiency on benchmark 1D and 2D parameterized PDEs and are also effective in overcoming the known "failure modes".
Authors: Milan Pape\v{z}, Martin Rektoris, V\'aclav \v{S}m\'idl, Tom\'a\v{s} Pevn\'y
Abstract: Deep generative models have recently made a remarkable progress in capturing complex probability distributions over graphs. However, they are intractable and thus unable to answer even the most basic probabilistic inference queries without resorting to approximations. Therefore, we propose graph sum-product networks (GraphSPNs), a tractable deep generative model which provides exact and efficient inference over (arbitrary parts of) graphs. We investigate different principles to make SPNs permutation invariant. We demonstrate that GraphSPNs are able to (conditionally) generate novel and chemically valid molecular graphs, being competitive to, and sometimes even better than, existing intractable models. We find out that (Graph)SPNs benefit from ensuring the permutation invariance via canonical ordering.
Authors: Harry Jake Cunningham, Giorgio Giannone, Mingtian Zhang, Marc Peter Deisenroth
Abstract: Global convolutions have shown increasing promise as powerful general-purpose sequence models. However, training long convolutions is challenging, and kernel parameterizations must be able to learn long-range dependencies without overfitting. This work introduces reparameterized multi-resolution convolutions ($\texttt{MRConv}$), a novel approach to parameterizing global convolutional kernels for long-sequence modelling. By leveraging multi-resolution convolutions, incorporating structural reparameterization and introducing learnable kernel decay, $\texttt{MRConv}$ learns expressive long-range kernels that perform well across various data modalities. Our experiments demonstrate state-of-the-art performance on the Long Range Arena, Sequential CIFAR, and Speech Commands tasks among convolution models and linear-time transformers. Moreover, we report improved performance on ImageNet classification by replacing 2D convolutions with 1D $\texttt{MRConv}$ layers.
Authors: Tanya Liyaqat, Tanvir Ahmad, Chandni Saxena
Abstract: Molecular Property Prediction (MPP) plays a pivotal role across diverse domains, spanning drug discovery, material science, and environmental chemistry. Fueled by the exponential growth of chemical data and the evolution of artificial intelligence, recent years have witnessed remarkable strides in MPP. However, the multifaceted nature of molecular data, such as molecular structures, SMILES notation, and molecular images, continues to pose a fundamental challenge in its effective representation. To address this, representation learning techniques are instrumental as they acquire informative and interpretable representations of molecular data. This article explores recent AI/-based approaches in MPP, focusing on both single and multiple modality representation techniques. It provides an overview of various molecule representations and encoding schemes, categorizes MPP methods by their use of modalities, and outlines datasets and tools available for feature generation. The article also analyzes the performance of recent methods and suggests future research directions to advance the field of MPP.
Authors: Huitong Jin, Yipeng Zhou, Laizhong Cui, Quan Z. Sheng
Abstract: Pre-training exploits public datasets to pre-train an advanced machine learning model, so that the model can be easily tuned to adapt to various downstream tasks. Pre-training has been extensively explored to mitigate computation and communication resource consumption. Inspired by these advantages, we are the first to explore how model pre-training can mitigate noise detriment in differentially private federated learning (DPFL). DPFL is upgraded from federated learning (FL), the de-facto standard for privacy preservation when training the model across multiple clients owning private data. DPFL introduces differentially private (DP) noises to obfuscate model gradients exposed in FL, which however can considerably impair model accuracy. In our work, we compare head fine-tuning (HT) and full fine-tuning (FT), which are based on pre-training, with scratch training (ST) in DPFL through a comprehensive empirical study. Our experiments tune pre-trained models (obtained by pre-training on ImageNet-1K) with CIFAR-10, CHMNIST and Fashion-MNIST (FMNIST) datasets, respectively. The results demonstrate that HT and FT can significantly mitigate noise influence by diminishing gradient exposure times. In particular, HT outperforms FT when the privacy budget is tight or the model size is large. Visualization and explanation study further substantiates our findings. Our pioneering study introduces a new perspective on enhancing DPFL and expanding its practical applications.
Authors: Jinluan Yang, Zhengyu Chen, Teng Xiao, Wenqiao Zhang, Yong Lin, Kun Kuang
Abstract: Heterophilic Graph Neural Networks (HGNNs) have shown promising results for semi-supervised learning tasks on graphs. Notably, most real-world heterophilic graphs are composed of a mixture of nodes with different neighbor patterns, exhibiting local node-level homophilic and heterophilic structures. However, existing works are only devoted to designing better HGNN backbones or architectures for node classification tasks on heterophilic and homophilic graph benchmarks simultaneously, and their analyses of HGNN performance with respect to nodes are only based on the determined data distribution without exploring the effect caused by this structural difference between training and testing nodes. How to learn invariant node representations on heterophilic graphs to handle this structure difference or distribution shifts remains unexplored. In this paper, we first discuss the limitations of previous graph-based invariant learning methods from the perspective of data augmentation. Then, we propose \textbf{HEI}, a framework capable of generating invariant node representations through incorporating heterophily information to infer latent environments without augmentation, which are then used for invariant prediction, under heterophilic graph structure distribution shifts. We theoretically show that our proposed method can achieve guaranteed performance under heterophilic graph structure distribution shifts. Extensive experiments on various benchmarks and backbones can also demonstrate the effectiveness of our method compared with existing state-of-the-art baselines.
Authors: So Nakashima, Tetsuya J. Kobayashi
Abstract: Reinforcement Learning (RL) offers a fundamental framework for discovering optimal action strategies through interactions within unknown environments. Recent advancement have shown that the performance and applicability of RL can significantly be enhanced by exploiting a population of agents in various ways. Zeroth-Order Optimization (ZOO) leverages an agent population to estimate the gradient of the objective function, enabling robust policy refinement even in non-differentiable scenarios. As another application, Genetic Algorithms (GA) boosts the exploration of policy landscapes by mutational generation of policy diversity in an agent population and its refinement by selection. A natural question is whether we can have the best of two worlds that the agent population can have. In this work, we propose Ancestral Reinforcement Learning (ARL), which synergistically combines the robust gradient estimation of ZOO with the exploratory power of GA. The key idea in ARL is that each agent within a population infers gradient by exploiting the history of its ancestors, i.e., the ancestor population in the past, while maintaining the diversity of policies in the current population as in GA. We also theoretically reveal that the populational search in ARL implicitly induces the KL-regularization of the objective function, resulting in the enhanced exploration. Our results extend the applicability of populational algorithms for RL.
Authors: Marco Bagatella, Andreas Krause, Georg Martius
Abstract: Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning, as it allows describing objectives beyond the expressivity of conventional discounted return formulations. Nonetheless, recent works have shown that LTL formulas can be translated into a variable rewarding and discounting scheme, whose optimization produces a policy maximizing a lower bound on the probability of formula satisfaction. However, the synthesized reward signal remains fundamentally sparse, making exploration challenging. We aim to overcome this limitation, which can prevent current algorithms from scaling beyond low-dimensional, short-horizon problems. We show how better exploration can be achieved by further leveraging the LTL specification and casting its corresponding Limit Deterministic B\"uchi Automaton (LDBA) as a Markov reward process, thus enabling a form of high-level value estimation. By taking a Bayesian perspective over LDBA dynamics and proposing a suitable prior distribution, we show that the values estimated through this procedure can be treated as a shaping potential and mapped to informative intrinsic rewards. Empirically, we demonstrate applications of our method from tabular settings to high-dimensional continuous systems, which have so far represented a significant challenge for LTL-based reinforcement learning algorithms.
Authors: Yukun Zhang
Abstract: This paper presents a novel unified theoretical framework for understanding Transformer architectures by integrating Partial Differential Equations (PDEs), Neural Information Flow Theory, and Information Bottleneck Theory. We model Transformer information dynamics as a continuous PDE process, encompassing diffusion, self-attention, and nonlinear residual components. Our comprehensive experiments across image and text modalities demonstrate that the PDE model effectively captures key aspects of Transformer behavior, achieving high similarity (cosine similarity > 0.98) with Transformer attention distributions across all layers. While the model excels in replicating general information flow patterns, it shows limitations in fully capturing complex, non-linear transformations. This work provides crucial theoretical insights into Transformer mechanisms, offering a foundation for future optimizations in deep learning architectural design. We discuss the implications of our findings, potential applications in model interpretability and efficiency, and outline directions for enhancing PDE models to better mimic the intricate behaviors observed in Transformers, paving the way for more transparent and optimized AI systems.
Authors: Meng Xu, Ke Han, Weijian Hu, Wen Ji
Abstract: Fine-grained air quality (AQ) mapping is made possible by the proliferation of cheap AQ micro-stations (MSs). However, their measurements are often inaccurate and sensitive to local disturbances, in contrast to standardized stations (SSs) that provide accurate readings but fall short in number. To simultaneously address the issues of low data quality (MSs) and high label sparsity (SSs), a multi-task spatio-temporal network (MTSTN) is proposed, which employs self-supervised learning to utilize massive unlabeled data, aided by seasonal and trend decomposition of MS data offering reliable information as features. The MTSTN is applied to infer NO$_2$, O$_3$ and PM$_{2.5}$ concentrations in a 250 km$^2$ area in Chengdu, China, at a resolution of 500m$\times$500m$\times$1hr. Data from 55 SSs and 323 MSs were used, along with meteorological, traffic, geographic and timestamp data as features. The MTSTN excels in accuracy compared to several benchmarks, and its performance is greatly enhanced by utilizing low-quality MS data. A series of ablation and pressure tests demonstrate the results' robustness and interpretability, showcasing the MTSTN's practical value for accurate and affordable AQ inference.
Authors: Shiyuan Zuo, Xingrun Yan, Rongfei Fan, Li Shen, Puning Zhao, Jie Xu, Han Hu
Abstract: In practical federated learning (FL) systems, the presence of malicious Byzantine attacks and data heterogeneity often introduces biases into the learning process. However, existing Byzantine-robust methods typically only achieve a compromise between adaptability to different loss function types (including both strongly convex and non-convex) and robustness to heterogeneous datasets, but with non-zero optimality gap. Moreover, this compromise often comes at the cost of high computational complexity for aggregation, which significantly slows down the training speed. To address this challenge, we propose a federated learning approach called Federated Normalized Gradients Algorithm (Fed-NGA). Fed-NGA simply normalizes the uploaded local gradients to be unit vectors before aggregation, achieving a time complexity of $\mathcal{O}(pM)$, where $p$ represents the dimension of model parameters and $M$ is the number of participating clients. This complexity scale achieves the best level among all the existing Byzantine-robust methods. Furthermore, through rigorous proof, we demonstrate that Fed-NGA transcends the trade-off between adaptability to loss function type and data heterogeneity and the limitation of non-zero optimality gap in existing literature. Specifically, Fed-NGA can adapt to both non-convex loss functions and non-IID datasets simultaneously, with zero optimality gap at a rate of $\mathcal{O} (1/T^{\frac{1}{2} - \delta})$, where T is the iteration number and $\delta \in (0,\frac{1}{2})$. In cases where the loss function is strongly convex, the zero optimality gap achieving rate can be improved to be linear. Experimental results provide evidence of the superiority of our proposed Fed-NGA on time complexity and convergence performance over baseline methods.
Authors: Tatjana Legler, Vinit Hegiste, Martin Ruskowski
Abstract: Federated Learning (FL) represents a paradigm shift in the field of machine learning, offering an approach for a decentralized training of models across a multitude of devices while maintaining the privacy of local data. However, the dynamic nature of FL systems, characterized by the ongoing incorporation of new clients with potentially diverse data distributions and computational capabilities, poses a significant challenge to the stability and efficiency of these distributed learning networks. The seamless integration of new clients is imperative to sustain and enhance the performance and robustness of FL systems. This paper looks into the complexities of integrating new clients into existing FL systems and explores how data heterogeneity and varying data distribution (not independent and identically distributed) among them can affect model training, system efficiency, scalability and stability. Despite these challenges, the integration of new clients into FL systems presents opportunities to enhance data diversity, improve learning performance, and leverage distributed computational power. In contrast to other fields of application such as the distributed optimization of word predictions on Gboard (where federated learning once originated), there are usually only a few clients in the production environment, which is why information from each new client becomes all the more valuable. This paper outlines strategies for effective client selection strategies and solutions for ensuring system scalability and stability. Using the example of images from optical quality inspection, it offers insights into practical approaches. In conclusion, this paper proposes that addressing the challenges presented by new client integration is crucial to the advancement and efficiency of distributed learning networks, thus paving the way for the adoption of Federated Learning in production environments.
Authors: Tatjana Legler, Vinit Hegiste, Ahmed Anwar, Martin Ruskowski
Abstract: Federated learning (FL) has emerged as a promising approach to training machine learning models across decentralized data sources while preserving data privacy, particularly in manufacturing and shared production environments. However, the presence of data heterogeneity variations in data distribution, quality, and volume across different or clients and production sites, poses significant challenges to the effectiveness and efficiency of FL. This paper provides a comprehensive overview of heterogeneity in FL within the context of manufacturing, detailing the types and sources of heterogeneity, including non-independent and identically distributed (non-IID) data, unbalanced data, variable data quality, and statistical heterogeneity. We discuss the impact of these types of heterogeneity on model training and review current methodologies for mitigating their adverse effects. These methodologies include personalized and customized models, robust aggregation techniques, and client selection techniques. By synthesizing existing research and proposing new strategies, this paper aims to provide insight for effectively managing data heterogeneity in FL, enhancing model robustness, and ensuring fair and efficient training across diverse environments. Future research directions are also identified, highlighting the need for adaptive and scalable solutions to further improve the FL paradigm in the context of Industry 4.0.
Authors: Massimiliano Ciranni, Luca Molinaro, Carlo Alberto Barbano, Attilio Fiandrotti, Vittorio Murino, Vito Paolo Pastore, Enzo Tartaglione
Abstract: In the last few years, due to the broad applicability of deep learning to downstream tasks and end-to-end training capabilities, increasingly more concerns about potential biases to specific, non-representative patterns have been raised. Many works focusing on unsupervised debiasing usually leverage the tendency of deep models to learn ``easier'' samples, for example by clustering the latent space to obtain bias pseudo-labels. However, the interpretation of such pseudo-labels is not trivial, especially for a non-expert end user, as it does not provide semantic information about the bias features. To address this issue, we introduce ``Say My Name'' (SaMyNa), the first tool to identify biases within deep models semantically. Unlike existing methods, our approach focuses on biases learned by the model. Our text-based pipeline enhances explainability and supports debiasing efforts: applicable during either training or post-hoc validation, our method can disentangle task-related information and proposes itself as a tool to analyze biases. Evaluation on traditional benchmarks demonstrates its effectiveness in detecting biases and even disclaiming them, showcasing its broad applicability for model diagnosis.
Authors: Fouad Oubari, Mohamed El Baha, Raphael Meunier, Rodrigue D\'ecatoire, Mathilde Mougeot
Abstract: Recent advancements in multimodal Variational AutoEncoders (VAEs) have highlighted their potential for modeling complex data from multiple modalities. However, many existing approaches use relatively straightforward aggregating schemes that may not fully capture the complex dynamics present between different modalities. This work introduces a novel multimodal VAE that incorporates a Markov Random Field (MRF) into both the prior and posterior distributions. This integration aims to capture complex intermodal interactions more effectively. Unlike previous models, our approach is specifically designed to model and leverage the intricacies of these relationships, enabling a more faithful representation of multimodal data. Our experiments demonstrate that our model performs competitively on the standard PolyMNIST dataset and shows superior performance in managing complex intermodal dependencies in a specially designed synthetic dataset, intended to test intricate relationships.
Authors: Jatin Prakash, Anirudh Buvanesh, Bishal Santra, Deepak Saini, Sachin Yadav, Jian Jiao, Yashoteja Prabhu, Amit Sharma, Manik Varma
Abstract: Extreme Classification (XC) aims to map a query to the most relevant documents from a very large document set. XC algorithms used in real-world applications learn this mapping from datasets curated from implicit feedback, such as user clicks. However, these datasets inevitably suffer from missing labels. In this work, we observe that systematic missing labels lead to missing knowledge, which is critical for accurately modelling relevance between queries and documents. We formally show that this absence of knowledge cannot be recovered using existing methods such as propensity weighting and data imputation strategies that solely rely on the training dataset. While LLMs provide an attractive solution to augment the missing knowledge, leveraging them in applications with low latency requirements and large document sets is challenging. To incorporate missing knowledge at scale, we propose SKIM (Scalable Knowledge Infusion for Missing Labels), an algorithm that leverages a combination of small LM and abundant unstructured meta-data to effectively mitigate the missing label problem. We show the efficacy of our method on large-scale public datasets through exhaustive unbiased evaluation ranging from human annotations to simulations inspired from industrial settings. SKIM outperforms existing methods on Recall@100 by more than 10 absolute points. Additionally, SKIM scales to proprietary query-ad retrieval datasets containing 10 million documents, outperforming contemporary methods by 12% in offline evaluation and increased ad click-yield by 1.23% in an online A/B test conducted on a popular search engine. We release our code, prompts, trained XC models and finetuned SLMs at: https://github.com/bicycleman15/skim
Authors: Chi-Heng Lin, Shangqian Gao, James Seale Smith, Abhishek Patel, Shikhar Tuli, Yilin Shen, Hongxia Jin, Yen-Chang Hsu
Abstract: Large Language Models (LLMs) have reshaped the landscape of artificial intelligence by demonstrating exceptional performance across various tasks. However, substantial computational requirements make their deployment challenging on devices with limited resources. Recently, compression methods using low-rank matrix techniques have shown promise, yet these often lead to degraded accuracy or introduce significant overhead in parameters and inference latency. This paper introduces \textbf{Mo}dular \textbf{De}composition (MoDeGPT), a novel structured compression framework that does not need recovery fine-tuning while resolving the above drawbacks. MoDeGPT partitions the Transformer block into modules comprised of matrix pairs and reduces the hidden dimensions via reconstructing the module-level outputs. MoDeGPT is developed based on a theoretical framework that utilizes three well-established matrix decomposition algorithms -- Nystr\"om approximation, CR decomposition, and SVD -- and applies them to our redefined transformer modules. Our comprehensive experiments show MoDeGPT, without backward propagation, matches or surpasses previous structured compression methods that rely on gradient information, and saves 98% of compute costs on compressing a 13B model. On \textsc{Llama}-2/3 and OPT models, MoDeGPT maintains 90-95% zero-shot performance with 25-30% compression rates. Moreover, the compression can be done on a single GPU within a few hours and increases the inference throughput by up to 46%.
Authors: Arya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Cuncong Zhong, Zijun Yao
Abstract: Gene expression profiles obtained through DNA microarray have proven successful in providing critical information for cancer detection classifiers. However, the limited number of samples in these datasets poses a challenge to employ complex methodologies such as deep neural networks for sophisticated analysis. To address this "small data" dilemma, Meta-Learning has been introduced as a solution to enhance the optimization of machine learning models by utilizing similar datasets, thereby facilitating a quicker adaptation to target datasets without the requirement of sufficient samples. In this study, we present a meta-learning-based approach for predicting lung cancer from gene expression profiles. We apply this framework to well-established deep learning methodologies and employ four distinct datasets for the meta-learning tasks, where one as the target dataset and the rest as source datasets. Our approach is evaluated against both traditional and deep learning methodologies, and the results show the superior performance of meta-learning on augmented source data compared to the baselines trained on single datasets. Moreover, we conduct the comparative analysis between meta-learning and transfer learning methodologies to highlight the efficiency of the proposed approach in addressing the challenges associated with limited sample sizes. Finally, we incorporate the explainability study to illustrate the distinctiveness of decisions made by meta-learning.
Authors: Puning Zhao, Jiafei Wu, Zhe Liu, Huiwen Wu
Abstract: Nonparametric contextual bandit is an important model of sequential decision making problems. Under $\alpha$-Tsybakov margin condition, existing research has established a regret bound of $\tilde{O}\left(T^{1-\frac{\alpha+1}{d+2}}\right)$ for bounded supports. However, the optimal regret with unbounded contexts has not been analyzed. The challenge of solving contextual bandit problems with unbounded support is to achieve both exploration-exploitation tradeoff and bias-variance tradeoff simultaneously. In this paper, we solve the nonparametric contextual bandit problem with unbounded contexts. We propose two nearest neighbor methods combined with UCB exploration. The first method uses a fixed $k$. Our analysis shows that this method achieves minimax optimal regret under a weak margin condition and relatively light-tailed context distributions. The second method uses adaptive $k$. By a proper data-driven selection of $k$, this method achieves an expected regret of $\tilde{O}\left(T^{1-\frac{(\alpha+1)\beta}{\alpha+(d+2)\beta}}+T^{1-\beta}\right)$, in which $\beta$ is a parameter describing the tail strength. This bound matches the minimax lower bound up to logarithm factors, indicating that the second method is approximately optimal.
Authors: Jie Wang, Rui Gao, Yao Xie
Abstract: Despite the growing prevalence of artificial neural networks in real-world applications, their vulnerability to adversarial attacks remains to be a significant concern, which motivates us to investigate the robustness of machine learning models. While various heuristics aim to optimize the distributionally robust risk using the $\infty$-Wasserstein metric, such a notion of robustness frequently encounters computation intractability. To tackle the computational challenge, we develop a novel approach to adversarial training that integrates $\phi$-divergence regularization into the distributionally robust risk function. This regularization brings a notable improvement in computation compared with the original formulation. We develop stochastic gradient methods with biased oracles to solve this problem efficiently, achieving the near-optimal sample complexity. Moreover, we establish its regularization effects and demonstrate it is asymptotic equivalence to a regularized empirical risk minimization (ERM) framework, by considering various scaling regimes of the regularization parameter $\eta$ and robustness level $\rho$. These regimes yield gradient norm regularization, variance regularization, or a smoothed gradient norm regularization that interpolates between these extremes. We numerically validate our proposed method in supervised learning, reinforcement learning, and contextual learning and showcase its state-of-the-art performance against various adversarial attacks.
Authors: Yisong Fu, Fei Wang, Zezhi Shao, Chengqing Yu, Yujie Li, Zhao Chen, Zhulin An, Yongjun Xu
Abstract: Recently, Transformers have gained traction in weather forecasting for their capability to capture long-term spatial-temporal correlations. However, their complex architectures result in large parameter counts and extended training times, limiting their practical application and scalability to global-scale forecasting. This paper aims to explore the key factor for accurate weather forecasting and design more efficient solutions. Interestingly, our empirical findings reveal that absolute positional encoding is what really works in Transformer-based weather forecasting models, which can explicitly model the spatial-temporal correlations even without attention mechanisms. We theoretically prove that its effectiveness stems from the integration of geographical coordinates and real-world time features, which are intrinsically related to the dynamics of weather. Based on this, we propose LightWeather, a lightweight and effective model for station-based global weather forecasting. We employ absolute positional encoding and a simple MLP in place of other components of Transformer. With under 30k parameters and less than one hour of training time, LightWeather achieves state-of-the-art performance on global weather datasets compared to other advanced DL methods. The results underscore the superiority of integrating spatial-temporal knowledge over complex architectures, providing novel insights for DL in weather forecasting.
Authors: Yi Li, Shichao Zhang, Guixian Zhang, Debo Cheng
Abstract: Graph unlearning technology has become increasingly important since the advent of the `right to be forgotten' and the growing concerns about the privacy and security of artificial intelligence. Graph unlearning aims to quickly eliminate the effects of specific data on graph neural networks (GNNs). However, most existing deterministic graph unlearning frameworks follow a balanced partition-submodel training-aggregation paradigm, resulting in a lack of structural information between subgraph neighborhoods and redundant unlearning parameter calculations. To address this issue, we propose a novel Graph Structure Mapping Unlearning paradigm (GSMU) and a novel method based on it named Community-centric Graph Eraser (CGE). CGE maps community subgraphs to nodes, thereby enabling the reconstruction of a node-level unlearning operation within a reduced mapped graph. CGE makes the exponential reduction of both the amount of training data and the number of unlearning parameters. Extensive experiments conducted on five real-world datasets and three widely used GNN backbones have verified the high performance and efficiency of our CGE method, highlighting its potential in the field of graph unlearning.
Authors: Hui Xue, Yuexuan An, Yongchun Qin, Wenqian Li, Yixin Wu, Yongjuan Che, Pengfei Fang, Minling Zhang
Abstract: Human intelligence is characterized by our ability to absorb and apply knowledge from the world around us, especially in rapidly acquiring new concepts from minimal examples, underpinned by prior knowledge. Few-shot learning (FSL) aims to mimic this capacity by enabling significant generalizations and transferability. However, traditional FSL frameworks often rely on assumptions of clean, complete, and static data, conditions that are seldom met in real-world environments. Such assumptions falter in the inherently uncertain, incomplete, and dynamic contexts of the open world. This paper presents a comprehensive review of recent advancements designed to adapt FSL for use in open-world settings. We categorize existing methods into three distinct types of open-world few-shot learning: those involving varying instances, varying classes, and varying distributions. Each category is discussed in terms of its specific challenges and methods, as well as its strengths and weaknesses. We standardize experimental settings and metric benchmarks across scenarios, and provide a comparative analysis of the performance of various methods. In conclusion, we outline potential future research directions for this evolving field. It is our hope that this review will catalyze further development of effective solutions to these complex challenges, thereby advancing the field of artificial intelligence.
Authors: Jiaheng Yin, Zhengxin Shi, Jianshen Zhang, Xiaomin Lin, Yulin Huang, Yongzhi Qi, Wei Qi
Abstract: In recent years, numerous Transformer-based models have been applied to long-term time-series forecasting (LTSF) tasks. However, recent studies with linear models have questioned their effectiveness, demonstrating that simple linear layers can outperform sophisticated Transformer-based models. In this work, we review and categorize existing Transformer-based models into two main types: (1) modifications to the model structure and (2) modifications to the input data. The former offers scalability but falls short in capturing inter-sequential information, while the latter preprocesses time-series data but is challenging to use as a scalable module. We propose $\textbf{sTransformer}$, which introduces the Sequence and Temporal Convolutional Network (STCN) to fully capture both sequential and temporal information. Additionally, we introduce a Sequence-guided Mask Attention mechanism to capture global feature information. Our approach ensures the capture of inter-sequential information while maintaining module scalability. We compare our model with linear models and existing forecasting models on long-term time-series forecasting, achieving new state-of-the-art results. We also conducted experiments on other time-series tasks, achieving strong performance. These demonstrate that Transformer-based structures remain effective and our model can serve as a viable baseline for time-series tasks.
Authors: Jingyu Hu, Weiru Liu, Mengnan Du
Abstract: Recent studies highlight the effectiveness of using in-context learning (ICL) to steer large language models (LLMs) in processing tabular data, a challenging task given the structured nature of such data. Despite advancements in performance, the fairness implications of these methods are less understood. This study investigates how varying demonstrations within ICL prompts influence the fairness outcomes of LLMs. Our findings reveal that deliberately including minority group samples in prompts significantly boosts fairness without sacrificing predictive accuracy. Further experiments demonstrate that the proportion of minority to majority samples in demonstrations affects the trade-off between fairness and prediction accuracy. Based on these insights, we introduce a mitigation technique that employs clustering and evolutionary strategies to curate a diverse and representative sample set from the training data. This approach aims to enhance both predictive performance and fairness in ICL applications. Experimental results validate that our proposed method dramatically improves fairness across various metrics, showing its efficacy in real-world scenarios.
Authors: Xingrun Yan, Shiyuan Zuo, Rongfei Fan, Han Hu, Li Shen, Puning Zhao, Yong Luo
Abstract: In a real federated learning (FL) system, communication overhead for passing model parameters between the clients and the parameter server (PS) is often a bottleneck. Hierarchical federated learning (HFL) that poses multiple edge servers (ESs) between clients and the PS can partially alleviate communication pressure but still needs the aggregation of model parameters from multiple ESs at the PS. To further reduce communication overhead, we bring sequential FL (SFL) into HFL for the first time, which removes the central PS and enables the model training to be completed only through passing the global model between two adjacent ESs for each iteration, and propose a novel algorithm adaptive to such a combinational framework, referred to as Fed-CHS. Convergence results are derived for strongly convex and non-convex loss functions under various data heterogeneity setups, which show comparable convergence performance with the algorithms for HFL or SFL solely. Experimental results provide evidence of the superiority of our proposed Fed-CHS on both communication overhead saving and test accuracy over baseline methods.
Authors: Xu Han, Felix Yu, Joao Sedoc, Benjamin Van Durme
Abstract: Our goal is a mechanism for efficiently assigning scalar ratings to each of a large set of elements. For example, "what percent positive or negative is this product review?" When sample sizes are small, prior work has advocated for methods such as Best Worst Scaling (BWS) as being more robust than direct ordinal annotation ("Likert scales"). Here we first introduce IBWS, which iteratively collects annotations through Best-Worst Scaling, resulting in robustly ranked crowd-sourced data. While effective, IBWS is too expensive for large-scale tasks. Using the results of IBWS as a best-desired outcome, we evaluate various direct assessment methods to determine what is both cost-efficient and best correlating to a large scale BWS annotation strategy. Finally, we illustrate in the domains of dialogue and sentiment how these annotations can support robust learning-to-rank models.
Authors: Feihu Huang, Jianyu Zhao
Abstract: Decentralized learning recently has received increasing attention in machine learning due to its advantages in implementation simplicity and system robustness, data privacy. Meanwhile, the adaptive gradient methods show superior performances in many machine learning tasks such as training neural networks. Although some works focus on studying decentralized optimization algorithms with adaptive learning rates, these adaptive decentralized algorithms still suffer from high sample complexity. To fill these gaps, we propose a class of faster adaptive decentralized algorithms (i.e., AdaMDOS and AdaMDOF) for distributed nonconvex stochastic and finite-sum optimization, respectively. Moreover, we provide a solid convergence analysis framework for our methods. In particular, we prove that our AdaMDOS obtains a near-optimal sample complexity of $\tilde{O}(\epsilon^{-3})$ for finding an $\epsilon$-stationary solution of nonconvex stochastic optimization. Meanwhile, our AdaMDOF obtains a near-optimal sample complexity of $O(\sqrt{n}\epsilon^{-2})$ for finding an $\epsilon$-stationary solution of nonconvex finite-sum optimization, where $n$ denotes the sample size. To the best of our knowledge, our AdaMDOF algorithm is the first adaptive decentralized algorithm for nonconvex finite-sum optimization. Some experimental results demonstrate efficiency of our algorithms.
Authors: Xunlian Wu, Jingqi Hu, Anqi Zhang, Yining Quan, Qiguang Miao, Peng Gang Sun
Abstract: Graph clustering is a crucial task in network analysis with widespread applications, focusing on partitioning nodes into distinct groups with stronger intra-group connections than inter-group ones. Recently, contrastive learning has achieved significant progress in graph clustering. However, most methods suffer from the following issues: 1) an over-reliance on meticulously designed data augmentation strategies, which can undermine the potential of contrastive learning. 2) overlooking cluster-oriented structural information, particularly the higher-order cluster(community) structure information, which could unveil the mesoscopic cluster structure information of the network. In this study, Structure-enhanced Contrastive Learning (SECL) is introduced to addresses these issues by leveraging inherent network structures. SECL utilizes a cross-view contrastive learning mechanism to enhance node embeddings without elaborate data augmentations, a structural contrastive learning module for ensuring structural consistency, and a modularity maximization strategy for harnessing clustering-oriented information. This comprehensive approach results in robust node representations that greatly enhance clustering performance. Extensive experiments on six datasets confirm SECL's superiority over current state-of-the-art methods, indicating a substantial improvement in the domain of graph clustering.
Authors: Giovanni Bindi, Philippe Esling
Abstract: Current generative models are able to generate high-quality artefacts but have been shown to struggle with compositional reasoning, which can be defined as the ability to generate complex structures from simpler elements. In this paper, we focus on the problem of compositional representation learning for music data, specifically targeting the fully-unsupervised setting. We propose a simple and extensible framework that leverages an explicit compositional inductive bias, defined by a flexible auto-encoding objective that can leverage any of the current state-of-art generative models. We demonstrate that our framework, used with diffusion models, naturally addresses the task of unsupervised audio source separation, showing that our model is able to perform high-quality separation. Our findings reveal that our proposal achieves comparable or superior performance with respect to other blind source separation methods and, furthermore, it even surpasses current state-of-art supervised baselines on signal-to-interference ratio metrics. Additionally, by learning an a-posteriori masking diffusion model in the space of composable representations, we achieve a system capable of seamlessly performing unsupervised source separation, unconditional generation, and variation generation. Finally, as our proposal works in the latent space of pre-trained neural audio codecs, it also provides a lower computational cost with respect to other neural baselines.
Authors: Yun-Da Tsai, Ting-Yu Yen, Keng-Te Liao, Shou-De Lin
Abstract: Converting different modalities into generalized text, which then serves as input prompts for large language models (LLMs), is a common approach for aligning multimodal models, particularly when pairwise data is limited. Text-centric alignment method leverages the unique properties of text as a modality space, transforming diverse inputs into a unified textual representation, thereby enabling downstream models to effectively interpret various modal inputs. This study evaluates the quality and robustness of multimodal representations in the face of noise imperfections, dynamic input order permutations, and missing modalities, revealing that current text-centric alignment methods can compromise downstream robustness. To address this issue, we propose a new text-centric adversarial training approach that significantly enhances robustness compared to traditional robust training methods and pre-trained multimodal foundation models. Our findings underscore the potential of this approach to improve the robustness and adaptability of multimodal representations, offering a promising solution for dynamic and real-world applications.
Authors: Jiahui Gong, Jingtao Ding, Fanjin Meng, Guilong Chen, Hong Chen, Shen Zhao, Haisheng Lu, Yong Li
Abstract: Mobile devices, especially smartphones, can support rich functions and have developed into indispensable tools in daily life. With the rise of generative AI services, smartphones can potentially transform into personalized assistants, anticipating user needs and scheduling services accordingly. Predicting user intents on smartphones, and reflecting anticipated activities based on past interactions and context, remains a pivotal step towards this vision. Existing research predominantly focuses on specific domains, neglecting the challenge of modeling diverse event sequences across dynamic contexts. Leveraging pre-trained language models (PLMs) offers a promising avenue, yet adapting PLMs to on-device user intent prediction presents significant challenges. To address these challenges, we propose PITuning, a Population-to-Individual Tuning framework. PITuning enhances common pattern extraction through dynamic event-to-intent transition modeling and addresses long-tailed preferences via adaptive unlearning strategies. Experimental results on real-world datasets demonstrate PITuning's superior intent prediction performance, highlighting its ability to capture long-tailed preferences and its practicality for on-device prediction scenarios.
Authors: Matteo Salvador, Alison L. Marsden
Abstract: Scientific Machine Learning (ML) is gaining momentum as a cost-effective alternative to physics-based numerical solvers in many engineering applications. In fact, scientific ML is currently being used to build accurate and efficient surrogate models starting from high-fidelity numerical simulations, effectively encoding the parameterized temporal dynamics underlying Ordinary Differential Equations (ODEs), or even the spatio-temporal behavior underlying Partial Differential Equations (PDEs), in appropriately designed neural networks. We propose an extension of Latent Dynamics Networks (LDNets), namely Liquid Fourier LDNets (LFLDNets), to create parameterized space-time surrogate models for multiscale and multiphysics sets of highly nonlinear differential equations on complex geometries. LFLDNets employ a neurologically-inspired, sparse, liquid neural network for temporal dynamics, relaxing the requirement of a numerical solver for time advancement and leading to superior performance in terms of tunable parameters, accuracy, efficiency and learned trajectories with respect to neural ODEs based on feedforward fully-connected neural networks. Furthermore, in our implementation of LFLDNets, we use a Fourier embedding with a tunable kernel in the reconstruction network to learn high-frequency functions better and faster than using space coordinates directly as input. We challenge LFLDNets in the framework of computational cardiology and evaluate their capabilities on two 3-dimensional test cases arising from multiscale cardiac electrophysiology and cardiovascular hemodynamics. This paper illustrates the capability to run Artificial Intelligence-based numerical simulations on single or multiple GPUs in a matter of minutes and represents a significant step forward in the development of physics-informed digital twins.
Authors: Benjamin K Tapley
Abstract: We present and analyze a framework for designing symplectic neural networks (SympNets) based on geometric integrators for Hamiltonian differential equations. The SympNets are universal approximators in the space of Hamiltonian diffeomorphisms, interpretable and have a non-vanishing gradient property. We also give a representation theory for linear systems, meaning the proposed P-SympNets can exactly parameterize any symplectic map corresponding to quadratic Hamiltonians. Extensive numerical tests demonstrate increased expressiveness and accuracy -- often several orders of magnitude better -- for lower training cost over existing architectures. Lastly, we show how to perform symbolic Hamiltonian regression with SympNets for polynomial systems using backward error analysis.
Authors: Achref Jaziri, Etienne K\"unzel, Visvanathan Ramesh
Abstract: A continual learning agent builds on previous experiences to develop increasingly complex behaviors by adapting to non-stationary and dynamic environments while preserving previously acquired knowledge. However, scaling these systems presents significant challenges, particularly in balancing the preservation of previous policies with the adaptation of new ones to current environments. This balance, known as the stability-plasticity dilemma, is especially pronounced in complex multi-agent domains such as the train scheduling problem, where environmental and agent behaviors are constantly changing, and the search space is vast. In this work, we propose addressing these challenges in the train scheduling problem using curriculum learning. We design a curriculum with adjacent skills that build on each other to improve generalization performance. Introducing a curriculum with distinct tasks introduces non-stationarity, which we address by proposing a new algorithm: Continual Deep Q-Network (DQN) Expansion (CDE). Our approach dynamically generates and adjusts Q-function subspaces to handle environmental changes and task requirements. CDE mitigates catastrophic forgetting through EWC while ensuring high plasticity using adaptive rational activation functions. Experimental results demonstrate significant improvements in learning efficiency and adaptability compared to RL baselines and other adapted methods for continual learning, highlighting the potential of our method in managing the stability-plasticity dilemma in the adaptive train scheduling setting.
Authors: Joe Watson, Chen Song, Oliver Weeger, Theo Gruner, An T. Le, Kay Hansel, Ahmed Hendawy, Oleg Arenz, Will Trojak, Miles Cranmer, Carlo D'Eramo, Fabian B\"ulow, Tanmay Goyal, Jan Peters, Martin W. Hoffman
Abstract: This survey examines the broad suite of methods and models for combining machine learning with physics knowledge for prediction and forecast, with a focus on partial differential equations. These methods have attracted significant interest due to their potential impact on advancing scientific research and industrial practices by improving predictive models with small- or large-scale datasets and expressive predictive models with useful inductive biases. The survey has two parts. The first considers incorporating physics knowledge on an architectural level through objective functions, structured predictive models, and data augmentation. The second considers data as physics knowledge, which motivates looking at multi-task, meta, and contextual learning as an alternative approach to incorporating physics knowledge in a data-driven fashion. Finally, we also provide an industrial perspective on the application of these methods and a survey of the open-source ecosystem for physics-informed machine learning.
Authors: Dimitrios Tsaras, Antoine Grosnit, Lei Chen, Zhiyao Xie, Haitham Bou-Ammar, Mingxuan Yuan
Abstract: Chip design relies heavily on generating Boolean circuits, such as AND-Inverter Graphs (AIGs), from functional descriptions like truth tables. While recent advances in deep learning have aimed to accelerate circuit design, these efforts have mostly focused on tasks other than synthesis, and traditional heuristic methods have plateaued. In this paper, we introduce ShortCircuit, a novel transformer-based architecture that leverages the structural properties of AIGs and performs efficient space exploration. Contrary to prior approaches attempting end-to-end generation of logic circuits using deep networks, ShortCircuit employs a two-phase process combining supervised with reinforcement learning to enhance generalization to unseen truth tables. We also propose an AlphaZero variant to handle the double exponentially large state space and the sparsity of the rewards, enabling the discovery of near-optimal designs. To evaluate the generative performance of our trained model , we extract 500 truth tables from a benchmark set of 20 real-world circuits. ShortCircuit successfully generates AIGs for 84.6% of the 8-input test truth tables, and outperforms the state-of-the-art logic synthesis tool, ABC, by 14.61% in terms of circuits size.
Authors: Ching-Wen Yang, Che Wei Chen, Kun-da Wu, Hao Xu, Jui-Feng Yao, Hung-Yu Kao
Abstract: Explainable Recommendation task is designed to receive a pair of user and item and output explanations to justify why an item is recommended to a user. Many models treat review-generation as a proxy of explainable recommendation. Although they are able to generate fluent and grammatical sentences, they suffer from generality and hallucination issues. We propose a personalized, aspect-controlled model called Multi-Aspect Prompt LEarner (MAPLE), in which it integrates aspect category as another input dimension to facilitate the memorization of fine-grained aspect terms. Experiments on two real-world review datasets in restaurant domain show that MAPLE outperforms the baseline review-generation models in terms of text and feature diversity while maintaining excellent coherence and factual relevance. We further treat MAPLE as a retriever component in the retriever-reader framework and employ a Large-Language Model (LLM) as the reader, showing that MAPLE's explanation along with the LLM's comprehension ability leads to enriched and personalized explanation as a result. We will release the code and data in this http upon acceptance.
Authors: Silvia Seidlitz, Katharina H\"olzl, Ayca von Garrel, Jan Sellner, Stephan Katzenschlager, Tobias H\"olle, Dania Fischer, Maik von der Forst, Felix C. F. Schmitt, Markus A. Weigand, Lena Maier-Hein, Maximilian Dietrich
Abstract: With sepsis remaining a leading cause of mortality, early identification of septic patients and those at high risk of death is a challenge of high socioeconomic importance. The driving hypothesis of this study was that hyperspectral imaging (HSI) could provide novel biomarkers for sepsis diagnosis and treatment management due to its potential to monitor microcirculatory alterations. We conducted a comprehensive study involving HSI data of the palm and fingers from more than 480 patients on the day of their intensive care unit (ICU) admission. The findings demonstrate that HSI measurements can predict sepsis with an area under the receiver operating characteristic curve (AUROC) of 0.80 (95 % confidence interval (CI) [0.76; 0.84]) and mortality with an AUROC of 0.72 (95 % CI [0.65; 0.79]). The predictive performance improves substantially when additional clinical data is incorporated, leading to an AUROC of up to 0.94 (95 % CI [0.92; 0.96]) for sepsis and 0.84 (95 % CI [0.78; 0.89]) for mortality. We conclude that HSI presents novel imaging biomarkers for the rapid, non-invasive prediction of sepsis and mortality, suggesting its potential as an important modality for guiding diagnosis and treatment.
Authors: Gongpu Chen, Soung Chang Liew, Deniz Gunduz
Abstract: The restless multi-armed bandit (RMAB) framework is a popular model with applications across a wide variety of fields. However, its solution is hindered by the exponentially growing state space (with respect to the number of arms) and the combinatorial action space, making traditional reinforcement learning methods infeasible for large-scale instances. In this paper, we propose GINO-Q, a three-timescale stochastic approximation algorithm designed to learn an asymptotically optimal index policy for RMABs. GINO-Q mitigates the curse of dimensionality by decomposing the RMAB into a series of subproblems, each with the same dimension as a single arm, ensuring that complexity increases linearly with the number of arms. Unlike recently developed Whittle-index-based algorithms, GINO-Q does not require RMABs to be indexable, enhancing its flexibility and applicability. Our experimental results demonstrate that GINO-Q consistently learns near-optimal policies, even for non-indexable RMABs where Whittle-index-based algorithms perform poorly, and it converges significantly faster than existing baselines.
Authors: Puning Zhao, Jiafei Wu, Zhe Liu, Chong Wang, Rongfei Fan, Qingming Li
Abstract: We study convex optimization problems under differential privacy (DP). With heavy-tailed gradients, existing works achieve suboptimal rates. The main obstacle is that existing gradient estimators have suboptimal tail properties, resulting in a superfluous factor of $d$ in the union bound. In this paper, we explore algorithms achieving optimal rates of DP optimization with heavy-tailed gradients. Our first method is a simple clipping approach. Under bounded $p$-th order moments of gradients, with $n$ samples, it achieves $\tilde{O}(\sqrt{d/n}+\sqrt{d}(\sqrt{d}/n\epsilon)^{1-1/p})$ population risk with $\epsilon\leq 1/\sqrt{d}$. We then propose an iterative updating method, which is more complex but achieves this rate for all $\epsilon\leq 1$. The results significantly improve over existing methods. Such improvement relies on a careful treatment of the tail behavior of gradient estimators. Our results match the minimax lower bound in \cite{kamath2022improved}, indicating that the theoretical limit of stochastic convex optimization under DP is achievable.
Authors: Yuran Xiang, Haiteng Zhao, Chang Ma, Zhi-Hong Deng
Abstract: Recent advancements in computational chemistry have increasingly focused on synthesizing molecules based on textual instructions. Integrating graph generation with these instructions is complex, leading most current methods to use molecular sequences with pre-trained large language models. In response to this challenge, we propose a novel framework, named $\textbf{UTGDiff (Unified Text-Graph Diffusion Model)}$, which utilizes language models for discrete graph diffusion to generate molecular graphs from instructions. UTGDiff features a unified text-graph transformer as the denoising network, derived from pre-trained language models and minimally modified to process graph data through attention bias. Our experimental results demonstrate that UTGDiff consistently outperforms sequence-based baselines in tasks involving instruction-based molecule generation and editing, achieving superior performance with fewer parameters given an equivalent level of pretraining corpus. Our code is availble at https://github.com/ran1812/UTGDiff.
Authors: Haoxiang Sun
Abstract: Support Vector Machines (SVMs) based on hinge loss have been extensively discussed and applied to various binary classification tasks. These SVMs achieve a balance between margin maximization and the minimization of slack due to outliers. Although many efforts have been dedicated to enhancing the performance of SVMs with hinge loss, studies on $p$SVMs, soft-margin SVMs with $p$-norm hinge loss, remain relatively scarce. In this paper, we explore the properties, performance, and training algorithms of $p$SVMs. We first derive the generalization bound of $p$SVMs, then formulate the dual optimization problem, comparing it with the traditional approach. Furthermore, we discuss a generalized version of the Sequential Minimal Optimization (SMO) algorithm, $p$SMO, to train our $p$SVM model. Comparative experiments on various datasets, including binary and multi-class classification tasks, demonstrate the effectiveness and advantages of our $p$SVM model and the $p$SMO method.
Authors: Przemys{\l}aw Andrzej Wa{\l}\k{e}ga, Michael Rawson
Abstract: Graph neural networks (GNNs) have recently been adapted to temporal settings, often employing temporal versions of the message-passing mechanism known from GNNs. We divide temporal message passing mechanisms from literature into two main types: global and local, and establish Weisfeiler-Leman characterisations for both. This allows us to formally analyse expressive power of temporal message-passing models. We show that global and local temporal message-passing mechanisms have incomparable expressive power when applied to arbitrary temporal graphs. However, the local mechanism is strictly more expressive than the global mechanism when applied to colour-persistent temporal graphs, whose node colours are initially the same in all time points. Our theoretical findings are supported by experimental evidence, underlining practical implications of our analysis.
Authors: Hongyuan Zhang, Yanchen Xu, Sida Huang, Xuelong Li
Abstract: Inspired by the idea of Positive-incentive Noise (Pi-Noise or $\pi$-Noise) that aims at learning the reliable noise beneficial to tasks, we scientifically investigate the connection between contrastive learning and $\pi$-noise in this paper. By converting the contrastive loss to an auxiliary Gaussian distribution to quantitatively measure the difficulty of the specific contrastive model under the information theory framework, we properly define the task entropy, the core concept of $\pi$-noise, of contrastive learning. It is further proved that the predefined data augmentation in the standard contrastive learning paradigm can be regarded as a kind of point estimation of $\pi$-noise. Inspired by the theoretical study, a framework that develops a $\pi$-noise generator to learn the beneficial noise (instead of estimation) as data augmentations for contrast is proposed. The designed framework can be applied to diverse types of data and is also completely compatible with the existing contrastive models. From the visualization, we surprisingly find that the proposed method successfully learns effective augmentations.
Authors: Hong Su
Abstract: In very deep neural networks, gradients can become extremely small during backpropagation, making it challenging to train the early layers. ResNet (Residual Network) addresses this issue by enabling gradients to flow directly through the network via skip connections, facilitating the training of much deeper networks. However, in these skip connections, the input ipd is directly added to the transformed data tfd, treating ipd and tfd equally, without adapting to different scenarios. In this paper, we propose AdaResNet (Auto-Adapting Residual Network), which automatically adjusts the ratio between ipd and tfd based on the training data. We introduce a variable, weight}_{tfd}^{ipd, to represent this ratio. This variable is dynamically adjusted during backpropagation, allowing it to adapt to the training data rather than remaining fixed. Experimental results demonstrate that AdaResNet achieves a maximum accuracy improvement of over 50\% compared to traditional ResNet.
Authors: Tom Jacobs, Rebekka Burkholz
Abstract: Sparsifying deep neural networks to reduce their inference cost is an NP-hard problem and difficult to optimize due to its mixed discrete and continuous nature. Yet, as we prove, continuous sparsification has already an implicit bias towards sparsity that would not require common projections of relaxed mask variables. While implicit rather than explicit regularization induces benefits, it usually does not provide enough flexibility in practice, as only a specific target sparsity is obtainable. To exploit its potential for continuous sparsification, we propose a way to control the strength of the implicit bias. Based on the mirror flow framework, we derive resulting convergence and optimality guarantees in the context of underdetermined linear regression and demonstrate the utility of our insights in more general neural network sparsification experiments, achieving significant performance gains, particularly in the high-sparsity regime. Our theoretical contribution might be of independent interest, as we highlight a way to enter the rich regime and show that implicit bias is controllable by a time-dependent Bregman potential.
Authors: Andrew Kiruluta, Andreas Lemos
Abstract: This paper presents a novel hybrid approach that integrates linear programming (LP) within the loss function of an unsupervised machine learning model. By leveraging the strengths of both optimization techniques and machine learning, this method introduces a robust framework for solving complex optimization problems where traditional methods may fall short. The proposed approach encapsulates the constraints and objectives of a linear programming problem directly into the loss function, guiding the learning process to adhere to these constraints while optimizing the desired outcomes. This technique not only preserves the interpretability of linear programming but also benefits from the flexibility and adaptability of machine learning, making it particularly well-suited for unsupervised or semi-supervised learning scenarios.
Authors: Renye Yan, Yaozhong Gan, You Wu, Ling Liang, Junliang Xing, Yimao Cai, Ru Huang
Abstract: The imbalance of exploration and exploitation has long been a significant challenge in reinforcement learning. In policy optimization, excessive reliance on exploration reduces learning efficiency, while over-dependence on exploitation might trap agents in local optima. This paper revisits the exploration-exploitation dilemma from the perspective of entropy by revealing the relationship between entropy and the dynamic adaptive process of exploration and exploitation. Based on this theoretical insight, we establish an end-to-end adaptive framework called AdaZero, which automatically determines whether to explore or to exploit as well as their balance of strength. Experiments show that AdaZero significantly outperforms baseline models across various Atari and MuJoCo environments with only a single setting. Especially in the challenging environment of Montezuma, AdaZero boosts the final returns by up to fifteen times. Moreover, we conduct a series of visualization analyses to reveal the dynamics of our self-adaptive mechanism, demonstrating how entropy reflects and changes with respect to the agent's performance and adaptive process.
Authors: Zhang Haishan, Diptesh Das, Koji Tsuda
Abstract: Multi-Objective Optimization (MOO) is an important problem in real-world applications. However, for a non-trivial problem, no single solution exists that can optimize all the objectives simultaneously. In a typical MOO problem, the goal is to find a set of optimum solutions (Pareto set) that trades off the preferences among objectives. Scalarization in MOO is a well-established method for finding a finite set approximation of the whole Pareto set (PS). However, in real-world experimental design scenarios, it's beneficial to obtain the whole PS for flexible exploration of the design space. Recently Pareto set learning (PSL) has been introduced to approximate the whole PS. PSL involves creating a manifold representing the Pareto front of a multi-objective optimization problem. A naive approach includes finding discrete points on the Pareto front through randomly generated preference vectors and connecting them by regression. However, this approach is computationally expensive and leads to a poor PS approximation. We propose to optimize the preference points to be distributed evenly on the Pareto front. Our formulation leads to a bilevel optimization problem that can be solved by e.g. differentiable cross-entropy methods. We demonstrated the efficacy of our method for complex and difficult black-box MOO problems using both synthetic and real-world benchmark data.
Authors: Aleksandr Yugay, Alexey Zaytsev
Abstract: High-quality representation of transactional sequences is vital for modern banking applications, including risk management, churn prediction, and personalized customer offers. Different tasks require distinct representation properties: local tasks benefit from capturing the client's current state, while global tasks rely on general behavioral patterns. Previous research has demonstrated that various self-supervised approaches yield representations that better capture either global or local qualities. This study investigates the integration of two self-supervised learning techniques - instance-wise contrastive learning and a generative approach based on restoring masked events in latent space. The combined approach creates representations that balance local and global transactional data characteristics. Experiments conducted on several public datasets, focusing on sequence classification and next-event type prediction, show that the integrated method achieves superior performance compared to individual approaches and demonstrates synergistic effects. These findings suggest that the proposed approach offers a robust framework for advancing event sequences representation learning in the financial sector.
Authors: Rashida Hakim, Ana-Andreea Stoica, Christos H. Papadimitriou, Mihalis Yannakakis
Abstract: Fairness in clustering has been considered extensively in the past; however, the trade-off between the two objectives -- e.g., can we sacrifice just a little in the quality of the clustering to significantly increase fairness, or vice-versa? -- has rarely been addressed. We introduce novel algorithms for tracing the complete trade-off curve, or Pareto front, between quality and fairness in clustering problems; that is, computing all clusterings that are not dominated in both objectives by other clusterings. Unlike previous work that deals with specific objectives for quality and fairness, we deal with all objectives for fairness and quality in two general classes encompassing most of the special cases addressed in previous work. Our algorithm must take exponential time in the worst case as the Pareto front itself can be exponential. Even when the Pareto front is polynomial, our algorithm may take exponential time, and we prove that this is inevitable unless P = NP. However, we also present a new polynomial-time algorithm for computing the entire Pareto front when the cluster centers are fixed, and for perhaps the most natural fairness objective: minimizing the sum, over all clusters, of the imbalance between the two groups in each cluster.
Authors: Yaxuan Kong, Zepu Wang, Yuqi Nie, Tian Zhou, Stefan Zohren, Yuxuan Liang, Peng Sun, Qingsong Wen
Abstract: Traditional recurrent neural network architectures, such as long short-term memory neural networks (LSTM), have historically held a prominent role in time series forecasting (TSF) tasks. While the recently introduced sLSTM for Natural Language Processing (NLP) introduces exponential gating and memory mixing that are beneficial for long term sequential learning, its potential short memory issue is a barrier to applying sLSTM directly in TSF. To address this, we propose a simple yet efficient algorithm named P-sLSTM, which is built upon sLSTM by incorporating patching and channel independence. These modifications substantially enhance sLSTM's performance in TSF, achieving state-of-the-art results. Furthermore, we provide theoretical justifications for our design, and conduct extensive comparative and analytical experiments to fully validate the efficiency and superior performance of our model.
Authors: Jason Matthews, Alex Bihlo
Abstract: In recent years the study of deep learning for solving differential equations has grown substantially. The use of physics-informed neural networks (PINNs) and deep operator networks (DeepONets) have emerged as two of the most useful approaches in approximating differential equation solutions using machine learning. Here, we propose PinnDE, an open-source python library for solving differential equations with both PINNs and DeepONets. We give a brief review of both PINNs and DeepONets, introduce PinnDE along with the structure and usage of the package, and present worked examples to show PinnDE's effectiveness in approximating solutions with both PINNs and DeepONets.
Authors: Jiaming Liu, Hongyuan Liu, Zhili Qin, Wei Han, Yulu Fan, Qinli Yang, Junming Shao
Abstract: The dynamic nature of open-world scenarios has attracted more attention to class incremental learning (CIL). However, existing CIL methods typically presume the availability of complete ground-truth labels throughout the training process, an assumption rarely met in practical applications. Consequently, this paper explores a more challenging problem of unsupervised class incremental learning (UCIL). The essence of addressing this problem lies in effectively capturing comprehensive feature representations and discovering unknown novel classes. To achieve this, we first model the knowledge of class distribution by exploiting fine-grained prototypes. Subsequently, a granularity alignment technique is introduced to enhance the unsupervised class discovery. Additionally, we proposed a strategy to minimize overlap between novel and existing classes, thereby preserving historical knowledge and mitigating the phenomenon of catastrophic forgetting. Extensive experiments on the five datasets demonstrate that our approach significantly outperforms current state-of-the-art methods, indicating the effectiveness of the proposed method.
Authors: Nikolai Rozanov
Abstract: Reinforcement learning (RL) and Deep Reinforcement Learning (DRL), in particular, have the potential to disrupt and are already changing the way we interact with the world. One of the key indicators of their applicability is their ability to scale and work in real-world scenarios, that is in large-scale problems. This scale can be achieved via a combination of factors, the algorithm's ability to make use of large amounts of data and computational resources and the efficient exploration of the environment for viable solutions (i.e. policies). In this work, we investigate and motivate some theoretical foundations for deep reinforcement learning. We start with exact dynamic programming and work our way up to stochastic approximations and stochastic approximations for a model-free scenario, which forms the theoretical basis of modern reinforcement learning. We present an overview of this highly varied and rapidly changing field from the perspective of Approximate Dynamic Programming. We then focus our study on the short-comings with respect to exploration of the cornerstone approaches (i.e. DQN, DDQN, A2C) in deep reinforcement learning. On the theory side, our main contribution is the proposal of a novel Bayesian actor-critic algorithm. On the empirical side, we evaluate Bayesian exploration as well as actor-critic algorithms on standard benchmarks as well as state-of-the-art evaluation suites and show the benefits of both of these approaches over current state-of-the-art deep RL methods. We release all the implementations and provide a full python library that is easy to install and hopefully will serve the reinforcement learning community in a meaningful way, and provide a strong foundation for future work.
Authors: Sriyash Poddar, Yanming Wan, Hamish Ivison, Abhishek Gupta, Natasha Jaques
Abstract: Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual human preferences across a diverse population. When these differences arise, traditional RLHF frameworks simply average over them, leading to inaccurate rewards and poor performance for individual subgroups. To address the need for pluralistic alignment, we develop a class of multimodal RLHF methods. Our proposed techniques are based on a latent variable formulation - inferring a novel user-specific latent and learning reward models and policies conditioned on this latent without additional user-specific data. While conceptually simple, we show that in practice, this reward modeling requires careful algorithmic considerations around model architecture and reward scaling. To empirically validate our proposed technique, we first show that it can provide a way to combat underspecification in simulated control problems, inferring and optimizing user-specific reward functions. Next, we conduct experiments on pluralistic language datasets representing diverse user preferences and demonstrate improved reward function accuracy. We additionally show the benefits of this probabilistic framework in terms of measuring uncertainty, and actively learning user preferences. This work enables learning from diverse populations of users with divergent preferences, an important challenge that naturally occurs in problems from robot learning to foundation model alignment.
Authors: Haowen Ma, Zhiguo Long, Hua Meng
Abstract: Density-based clustering methods by mode-seeking usually achieve clustering by using local density estimation to mine structural information, such as local dependencies from lower density points to higher neighbors. However, they often rely too heavily on \emph{local} structures and neglect \emph{global} characteristics, which can lead to significant errors in peak selection and dependency establishment. Although introducing more hyperparameters that revise dependencies can help mitigate this issue, tuning them is challenging and even impossible on real-world datasets. In this paper, we propose a new algorithm (TANGO) to establish local dependencies by exploiting a global-view \emph{typicality} of points, which is obtained by mining further the density distributions and initial dependencies. TANGO then obtains sub-clusters with the help of the adjusted dependencies, and characterizes the similarity between sub-clusters by incorporating path-based connectivity. It achieves final clustering by employing graph-cut on sub-clusters, thus avoiding the challenging selection of cluster centers. Moreover, this paper provides theoretical analysis and an efficient method for the calculation of typicality. Experimental results on several synthetic and $16$ real-world datasets demonstrate the effectiveness and superiority of TANGO.
Authors: Saif Anwar, Nathan Griffiths, Abhir Bhalerao, Thomas Popham
Abstract: Existing local Explainable AI (XAI) methods, such as LIME, select a region of the input space in the vicinity of a given input instance, for which they approximate the behaviour of a model using a simpler and more interpretable surrogate model. The size of this region is often controlled by a user-defined locality hyperparameter. In this paper, we demonstrate the difficulties associated with defining a suitable locality size to capture impactful model behaviour, as well as the inadequacy of using a single locality size to explain all predictions. We propose a novel method, MASALA, for generating explanations, which automatically determines the appropriate local region of impactful model behaviour for each individual instance being explained. MASALA approximates the local behaviour used by a complex model to make a prediction by fitting a linear surrogate model to a set of points which experience similar model behaviour. These points are found by clustering the input space into regions of linear behavioural trends exhibited by the model. We compare the fidelity and consistency of explanations generated by our method with existing local XAI methods, namely LIME and CHILLI. Experiments on the PHM08 and MIDAS datasets show that our method produces more faithful and consistent explanations than existing methods, without the need to define any sensitive locality hyperparameters.
Authors: Ali Dadras, Sourasekhar Banerjee, Karthik Prakhya, Alp Yurtsever
Abstract: Federated learning (FL) has gained a lot of attention in recent years for building privacy-preserving collaborative learning systems. However, FL algorithms for constrained machine learning problems are still limited, particularly when the projection step is costly. To this end, we propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW features data privacy, low per-iteration cost, and communication of sparse signals. In the deterministic setting, FedFW achieves an $\varepsilon$-suboptimal solution within $O(\varepsilon^{-2})$ iterations for smooth and convex objectives, and $O(\varepsilon^{-3})$ iterations for smooth but non-convex objectives. Furthermore, we present a stochastic variant of FedFW and show that it finds a solution within $O(\varepsilon^{-3})$ iterations in the convex setting. We demonstrate the empirical performance of FedFW on several machine learning tasks.
Authors: Heeyoung Lee, Hoyoon Byun, Changdae Oh, JinYeong Bak, Kyungwoo Song
Abstract: Accessing machine learning models through remote APIs has been gaining prevalence following the recent trend of scaling up model parameters for increased performance. Even though these models exhibit remarkable ability, detecting out-of-distribution (OOD) samples remains a crucial safety concern for end users as these samples may induce unreliable outputs from the model. In this work, we propose an OOD detection framework, MixDiff, that is applicable even when the model's parameters or its activations are not accessible to the end user. To bypass the access restriction, MixDiff applies an identical input-level perturbation to a given target sample and a similar in-distribution (ID) sample, then compares the relative difference in the model outputs of these two samples. MixDiff is model-agnostic and compatible with existing output-based OOD detection methods. We provide theoretical analysis to illustrate MixDiff's effectiveness in discerning OOD samples that induce overconfident outputs from the model and empirically demonstrate that MixDiff consistently enhances the OOD detection performance on various datasets in vision and text domains.
Authors: Tianyu Zhang, Yuxiang Ren, Chengbin Hou, Hairong Lv, Xuegong Zhang
Abstract: Molecular property prediction is a crucial foundation for drug discovery. In recent years, pre-trained deep learning models have been widely applied to this task. Some approaches that incorporate prior biological domain knowledge into the pre-training framework have achieved impressive results. However, these methods heavily rely on biochemical experts, and retrieving and summarizing vast amounts of domain knowledge literature is both time-consuming and expensive. Large Language Models (LLMs) have demonstrated remarkable performance in understanding and efficiently providing general knowledge. Nevertheless, they occasionally exhibit hallucinations and lack precision in generating domain-specific knowledge. Conversely, Domain-specific Small Models (DSMs) possess rich domain knowledge and can accurately calculate molecular domain-related metrics. However, due to their limited model size and singular functionality, they lack the breadth of knowledge necessary for comprehensive representation learning. To leverage the advantages of both approaches in molecular property prediction, we propose a novel Molecular Graph representation learning framework that integrates Large language models and Domain-specific small models (MolGraph-LarDo). Technically, we design a two-stage prompt strategy where DSMs are introduced to calibrate the knowledge provided by LLMs, enhancing the accuracy of domain-specific information and thus enabling LLMs to generate more precise textual descriptions for molecular samples. Subsequently, we employ a multi-modal alignment method to coordinate various modalities, including molecular graphs and their corresponding descriptive texts, to guide the pre-training of molecular representations. Extensive experiments demonstrate the effectiveness of the proposed method.
Authors: Tong Yang, Yu Huang, Yingbin Liang, Yuejie Chi
Abstract: In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored, particularly whether transformers can be trained to generalize to unseen examples in a prompt, which will require the model to acquire contextual knowledge of the prompt for generalization. This paper investigates the training dynamics of transformers by gradient descent through the lens of non-linear regression tasks. The contextual generalization here can be attained via learning the template function for each task in-context, where all template functions lie in a linear space with $m$ basis functions. We analyze the training dynamics of one-layer multi-head transformers to in-contextly predict unlabeled inputs given partially labeled prompts, where the labels contain Gaussian noise and the number of examples in each prompt are not sufficient to determine the template. Under mild assumptions, we show that the training loss for a one-layer multi-head transformer converges linearly to a global minimum. Moreover, the transformer effectively learns to perform ridge regression over the basis functions. To our knowledge, this study is the first provable demonstration that transformers can learn contextual (i.e., template) information to generalize to both unseen examples and tasks when prompts contain only a small number of query-answer pairs.
Authors: Anke Tang, Li Shen, Yong Luo, Shuai Xie, Han Hu, Lefei Zhang, Bo Du, Dacheng Tao
Abstract: Deep model training on extensive datasets is increasingly becoming cost-prohibitive, prompting the widespread adoption of deep model fusion techniques to leverage knowledge from pre-existing models. From simple weight averaging to more sophisticated methods like AdaMerging, model fusion effectively improves model performance and accelerates the development of new models. However, potential interference between parameters of individual models and the lack of interpretability in the fusion progress remain significant challenges. Existing methods often try to resolve the parameter interference issue by evaluating attributes of parameters, such as their magnitude or sign, or by parameter pruning. In this study, we begin by examining the fine-tuning of linear layers through the lens of subspace analysis and explicitly define parameter interference as an optimization problem to shed light on this subject. Subsequently, we introduce an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction, which allows for the upscaling of source models into an MoE model without extra data or further training. Our approach relies on the observation that fine-tuning mostly keeps the important parts from the pre-training, but it uses less significant or unused areas to adapt to new tasks. Also, the issue of parameter interference, which is intrinsically intractable in the original parameter space, can be managed by expanding the dimensions. We conduct extensive experiments across diverse scenarios, such as image classification and text generalization tasks, using full fine-tuning and LoRA fine-tuning, and we apply our method to large language models (CLIP models, Flan-T5 models, and Mistral-7B models), highlighting the adaptability and scalability of SMILE. Code is available at https://github.com/tanganke/fusion_bench
Authors: Aviv Bick, Kevin Y. Li, Eric P. Xing, J. Zico Kolter, Albert Gu
Abstract: Transformer architectures have become a dominant paradigm for domains like language modeling but suffer in many inference settings due to their quadratic-time self-attention. Recently proposed subquadratic architectures, such as Mamba, have shown promise, but have been pretrained with substantially less computational resources than the strongest Transformer models. In this work, we present a method that is able to distill a pretrained Transformer architecture into alternative architectures such as state space models (SSMs). The key idea to our approach is that we can view both Transformers and SSMs as applying different forms of mixing matrices over the token sequences. We can thus progressively distill the Transformer architecture by matching different degrees of granularity in the SSM: first matching the mixing matrices themselves, then the hidden units at each block, and finally the end-to-end predictions. Our method, called MOHAWK, is able to distill a Mamba-2 variant based on the Phi-1.5 architecture (Phi-Mamba) using only 3B tokens and a hybrid version (Hybrid Phi-Mamba) using 5B tokens. Despite using less than 1% of the training data typically used to train models from scratch, Phi-Mamba boasts substantially stronger performance compared to all past open-source non-Transformer models. MOHAWK allows models like SSMs to leverage computational resources invested in training Transformer-based architectures, highlighting a new avenue for building such models.
Authors: Bhavna Gopal, Huanrui Yang, Jingyang Zhang, Mark Horton, Yiran Chen
Abstract: Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an innovative approach that mitigates adversarial overfitting by introducing parameter efficiency into the adversarial training process, improving both clean accuracy and adversarial robustness. Instead of tuning the entire model, CLAT identifies and fine-tunes robustness-critical layers - those predominantly learning non-robust features - while freezing the remaining model to enhance robustness. It employs dynamic critical layer selection to adapt to changes in layer criticality throughout the fine-tuning process. Empirically, CLAT can be applied on top of existing adversarial training methods, significantly reduces the number of trainable parameters by approximately 95%, and achieves more than a 2% improvement in adversarial robustness compared to baseline methods.
Authors: Ziming Liu, Pingchuan Ma, Yixuan Wang, Wojciech Matusik, Max Tegmark
Abstract: A major challenge of AI + Science lies in their inherent incompatibility: today's AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a framework to seamlessly synergize Kolmogorov-Arnold Networks (KANs) and science. The framework highlights KANs' usage for three aspects of scientific discovery: identifying relevant features, revealing modular structures, and discovering symbolic formulas. The synergy is bidirectional: science to KAN (incorporating scientific knowledge into KANs), and KAN to science (extracting scientific insights from KANs). We highlight major new functionalities in the pykan package: (1) MultKAN: KANs with multiplication nodes. (2) kanpiler: a KAN compiler that compiles symbolic formulas into KANs. (3) tree converter: convert KANs (or any neural networks) to tree graphs. Based on these tools, we demonstrate KANs' capability to discover various types of physical laws, including conserved quantities, Lagrangians, symmetries, and constitutive laws.
Authors: Yifan Chen, Wuchen Li
Abstract: We study the Wasserstein natural gradient in parametric statistical models with continuous sample spaces. Our approach is to pull back the $L^2$-Wasserstein metric tensor in the probability density space to a parameter space, equipping the latter with a positive definite metric tensor, under which it becomes a Riemannian manifold, named the Wasserstein statistical manifold. In general, it is not a totally geodesic sub-manifold of the density space, and therefore its geodesics will differ from the Wasserstein geodesics, except for the well-known Gaussian distribution case, a fact which can also be validated under our framework. We use the sub-manifold geometry to derive a gradient flow and natural gradient descent method in the parameter space. When parametrized densities lie in $\bR$, the induced metric tensor establishes an explicit formula. In optimization problems, we observe that the natural gradient descent outperforms the standard gradient descent when the Wasserstein distance is the objective function. In such a case, we prove that the resulting algorithm behaves similarly to the Newton method in the asymptotic regime. The proof calculates the exact Hessian formula for the Wasserstein distance, which further motivates another preconditioner for the optimization process. To the end, we present examples to illustrate the effectiveness of the natural gradient in several parametric statistical models, including the Gaussian measure, Gaussian mixture, Gamma distribution, and Laplace distribution.
Authors: Zhili Cheng, Zhitong Wang, Jinyi Hu, Shengding Hu, An Liu, Yuge Tu, Pengkai Li, Lei Shi, Zhiyuan Liu, Maosong Sun
Abstract: Despite advancements in Large Language Models (LLMs) and Large Multimodal Models (LMMs), their integration into language-grounded, human-like embodied agents remains incomplete, hindering complex real-life task performance in physical environments. Existing integrations often feature limited open sourcing, challenging collective progress in this field. We introduce LEGENT, an open, scalable platform for developing embodied agents using LLMs and LMMs. LEGENT offers a dual approach: a rich, interactive 3D environment with communicable and actionable agents, paired with a user-friendly interface, and a sophisticated data generation pipeline utilizing advanced algorithms to exploit supervision from simulated worlds at scale. In our experiments, an embryonic vision-language-action model trained on LEGENT-generated data surpasses GPT-4V in embodied tasks, showcasing promising generalization capabilities.
Authors: Robert J. Moss
Abstract: Eliciting harmful behavior from large language models (LLMs) is an important task to ensure the proper alignment and safety of the models. Often when training LLMs, ethical guidelines are followed yet alignment failures may still be uncovered through red teaming adversarial attacks. This work frames the red-teaming problem as a Markov decision process (MDP) and uses Monte Carlo tree search to find harmful behaviors of black-box, closed-source LLMs. We optimize token-level prompt suffixes towards targeted harmful behaviors on white-box LLMs and include a naturalistic loss term, log-perplexity, to generate more natural language attacks for better interpretability. The proposed algorithm, Kov, trains on white-box LLMs to optimize the adversarial attacks and periodically evaluates responses from the black-box LLM to guide the search towards more harmful black-box behaviors. In our preliminary study, results indicate that we can jailbreak black-box models, such as GPT-3.5, in only 10 queries, yet fail on GPT-4$-$which may indicate that newer models are more robust to token-level attacks. All work to reproduce these results is open sourced (https://github.com/sisl/Kov.jl).
Authors: Pablo Cecilio, Ant\^onio Perreira, Juliana Santos Rosa Viegas, Washington Cunha, Felipe Viegas, Elisa Tuler, Fabiana Testa Moura de Carvalho Vicentini, Leonardo Rocha
Abstract: Pharmaceutical patents play an important role by protecting the innovation from copies but also drive researchers to innovate, create new products, and promote disruptive innovations focusing on collective health. The study of patent management usually refers to an exhaustive manual search. This happens, because patent documents are complex with a lot of details regarding the claims and methodology/results explanation of the invention. To mitigate the manual search, we proposed PATopics, a framework specially designed to extract relevant information for Pharmaceutical patents. PATopics is composed of four building blocks that extract textual information from the patents, build relevant topics that are capable of summarizing the patents, correlate these topics with useful patent characteristics and then, summarize the information in a friendly web interface to final users. The general contributions of PATopics are its ability to centralize patents and to manage patents into groups based on their similarities. We extensively analyzed the framework using 4,832 pharmaceutical patents concerning 809 molecules patented by 478 companies. In our analysis, we evaluate the use of the framework considering the demands of three user profiles -- researchers, chemists, and companies. We also designed four real-world use cases to evaluate the framework's applicability. Our analysis showed how practical and helpful PATopics are in the pharmaceutical scenario.
Authors: Andy K. Zhang, Neil Perry, Riya Dulepet, Eliot Jones, Justin W. Lin, Joey Ji, Celeste Menders, Gashon Hussein, Samantha Liu, Donovan Jasper, Pura Peetathawatchai, Ari Glenn, Vikram Sivashankar, Daniel Zamoshchin, Leo Glikbarg, Derek Askaryar, Mike Yang, Teddy Zhang, Rishi Alluri, Nathan Tran, Rinnara Sangpisit, Polycarpos Yiorkadjis, Kenny Osele, Gautham Raghupathi, Dan Boneh, Daniel E. Ho, Percy Liang
Abstract: Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have the potential to cause real-world impact. Policymakers, model providers, and other researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such agents to help mitigate cyberrisk and investigate opportunities for penetration testing. Toward that end, we introduce Cybench, a framework for specifying cybersecurity tasks and evaluating agents on those tasks. We include 40 professional-level Capture the Flag (CTF) tasks from 4 distinct CTF competitions, chosen to be recent, meaningful, and spanning a wide range of difficulties. Each task includes its own description, starter files, and is initialized in an environment where an agent can execute bash commands and observe outputs. Since many tasks are beyond the capabilities of existing LM agents, we introduce subtasks, which break down a task into intermediary steps for more gradated evaluation; we add subtasks for 17 of the 40 tasks. To evaluate agent capabilities, we construct a cybersecurity agent and evaluate 7 models: GPT-4o, Claude 3 Opus, Claude 3.5 Sonnet, Mixtral 8x22b Instruct, Gemini 1.5 Pro, Llama 3 70B Chat, and Llama 3.1 405B Instruct. Without guidance, we find that agents are able to solve only the easiest complete tasks that took human teams up to 11 minutes to solve, with Claude 3.5 Sonnet and GPT-4o having the highest success rates. Finally, subtasks provide more signal for measuring performance compared to unguided runs, with models achieving a 3.2\% higher success rate on complete tasks with subtask-guidance than without subtask-guidance. All code and data are publicly available at https://cybench.github.io
Authors: Zhiwei Li, Guodong Long, Tianyi Zhou, Jing Jiang, Chengqi Zhang
Abstract: Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy in a federated setting. Existing FedCF methods typically combine distributed Collaborative Filtering (CF) algorithms with privacy-preserving mechanisms, and then preserve personalized information into a user embedding vector. However, the user embedding is usually insufficient to preserve the rich information of the fine-grained personalization across heterogeneous clients. This paper proposes a novel personalized FedCF method by preserving users' personalized information into a latent variable and a neural model simultaneously. Specifically, we decompose the modeling of user knowledge into two encoders, each designed to capture shared knowledge and personalized knowledge separately. A personalized gating network is then applied to balance personalization and generalization between the global and local encoders. Moreover, to effectively train the proposed framework, we model the CF problem as a specialized Variational AutoEncoder (VAE) task by integrating user interaction vector reconstruction with missing value prediction. The decoder is trained to reconstruct the implicit feedback from items the user has interacted with, while also predicting items the user might be interested in but has not yet interacted with. Experimental results on benchmark datasets demonstrate that the proposed method outperforms other baseline methods, showcasing superior performance.
Authors: Cyril Shih-Huan Hsu, Danny De Vleeschauwer, Chrysa Papagianni
Abstract: When a network slice spans multiple domains, each domain must uphold the End-to-End (E2E) Service Level Agreement (SLA). This requires decomposing the End-to-End (E2E) Service Level Agreement (SLA) into partial SLAs for each domain. In a two-level network slicing management system with an E2E orchestrator and local controllers, we propose an online learning-decomposition framework that dynamically updates risk models using recent feedback. This approach utilizes online gradient descent and FIFO memory buffers to enhance stability and robustness. Our empirical study shows the proposed framework outperforms state-of-the-art static methods, offering more accurate and resilient SLA decomposition under varying conditions and sparse data.
Authors: Debashis Gupta, Aditi Golder, Luis Fernendez, Miles Silman, Greg Lersen, Fan Yang, Bob Plemmons, Sarra Alqahtani, Paul Victor Pauca
Abstract: Artisanal and Small-Scale Gold Mining (ASGM) is a low-cost yet highly destructive mining practice, leading to environmental disasters across the world's tropical watersheds. The topic of ASGM spans multiple domains of research and information, including natural and social systems, and knowledge is often atomized across a diversity of media and documents. We therefore introduce a knowledge graph (ASGM-KG) that consolidates and provides crucial information about ASGM practices and their environmental effects. The current version of ASGM-KG consists of 1,899 triples extracted using a large language model (LLM) from documents and reports published by both non-governmental and governmental organizations. These documents were carefully selected by a group of tropical ecologists with expertise in ASGM. This knowledge graph was validated using two methods. First, a small team of ASGM experts reviewed and labeled triples as factual or non-factual. Second, we devised and applied an automated factual reduction framework that relies on a search engine and an LLM for labeling triples. Our framework performs as well as five baselines on a publicly available knowledge graph and achieves over 90 accuracy on our ASGM-KG validated by domain experts. ASGM-KG demonstrates an advancement in knowledge aggregation and representation for complex, interdisciplinary environmental crises such as ASGM.
Authors: Vinit Hegiste, Snehal Walunj, Jibinraj Antony, Tatjana Legler, Martin Ruskowski
Abstract: Federated Learning (FL) has garnered significant attention in manufacturing for its robust model development and privacy-preserving capabilities. This paper contributes to research focused on the robustness of FL models in object detection, hereby presenting a comparative study with conventional techniques using a hybrid dataset for small object detection. Our findings demonstrate the superior performance of FL over centralized training models and different deep learning techniques when tested on test data recorded in a different environment with a variety of object viewpoints, lighting conditions, cluttered backgrounds, etc. These results highlight the potential of FL in achieving robust global models that perform efficiently even in unseen environments. The study provides valuable insights for deploying resilient object detection models in manufacturing environments.
Authors: Jungeum Kim, Sean O'Hagan, Veronika Rockova
Abstract: This work is concerned with conformal prediction in contemporary applications (including generative AI) where a black-box model has been trained on data that are not accessible to the user. Mirroring split-conformal inference, we design a wrapper around a black-box algorithm which calibrates conformity scores. This calibration is local and proceeds in two stages by first adaptively partitioning the predictor space into groups and then calibrating sectionally group by group. Adaptive partitioning (self-grouping) is achieved by fitting a robust regression tree to the conformity scores on the calibration set. This new tree variant is designed in such a way that adding a single new observation does not change the tree fit with overwhelmingly large probability. This add-one-in robustness property allows us to conclude a finite sample group-conditional coverage guarantee, a refinement of the marginal guarantee. In addition, unlike traditional split-conformal inference, adaptive splitting and within-group calibration yields adaptive bands which can stretch and shrink locally. We demonstrate benefits of local tightening on several simulated as well as real examples using non-parametric regression. Finally, we consider two contemporary classification applications for obtaining uncertainty quantification around GPT-4o predictions. We conformalize skin disease diagnoses based on self-reported symptoms as well as predicted states of U.S. legislators based on summaries of their ideology. We demonstrate substantial local tightening of the uncertainty sets while attaining similar marginal coverage.
Authors: Yan Sun, Pratik Chaudhari, Ian J. Barnett, Edgar Dobriban
Abstract: Recent advances in machine learning have significantly improved prediction accuracy in various applications. However, ensuring the calibration of probabilistic predictions remains a significant challenge. Despite efforts to enhance model calibration, the rigorous statistical evaluation of model calibration remains less explored. In this work, we develop confidence intervals the $\ell_2$ Expected Calibration Error (ECE). We consider top-1-to-$k$ calibration, which includes both the popular notion of confidence calibration as well as full calibration. For a debiased estimator of the ECE, we show asymptotic normality, but with different convergence rates and asymptotic variances for calibrated and miscalibrated models. We develop methods to construct asymptotically valid confidence intervals for the ECE, accounting for this behavior as well as non-negativity. Our theoretical findings are supported through extensive experiments, showing that our methods produce valid confidence intervals with shorter lengths compared to those obtained by resampling-based methods.
Authors: Unique Subedi, Ambuj Tewari
Abstract: We investigate the problem of learning operators between function spaces, focusing on the linear layer of the Fourier Neural Operator. First, we identify three main errors that occur during the learning process: statistical error due to finite sample size, truncation error from finite rank approximation of the operator, and discretization error from handling functional data on a finite grid of domain points. Finally, we analyze a Discrete Fourier Transform (DFT) based least squares estimator, establishing both upper and lower bounds on the aforementioned errors.
Authors: Honggen Zhang, Xiangrui Gao, June Zhang, Lipeng Lai
Abstract: Messenger RNA (mRNA)-based vaccines are accelerating the discovery of new drugs and revolutionizing the pharmaceutical industry. However, selecting particular mRNA sequences for vaccines and therapeutics from extensive mRNA libraries is costly. Effective mRNA therapeutics require carefully designed sequences with optimized expression levels and stability. This paper proposes a novel contextual language model (LM)-based embedding method: mRNA2vec. In contrast to existing mRNA embedding approaches, our method is based on the self-supervised teacher-student learning framework of data2vec. We jointly use the 5' untranslated region (UTR) and coding sequence (CDS) region as the input sequences. We adapt our LM-based approach specifically to mRNA by 1) considering the importance of location on the mRNA sequence with probabilistic masking, 2) using Minimum Free Energy (MFE) prediction and Secondary Structure (SS) classification as additional pretext tasks. mRNA2vec demonstrates significant improvements in translation efficiency (TE) and expression level (EL) prediction tasks in UTR compared to SOTA methods such as UTR-LM. It also gives a competitive performance in mRNA stability and protein production level tasks in CDS such as CodonBERT.
Authors: Zhiyi Shi, Junsik Kim, Wanhua Li, Yicong Li, Hanspeter Pfister
Abstract: Multi-modal pre-trained models efficiently extract and fuse features from different modalities with low memory requirements for fine-tuning. Despite this efficiency, their application in disease diagnosis is under-explored. A significant challenge is the frequent occurrence of missing modalities, which impairs performance. Additionally, fine-tuning the entire pre-trained model demands substantial computational resources. To address these issues, we introduce Modality-aware Low-Rank Adaptation (MoRA), a computationally efficient method. MoRA projects each input to a low intrinsic dimension but uses different modality-aware up-projections for modality-specific adaptation in cases of missing modalities. Practically, MoRA integrates into the first block of the model, significantly improving performance when a modality is missing. It requires minimal computational resources, with less than 1.6% of the trainable parameters needed compared to training the entire model. Experimental results show that MoRA outperforms existing techniques in disease diagnosis, demonstrating superior performance, robustness, and training efficiency.
Authors: Shashank Kotyan, Pin-Yu Chen, Danilo Vasconcellos Vargas
Abstract: Most evaluations of vision models use indirect methods to assess latent space quality. These methods often involve adding extra layers to project the latent space into a new one. This projection makes it difficult to analyze and compare the original latent space. This article uses the k* Distribution, a local neighborhood analysis method, to examine the learned latent space at the level of individual concepts, which can be extended to examine the entire latent space. We introduce skewness-based true and approximate metrics for interpreting individual concepts to assess the overall quality of vision models' latent space. Our findings indicate that current vision models frequently fracture the distributions of individual concepts within the latent space. Nevertheless, as these models improve in generalization across multiple datasets, the degree of fracturing diminishes. A similar trend is observed in robust vision models, where increased robustness correlates with reduced fracturing. Ultimately, this approach enables a direct interpretation and comparison of the latent spaces of different vision models and reveals a relationship between a model's generalizability and robustness. Results show that as a model becomes more general and robust, it tends to learn features that result in better clustering of concepts. Project Website is available online at https://shashankkotyan.github.io/k-Distribution/
Authors: Julio-Omar Palacio-Ni\~no, Fernando Berzal
Abstract: The analysis and detection of communities in network structures are becoming increasingly relevant for understanding social behavior. One of the principal challenges in this field is the complexity of existing algorithms. The Girvan-Newman algorithm, which uses the betweenness metric as a measure of node similarity, is one of the most representative algorithms in this area. This study employs the same method to evaluate the relevance of using local similarity metrics for community detection. A series of local metrics were tested on a set of networks constructed using the Girvan-Newman basic algorithm. The efficacy of these metrics was evaluated by applying the base algorithm to several real networks with varying community sizes, using modularity and NMI. The results indicate that approaches based on local similarity metrics have significant potential for community detection.
Authors: Kenneth J. Sible, David Chiang
Abstract: In machine translation, rare words continue to be a problem for the dominant encoder-decoder architecture, especially in low-resource and out-of-domain translation settings. Human translators solve this problem with monolingual or bilingual dictionaries. In this paper, we propose appending definitions from a bilingual dictionary to source sentences and using attention masking to link together rare words with their definitions. We find that including definitions for rare words improves performance by up to 1.0 BLEU and 1.6 MacroF1.
Authors: N P Sharvari, Dibakar Das, Jyotsna Bapat, Debabrata Das
Abstract: Designing effective Unmanned Aerial Vehicle(UAV)-assisted routing protocols is challenging due to changing topology, limited battery capacity, and the dynamic nature of communication environments. Current protocols prioritize optimizing individual network parameters, overlooking the necessity for a nuanced approach in scenarios with intermittent connectivity, fluctuating signal strength, and varying network densities, ultimately failing to address aerial network requirements comprehensively. This paper proposes a novel, Improved Q-learning-based Multi-hop Routing (IQMR) algorithm for optimal UAV-assisted communication systems. Using Q(\lambda) learning for routing decisions, IQMR substantially enhances energy efficiency and network data throughput. IQMR improves system resilience by prioritizing reliable connectivity and inter-UAV collision avoidance while integrating real-time network status information, all in the absence of predefined UAV path planning, thus ensuring dynamic adaptability to evolving network conditions. The results validate IQMR's adaptability to changing system conditions and superiority over the current techniques. IQMR showcases 36.35\% and 32.05\% improvements in energy efficiency and data throughput over the existing methods.
Authors: Andr\'e Ramos, Davi Vallad\~ao, Alexandre Street
Abstract: Time series analysis by state-space models is widely used in forecasting and extracting unobservable components like level, slope, and seasonality, along with explanatory variables. However, their reliance on traditional Kalman filtering frequently hampers their effectiveness, primarily due to Gaussian assumptions and the absence of efficient subset selection methods to accommodate the multitude of potential explanatory variables in today's big-data applications. Our research introduces the State Space Learning (SSL), a novel framework and paradigm that leverages the capabilities of statistical learning to construct a comprehensive framework for time series modeling and forecasting. By utilizing a regularized high-dimensional regression framework, our approach jointly extracts typical time series unobservable components, detects and addresses outliers, and selects the influence of exogenous variables within a high-dimensional space in polynomial time and global optimality guarantees. Through a controlled numerical experiment, we demonstrate the superiority of our approach in terms of subset selection of explanatory variables accuracy compared to relevant benchmarks. We also present an intuitive forecasting scheme and showcase superior performances relative to traditional time series models using a dataset of 48,000 monthly time series from the M4 competition. We extend the applicability of our approach to reformulate any linear state space formulation featuring time-varying coefficients into high-dimensional regularized regressions, expanding the impact of our research to other engineering applications beyond time series analysis. Finally, our proposed methodology is implemented within the Julia open-source package, ``StateSpaceLearning.jl".
Authors: Tianhao Hu, Bangti Jin, Zhi Zhou
Abstract: The inverse problem of recovering point sources represents an important class of applied inverse problems. However, there is still a lack of neural network-based methods for point source identification, mainly due to the inherent solution singularity. In this work, we develop a novel algorithm to identify point sources, utilizing a neural network combined with a singularity enrichment technique. We employ the fundamental solution and neural networks to represent the singular and regular parts, respectively, and then minimize an empirical loss involving the intensities and locations of the unknown point sources, as well as the parameters of the neural network. Moreover, by combining the conditional stability argument of the inverse problem with the generalization error of the empirical loss, we conduct a rigorous error analysis of the algorithm. We demonstrate the effectiveness of the method with several challenging experiments.
Authors: Aniket Didolkar, Andrii Zadaianchuk, Anirudh Goyal, Mike Mozer, Yoshua Bengio, Georg Martius, Maximilian Seitzer
Abstract: The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to real-world scenes by utilizing pre-trained self-supervised features. However, so far, object-centric methods have mostly been applied in-distribution, with models trained and evaluated on the same dataset. This is in contrast to the wider trend in machine learning towards general-purpose models directly applicable to unseen data and tasks. Thus, in this work, we study current object-centric methods through the lens of zero-shot generalization by introducing a benchmark comprising eight different synthetic and real-world datasets. We analyze the factors influencing zero-shot performance and find that training on diverse real-world images improves transferability to unseen scenarios. Furthermore, inspired by the success of task-specific fine-tuning in foundation models, we introduce a novel fine-tuning strategy to adapt pre-trained vision encoders for the task of object discovery. We find that the proposed approach results in state-of-the-art performance for unsupervised object discovery, exhibiting strong zero-shot transfer to unseen datasets.
Authors: Jan Malte Lichtenberg, Giuseppe Di Benedetto, Matteo Ruffini
Abstract: An increasing number of media streaming services have expanded their offerings to include entities of multiple content types. For instance, audio streaming services that started by offering music only, now also offer podcasts, merchandise items, and videos. Ranking items across different content types into a single slate poses a significant challenge for traditional learning-to-rank (LTR) algorithms due to differing user engagement patterns for different content types. We explore a simple method for cross-content-type ranking, called multinomial blending (MB), which can be used in conjunction with most existing LTR algorithms. We compare MB to existing baselines not only in terms of ranking quality but also from other industry-relevant perspectives such as interpretability, ease-of-use, and stability in dynamic environments with changing user behavior and ranking model retraining. Finally, we report the results of an A/B test from an Amazon Music ranking use-case.
Authors: Jiawei Lian, Jianhong Pan, Lefan Wang, Yi Wang, Lap-Pui Chau, Shaohui Mei
Abstract: Physical attacks against object detection have gained increasing attention due to their significant practical implications. However, conducting physical experiments is extremely time-consuming and labor-intensive. Moreover, physical dynamics and cross-domain transformation are challenging to strictly regulate in the real world, leading to unaligned evaluation and comparison, severely hindering the development of physically robust models. To accommodate these challenges, we explore utilizing realistic simulation to thoroughly and rigorously benchmark physical attacks with fairness under controlled physical dynamics and cross-domain transformation. This resolves the problem of capturing identical adversarial images that cannot be achieved in the real world. Our benchmark includes 20 physical attack methods, 48 object detectors, comprehensive physical dynamics, and evaluation metrics. We also provide end-to-end pipelines for dataset generation, detection, evaluation, and further analysis. In addition, we perform 8064 groups of evaluation based on our benchmark, which includes both overall evaluation and further detailed ablation studies for controlled physical dynamics. Through these experiments, we provide in-depth analyses of physical attack performance and physical adversarial robustness, draw valuable observations, and discuss potential directions for future research. Codebase: https://github.com/JiaweiLian/Benchmarking_Physical_Attack
URLs: https://github.com/JiaweiLian/Benchmarking_Physical_Attack
Authors: Xueying Gu, Qiong Wu, Pingyi Fan, Qiang Fan, Nan Cheng, Wen Chen, Khaled B. Letaief
Abstract: In the Internet of Vehicles (IoV), Federated Learning (FL) provides a privacy-preserving solution by aggregating local models without sharing data. Traditional supervised learning requires image data with labels, but data labeling involves significant manual effort. Federated Self-Supervised Learning (FSSL) utilizes Self-Supervised Learning (SSL) for local training in FL, eliminating the need for labels while protecting privacy. Compared to other SSL methods, Momentum Contrast (MoCo) reduces the demand for computing resources and storage space by creating a dictionary. However, using MoCo in FSSL requires uploading the local dictionary from vehicles to Base Station (BS), which poses a risk of privacy leakage. Simplified Contrast (SimCo) addresses the privacy leakage issue in MoCo-based FSSL by using dual temperature instead of a dictionary to control sample distribution. Additionally, considering the negative impact of motion blur on model aggregation, and based on SimCo, we propose a motion blur-resistant FSSL method, referred to as BFSSL. Furthermore, we address energy consumption and delay in the BFSSL process by proposing a Deep Reinforcement Learning (DRL)-based resource allocation scheme, called DRL-BFSSL. In this scheme, BS allocates the Central Processing Unit (CPU) frequency and transmission power of vehicles to minimize energy consumption and latency, while aggregating received models based on the motion blur level. Simulation results validate the effectiveness of our proposed aggregation and resource allocation methods.
Authors: Mario Doumet, Marius Stan, Mathew Hall, Vaughn Betz
Abstract: Convolutional Neural Networks (CNNs) combine large amounts of parallelizable computation with frequent memory access. Field Programmable Gate Arrays (FPGAs) can achieve low latency and high throughput CNN inference by implementing dataflow accelerators that pipeline layer-specific hardware to implement an entire network. By implementing a different processing element for each CNN layer, these layer-pipelined accelerators can achieve high compute density, but having all layers processing in parallel requires high memory bandwidth. Traditionally this has been satisfied by storing all weights on chip, but this is infeasible for the largest CNNs, which are often those most in need of acceleration. In this work we augment a state-of-the-art dataflow accelerator (HPIPE) to leverage both High-Bandwidth Memory (HBM) and on-chip storage, enabling high performance layer-pipelined dataflow acceleration of large CNNs. Based on profiling results of HBM's latency and throughput against expected address patterns, we develop an algorithm to choose which weight buffers should be moved off chip and how deep the on-chip FIFOs to HBM should be to minimize compute unit stalling. We integrate the new hardware generation within the HPIPE domain-specific CNN compiler and demonstrate good bandwidth efficiency against theoretical limits. Compared to the best prior work we obtain speed-ups of at least 19.4x, 5.1x and 10.5x on ResNet-18, ResNet-50 and VGG-16 respectively.
Authors: Cho Yang
Abstract: CycleGAN was trained on SynthRAD Grand Challenge Dataset using the single-epoch modification (SEM) method proposed in this paper which is referred to as (CycleGAN-single) compared to the usual method of training CycleGAN on around 200 epochs (CycleGAN-multi). Model performance were evaluated qualitatively and quantitatively with quantitative performance metrics like PSNR, SSIM, MAE and MSE. The consideration of both quantitative and qualitative performance when evaluating a model is unique to certain image-translation tasks like medical imaging as detailed in this paper. Also, this paper shows that good quantitative performance does not always imply good qualitative performance and the converse is also not always True (i.e. good qualitative performance does not always imply good quantitative performance). This paper also proposes FQGA (Fast Paired Image-to-Image Translation Quarter-Generator Adversary) Model which has 1/4 the number of parameters compared to CycleGAN (when comparing their Generator Models). FQGA outperforms CycleGAN qualitatively and quantitatively even only after training on 20 epochs. Finally, using SEM method on FQGA allowed it to again outperform CycleGAN both quantitatively and qualitatively. These performance gains with fewer model parameters and time savings from running fewer epochs may also be applicable to other image-to-image translation tasks in Machine Learning apart from the Medical image-translation task discussed in this paper between Cone Beam Computed Tomography (CBCT) and Computed Tomography (CT) images.
Authors: Alex Sanchez-Stern, Abhishek Varghese, Zhanna Kaufman, Dylan Zhang, Talia Ringer, Yuriy Brun
Abstract: Formal verification is a promising method for producing reliable software, but the difficulty of manually writing verification proofs severely limits its utility in practice. Recent methods have automated some proof synthesis by guiding a search through the proof space using a theorem prover. Unfortunately, the theorem prover provides only the crudest estimate of progress, resulting in effectively undirected search. To address this problem, we create QEDCartographer, an automated proof-synthesis tool that combines supervised and reinforcement learning to more effectively explore the proof space. QEDCartographer incorporates the proofs' branching structure, enabling reward-free search and overcoming the sparse reward problem inherent to formal verification. We evaluate QEDCartographer using the CoqGym benchmark of 68.5K theorems from 124 open-source Coq projects. QEDCartographer fully automatically proves 21.4% of the test-set theorems. Previous search-based proof-synthesis tools Tok, Tac, ASTactic, Passport, and Proverbot9001, which rely only on supervised learning, prove 9.6%, 9.8%, 10.9%, 12.5%, and 19.8%, respectively. Diva, which combines 62 tools, proves 19.2%. Comparing to the most effective prior tool, Proverbot9001, QEDCartographer produces 26% shorter proofs 27% faster, on average over the theorems both tools prove. Together, QEDCartographer and non-learning-based CoqHammer prove 31.8% of the theorems, while CoqHammer alone proves 26.6%. Our work demonstrates that reinforcement learning is a fruitful research direction for improving proof-synthesis tools' search mechanisms.
Authors: Junwei You, Haotian Shi, Zhuoyu Jiang, Zilin Huang, Rui Gan, Keshu Wu, Xi Cheng, Xiaopeng Li, Bin Ran
Abstract: Advancements in autonomous driving have increasingly focused on end-to-end (E2E) systems that manage the full spectrum of driving tasks, from environmental perception to vehicle navigation and control. This paper introduces V2X-VLM, an innovative E2E vehicle-infrastructure cooperative autonomous driving (VICAD) framework with large vision-language models (VLMs). V2X-VLM is designed to enhance situational awareness, decision-making, and ultimate trajectory planning by integrating data from vehicle-mounted cameras, infrastructure sensors, and textual information. The strength of the comprehensive multimodel data fusion of the VLM enables precise and safe E2E trajectory planning in complex and dynamic driving scenarios. Validation on the DAIR-V2X dataset demonstrates that V2X-VLM outperforms existing state-of-the-art methods in cooperative autonomous driving.
Authors: Xiaojie Lin, Baihe Ma, Xu Wang, Guangsheng Yu, Ying He, Ren Ping Liu, Wei Ni
Abstract: As the primary standard protocol for modern cars, the Controller Area Network (CAN) is a critical research target for automotive cybersecurity threats and autonomous applications. As the decoding specification of CAN is a proprietary black-box maintained by Original Equipment Manufacturers (OEMs), conducting related research and industry developments can be challenging without a comprehensive understanding of the meaning of CAN messages. In this paper, we propose a fully automated reverse-engineering system, named ByCAN, to reverse engineer CAN messages. ByCAN outperforms existing research by introducing byte-level clusters and integrating multiple features at both byte and bit levels. ByCAN employs the clustering and template matching algorithms to automatically decode the specifications of CAN frames without the need for prior knowledge. Experimental results demonstrate that ByCAN achieves high accuracy in slicing and labeling performance, i.e., the identification of CAN signal boundaries and labels. In the experiments, ByCAN achieves slicing accuracy of 80.21%, slicing coverage of 95.21%, and labeling accuracy of 68.72% for general labels when analyzing the real-world CAN frames.
Authors: Anshuman Sinha, Camille Migozzi, Aubin Rey, Chao Zhang
Abstract: Research on multi-modal contrastive learning strategies for audio and text has rapidly gained interest. Contrastively trained Audio-Language Models (ALMs), such as CLAP, which establish a unified representation across audio and language modalities, have enhanced the efficacy in various subsequent tasks by providing good text aligned audio encoders and vice versa. These improvements are evident in areas like zero-shot audio classification and audio retrieval, among others. However, the ability of these models to understand natural language and temporal relations is still a largely unexplored and open field for research. In this paper, we propose to equip the multi-modal ALMs with temporal understanding without loosing their inherent prior capabilities of audio-language tasks with a temporal instillation method TeminAL. We implement a two-stage training scheme TeminAL A $\&$ B, where the model first learns to differentiate between multiple sounds in TeminAL A, followed by a phase that instills a sense of time, thereby enhancing its temporal understanding in TeminAL B. This approach results in an average performance gain of $5.28\%$ in temporal understanding on the ESC-50 dataset, while the model remains competitive in zero-shot retrieval and classification tasks on the AudioCap/Clotho datasets. We also note the lack of proper evaluation techniques for contrastive ALMs and propose a strategy for evaluating ALMs in zero-shot settings. The general-purpose zero-shot model evaluation strategy ZSTE, is used to evaluate various prior models. ZSTE demonstrates a general strategy to evaluate all ZS contrastive models. The model trained with TeminAL successfully outperforms current models on most downstream tasks.
Authors: Qinyang Li, Nicholas Miklaucic, Jianjun Hu
Abstract: The accurate prediction of material properties is crucial in a wide range of scientific and engineering disciplines. Machine learning (ML) has advanced the state of the art in this field, enabling scientists to discover novel materials and design materials with specific desired properties. However, one major challenge that persists in material property prediction is the generalization of models to out-of-distribution (OOD) samples,i.e., samples that differ significantly from those encountered during training. In this paper, we explore the application of advancements in OOD learning approaches to enhance the robustness and reliability of material property prediction models. We propose and apply the Crystal Adversarial Learning (CAL) algorithm for OOD materials property prediction,which generates synthetic data during training to bias the training towards those samples with high prediction uncertainty. We further propose an adversarial learning based targeting finetuning approach to make the model adapted to a particular OOD dataset, as an alternative to traditional fine-tuning. Our experiments demonstrate the success of our CAL algorithm with its high effectiveness in ML with limited samples which commonly occurs in materials science. Our work represents a promising direction toward better OOD learning and materials property prediction.
Authors: Massimiliano Todisco, Michele Panariello, Xin Wang, H\'ector Delgado, Kong Aik Lee, Nicholas Evans
Abstract: We present Malacopula, a neural-based generalised Hammerstein model designed to introduce adversarial perturbations to spoofed speech utterances so that they better deceive automatic speaker verification (ASV) systems. Using non-linear processes to modify speech utterances, Malacopula enhances the effectiveness of spoofing attacks. The model comprises parallel branches of polynomial functions followed by linear time-invariant filters. The adversarial optimisation procedure acts to minimise the cosine distance between speaker embeddings extracted from spoofed and bona fide utterances. Experiments, performed using three recent ASV systems and the ASVspoof 2019 dataset, show that Malacopula increases vulnerabilities by a substantial margin. However, speech quality is reduced and attacks can be detected effectively under controlled conditions. The findings emphasise the need to identify new vulnerabilities and design defences to protect ASV systems from adversarial attacks in the wild.
Authors: Jodi Dianetti, Giorgio Ferrari, Renyuan Xu
Abstract: This paper explores continuous-time and state-space optimal stopping problems from a reinforcement learning perspective. We begin by formulating the stopping problem using randomized stopping times, where the decision maker's control is represented by the probability of stopping within a given time--specifically, a bounded, non-decreasing, c\`adl\`ag control process. To encourage exploration and facilitate learning, we introduce a regularized version of the problem by penalizing it with the cumulative residual entropy of the randomized stopping time. The regularized problem takes the form of an (n+1)-dimensional degenerate singular stochastic control with finite-fuel. We address this through the dynamic programming principle, which enables us to identify the unique optimal exploratory strategy. For the specific case of a real option problem, we derive a semi-explicit solution to the regularized problem, allowing us to assess the impact of entropy regularization and analyze the vanishing entropy limit. Finally, we propose a reinforcement learning algorithm based on policy iteration. We show both policy improvement and policy convergence results for our proposed algorithm.
Authors: Shumpei Wakabayashi, Kento Kawaharazuka, Kei Okada, Masayuki Inaba
Abstract: Robots are expected to manipulate objects in a safe and dexterous way. For example, washing dishes is a dexterous operation that involves scrubbing the dishes with a sponge and rinsing them with water. It is necessary to learn it safely without splashing water and without dropping the dishes. In this study, we propose a safe and dexterous manipulation system. %that can scrub and rinse dirty dishes. The robot learns a dynamics model of the object by estimating the state of the object and the robot itself, the control input, and the amount of human assistance required (assistance rate) after the human corrects the initial trajectory of the robot's hands by interruptive direct teaching. By backpropagating the error between the estimated and the reference value %at the next time using the acquired dynamics model, the robot can generate a control input that approaches the reference value, for example, so that human assistance is not required and the dish does not move excessively. This allows for adaptive rinsing and scrubbing of dishes with unknown shapes and properties. As a result, it is possible to generate safe actions that require less human assistance.
Authors: Taharim Rahman Anon, Jakaria Islam Emon
Abstract: As artificial intelligence progresses, the task of distinguishing between real and AI-generated images is increasingly complicated by sophisticated generative models. This paper presents a novel detection framework adept at robustly identifying images produced by cutting-edge generative AI models, such as DALL-E 3, MidJourney, and Stable Diffusion 3. We introduce a comprehensive dataset, tailored to include images from these advanced generators, which serves as the foundation for extensive evaluation. we propose a classification system that integrates semantic image embeddings with a traditional Multilayer Perceptron (MLP). This baseline system is designed to effectively differentiate between real and AI-generated images under various challenging conditions. Enhancing this approach, we introduce a hybrid architecture that combines Kolmogorov-Arnold Networks (KAN) with the MLP. This hybrid model leverages the adaptive, high-resolution feature transformation capabilities of KAN, enabling our system to capture and analyze complex patterns in AI-generated images that are typically overlooked by conventional models. In out-of-distribution testing, our proposed model consistently outperformed the standard MLP across three out of distribution test datasets, demonstrating superior performance and robustness in classifying real images from AI-generated images with impressive F1 scores.
Authors: Zhiwei Shan, Xinping Yi, Le Liang, Chung-Shou Liao, Shi Jin
Abstract: Device-to-device (D2D) spectrum sharing in wireless communications is a challenging non-convex combinatorial optimization problem, involving entangled link scheduling and power control in a large-scale network. The state-of-the-art methods, either from a model-based or a data-driven perspective, exhibit certain limitations such as the critical need for channel state information (CSI) and/or a large number of (solved) instances (e.g., network layouts) as training samples. To advance this line of research, we propose a novel hybrid model/datadriven spectrum sharing mechanism with graph reinforcement learning for link scheduling (GRLinQ), injecting information theoretical insights into machine learning models, in such a way that link scheduling and power control can be solved in an intelligent yet explainable manner. Through an extensive set of experiments, GRLinQ demonstrates superior performance to the existing model-based and data-driven link scheduling and/or power control methods, with a relaxed requirement for CSI, a substantially reduced number of unsolved instances as training samples, a possible distributed deployment, reduced online/offline computational complexity, and more remarkably excellent scalability and generalizability over different network scenarios and system configurations.
Authors: Gao Zitian, Xiao Yihao
Abstract: In the Venture Capital(VC) industry, predicting the success of startups is challenging due to limited financial data and the need for subjective revenue forecasts. Previous methods based on time series analysis or deep learning often fall short as they fail to incorporate crucial inter-company relationships such as competition and collaboration. Regarding the issues, we propose a novel approach using GrahphRAG augmented time series model. With GraphRAG, time series predictive methods are enhanced by integrating these vital relationships into the analysis framework, allowing for a more dynamic understanding of the startup ecosystem in venture capital. Our experimental results demonstrate that our model significantly outperforms previous models in startup success predictions. To the best of our knowledge, our work is the first application work of GraphRAG.
Authors: Nima Anari, Ruiquan Gao, Aviad Rubinstein
Abstract: We show how to use parallelization to speed up sampling from an arbitrary distribution $\mu$ on a product space $[q]^n$, given oracle access to counting queries: $\mathbb{P}_{X\sim \mu}[X_S=\sigma_S]$ for any $S\subseteq [n]$ and $\sigma_S \in [q]^S$. Our algorithm takes $O({n^{2/3}\cdot \operatorname{polylog}(n,q)})$ parallel time, to the best of our knowledge, the first sublinear in $n$ runtime for arbitrary distributions. Our results have implications for sampling in autoregressive models. Our algorithm directly works with an equivalent oracle that answers conditional marginal queries $\mathbb{P}_{X\sim \mu}[X_i=\sigma_i\;\vert\; X_S=\sigma_S]$, whose role is played by a trained neural network in autoregressive models. This suggests a roughly $n^{1/3}$-factor speedup is possible for sampling in any-order autoregressive models. We complement our positive result by showing a lower bound of $\widetilde{\Omega}(n^{1/3})$ for the runtime of any parallel sampling algorithm making at most $\operatorname{poly}(n)$ queries to the counting oracle, even for $q=2$.
Authors: Xin Liu, Weijia Zhang, Min-Ling Zhang
Abstract: Although attention-based multi-instance learning algorithms have achieved impressive performances on slide-level whole slide image (WSI) classification tasks, they are prone to mistakenly focus on irrelevant patterns such as staining conditions and tissue morphology, leading to incorrect patch-level predictions and unreliable interpretability. Moreover, these attention-based MIL algorithms tend to focus on salient instances and struggle to recognize hard-to-classify instances. In this paper, we first demonstrate that attention-based WSI classification methods do not adhere to the standard MIL assumptions. From the standard MIL assumptions, we propose a surprisingly simple yet effective instance-based MIL method for WSI classification (FocusMIL) based on max-pooling and forward amortized variational inference. We argue that synergizing the standard MIL assumption with variational inference encourages the model to focus on tumour morphology instead of spurious correlations. Our experimental evaluations show that FocusMIL significantly outperforms the baselines in patch-level classification tasks on the Camelyon16 and TCGA-NSCLC benchmarks. Visualization results show that our method also achieves better classification boundaries for identifying hard instances and mitigates the effect of spurious correlations between bags and labels.
Authors: Omar Ghazal, Tian Lan, Shalman Ojukwu, Komal Krishnamurthy, Alex Yakovlev, Rishad Shafik
Abstract: The modern implementation of machine learning architectures faces significant challenges due to frequent data transfer between memory and processing units. In-memory computing, primarily through memristor-based analog computing, offers a promising solution to overcome this von Neumann bottleneck. In this technology, data processing and storage are located inside the memory. Here, we introduce a novel approach that utilizes floating-gate Y-Flash memristive devices manufactured with a standard 180 nm CMOS process. These devices offer attractive features, including analog tunability and moderate device-to-device variation; such characteristics are essential for reliable decision-making in ML applications. This paper uses a new machine learning algorithm, the Tsetlin Machine (TM), for in-memory processing architecture. The TM's learning element, Automaton, is mapped into a single Y-Flash cell, where the Automaton's range is transferred into the Y-Flash's conductance scope. Through comprehensive simulations, the proposed hardware implementation of the learning automata, particularly for Tsetlin machines, has demonstrated enhanced scalability and on-edge learning capabilities.
Authors: Jun Wang, Yu Mao, Nan Guan, Chun Jason Xue
Abstract: Whole slide images (WSIs) are gigapixel-scale digital images of H\&E-stained tissue samples widely used in pathology. The substantial size and complexity of WSIs pose unique analytical challenges. Multiple Instance Learning (MIL) has emerged as a powerful approach for addressing these challenges, particularly in cancer classification and detection. This survey provides a comprehensive overview of the challenges and methodologies associated with applying MIL to WSI analysis, including attention mechanisms, pseudo-labeling, transformers, pooling functions, and graph neural networks. Additionally, it explores the potential of MIL in discovering cancer cell morphology, constructing interpretable machine learning models, and quantifying cancer grading. By summarizing the current challenges, methodologies, and potential applications of MIL in WSI analysis, this survey aims to inform researchers about the state of the field and inspire future research directions.
Authors: Jiajun Song, Zhuoyan Xu, Yiqiao Zhong
Abstract: Large language models (LLMs) such as GPT-4 sometimes appear to be creative, solving novel tasks often with a few demonstrations in the prompt. These tasks require the models to generalize on distributions different from those from training data -- which is known as out-of-distribution (OOD) generalization. Despite the tremendous success of LLMs, how they approach OOD generalization remains an open and underexplored question. We examine OOD generalization in settings where instances are generated according to hidden rules, including in-context learning with symbolic reasoning. Models are required to infer the hidden rules behind input prompts without any fine-tuning. We empirically examined the training dynamics of Transformers on a synthetic example and conducted extensive experiments on a variety of pretrained LLMs, focusing on a type of components known as induction heads. We found that OOD generalization and composition are tied together -- models can learn rules by composing two self-attention layers, thereby achieving OOD generalization. Furthermore, a shared latent subspace in the embedding (or feature) space acts as a bridge for composition by aligning early layers and later layers, which we refer to as the common bridge representation hypothesis.
Authors: Mincheol Park, Nishad Maskara, Marcin Kalinowski, Mikhail D. Lukin
Abstract: Reliable quantum computation requires systematic identification and correction of errors that occur and accumulate in quantum hardware. To diagnose and correct such errors, standard quantum error-correcting protocols utilize $\textit{global}$ error information across the system obtained by mid-circuit readout of ancillary qubits. We investigate circuit-level error-correcting protocols that are measurement-free and based on $\textit{local}$ error information. Such a local error correction (LEC) circuit consists of faulty multi-qubit gates to perform both syndrome extraction and ancilla-controlled error removal. We develop and implement a reinforcement learning framework that takes a fixed set of faulty gates as inputs and outputs an optimized LEC circuit. To evaluate this approach, we quantitatively characterize an extension of logical qubit lifetime by a noisy LEC circuit. For the 2D classical Ising model and 4D toric code, our optimized LEC circuit performs better at extending a memory lifetime compared to a conventional LEC circuit based on Toom's rule in a sub-threshold gate error regime. We further show that such circuits can be used to reduce the rate of mid-circuit readouts to preserve a 2D toric code memory. Finally, we discuss the application of the LEC protocol on dissipative preparation of quantum states with topological phases.
Authors: Kejin Wu, Dimitris N. Politis
Abstract: In this paper, we provide a novel Model-free approach based on Deep Neural Network (DNN) to accomplish point prediction and prediction interval under a general regression setting. Usually, people rely on parametric or non-parametric models to bridge dependent and independent variables (Y and X). However, this classical method relies heavily on the correct model specification. Even for the non-parametric approach, some additive form is often assumed. A newly proposed Model-free prediction principle sheds light on a prediction procedure without any model assumption. Previous work regarding this principle has shown better performance than other standard alternatives. Recently, DNN, one of the machine learning methods, has received increasing attention due to its great performance in practice. Guided by the Model-free prediction idea, we attempt to apply a fully connected forward DNN to map X and some appropriate reference random variable Z to Y. The targeted DNN is trained by minimizing a specially designed loss function so that the randomness of Y conditional on X is outsourced to Z through the trained DNN. Our method is more stable and accurate compared to other DNN-based counterparts, especially for optimal point predictions. With a specific prediction procedure, our prediction interval can capture the estimation variability so that it can render a better coverage rate for finite sample cases. The superior performance of our method is verified by simulation and empirical studies.
Authors: Zaile Li, Weiwei Fan, L. Jeff Hong
Abstract: Ranking and selection (R&S) conventionally aims to select the unique best alternative with the largest mean performance from a finite set of alternatives. However, for better supporting decision making, it may be more informative to deliver a small menu of alternatives whose mean performances are among the top $m$. Such problem, called optimal subset selection (OSS), is generally more challenging to address than the conventional R&S. This challenge becomes even more significant when the number of alternatives is considerably large. Thus, the focus of this paper is on addressing the large-scale OSS problem. To achieve this goal, we design a top-$m$ greedy selection mechanism that keeps sampling the current top $m$ alternatives with top $m$ running sample means and propose the explore-first top-$m$ greedy (EFG-$m$) procedure. Through an extended boundary-crossing framework, we prove that the EFG-$m$ procedure is both sample optimal and consistent in terms of the probability of good selection, confirming its effectiveness in solving large-scale OSS problem. Surprisingly, we also demonstrate that the EFG-$m$ procedure enables to achieve an indifference-based ranking within the selected subset of alternatives at no extra cost. This is highly beneficial as it delivers deeper insights to decision-makers, enabling more informed decision-makings. Lastly, numerical experiments validate our results and demonstrate the efficiency of our procedures.
Authors: Satwik Kundu, Swaroop Ghosh
Abstract: Quantum machine learning (QML) is a category of algorithms that employ variational quantum circuits (VQCs) to tackle machine learning tasks. Recent discoveries have shown that QML models can effectively generalize from limited training data samples. This capability has sparked increased interest in deploying these models to address practical, real-world challenges, resulting in the emergence of Quantum Machine Learning as a Service (QMLaaS). QMLaaS represents a hybrid model that utilizes both classical and quantum computing resources. Classical computers play a crucial role in this setup, handling initial pre-processing and subsequent post-processing of data to compensate for the current limitations of quantum hardware. Since this is a new area, very little work exists to paint the whole picture of QMLaaS in the context of known security threats in the domain of classical and quantum machine learning. This SoK paper is aimed to bridge this gap by outlining the complete QMLaaS workflow, which encompasses both the training and inference phases and highlighting significant security concerns involving untrusted classical or quantum providers. QML models contain several sensitive assets, such as the model architecture, training/testing data, encoding techniques, and trained parameters. Unauthorized access to these components could compromise the model's integrity and lead to intellectual property (IP) theft. We pinpoint the critical security issues that must be considered to pave the way for a secure QMLaaS deployment.
Authors: Wessel P. Bruinsma
Abstract: Neural processes are a family of models which use neural networks to directly parametrise a map from data sets to predictions. Directly parametrising this map enables the use of expressive neural networks in small-data problems where neural networks would traditionally overfit. Neural processes can produce well-calibrated uncertainties, effectively deal with missing data, and are simple to train. These properties make this family of models appealing for a breadth of applications areas, such as healthcare or environmental sciences. This thesis advances neural processes in three ways. First, we propose convolutional neural processes (ConvNPs). ConvNPs improve data efficiency of neural processes by building in a symmetry called translation equivariance. ConvNPs rely on convolutional neural networks rather than multi-layer perceptrons. Second, we propose Gaussian neural processes (GNPs). GNPs directly parametrise dependencies in the predictions of a neural process. Current approaches to modelling dependencies in the predictions depend on a latent variable, which consequently requires approximate inference, undermining the simplicity of the approach. Third, we propose autoregressive conditional neural processes (AR CNPs). AR CNPs train a neural process without any modifications to the model or training procedure and, at test time, roll out the model in an autoregressive fashion. AR CNPs equip the neural process framework with a new knob where modelling complexity and computational expense at training time can be traded for computational expense at test time. In addition to methodological advancements, this thesis also proposes a software abstraction that enables a compositional approach to implementing neural processes. This approach allows the user to rapidly explore the space of neural process models by putting together elementary building blocks in different ways.
Authors: Steven A. Frank
Abstract: A biological circuit is a neural or biochemical cascade, taking inputs and producing outputs. How have biological circuits learned to solve environmental challenges over the history of life? The answer certainly follows Dobzhansky's famous quote that ``nothing in biology makes sense except in the light of evolution.'' But that quote leaves out the mechanistic basis by which natural selection's trial-and-error learning happens, which is exactly what we have to understand. How does the learning process that designs biological circuits actually work? How much insight can we gain about the form and function of biological circuits by studying the processes that have made those circuits? Because life's circuits must often solve the same problems as those faced by machine learning, such as environmental tracking, homeostatic control, dimensional reduction, or classification, we can begin by considering how machine learning designs computational circuits to solve problems. We can then ask: How much insight do those computational circuits provide about the design of biological circuits? How much does biology differ from computers in the particular circuit designs that it uses to solve problems? This article steps through two classic machine learning models to set the foundation for analyzing broad questions about the design of biological circuits. One insight is the surprising power of randomly connected networks. Another is the central role of internal models of the environment embedded within biological circuits, illustrated by a model of dimensional reduction and trend prediction. Overall, many challenges in biology have machine learning analogs, suggesting hypotheses about how biology's circuits are designed.
Authors: Zehua Lai, Lek-Heng Lim, Yucong Liu
Abstract: We highlight a perhaps important but hitherto unobserved insight: The attention module in a transformer is a smoothed cubic spline. Viewed in this manner, this mysterious but critical component of a transformer becomes a natural development of an old notion deeply entrenched in classical approximation theory. More precisely, we show that with ReLU-activation, attention, masked attention, encoder-decoder attention are all cubic splines. As every component in a transformer is constructed out of compositions of various attention modules (= cubic splines) and feed forward neural networks (= linear splines), all its components -- encoder, decoder, and encoder-decoder blocks; multilayered encoders and decoders; the transformer itself -- are cubic or higher-order splines. If we assume the Pierce-Birkhoff conjecture, then the converse also holds, i.e., every spline is a ReLU-activated encoder. Since a spline is generally just $C^2$, one way to obtain a smoothed $C^\infty$-version is by replacing ReLU with a smooth activation; and if this activation is chosen to be SoftMax, we recover the original transformer as proposed by Vaswani et al. This insight sheds light on the nature of the transformer by casting it entirely in terms of splines, one of the best known and thoroughly understood objects in applied mathematics.
Authors: Brian Knaeble, R. Mitchell Hughes, George Rudolph, Mark A. Abramson, Daniel Razo
Abstract: It can be difficult to interpret a coefficient of an uncertain model. A slope coefficient of a regression model may change as covariates are added or removed from the model. In the context of high-dimensional data, there are too many model extensions to check. However, as we show here, it is possible to efficiently search, with a branch and bound algorithm, for maximum and minimum values of that adjusted slope coefficient over a discrete space of regularized regression models. Here we introduce our algorithm, along with supporting mathematical results, an example application, and a link to our computer code, to help researchers summarize high-dimensional data and assess the stability of regression coefficients in uncertain models.
Authors: Zhi Qiao, Linbin Han, Xiantong Zhen, Jia-Hong Gao, Zhen Qian
Abstract: In light of the inherent entailment relations between images and text, hyperbolic point vector embeddings, leveraging the hierarchical modeling advantages of hyperbolic space, have been utilized for visual semantic representation learning. However, point vector embedding approaches fail to address the issue of semantic uncertainty, where an image may have multiple interpretations, and text may refer to different images, a phenomenon particularly prevalent in the medical domain. Therefor, we propose \textbf{HYDEN}, a novel hyperbolic density embedding based image-text representation learning approach tailored for specific medical domain data. This method integrates text-aware local features alongside global features from images, mapping image-text features to density features in hyperbolic space via using hyperbolic pseudo-Gaussian distributions. An encapsulation loss function is employed to model the partial order relations between image-text density distributions. Experimental results demonstrate the interpretability of our approach and its superior performance compared to the baseline methods across various zero-shot tasks and different datasets.
Authors: Amnon Balanov, Tamir Bendory, Wasim Huleihel
Abstract: Confirmation bias, the tendency to interpret information in a way that aligns with one's preconceptions, can profoundly impact scientific research, leading to conclusions that reflect the researcher's hypotheses even when the observational data do not support them. This issue is especially critical in scientific fields involving highly noisy observations, such as cryo-electron microscopy. This study investigates confirmation bias in Gaussian mixture models. We consider the following experiment: A team of scientists assumes they are analyzing data drawn from a Gaussian mixture model with known signals (hypotheses) as centroids. However, in reality, the observations consist entirely of noise without any informative structure. The researchers use a single iteration of the K-means or expectation-maximization algorithms, two popular algorithms to estimate the centroids. Despite the observations being pure noise, we show that these algorithms yield biased estimates that resemble the initial hypotheses, contradicting the unbiased expectation that averaging these noise observations would converge to zero. Namely, the algorithms generate estimates that mirror the postulated model, although the hypotheses (the presumed centroids of the Gaussian mixture) are not evident in the observations. Specifically, among other results, we prove a positive correlation between the estimates produced by the algorithms and the corresponding hypotheses. We also derive explicit closed-form expressions of the estimates for a finite and infinite number of hypotheses. This study underscores the risks of confirmation bias in low signal-to-noise environments, provides insights into potential pitfalls in scientific methodologies, and highlights the importance of prudent data interpretation.
Authors: Giriprasad Sridhara, Sujoy Roychowdhury, Sumit Soman, Ranjani H G, Ricardo Britto
Abstract: This paper presents our findings on the automatic summarization of Java methods within Ericsson, a global telecommunications company. We evaluate the performance of an approach called Automatic Semantic Augmentation of Prompts (ASAP), which uses a Large Language Model (LLM) to generate leading summary comments for Java methods. ASAP enhances the $LLM's$ prompt context by integrating static program analysis and information retrieval techniques to identify similar exemplar methods along with their developer-written Javadocs, and serves as the baseline in our study. In contrast, we explore and compare the performance of four simpler approaches that do not require static program analysis, information retrieval, or the presence of exemplars as in the ASAP method. Our methods rely solely on the Java method body as input, making them lightweight and more suitable for rapid deployment in commercial software development environments. We conducted experiments on an Ericsson software project and replicated the study using two widely-used open-source Java projects, Guava and Elasticsearch, to ensure the reliability of our results. Performance was measured across eight metrics that capture various aspects of similarity. Notably, one of our simpler approaches performed as well as or better than the ASAP method on both the Ericsson project and the open-source projects. Additionally, we performed an ablation study to examine the impact of method names on Javadoc summary generation across our four proposed approaches and the ASAP method. By masking the method names and observing the generated summaries, we found that our approaches were statistically significantly less influenced by the absence of method names compared to the baseline. This suggests that our methods are more robust to variations in method names and may derive summaries more comprehensively from the method body than the ASAP approach.
Authors: Marta M. Betcke, Lisa Maria Kreusser, Davide Murari
Abstract: This paper considers one of the fundamental parallel-in-time methods for the solution of ordinary differential equations, Parareal, and extends it by adopting a neural network as a coarse propagator. We provide a theoretical analysis of the convergence properties of the proposed algorithm and show its effectiveness for several examples, including Lorenz and Burgers' equations. In our numerical simulations, we further specialize the underpinning neural architecture to Random Projection Neural Networks (RPNNs), a 2-layer neural network where the first layer weights are drawn at random rather than optimized. This restriction substantially increases the efficiency of fitting RPNN's weights in comparison to a standard feedforward network without negatively impacting the accuracy, as demonstrated in the SIR system example.
Authors: Seoyoung Cho, Jaesung Hwang, Kwan-Young Bak, Dongha Kim
Abstract: Outlier detection (OD) is the task of identifying unusual observations (or outliers) from a given or upcoming data by learning unique patterns of normal observations (or inliers). Recently, a study introduced a powerful unsupervised OD (UOD) solver based on a new observation of deep generative models, called inlier-memorization (IM) effect, which suggests that generative models memorize inliers before outliers in early learning stages. In this study, we aim to develop a theoretically principled method to address UOD tasks by maximally utilizing the IM effect. We begin by observing that the IM effect is observed more clearly when the given training data contain fewer outliers. This finding indicates a potential for enhancing the IM effect in UOD regimes if we can effectively exclude outliers from mini-batches when designing the loss function. To this end, we introduce two main techniques: 1) increasing the mini-batch size as the model training proceeds and 2) using an adaptive threshold to calculate the truncated loss function. We theoretically show that these two techniques effectively filter out outliers from the truncated loss function, allowing us to utilize the IM effect to the fullest. Coupled with an additional ensemble strategy, we propose our method and term it Adaptive Loss Truncation with Batch Increment (ALTBI). We provide extensive experimental results to demonstrate that ALTBI achieves state-of-the-art performance in identifying outliers compared to other recent methods, even with significantly lower computation costs. Additionally, we show that our method yields robust performances when combined with privacy-preserving algorithms.
Authors: Yash Bhalgat, Vadim Tschernezki, Iro Laina, Jo\~ao F. Henriques, Andrea Vedaldi, Andrew Zisserman
Abstract: Egocentric videos present unique challenges for 3D scene understanding due to rapid camera motion, frequent object occlusions, and limited object visibility. This paper introduces a novel approach to instance segmentation and tracking in first-person video that leverages 3D awareness to overcome these obstacles. Our method integrates scene geometry, 3D object centroid tracking, and instance segmentation to create a robust framework for analyzing dynamic egocentric scenes. By incorporating spatial and temporal cues, we achieve superior performance compared to state-of-the-art 2D approaches. Extensive evaluations on the challenging EPIC Fields dataset demonstrate significant improvements across a range of tracking and segmentation consistency metrics. Specifically, our method outperforms the next best performing approach by $7$ points in Association Accuracy (AssA) and $4.5$ points in IDF1 score, while reducing the number of ID switches by $73\%$ to $80\%$ across various object categories. Leveraging our tracked instance segmentations, we showcase downstream applications in 3D object reconstruction and amodal video object segmentation in these egocentric settings.
Authors: Chuhan Wu, Ruiming Tang
Abstract: Guided by the belief of the scaling law, large language models (LLMs) have achieved impressive performance in recent years. However, scaling law only gives a qualitative estimation of loss, which is influenced by various factors such as model architectures, data distributions, tokenizers, and computation precision. Thus, estimating the real performance of LLMs with different training settings rather than loss may be quite useful in practical development. In this article, we present an empirical equation named "Performance Law" to directly predict the MMLU score of an LLM, which is a widely used metric to indicate the general capability of LLMs in real-world conversations and applications. Based on only a few key hyperparameters of the LLM architecture and the size of training data, we obtain a quite accurate MMLU prediction of various LLMs with diverse sizes and architectures developed by different organizations in different years. Performance law can be used to guide the choice of LLM architecture and the effective allocation of computational resources without extensive experiments.
Authors: David Hanny, Sebastian Schmidt, Bernd Resch
Abstract: Information from social media can provide essential information for emergency response during natural disasters in near real-time. However, it is difficult to identify the disaster-related posts among the large amounts of unstructured data available. Previous methods often use keyword filtering, topic modelling or classification-based techniques to identify such posts. Active Learning (AL) presents a promising sub-field of Machine Learning (ML) that has not been used much in the field of text classification of social media content. This study therefore investigates the potential of AL for identifying disaster-related Tweets. We compare a keyword filtering approach, a RoBERTa model fine-tuned with generic data from CrisisLex, a base RoBERTa model trained with AL and a fine-tuned RoBERTa model trained with AL regarding classification performance. For testing, data from CrisisLex and manually labelled data from the 2021 flood in Germany and the 2023 Chile forest fires were considered. The results show that generic fine-tuning combined with 10 rounds of AL outperformed all other approaches. Consequently, a broadly applicable model for the identification of disaster-related Tweets could be trained with very little labelling effort. The model can be applied to use cases beyond this study and provides a useful tool for further research in social media analysis.
Authors: Krzysztof M. Graczyk, Beata E. Kowal, Artur M. Ankowski, Rwik Dharmapal Banerjee, Jose Luis Bonilla, Hemant Prasad, Jan T. Sobczyk
Abstract: Transfer learning (TL) allows a deep neural network (DNN) trained on one type of data to be adapted for new problems with limited information. We propose to use the TL technique in physics. The DNN learns the physics of one process, and after fine-tuning, it makes predictions for related processes. We consider the DNNs, trained on inclusive electron-carbon scattering data, and show that after fine-tuning, they accurately predict cross sections for electron interactions with nuclear targets ranging from lithium to iron. The method works even when the DNN is fine-tuned on a small dataset.
Authors: Kaining Zhang, Junyu Liu, Liu Liu, Liang Jiang, Min-Hsiu Hsieh, Dacheng Tao
Abstract: Quantum machine learning, which involves running machine learning algorithms on quantum devices, may be one of the most significant flagship applications for these devices. Unlike its classical counterparts, the role of data in quantum machine learning has not been fully understood. In this work, we quantify the performances of quantum machine learning in the landscape of quantum data. Provided that the encoding of quantum data is sufficiently random, the performance, we find that the training efficiency and generalization capabilities in quantum machine learning will be exponentially suppressed with the increase in the number of qubits, which we call "the curse of random quantum data". Our findings apply to both the quantum kernel method and the large-width limit of quantum neural networks. Conversely, we highlight that through meticulous design of quantum datasets, it is possible to avoid these curses, thereby achieving efficient convergence and robust generalization. Our conclusions are corroborated by extensive numerical simulations.
Authors: Ik Jun Moon, Junho Moon, Ikbeom Jang
Abstract: 1. Research question: With the growing interest in skin diseases and skin aesthetics, the ability to predict facial wrinkles is becoming increasingly important. This study aims to evaluate whether a computational model, convolutional neural networks (CNN), can be trained for automated facial wrinkle segmentation. 2. Findings: Our study presents an effective technique for integrating data from multiple annotators and illustrates that transfer learning can enhance performance, resulting in dependable segmentation of facial wrinkles. 3. Meaning: This approach automates intricate and time-consuming tasks of wrinkle analysis with a deep learning framework. It could be used to facilitate skin treatments and diagnostics.
Authors: Michael Unser, Stanislas Ducotterd
Abstract: We first establish a kernel theorem that characterizes all linear shift-invariant (LSI) operators acting on discrete multicomponent signals. This result naturally leads to the identification of the Parseval convolution operators as the class of energy-preserving filterbanks. We then present a constructive approach for the design/specification of such filterbanks via the chaining of elementary Parseval modules, each of which being parameterized by an orthogonal matrix or a 1-tight frame. Our analysis is complemented with explicit formulas for the Lipschitz constant of all the components of a convolutional neural network (CNN), which gives us a handle on their stability. Finally, we demonstrate the usage of those tools with the design of a CNN-based algorithm for the iterative reconstruction of biomedical images. Our algorithm falls within the plug-and-play framework for the resolution of inverse problems. It yields better-quality results than the sparsity-based methods used in compressed sensing, while offering essentially the same convergence and robustness guarantees.
Authors: Junho Moon, Haejun Chung, Ikbeom Jang
Abstract: Facial wrinkle detection plays a crucial role in cosmetic dermatology. Precise manual segmentation of facial wrinkles is challenging and time-consuming, with inherent subjectivity leading to inconsistent results among graders. To address this issue, we propose two solutions. First, we build and release the first public facial wrinkle dataset, `FFHQ-Wrinkle', an extension of the NVIDIA FFHQ dataset. This dataset includes 1,000 images with human labels and 50,000 images with automatically generated weak labels. This dataset can foster the research community to develop advanced wrinkle detection algorithms. Second, we introduce a training strategy for U-Net-like encoder-decoder models to detect wrinkles across the face automatically. Our method employs a two-stage training strategy: texture map pretraining and finetuning on human-labeled data. Initially, we pretrain models on a large dataset with weak labels (N=50k) or masked texture maps generated through computer vision techniques, without human intervention. Subsequently, we finetune the models using human-labeled data (N=1k), which consists of manually labeled wrinkle masks. During finetuning, the network inputs a combination of RGB and masked texture maps, comprising four channels. We effectively combine labels from multiple annotators to minimize subjectivity in manual labeling. Our strategies demonstrate improved segmentation performance in facial wrinkle segmentation both quantitatively and visually compared to existing pretraining methods.
Authors: Shunya Noda, Genta Okada
Abstract: We study efficient mechanism design for allocating multiple heterogeneous objects. We aim to maximize the residual surplus, the total value generated from an allocation minus the costs for screening agents' values. We discover a robust trend indicating that no-screening mechanisms such as serial dictatorship with exogenous priority order tend to perform better as the variety of goods increases. We analyze the underlying reasons by characterizing efficient mechanisms in a stylized environment. We also apply an automated mechanism design approach to numerically derive efficient mechanisms and validate the trend in general environments. Building on this implication, we propose the register-invite-book system (RIB) as an efficient system for scheduling vaccination against pandemic diseases.
Authors: Yuanjian Xu, Anxian Liu, Jianing Hao, Zhenzhuo Li, Shichang Meng, Guang Zhang
Abstract: Financial time series modeling is crucial for understanding and predicting market behaviors but faces challenges such as non-linearity, non-stationarity, and high noise levels. Traditional models struggle to capture complex patterns due to these issues, compounded by limitations in computational resources and model capacity. Inspired by the success of large language models in NLP, we introduce \textbf{PLUTUS}, a \textbf{P}re-trained \textbf{L}arge \textbf{U}nified \textbf{T}ransformer-based model that \textbf{U}nveils regularities in financial time \textbf{S}eries. PLUTUS uses an invertible embedding module with contrastive learning and autoencoder techniques to create an approximate one-to-one mapping between raw data and patch embeddings. TimeFormer, an attention based architecture, forms the core of PLUTUS, effectively modeling high-noise time series. We incorporate a novel attention mechanisms to capture features across both variable and temporal dimensions. PLUTUS is pre-trained on an unprecedented dataset of 100 billion observations, designed to thrive in noisy financial environments. To our knowledge, PLUTUS is the first open-source, large-scale, pre-trained financial time series model with over one billion parameters. It achieves state-of-the-art performance in various tasks, demonstrating strong transferability and establishing a robust foundational model for finance. Our research provides technical guidance for pre-training financial time series data, setting a new standard in the field.
Authors: Emanuele De Angelis (CNR-IASI, Rome, Italy), Maurizio Proietti (CNR-IASI, Rome, Italy), Francesca Toni (Imperial, London, UK)
Abstract: Assumption-based Argumentation (ABA) is advocated as a unifying formalism for various forms of non-monotonic reasoning, including logic programming. It allows capturing defeasible knowledge, subject to argumentative debate. While, in much existing work, ABA frameworks are given up-front, in this paper we focus on the problem of automating their learning from background knowledge and positive/negative examples. Unlike prior work, we newly frame the problem in terms of brave reasoning under stable extensions for ABA. We present a novel algorithm based on transformation rules (such as Rote Learning, Folding, Assumption Introduction and Fact Subsumption) and an implementation thereof that makes use of Answer Set Programming. Finally, we compare our technique to state-of-the-art ILP systems that learn defeasible knowledge.
Authors: Manjil Karki, Pratik Shakya, Sandesh Acharya, Ravi Pandit, Dinesh Gothe
Abstract: Voice cloning is a prominent feature in personalized speech interfaces. A neural vocal cloning system can mimic someone's voice using just a few audio samples. Both speaker encoding and speaker adaptation are topics of research in the field of voice cloning. Speaker adaptation relies on fine-tuning a multi-speaker generative model, which involves training a separate model to infer a new speaker embedding used for speaker encoding. Both methods can achieve excellent performance, even with a small number of cloning audios, in terms of the speech's naturalness and similarity to the original speaker. Speaker encoding approaches are more appropriate for low-resource deployment since they require significantly less memory and have a faster cloning time than speaker adaption, which can offer slightly greater naturalness and similarity. The main goal is to create a vocal cloning system that produces audio output with a Nepali accent or that sounds like Nepali. For the further advancement of TTS, the idea of transfer learning was effectively used to address several issues that were encountered in the development of this system, including the poor audio quality and the lack of available data.
Authors: Joshua Cape, Xianshi Yu, Jonquil Z. Liao
Abstract: This paper analyzes the statistical performance of a robust spectral clustering method for latent structure recovery in noisy data matrices. We consider eigenvector-based clustering applied to a matrix of nonparametric rank statistics that is derived entrywise from the raw, original data matrix. This approach is robust in the sense that, unlike traditional spectral clustering procedures, it can provably recover population-level latent block structure even when the observed data matrix includes heavy-tailed entries and has a heterogeneous variance profile. Our main theoretical contributions are threefold and hold under flexible data generating conditions. First, we establish that robust spectral clustering with rank statistics can consistently recover latent block structure, viewed as communities of nodes in a graph, in the sense that unobserved community memberships for all but a vanishing fraction of nodes are correctly recovered with high probability when the data matrix is large. Second, we refine the former result and further establish that, under certain conditions, the community membership of any individual, specified node of interest can be asymptotically exactly recovered with probability tending to one in the large-data limit. Third, we establish asymptotic normality results associated with the truncated eigenstructure of matrices whose entries are rank statistics, made possible by synthesizing contemporary entrywise matrix perturbation analysis with the classical nonparametric theory of so-called simple linear rank statistics. Collectively, these results demonstrate the statistical utility of rank-based data transformations when paired with spectral techniques for dimensionality reduction. Additionally, for a dataset of human connectomes, our approach yields parsimonious dimensionality reduction and improved recovery of ground-truth neuroanatomical cluster structure.
Authors: Amey Hengle, Prasoon Bajpai, Soham Dan, Tanmoy Chakraborty
Abstract: While recent large language models (LLMs) demonstrate remarkable abilities in responding to queries in diverse languages, their ability to handle long multilingual contexts is unexplored. As such, a systematic evaluation of the long-context capabilities of LLMs in multilingual settings is crucial, specifically in the context of information retrieval. To address this gap, we introduce the MultiLingual Needle-in-a-Haystack (MLNeedle) test, designed to assess a model's ability to retrieve relevant information (the needle) from a collection of multilingual distractor texts (the haystack). This test serves as an extension of the multilingual question-answering task, encompassing both monolingual and cross-lingual retrieval. We evaluate four state-of-the-art LLMs on MLNeedle. Our findings reveal that model performance can vary significantly with language and needle position. Specifically, we observe that model performance is the lowest when the needle is (i) in a language outside the English language family and (ii) located in the middle of the input context. Furthermore, although some models claim a context size of $8k$ tokens or greater, none demonstrate satisfactory cross-lingual retrieval performance as the context length increases. Our analysis provides key insights into the long-context behavior of LLMs in multilingual settings to guide future evaluation protocols. To our knowledge, this is the first study to investigate the multilingual long-context behavior of LLMs.
Authors: Ruixuan Liu, Alan Chen, Weiye Zhao, Changliu Liu
Abstract: Combinatorial assembly uses standardized unit primitives to build objects that satisfy user specifications. Lego is a widely used platform for combinatorial assembly, in which people use unit primitives (ie Lego bricks) to build highly customizable 3D objects. This paper studies sequence planning for physical combinatorial assembly using Lego. Given the shape of the desired object, we want to find a sequence of actions for placing Lego bricks to build the target object. In particular, we aim to ensure the planned assembly sequence is physically executable. However, assembly sequence planning (ASP) for combinatorial assembly is particularly challenging due to its combinatorial nature, ie the vast number of possible combinations and complex constraints. To address the challenges, we employ deep reinforcement learning to learn a construction policy for placing unit primitives sequentially to build the desired object. Specifically, we design an online physics-aware action mask that efficiently filters out invalid actions and guides policy learning. In the end, we demonstrate that the proposed method successfully plans physically valid assembly sequences for constructing different Lego structures. The generated construction plan can be executed in real.
Authors: Jing Li
Abstract: Evaluation Metrics is an important question for model evaluation and model selection in binary classification tasks. This study investigates how consistent metrics are at evaluating different models under different data scenarios. Analyzing over 150 data scenarios and 18 model evaluation metrics using statistical simulation, I find that for binary classification tasks, evaluation metrics that are less influenced by prevalence offer more consistent ranking of a set of different models. In particular, Area Under the ROC Curve (AUC) has smallest variance in ranking of different models. Matthew's correlation coefficient as a more strict measure of model performance has the second smallest variance. These patterns holds across a rich set of data scenarios and five commonly used machine learning models as well as a naive random guess model. The results have significant implications for model evaluation and model selection in binary classification tasks.
Authors: Bernd Fritzke (individual researcher)
Abstract: We introduce the breathing k-means algorithm, which on average significantly improves solutions obtained by the widely-known greedy k-means++ algorithm, the default method for k-means clustering in the scikit-learn package. The improvements are achieved through a novel ``breathing'' technique, that cyclically increases and decreases the number of centroids based on local error and utility measures. We conducted experiments using greedy k-means++ as a baseline, comparing it with breathing k-means and five other k-means algorithms. Among the methods investigated, only breathing k-means and better k-means++ consistently outperformed the baseline, with breathing k-means demonstrating a substantial lead. This superior performance was maintained even when comparing the best result of ten runs for all other algorithms to a single run of breathing k-means, highlighting its effectiveness and speed. Our findings indicate that the breathing k-means algorithm outperforms the other k-means techniques, especially greedy k-means++ with ten repetitions, which it dominates in both solution quality and speed. This positions breathing k-means (with the built-in initialization by a single run of greedy k-means++) as a superior alternative to running greedy k-means++ on its own.
Authors: Yonghao Zhuang, Hexu Zhao, Lianmin Zheng, Zhuohan Li, Eric P. Xing, Qirong Ho, Joseph E. Gonzalez, Ion Stoica, Hao Zhang
Abstract: We study a novel and important communication pattern in large-scale model-parallel deep learning (DL), which we call cross-mesh resharding. This pattern emerges when the two paradigms of model parallelism - intra-operator and inter-operator parallelism - are combined to support large models on large clusters. In cross-mesh resharding, a sharded tensor needs to be sent from a source device mesh to a destination device mesh, on which the tensor may be distributed with the same or different layouts. We formalize this as a many-to-many multicast communication problem, and show that existing approaches either are sub-optimal or do not generalize to different network topologies or tensor layouts, which result from different model architectures and parallelism strategies. We then propose two contributions to address cross-mesh resharding: an efficient broadcast-based communication system, and an "overlapping-friendly" pipeline schedule. On microbenchmarks, our overall system outperforms existing ones by up to 10x across various tensor and mesh layouts. On end-to-end training of two large models, GPT-3 and U-Transformer, we improve throughput by 10% and 50%, respectively.
Authors: Andrei Margeloiu, Nikola Simidjievski, Pietro Lio, Mateja Jamnik
Abstract: Neural networks often struggle with high-dimensional but small sample-size tabular datasets. One reason is that current weight initialisation methods assume independence between weights, which can be problematic when there are insufficient samples to estimate the model's parameters accurately. In such small data scenarios, leveraging additional structures can improve the model's performance and training stability. To address this, we propose GCondNet, a general approach to enhance neural networks by leveraging implicit structures present in tabular data. We create a graph between samples for each data dimension, and utilise Graph Neural Networks (GNNs) to extract this implicit structure, and for conditioning the parameters of the first layer of an underlying predictor network. By creating many small graphs, GCondNet exploits the data's high-dimensionality, and thus improves the performance of an underlying predictor network. We demonstrate GCondNet's effectiveness on 12 real-world datasets, where it outperforms 14 standard and state-of-the-art methods. The results show that GCondNet is a versatile framework for injecting graph-regularisation into various types of neural networks, including MLPs and tabular Transformers. Code is available at https://github.com/andreimargeloiu/GCondNet.
Authors: Zhaiming Shen, Ming-Jun Lai, Sheng Li
Abstract: Local clustering aims at extracting a local structure inside a graph without the necessity of knowing the entire graph structure. As the local structure is usually small in size compared to the entire graph, one can think of it as a compressive sensing problem where the indices of target cluster can be thought as a sparse solution to a linear system. In this paper, we apply this idea based on two pioneering works under the same framework and propose a new semi-supervised local clustering approach using only few labeled nodes. Our approach improves the existing works by making the initial cut to be the entire graph and hence overcomes a major limitation of the existing works, which is the low quality of initial cut. Extensive experimental results on various datasets demonstrate the effectiveness of our approach.
Authors: Andrea Apicella, Pasquale Arpaia, Giovanni D'Errico, Davide Marocco, Giovanna Mastrati, Nicola Moccaldi, Roberto Prevete
Abstract: A systematic review on machine-learning strategies for improving generalizability (cross-subjects and cross-sessions) electroencephalography (EEG) based in emotion classification was realized. In this context, the non-stationarity of EEG signals is a critical issue and can lead to the Dataset Shift problem. Several architectures and methods have been proposed to address this issue, mainly based on transfer learning methods. 418 papers were retrieved from the Scopus, IEEE Xplore and PubMed databases through a search query focusing on modern machine learning techniques for generalization in EEG-based emotion assessment. Among these papers, 75 were found eligible based on their relevance to the problem. Studies lacking a specific cross-subject and cross-session validation strategy and making use of other biosignals as support were excluded. On the basis of the selected papers' analysis, a taxonomy of the studies employing Machine Learning (ML) methods was proposed, together with a brief discussion on the different ML approaches involved. The studies with the best results in terms of average classification accuracy were identified, supporting that transfer learning methods seem to perform better than other approaches. A discussion is proposed on the impact of (i) the emotion theoretical models and (ii) psychological screening of the experimental sample on the classifier performances.
Authors: Max Vladymyrov, Andrey Zhmoginov, Mark Sandler
Abstract: We focus on the problem of learning without forgetting from multiple tasks arriving sequentially, where each task is defined using a few-shot episode of novel or already seen classes. We approach this problem using the recently published HyperTransformer (HT), a Transformer-based hypernetwork that generates specialized task-specific CNN weights directly from the support set. In order to learn from a continual sequence of tasks, we propose to recursively re-use the generated weights as input to the HT for the next task. This way, the generated CNN weights themselves act as a representation of previously learned tasks, and the HT is trained to update these weights so that the new task can be learned without forgetting past tasks. This approach is different from most continual learning algorithms that typically rely on using replay buffers, weight regularization or task-dependent architectural changes. We demonstrate that our proposed Continual HyperTransformer method equipped with a prototypical loss is capable of learning and retaining knowledge about past tasks for a variety of scenarios, including learning from mini-batches, and task-incremental and class-incremental learning scenarios.
Authors: Zhiyu Liang, Hongzhi Wang
Abstract: This paper explores how to build a shapelet-based time series classification (TSC) model in the federated learning (FL) scenario, that is, using more data from multiple owners without actually sharing the data. We propose FedST, a novel federated TSC framework extended from a centralized shapelet transformation method. We recognize the federated shapelet search step as the kernel of FedST. Thus, we design a basic protocol for the FedST kernel that we prove to be secure and accurate. However, we identify that the basic protocol suffers from efficiency bottlenecks and the centralized acceleration techniques lose their efficacy due to the security issues. To speed up the federated protocol with security guarantee, we propose several optimizations tailored for the FL setting. Our theoretical analysis shows that the proposed methods are secure and more efficient. We conduct extensive experiments using both synthetic and real-world datasets. Empirical results show that our FedST solution is effective in terms of TSC accuracy, and the proposed optimizations can achieve three orders of magnitude of speedup.
Authors: Chao Chen, Haoyu Geng, Nianzu Yang, Xiaokang Yang, Junchi Yan
Abstract: Dynamic graphs arise in various real-world applications, and it is often welcomed to model the dynamics directly in continuous time domain for its flexibility. This paper aims to design an easy-to-use pipeline (termed as EasyDGL which is also due to its implementation by DGL toolkit) composed of three key modules with both strong fitting ability and interpretability. Specifically the proposed pipeline which involves encoding, training and interpreting: i) a temporal point process (TPP) modulated attention architecture to endow the continuous-time resolution with the coupled spatiotemporal dynamics of the observed graph with edge-addition events; ii) a principled loss composed of task-agnostic TPP posterior maximization based on observed events on the graph, and a task-aware loss with a masking strategy over dynamic graph, where the covered tasks include dynamic link prediction, dynamic node classification and node traffic forecasting; iii) interpretation of the model outputs (e.g., representations and predictions) with scalable perturbation-based quantitative analysis in the graph Fourier domain, which could more comprehensively reflect the behavior of the learned model. Extensive experimental results on public benchmarks show the superior performance of our EasyDGL for time-conditioned predictive tasks, and in particular demonstrate that EasyDGL can effectively quantify the predictive power of frequency content that a model learn from the evolving graph data.
Authors: Zhiyu Liang, Chen Liang, Zheng Liang, Hongzhi Wang, Bo Zheng
Abstract: Machine learning has emerged as a powerful tool for time series analysis. Existing methods are usually customized for different analysis tasks and face challenges in tackling practical problems such as partial labeling and domain shift. To improve the performance and address the practical problems universally, we develop UniTS, a novel framework that incorporates self-supervised representation learning (or pre-training). The components of UniTS are designed using sklearn-like APIs to allow flexible extensions. We demonstrate how users can easily perform an analysis task using the user-friendly GUIs, and show the superior performance of UniTS over the traditional task-specific methods without self-supervised pre-training on five mainstream tasks and two practical settings.
Authors: Ignavier Ng, Biwei Huang, Kun Zhang
Abstract: This paper investigates in which cases continuous optimization for directed acyclic graph (DAG) structure learning can and cannot perform well and why this happens, and suggests possible directions to make the search procedure more reliable. Reisach et al. (2021) suggested that the remarkable performance of several continuous structure learning approaches is primarily driven by a high agreement between the order of increasing marginal variances and the topological order, and demonstrated that these approaches do not perform well after data standardization. We analyze this phenomenon for continuous approaches assuming equal and non-equal noise variances, and show that the statement may not hold in either case by providing counterexamples, justifications, and possible alternative explanations. We further demonstrate that nonconvexity may be a main concern especially for the non-equal noise variances formulation, while recent advances in continuous structure learning fail to achieve improvement in this case. Our findings suggest that future works should take into account the non-equal noise variances formulation to handle more general settings and for a more comprehensive empirical evaluation. Lastly, we provide insights into other aspects of the search procedure, including thresholding and sparsity, and show that they play an important role in the final solutions.
Authors: Martin Holen, Per-Arne Andersen, Kristian Muri Knausg{\aa}rd, Morten Goodwin
Abstract: This paper introduces two learning schemes for distributed agents in Reinforcement Learning (RL) environments, namely Reward-Weighted (R-Weighted) and Loss-Weighted (L-Weighted) gradient merger. The R/L weighted methods replace standard practices for training multiple agents, such as summing or averaging the gradients. The core of our methods is to scale the gradient of each actor based on how high the reward (for R-Weighted) or the loss (for L-Weighted) is compared to the other actors. During training, each agent operates in differently initialized versions of the same environment, which gives different gradients from different actors. In essence, the R-Weights and L-Weights of each agent inform the other agents of its potential, which again reports which environment should be prioritized for learning. This approach of distributed learning is possible because environments that yield higher rewards, or low losses, have more critical information than environments that yield lower rewards or higher losses. We empirically demonstrate that the R-Weighted methods work superior to the state-of-the-art in multiple RL environments.
Authors: Tsuyoshi Id\'e, Naoki Abe
Abstract: When the prediction of a black-box machine learning model deviates from the true observation, what can be said about the reason behind that deviation? This is a fundamental and ubiquitous question that the end user in a business or industrial AI application often asks. The deviation may be due to a sub-optimal black-box model, or it may be simply because the sample in question is an outlier. In either case, one would ideally wish to obtain some form of attribution score -- a value indicative of the extent to which an input variable is responsible for the anomaly. In the present paper we address this task of ``anomaly attribution,'' particularly in the setting in which the model is black-box and the training data are not available. Specifically, we propose a novel likelihood-based attribution framework we call the ``likelihood compensation (LC),'' in which the responsibility score is equated with the correction on each input variable needed to attain the highest possible likelihood. We begin by showing formally why mainstream model-agnostic explanation methods, such as the local linear surrogate modeling and Shapley values, are not designed to explain anomalies. In particular, we show that they are ``deviation-agnostic,'' namely, that their explanations are blind to the fact that there is a deviation in the model prediction for the sample of interest. We do this by positioning these existing methods under the unified umbrella of a function family we call the ``integrated gradient family.'' We validate the effectiveness of the proposed LC approach using publicly available data sets. We also conduct a case study with a real-world building energy prediction task and confirm its usefulness in practice based on expert feedback.
Authors: Zhiyu Liang, Jianfeng Zhang, Chen Liang, Hongzhi Wang, Zheng Liang, Lujia Pan
Abstract: Recent studies have shown great promise in unsupervised representation learning (URL) for multivariate time series, because URL has the capability in learning generalizable representation for many downstream tasks without using inaccessible labels. However, existing approaches usually adopt the models originally designed for other domains (e.g., computer vision) to encode the time series data and {rely on strong assumptions to design learning objectives, which limits their ability to perform well}. To deal with these problems, we propose a novel URL framework for multivariate time series by learning time-series-specific shapelet-based representation through a popular contrasting learning paradigm. To the best of our knowledge, this is the first work that explores the shapelet-based embedding in the unsupervised general-purpose representation learning. A unified shapelet-based encoder and a novel learning objective with multi-grained contrasting and multi-scale alignment are particularly designed to achieve our goal, and a data augmentation library is employed to improve the generalization. We conduct extensive experiments using tens of real-world datasets to assess the representation quality on many downstream tasks, including classification, clustering, and anomaly detection. The results demonstrate the superiority of our method against not only URL competitors, but also techniques specially designed for downstream tasks. Our code has been made publicly available at https://github.com/real2fish/CSL.
Authors: Jinke He, Thomas M. Moerland, Joery A. de Vries, Frans A. Oliehoek
Abstract: Model-based reinforcement learning has drawn considerable interest in recent years, given its promise to improve sample efficiency. Moreover, when using deep-learned models, it is potentially possible to learn compact models from complex sensor data. However, the effectiveness of these learned models, particularly their capacity to plan, i.e., to improve the current policy, remains unclear. In this work, we study MuZero, a well-known deep model-based reinforcement learning algorithm, and explore how far it achieves its learning objective of a value-equivalent model and how useful the learned models are for policy improvement. Amongst various other insights, we conclude that the model learned by MuZero cannot effectively generalize to evaluate unseen policies, which limits the extent to which we can additionally improve the current policy by planning with the model.
Authors: Chao Ren, Rudai Yan, Huihui Zhu, Han Yu, Minrui Xu, Yuan Shen, Yan Xu, Ming Xiao, Zhao Yang Dong, Mikael Skoglund, Dusit Niyato, Leong Chuan Kwek
Abstract: Quantum Federated Learning (QFL) is an emerging interdisciplinary field that merges the principles of Quantum Computing (QC) and Federated Learning (FL), with the goal of leveraging quantum technologies to enhance privacy, security, and efficiency in the learning process. Currently, there is no comprehensive survey for this interdisciplinary field. This review offers a thorough, holistic examination of QFL. We aim to provide a comprehensive understanding of the principles, techniques, and emerging applications of QFL. We discuss the current state of research in this rapidly evolving field, identify challenges and opportunities associated with integrating these technologies, and outline future directions and open research questions. We propose a unique taxonomy of QFL techniques, categorized according to their characteristics and the quantum techniques employed. As the field of QFL continues to progress, we can anticipate further breakthroughs and applications across various industries, driving innovation and addressing challenges related to data privacy, security, and resource optimization. This review serves as a first-of-its-kind comprehensive guide for researchers and practitioners interested in understanding and advancing the field of QFL.
Authors: Sarah Perez, Philippe Poncet
Abstract: In this article, we present a novel data assimilation strategy in pore-scale imaging and demonstrate that this makes it possible to robustly address reactive inverse problems incorporating Uncertainty Quantification (UQ). Pore-scale modeling of reactive flow offers a valuable opportunity to investigate the evolution of macro-scale properties subject to dynamic processes. Yet, they suffer from imaging limitations arising from the associated X-ray microtomography (X-ray microCT) process, which induces discrepancies in the properties estimates. Assessment of the kinetic parameters also raises challenges, as reactive coefficients are critical parameters that can cover a wide range of values. We account for these two issues and ensure reliable calibration of pore-scale modeling, based on dynamical microCT images, by integrating uncertainty quantification in the workflow. The present method is based on a multitasking formulation of reactive inverse problems combining data-driven and physics-informed techniques in calcite dissolution. This allows quantifying morphological uncertainties on the porosity field and estimating reactive parameter ranges through prescribed PDE models with a latent concentration field and dynamical microCT. The data assimilation strategy relies on sequential reinforcement incorporating successively additional PDE constraints. We guarantee robust and unbiased uncertainty quantification by straightforward adaptive weighting of Bayesian Physics-Informed Neural Networks (BPINNs), ensuring reliable micro-porosity changes during geochemical transformations. We demonstrate successful Bayesian Inference in 1D+Time and 2D+Time calcite dissolution based on synthetic microCT images with meaningful posterior distribution on the reactive parameters and dimensionless numbers.
Authors: Zhanhui Zhou, Jie Liu, Jing Shao, Xiangyu Yue, Chao Yang, Wanli Ouyang, Yu Qiao
Abstract: A single language model, even when aligned with labelers through reinforcement learning from human feedback (RLHF), may not suit all human preferences. Recent approaches therefore prefer customization, gathering multi-dimensional feedback, and creating distinct reward models for each dimension. Different language models are then optimized for various preferences using multi-objective RLHF (MORLHF) with varying reward weights. However, RL fine-tuning is unstable and resource-heavy, especially with diverse and usually conflicting objectives. In this paper, we present Multi-Objective Direct Preference Optimization (MODPO), an RL-free extension of Direct Preference Optimization (DPO) for multiple alignment objectives. Essentially, MODPO folds language modeling directly into reward modeling, training language models as implicit collective reward models that combine all objectives with specific weights. MODPO theoretically yields the same optimal solutions as MORLHF but is practically more stable and efficient. Empirical results in safety alignment and long-form question answering show that MODPO matches or outperforms existing methods, producing a Pareto front of language models catering to diverse preferences with three times less computational resources compared to MORLHF. Code is available at https://github.com/ZHZisZZ/modpo.
Authors: Luke Marks, Amir Abdullah, Clement Neo, Rauno Arike, David Krueger, Philip Torr, Fazl Barez
Abstract: Reinforcement learning from human feedback (RLHF) is widely used to train large language models (LLMs). However, it is unclear whether LLMs accurately learn the underlying preferences in human feedback data. We coin the term \textit{Learned Feedback Pattern} (LFP) for patterns in an LLM's activations learned during RLHF that improve its performance on the fine-tuning task. We hypothesize that LLMs with LFPs accurately aligned to the fine-tuning feedback exhibit consistent activation patterns for outputs that would have received similar feedback during RLHF. To test this, we train probes to estimate the feedback signal implicit in the activations of a fine-tuned LLM. We then compare these estimates to the true feedback, measuring how accurate the LFPs are to the fine-tuning feedback. Our probes are trained on a condensed, sparse and interpretable representation of LLM activations, making it easier to correlate features of the input with our probe's predictions. We validate our probes by comparing the neural features they correlate with positive feedback inputs against the features GPT-4 describes and classifies as related to LFPs. Understanding LFPs can help minimize discrepancies between LLM behavior and training objectives, which is essential for the safety of LLMs.
Authors: Ziru Niu, Hai Dong, A. Kai Qin, Tao Gu
Abstract: Federated Learning (FL) achieves great popularity in the Internet of Things (IoT) as a powerful interface to offer intelligent services to customers while maintaining data privacy. Under the orchestration of a server, edge devices (also called clients in FL) collaboratively train a global deep-learning model without sharing any local data. Nevertheless, the unequal training contributions among clients have made FL vulnerable, as clients with heavily biased datasets can easily compromise FL by sending malicious or heavily biased parameter updates. Furthermore, the resource shortage issue of the network also becomes a bottleneck. Due to overwhelming computation overheads generated by training deep-learning models on edge devices, and significant communication overheads for transmitting deep-learning models across the network, enormous amounts of resources are consumed in the FL process. This encompasses computation resources like energy and communication resources like bandwidth. To comprehensively address these challenges, in this paper, we present FLrce, an efficient FL framework with a relationship-based client selection and early-stopping strategy. FLrce accelerates the FL process by selecting clients with more significant effects, enabling the global model to converge to a high accuracy in fewer rounds. FLrce also leverages an early stopping mechanism that terminates FL in advance to save communication and computation resources. Experiment results show that, compared with existing efficient FL frameworks, FLrce improves the computation and communication efficiency by at least 30% and 43% respectively.
Authors: Zhongjian Qiao, Jiafei Lyu, Xiu Li
Abstract: The primacy bias in model-free reinforcement learning (MFRL), which refers to the agent's tendency to overfit early data and lose the ability to learn from new data, can significantly decrease the performance of MFRL algorithms. Previous studies have shown that employing simple techniques, such as resetting the agent's parameters, can substantially alleviate the primacy bias in MFRL. However, the primacy bias in model-based reinforcement learning (MBRL) remains unexplored. In this work, we focus on investigating the primacy bias in MBRL. We begin by observing that resetting the agent's parameters harms its performance in the context of MBRL. We further find that the primacy bias in MBRL is more closely related to the primacy bias of the world model instead of the primacy bias of the agent. Based on this finding, we propose \textit{world model resetting}, a simple yet effective technique to alleviate the primacy bias in MBRL. We apply our method to two different MBRL algorithms, MBPO and DreamerV2. We validate the effectiveness of our method on multiple continuous control tasks on MuJoCo and DeepMind Control Suite, as well as discrete control tasks on Atari 100k benchmark. The experimental results show that \textit{world model resetting} can significantly alleviate the primacy bias in the model-based setting and improve the algorithm's performance. We also give a guide on how to perform \textit{world model resetting} effectively.
Authors: Surbhi Mittal, Kartik Thakral, Richa Singh, Mayank Vatsa, Tamar Glaser, Cristian Canton Ferrer, Tal Hassner
Abstract: Artificial Intelligence (AI) has made its way into various scientific fields, providing astonishing improvements over existing algorithms for a wide variety of tasks. In recent years, there have been severe concerns over the trustworthiness of AI technologies. The scientific community has focused on the development of trustworthy AI algorithms. However, machine and deep learning algorithms, popular in the AI community today, depend heavily on the data used during their development. These learning algorithms identify patterns in the data, learning the behavioral objective. Any flaws in the data have the potential to translate directly into algorithms. In this study, we discuss the importance of Responsible Machine Learning Datasets and propose a framework to evaluate the datasets through a responsible rubric. While existing work focuses on the post-hoc evaluation of algorithms for their trustworthiness, we provide a framework that considers the data component separately to understand its role in the algorithm. We discuss responsible datasets through the lens of fairness, privacy, and regulatory compliance and provide recommendations for constructing future datasets. After surveying over 100 datasets, we use 60 datasets for analysis and demonstrate that none of these datasets is immune to issues of fairness, privacy preservation, and regulatory compliance. We provide modifications to the ``datasheets for datasets" with important additions for improved dataset documentation. With governments around the world regularizing data protection laws, the method for the creation of datasets in the scientific community requires revision. We believe this study is timely and relevant in today's era of AI.
Authors: Samuel E. Otto, Nicholas Zolman, J. Nathan Kutz, Steven L. Brunton
Abstract: Symmetry is present throughout nature and continues to play an increasingly central role in physics and machine learning. Fundamental symmetries, such as Poincar\'{e} invariance, allow physical laws discovered in laboratories on Earth to be extrapolated to the farthest reaches of the universe. Symmetry is essential to achieving this extrapolatory power in machine learning applications. For example, translation invariance in image classification allows models with fewer parameters, such as convolutional neural networks, to be trained on smaller data sets and achieve state-of-the-art performance. In this paper, we provide a unifying theoretical and methodological framework for incorporating symmetry into machine learning models in three ways: 1. enforcing known symmetry when training a model; 2. discovering unknown symmetries of a given model or data set; and 3. promoting symmetry during training by learning a model that breaks symmetries within a user-specified group of candidates when there is sufficient evidence in the data. We show that these tasks can be cast within a common mathematical framework whose central object is the Lie derivative associated with fiber-linear Lie group actions on vector bundles. We extend and unify several existing results by showing that enforcing and discovering symmetry are linear-algebraic tasks that are dual with respect to the bilinear structure of the Lie derivative. We also propose a novel way to promote symmetry by introducing a class of convex regularization functions based on the Lie derivative and nuclear norm relaxation to penalize symmetry breaking during training of machine learning models. We explain how these ideas can be applied to a wide range of machine learning models including basis function regression, dynamical systems discovery, neural networks, and neural operators acting on fields.
Authors: Mathieu Alain, So Takao, Brooks Paige, Marc Peter Deisenroth
Abstract: In recent years, there has been considerable interest in developing machine learning models on graphs to account for topological inductive biases. In particular, recent attention has been given to Gaussian processes on such structures since they can additionally account for uncertainty. However, graphs are limited to modelling relations between two vertices. In this paper, we go beyond this dyadic setting and consider polyadic relations that include interactions between vertices, edges and one of their generalisations, known as cells. Specifically, we propose Gaussian processes on cellular complexes, a generalisation of graphs that captures interactions between these higher-order cells. One of our key contributions is the derivation of two novel kernels, one that generalises the graph Mat\'ern kernel and one that additionally mixes information of different cell types.
Authors: Shashank Kotyan, Tatsuya Ueda, Danilo Vasconcellos Vargas
Abstract: Most examinations of neural networks' learned latent spaces typically employ dimensionality reduction techniques such as t-SNE or UMAP. These methods distort the local neighborhood in the visualization, making it hard to distinguish the structure of a subset of samples in the latent space. In response to this challenge, we introduce the {k*~distribution} and its corresponding visualization technique This method uses local neighborhood analysis to guarantee the preservation of the structure of sample distributions for individual classes within the subset of the learned latent space. This facilitates easy comparison of different k*~distributions, enabling analysis of how various classes are processed by the same neural network. Our study reveals three distinct distributions of samples within the learned latent space subset: a) Fractured, b) Overlapped, and c) Clustered, providing a more profound understanding of existing contemporary visualizations. Experiments show that the distribution of samples within the network's learned latent space significantly varies depending on the class. Furthermore, we illustrate that our analysis can be applied to explore the latent space of diverse neural network architectures, various layers within neural networks, transformations applied to input samples, and the distribution of training and testing data for neural networks. Thus, the k* distribution should aid in visualizing the structure inside neural networks and further foster their understanding. Project Website is available online at https://shashankkotyan.github.io/k-Distribution/.
Authors: Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal, Ahmad Beirami, Alex D'Amour, DJ Dvijotham, Adam Fisch, Katherine Heller, Stephen Pfohl, Deepak Ramachandran, Peter Shaw, Jonathan Berant
Abstract: Reward models play a key role in aligning language model applications towards human preferences. However, this setup creates an incentive for the language model to exploit errors in the reward model to achieve high estimated reward, a phenomenon often termed \emph{reward hacking}. A natural mitigation is to train an ensemble of reward models, aggregating over model outputs to obtain a more robust reward estimate. We explore the application of reward ensembles to alignment at both training time (through reinforcement learning) and inference time (through reranking). First, we show that reward models are \emph{underspecified}: reward models that perform similarly in-distribution can yield very different rewards when used in alignment, due to distribution shift. Second, underspecification results in overoptimization, where alignment to one reward model does not improve reward as measured by another reward model trained on the same data. Third, overoptimization is mitigated by the use of reward ensembles, and ensembles that vary by their \emph{pretraining} seeds lead to better generalization than ensembles that differ only by their \emph{fine-tuning} seeds, with both outperforming individual reward models. However, even pretrain reward ensembles do not eliminate reward hacking: we show several qualitative reward hacking phenomena that are not mitigated by ensembling because all reward models in the ensemble exhibit similar error patterns.
Authors: Kuangpu Guo, Yuhe Ding, Jian Liang, Ran He, Zilei Wang, Tieniu Tan
Abstract: Label skews, characterized by disparities in local label distribution across clients, pose a significant challenge in federated learning. As minority classes suffer from worse accuracy due to overfitting on local imbalanced data, prior methods often incorporate class-balanced learning techniques during local training. Although these methods improve the mean accuracy across all classes, we observe that vacant classes-referring to categories absent from a client's data distribution-remain poorly recognized. Besides, there is still a gap in the accuracy of local models on minority classes compared to the global model. This paper introduces FedVLS, a novel approach to label-skewed federated learning that integrates both vacant-class distillation and logit suppression simultaneously. Specifically, vacant-class distillation leverages knowledge distillation during local training on each client to retain essential information related to vacant classes from the global model. Moreover, logit suppression directly penalizes network logits for non-label classes, effectively addressing misclassifications in minority classes that may be biased toward majority classes. Extensive experiments validate the efficacy of FedVLS, demonstrating superior performance compared to previous state-of-the-art (SOTA) methods across diverse datasets with varying degrees of label skews. Code is available in the supplementary material.
Authors: Anna Varbella, Kenza Amara, Blazhe Gjorgiev, Mennatallah El-Assady, Giovanni Sansavini
Abstract: Power grids are critical infrastructures of paramount importance to modern society and, therefore, engineered to operate under diverse conditions and failures. The ongoing energy transition poses new challenges for the decision-makers and system operators. Therefore, developing grid analysis algorithms is important for supporting reliable operations. These key tools include power flow analysis and system security analysis, both needed for effective operational and strategic planning. The literature review shows a growing trend of machine learning (ML) models that perform these analyses effectively. In particular, Graph Neural Networks (GNNs) stand out in such applications because of the graph-based structure of power grids. However, there is a lack of publicly available graph datasets for training and benchmarking ML models in electrical power grid applications. First, we present PowerGraph, which comprises GNN-tailored datasets for i) power flows, ii) optimal power flows, and iii) cascading failure analyses of power grids. Second, we provide ground-truth explanations for the cascading failure analysis. Finally, we perform a complete benchmarking of GNN methods for node-level and graph-level tasks and explainability. Overall, PowerGraph is a multifaceted GNN dataset for diverse tasks that includes power flow and fault scenarios with real-world explanations, providing a valuable resource for developing improved GNN models for node-level, graph-level tasks and explainability methods in power system modeling. The dataset is available at https://figshare.com/articles/dataset/PowerGraph/22820534 and the code at https://github.com/PowerGraph-Datasets.
URLs: https://figshare.com/articles/dataset/PowerGraph/22820534, https://github.com/PowerGraph-Datasets.
Authors: Martijn de Vos, Akash Dhasade, Jade Garcia Bourr\'ee, Anne-Marie Kermarrec, Erwan Le Merrer, Benoit Rottembourg, Gilles Tredan
Abstract: Existing work in fairness auditing assumes that each audit is performed independently. In this paper, we consider multiple agents working together, each auditing the same platform for different tasks. Agents have two levers: their collaboration strategy, with or without coordination beforehand, and their strategy for sampling appropriate data points. We theoretically compare the interplay of these levers. Our main findings are that (i) collaboration is generally beneficial for accurate audits, (ii) basic sampling methods often prove to be effective, and (iii) counter-intuitively, extensive coordination on queries often deteriorates audits accuracy as the number of agents increases. Experiments on three large datasets confirm our theoretical results. Our findings motivate collaboration during fairness audits of platforms that use ML models for decision-making.
Authors: H. N. Mhaskar, Ryan O'Dowd
Abstract: Function approximation based on data drawn randomly from an unknown distribution is an important problem in machine learning. The manifold hypothesis assumes that the data is sampled from an unknown submanifold of a high dimensional Euclidean space. A great deal of research deals with obtaining information about this manifold, such as the eigendecomposition of the Laplace-Beltrami operator or coordinate charts, and using this information for function approximation. This two-step approach implies some extra errors in the approximation stemming from estimating the basic quantities of the data manifold in addition to the errors inherent in function approximation. In this paper, we project the unknown manifold as a submanifold of an ambient hypersphere and study the question of constructing a one-shot approximation using a specially designed sequence of localized spherical polynomial kernels on the hypersphere. Our approach does not require preprocessing of the data to obtain information about the manifold other than its dimension. We give optimal rates of approximation for relatively ``rough'' functions.
Authors: Qingyuan Wang, Barry Cardiff, Antoine Frapp\'e, Benoit Larras, Deepu John
Abstract: Conventional deep learning (DL) model compression and scaling methods focus on altering the model's components, impacting the results across all samples uniformly. However, since samples vary in difficulty, a dynamic model that adapts computation based on sample complexity offers a novel perspective for compression and scaling. Despite this potential, existing dynamic models are typically monolithic and model-specific, limiting their generalizability as broad compression and scaling methods. Additionally, most deployed DL systems are fixed, unable to adjust their scale once deployed and, therefore, cannot adapt to the varying real-time demands. This paper introduces DyCE, a dynamically configurable system that can adjust the performance-complexity trade-off of a DL model at runtime without requiring re-initialization or redeployment on inference hardware. DyCE achieves this by adding small exit networks to intermediate layers of the original model, allowing computation to terminate early if acceptable results are obtained. DyCE also decouples the design of an efficient dynamic model, facilitating easy adaptation to new base models and potential general use in compression and scaling. We also propose methods for generating optimized configurations and determining the types and positions of exit networks to achieve desired performance and complexity trade-offs. By enabling simple configuration switching, DyCE provides fine-grained performance tuning in real-time. We demonstrate the effectiveness of DyCE through image classification tasks using deep convolutional neural networks (CNNs). DyCE significantly reduces computational complexity by 23.5% for ResNet152 and 25.9% for ConvNextv2-tiny on ImageNet, with accuracy reductions of less than 0.5%.
Authors: Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor, Ioana Baldini, Sara E. Berger, Bishwaranjan Bhattacharjee, Djallel Bouneffouf, Subhajit Chaudhury, Pin-Yu Chen, Lamogha Chiazor, Elizabeth M. Daly, Kirushikesh DB, Rog\'erio Abreu de Paula, Pierre Dognin, Eitan Farchi, Soumya Ghosh, Michael Hind, Raya Horesh, George Kour, Ja Young Lee, Nishtha Madaan, Sameep Mehta, Erik Miehling, Keerthiram Murugesan, Manish Nagireddy, Inkit Padhi, David Piorkowski, Ambrish Rawat, Orna Raz, Prasanna Sattigeri, Hendrik Strobelt, Sarathkrishna Swaminathan, Christoph Tillmann, Aashka Trivedi, Kush R. Varshney, Dennis Wei, Shalisha Witherspooon, Marcel Zalmanovici
Abstract: Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy a library of detectors: compact and easy-to-build classification models that provide labels for various harms. In addition to the detectors themselves, we discuss a wide range of uses for these detector models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent challenges in their development and discuss future work aimed at making the detectors more reliable and broadening their scope.
Authors: Jiyi Chen, Pengyu Li, Yutong Wang, Pei-Cheng Ku, Qing Qu
Abstract: This work proposes a deep learning (DL)-based framework, namely Sim2Real, for spectral signal reconstruction in reconstructive spectroscopy, focusing on efficient data sampling and fast inference time. The work focuses on the challenge of reconstructing real-world spectral signals under the extreme setting where only device-informed simulated data are available for training. Such device-informed simulated data are much easier to collect than real-world data but exhibit large distribution shifts from their real-world counterparts. To leverage such simulated data effectively, a hierarchical data augmentation strategy is introduced to mitigate the adverse effects of this domain shift, and a corresponding neural network for the spectral signal reconstruction with our augmented data is designed. Experiments using a real dataset measured from our spectrometer device demonstrate that Sim2Real achieves significant speed-up during the inference while attaining on-par performance with the state-of-the-art optimization-based methods.
Authors: Yingtao Shen, Minqing Sun, Jianzhe Lin, Jie Zhao, An Zou
Abstract: Model compression has gained significant popularity as a means to alleviate the computational and memory demands of machine learning models. Each compression technique leverages unique features to reduce the size of neural networks. Although intuitively combining different techniques may enhance compression effectiveness, we find that the order in which they are combined significantly influences performance. To identify the optimal sequence for compressing neural networks, we propose the Order of Compression, a systematic and optimal sequence to apply multiple compression techniques in the most effective order. We start by building the foundations of the orders between any two compression approaches and then demonstrate inserting additional compression between any two compressions will not break the order of the two compression approaches. Based on the foundations, an optimal order is obtained with topological sorting. Validated on image-based regression and classification networks across different datasets, our proposed Order of Compression significantly reduces computational costs by up to 859 times on ResNet34, with negligible accuracy loss (-0.09% for CIFAR10) compared to the baseline model. We believe our simple yet effective exploration of the order of compression will shed light on the practice of model compression.
Authors: Michael Poli, Armin W Thomas, Eric Nguyen, Pragaash Ponnusamy, Bj\"orn Deiseroth, Kristian Kersting, Taiji Suzuki, Brian Hie, Stefano Ermon, Christopher R\'e, Ce Zhang, Stefano Massaroli
Abstract: The development of deep learning architectures is a resource-demanding process, due to a vast design space, long prototyping times, and high compute costs associated with at-scale model training and evaluation. We set out to simplify this process by grounding it in an end-to-end mechanistic architecture design (MAD) pipeline, encompassing small-scale capability unit tests predictive of scaling laws. Through a suite of synthetic token manipulation tasks such as compression and recall, designed to probe capabilities, we identify and test new hybrid architectures constructed from a variety of computational primitives. We experimentally validate the resulting architectures via an extensive compute-optimal and a new state-optimal scaling law analysis, training over 500 language models between 70M to 7B parameters. Surprisingly, we find MAD synthetics to correlate with compute-optimal perplexity, enabling accurate evaluation of new architectures via isolated proxy tasks. The new architectures found via MAD, based on simple ideas such as hybridization and sparsity, outperform state-of-the-art Transformer, convolutional, and recurrent architectures (Transformer++, Hyena, Mamba) in scaling, both at compute-optimal budgets and in overtrained regimes. Overall, these results provide evidence that performance on curated synthetic tasks can be predictive of scaling laws, and that an optimal architecture should leverage specialized layers via a hybrid topology.
Authors: Yasin Sonmez, Neelay Junnarkar, Murat Arcak
Abstract: Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dynamics and reward both exhibit the same symmetry; however, in many real-world environments, the dynamical model exhibits symmetry independent of the reward model. In this paper, we assume only the dynamics exhibit symmetry, extending the scope of problems in reinforcement learning and learning in control theory to which symmetry techniques can be applied. We use Cartan's moving frame method to introduce a technique for learning dynamics that, by construction, exhibit specified symmetries. Numerical experiments demonstrate that the proposed method learns a more accurate dynamical model
Authors: I-Hong Hou
Abstract: This paper studies multi-stage systems with end-to-end bandit feedback. In such systems, each job needs to go through multiple stages, each managed by a different agent, before generating an outcome. Each agent can only control its own action and learn the final outcome of the job. It has neither knowledge nor control on actions taken by agents in the next stage. The goal of this paper is to develop distributed online learning algorithms that achieve sublinear regret in adversarial environments. The setting of this paper significantly expands the traditional multi-armed bandit problem, which considers only one agent and one stage. In addition to the exploration-exploitation dilemma in the traditional multi-armed bandit problem, we show that the consideration of multiple stages introduces a third component, education, where an agent needs to choose its actions to facilitate the learning of agents in the next stage. To solve this newly introduced exploration-exploitation-education trilemma, we propose a simple distributed online learning algorithm, $\epsilon-$EXP3. We theoretically prove that the $\epsilon-$EXP3 algorithm is a no-regret policy that achieves sublinear regret. Simulation results show that the $\epsilon-$EXP3 algorithm significantly outperforms existing no-regret online learning algorithms for the traditional multi-armed bandit problem.
Authors: Omar Ghannou, Youn\`es Bennani
Abstract: Multi-source Domain Adaptation (MDA) seeks to adapt models trained on data from multiple labeled source domains to perform effectively on an unlabeled target domain data, assuming access to sources data. To address the challenges of model adaptation and data privacy, we introduce Collaborative MDA Through Optimal Transport (CMDA-OT), a novel framework consisting of two key phases. In the first phase, each source domain is independently adapted to the target domain using optimal transport methods. In the second phase, a centralized collaborative learning architecture is employed, which aggregates the N models from the N sources without accessing their data, thereby safeguarding privacy. During this process, the server leverages a small set of pseudo-labeled samples from the target domain, known as the target validation subset, to refine and guide the adaptation. This dual-phase approach not only improves model performance on the target domain but also addresses vital privacy challenges inherent in domain adaptation.
Authors: Hans Harder, Jean Rabault, Ricardo Vinuesa, Mikael Mortensen, Sebastian Peitz
Abstract: We utilize extreme-learning machines for the prediction of partial differential equations (PDEs). Our method splits the state space into multiple windows that are predicted individually using a single model. Despite requiring only few data points (in some cases, our method can learn from a single full-state snapshot), it still achieves high accuracy and can predict the flow of PDEs over long time horizons. Moreover, we show how additional symmetries can be exploited to increase sample efficiency and to enforce equivariance.
Authors: Jinying Xiao, Ping Li, Jie Nie
Abstract: Large language models have demonstrated strong performance in recent years, but the high cost of training drives the need for efficient methods to compress dataset sizes. We propose TED pruning, a method that addresses the challenge of overfitting under high pruning ratios by quantifying the model's ability to improve performance on pruned data while fitting retained data, known as Internal Generalization (IG). TED uses an optimization objective based on Internal Generalization Distance (IGD), measuring changes in IG before and after pruning to align with true generalization performance and achieve implicit regularization. The IGD optimization objective was verified to allow the model to achieve the smallest upper bound on generalization error. The impact of small mask fluctuations on IG is studied through masks and Taylor approximation, and fast estimation of IGD is enabled. In analyzing continuous training dynamics, the prior effect of IGD is validated, and a progressive pruning strategy is proposed. Experiments on image classification, natural language understanding, and large language model fine-tuning show TED achieves lossless performance with 60-70\% of the data. Upon acceptance, our code will be made publicly available.
Authors: Ye Yuan, Youyuan Zhang, Can Chen, Haolun Wu, Zixuan Li, Jianmo Li, James J. Clark, Xue Liu
Abstract: Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores. These tasks span various domains, such as robotics, material design, and protein and molecular engineering. A common approach involves training a surrogate model using existing designs and their corresponding scores, and then generating new designs through gradient-based updates with respect to the surrogate model. This method suffers from the out-of-distribution issue, where the surrogate model may erroneously predict high scores for unseen designs. To address this challenge, we introduce a novel method, Design Editing for Offline Model-based Optimization} (DEMO), which leverages a diffusion prior to calibrate overly optimized designs. DEMO first generates pseudo design candidates by performing gradient ascent with respect to a surrogate model. Then, an editing process refines these pseudo design candidates by introducing noise and subsequently denoising them with a diffusion prior trained on the offline dataset, ensuring they align with the distribution of valid designs. We provide a theoretical proof that the difference between the final optimized designs generated by DEMO and the prior distribution of the offline dataset is controlled by the noise injected during the editing process. Empirical evaluations on seven offline MBO tasks show that DEMO outperforms various baseline methods, achieving the highest mean rank of 2.1 and a median rank of 1.
Authors: Linian Wang, Jianghong Liu, Huibin Zhang, Leye Wang
Abstract: Accurate day-ahead electricity price forecasting is essential for residential welfare, yet current methods often fall short in forecast accuracy. We observe that commonly used time series models struggle to utilize the prior correlation between price and demand-supply, which, we found, can contribute a lot to a reliable electricity price forecaster. Leveraging this prior, we propose a simple piecewise linear model that significantly enhances forecast accuracy by directly deriving prices from readily forecastable demand-supply values. Experiments in the day-ahead electricity markets of Shanxi province and ISO New England reveal that such forecasts could potentially save residents millions of dollars a year compared to existing methods. Our findings underscore the value of suitably integrating time series modeling with economic prior for enhanced electricity price forecasting accuracy.
Authors: Seunghwan An, Gyeongdong Woo, Jaesung Lim, ChangHyun Kim, Sungchul Hong, Jong-June Jeon
Abstract: In this paper, our goal is to generate synthetic data for heterogeneous (mixed-type) tabular datasets with high machine learning utility (MLu). Since the MLu performance depends on accurately approximating the conditional distributions, we focus on devising a synthetic data generation method based on conditional distribution estimation. We introduce MaCoDE by redefining the consecutive multi-class classification task of Masked Language Modeling (MLM) as histogram-based non-parametric conditional density estimation. Our approach enables the estimation of conditional densities across arbitrary combinations of target and conditional variables. We bridge the theoretical gap between distributional learning and MLM by demonstrating that minimizing the orderless multi-class classification loss leads to minimizing the total variation distance between conditional distributions. To validate our proposed model, we evaluate its performance in synthetic data generation across 10 real-world datasets, demonstrating its ability to adjust data privacy levels easily without re-training. Additionally, since masked input tokens in MLM are analogous to missing data, we further assess its effectiveness in handling training datasets with missing values, including multiple imputations of the missing entries.
Authors: Truong Son Hy, Thieu Khang, Risi Kondor
Abstract: Multiresolution Matrix Factorization (MMF) is unusual amongst fast matrix factorization algorithms in that it does not make a low rank assumption. This makes MMF especially well suited to modeling certain types of graphs with complex multiscale or hierarchical strucutre. While MMF promises to yields a useful wavelet basis, finding the factorization itself is hard, and existing greedy methods tend to be brittle. In this paper, we propose a ``learnable'' version of MMF that carfully optimizes the factorization using metaheuristics, specifically evolutionary algorithms and directed evolution, along with Stiefel manifold optimization through backpropagating errors. We show that the resulting wavelet basis far outperforms prior MMF algorithms and gives comparable performance on standard learning tasks on graphs. Furthermore, we construct the wavelet neural networks (WNNs) learning graphs on the spectral domain with the wavelet basis produced by our MMF learning algorithm. Our wavelet networks are competitive against other state-of-the-art methods in molecular graphs classification and node classification on citation graphs. We release our implementation at https://github.com/HySonLab/LearnMMF
Authors: Hiroaki Chiba-Okabe, Weijie J. Su
Abstract: The rapid progress of generative AI technology has sparked significant copyright concerns, leading to numerous lawsuits filed against AI developers. While various techniques for mitigating copyright issues have been studied, significant risks remain. Here, we propose a genericization method that modifies the outputs of a generative model to make them more generic and less likely to infringe copyright. To achieve this, we introduce a metric for quantifying the level of originality of data in a manner that is consistent with the legal framework. This metric can be practically estimated by drawing samples from a generative model, which is then used for the genericization process. As a practical implementation, we introduce PREGen, which combines our genericization method with an existing mitigation technique. Experiments demonstrate that our genericization method successfully modifies the output of a text-to-image generative model so that it produces more generic, copyright-compliant images. PREGen dramatically improves the performance of the existing method, reducing the likelihood of generating copyrighted characters by more than half when the names of copyrighted characters are used as the prompt. Additionally, although generative models have been found to generate copyrighted characters even when the names of characters are not directly mentioned in the prompt, PREGen almost completely suppresses the generation of copyrighted characters for such prompts.
Authors: Chaolv Zeng, Zhanyu Liu, Guanjie Zheng, Linghe Kong
Abstract: In recent years, significant progress has been made in multivariate time series forecasting using Linear-based, Transformer-based, and Convolution-based models. However, these approaches face notable limitations: linear forecasters struggle with representation capacities, attention mechanisms suffer from quadratic complexity, and convolutional models have a restricted receptive field. These constraints impede their effectiveness in modeling complex time series, particularly those with numerous variables. Additionally, many models adopt the Channel-Independent (CI) strategy, treating multivariate time series as uncorrelated univariate series while ignoring their correlations. For models considering inter-channel relationships, whether through the self-attention mechanism, linear combination, or convolution, they all incur high computational costs and focus solely on weighted summation relationships, neglecting potential proportional relationships between channels. In this work, we address these issues by leveraging the newly introduced state space model and propose \textbf{C-Mamba}, a novel approach that captures cross-channel dependencies while maintaining linear complexity without losing the global receptive field. Our model consists of two key components: (i) channel mixup, where two channels are mixed to enhance the training sets; (ii) channel attention enhanced patch-wise Mamba encoder that leverages the ability of the state space models to capture cross-time dependencies and models correlations between channels by mining their weight relationships. Our model achieves state-of-the-art performance on seven real-world time series datasets. Moreover, the proposed mixup and attention strategy exhibits strong generalizability across other frameworks.
Authors: Giacomo Camposampiero, Michael Hersche, Aleksandar Terzi\'c, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
Abstract: We introduce the Abductive Rule Learner with Context-awareness (ARLC), a model that solves abstract reasoning tasks based on Learn-VRF. ARLC features a novel and more broadly applicable training objective for abductive reasoning, resulting in better interpretability and higher accuracy when solving Raven's progressive matrices (RPM). ARLC allows both programming domain knowledge and learning the rules underlying a data distribution. We evaluate ARLC on the I-RAVEN dataset, showcasing state-of-the-art accuracy across both in-distribution and out-of-distribution (unseen attribute-rule pairs) tests. ARLC surpasses neuro-symbolic and connectionist baselines, including large language models, despite having orders of magnitude fewer parameters. We show ARLC's robustness to post-programming training by incrementally learning from examples on top of programmed knowledge, which only improves its performance and does not result in catastrophic forgetting of the programmed solution. We validate ARLC's seamless transfer learning from a 2x2 RPM constellation to unseen constellations. Our code is available at https://github.com/IBM/abductive-rule-learner-with-context-awareness.
URLs: https://github.com/IBM/abductive-rule-learner-with-context-awareness.
Authors: Yanshu Wang, Wang Li, Tong Yang
Abstract: Matrix quantization involves encoding matrix elements in a more space-efficient manner to minimize storage requirements, with dequantization used to reconstruct the original matrix for practical use. We define the Quantization Error Minimization (QEM) problem as minimizing the difference between a matrix before and after quantization while ensuring that the quantized matrix occupies the same amount of memory. Matrix quantization is essential in various fields, including weight quantization in Large Language Models (LLMs), vector databases, KV cache quantization, graph compression, and image compression. The growing scale of LLMs, such as GPT-4 and BERT, underscores the need for matrix compression due to the large size of parameters and KV caches, which are stored as matrices. To address the QEM problem, we introduce HETA, an algorithm that leverages the local orderliness of matrix elements by iteratively swapping elements to create a locally ordered matrix. This matrix is then grouped and quantized by columns. To further improve HETA, we present two optimizations: additional quantization of residuals to reduce mean squared error (MSE) and the application of masking and batch processing to accelerate the algorithm. Our experiments show that HETA effectively reduces MSE to 12.3% of its original value at the same compression ratio, outperforming leading baseline algorithms. Our contributions include formalizing the QEM problem, developing the HETA algorithm, and proposing two optimizations to enhance both accuracy and processing speed.
Authors: Zhuoyuan Wang, Albert Chern, Yorie Nakahira
Abstract: Accurate estimate of long-term risk is critical for safe decision-making, but sampling from rare risk events and long-term trajectories can be prohibitively costly. Risk gradient can be used in many first-order techniques for learning and control methods, but gradient estimate is difficult to obtain using Monte Carlo (MC) methods because the infinitesimal divisor may significantly amplify sampling noise. Motivated by this gap, we propose an efficient method to evaluate long-term risk probabilities and their gradients using short-term samples without sufficient risk events. We first derive that four types of long-term risk probability are solutions of certain partial differential equations (PDEs). Then, we propose a physics-informed learning technique that integrates data and physics information (aforementioned PDEs). The physics information helps propagate information beyond available data and obtain provable generalization beyond available data, which in turn enables long-term risk to be estimated using short-term samples of safe events. Finally, we demonstrate in simulation that the proposed technique has improved sample efficiency, generalizes well to unseen regions, and adapts to changing system parameters.
Authors: Prasenjit Karmakar, Swadhin Pradhan, Sandip Chakraborty
Abstract: In recent years, indoor air pollution has posed a significant threat to our society, claiming over 3.2 million lives annually. Developing nations, such as India, are most affected since lack of knowledge, inadequate regulation, and outdoor air pollution lead to severe daily exposure to pollutants. However, only a limited number of studies have attempted to understand how indoor air pollution affects developing countries like India. To address this gap, we present spatiotemporal measurements of air quality from 30 indoor sites over six months during summer and winter seasons. The sites are geographically located across four regions of type: rural, suburban, and urban, covering the typical low to middle-income population in India. The dataset contains various types of indoor environments (e.g., studio apartments, classrooms, research laboratories, food canteens, and residential households), and can provide the basis for data-driven learning model research aimed at coping with unique pollution patterns in developing countries. This unique dataset demands advanced data cleaning and imputation techniques for handling missing data due to power failure or network outages during data collection. Furthermore, through a simple speech-to-text application, we provide real-time indoor activity labels annotated by occupants. Therefore, environmentalists and ML enthusiasts can utilize this dataset to understand the complex patterns of the pollutants under different indoor activities, identify recurring sources of pollution, forecast exposure, improve floor plans and room structures of modern indoor designs, develop pollution-aware recommender systems, etc.
Authors: Rui Xie, Asad Ul Haq, Linsen Ma, Krystal Sun, Sanchari Sen, Swagath Venkataramani, Liu Liu, Tong Zhang
Abstract: Recent studies have revealed that, during the inference on generative AI models such as transformer, the importance of different weights exhibits substantial context-dependent variations. This naturally manifests a promising potential of adaptively configuring weight quantization to improve the generative AI inference efficiency. Although configurable weight quantization can readily leverage the hardware support of variable-precision arithmetics in modern GPU and AI accelerators, little prior research has studied how one could exploit variable weight quantization to proportionally improve the AI model memory access speed and energy efficiency. Motivated by the rapidly maturing CXL ecosystem, this work develops a CXL-based design solution to fill this gap. The key is to allow CXL memory controllers play an active role in supporting and exploiting runtime configurable weight quantization. Using transformer as a representative generative AI model, we carried out experiments that well demonstrate the effectiveness of the proposed design solution.
Authors: Orfeas Menis-Mastromichalakis, Giorgos Filandrianos, Jason Liartis, Edmund Dervakos, Giorgos Stamou
Abstract: As machine learning (ML) models and datasets increase in complexity, the demand for methods that enhance explainability and interpretability becomes paramount. Prototypes, by encapsulating essential characteristics within data, offer insights that enable tactical decision-making and enhance transparency. Traditional prototype methods often rely on sub-symbolic raw data and opaque latent spaces, reducing explainability and increasing the risk of misinterpretations. This paper presents a novel framework that utilizes semantic descriptions to define prototypes and provide clear explanations, effectively addressing the shortcomings of conventional methods. Our approach leverages concept-based descriptions to cluster data on the semantic level, ensuring that prototypes not only represent underlying properties intuitively but are also straightforward to interpret. Our method simplifies the interpretative process and effectively bridges the gap between complex data structures and human cognitive processes, thereby enhancing transparency and fostering trust. Our approach outperforms existing widely-used prototype methods in facilitating human understanding and informativeness, as validated through a user survey.
Authors: Runpeng Yu, Weihao Yu, Xinchao Wang
Abstract: This paper does not introduce a novel method. Instead, it offers a fairer and more comprehensive comparison of KAN and MLP models across various tasks, including machine learning, computer vision, audio processing, natural language processing, and symbolic formula representation. Specifically, we control the number of parameters and FLOPs to compare the performance of KAN and MLP. Our main observation is that, except for symbolic formula representation tasks, MLP generally outperforms KAN. We also conduct ablation studies on KAN and find that its advantage in symbolic formula representation mainly stems from its B-spline activation function. When B-spline is applied to MLP, performance in symbolic formula representation significantly improves, surpassing or matching that of KAN. However, in other tasks where MLP already excels over KAN, B-spline does not substantially enhance MLP's performance. Furthermore, we find that KAN's forgetting issue is more severe than that of MLP in a standard class-incremental continual learning setting, which differs from the findings reported in the KAN paper. We hope these results provide insights for future research on KAN and other MLP alternatives. Project link: https://github.com/yu-rp/KANbeFair
Authors: Jiaxun Liu, Yue Tian, Guanjun Liu
Abstract: Graph Neural Networks (GNNs) are widely used in financial fraud detection due to their excellent ability on handling graph-structured financial data and modeling multilayer connections by aggregating information of neighbors. However, these GNN-based methods focus on extracting neighbor-level information but neglect a global perspective. This paper presents the concept and calculation formula of Global Confidence Degree (GCD) and thus designs GCD-based GNN (GCD-GNN) that can address the challenges of camouflage in fraudulent activities and thus can capture more global information. To obtain a precise GCD for each node, we use a multilayer perceptron to transform features and then the new features and the corresponding prototype are used to eliminate unnecessary information. The GCD of a node evaluates the typicality of the node and thus we can leverage GCD to generate attention values for message aggregation. This process is carried out through both the original GCD and its inverse, allowing us to capture both the typical neighbors with high GCD and the atypical ones with low GCD. Extensive experiments on two public datasets demonstrate that GCD-GNN outperforms state-of-the-art baselines, highlighting the effectiveness of GCD. We also design a lightweight GCD-GNN (GCD-GNN$_{light}$) that also outperforms the baselines but is slightly weaker than GCD-GNN on fraud detection performance. However, GCD-GNN$_{light}$ obviously outperforms GCD-GNN on convergence and inference speed.
Authors: Sevil Zanjani Miyandoab, Shahryar Rahnamayan, Azam Asilian Bidgoli, Sevda Ebrahimi, Masoud Makrehchi
Abstract: Feature selection plays a pivotal role in the data preprocessing and model-building pipeline, significantly enhancing model performance, interpretability, and resource efficiency across diverse domains. In population-based optimization methods, the generation of diverse individuals holds utmost importance for adequately exploring the problem landscape, particularly in highly multi-modal multi-objective optimization problems. Our study reveals that, in line with findings from several prior research papers, commonly employed crossover and mutation operations lack the capability to generate high-quality diverse individuals and tend to become confined to limited areas around various local optima. This paper introduces an augmentation to the diversity of the population in the well-established multi-objective scheme of the genetic algorithm, NSGA-II. This enhancement is achieved through two key components: the genuine initialization method and the substitution of the worst individuals with new randomly generated individuals as a re-initialization approach in each generation. The proposed multi-objective feature selection method undergoes testing on twelve real-world classification problems, with the number of features ranging from 2,400 to nearly 50,000. The results demonstrate that replacing the last front of the population with an equivalent number of new random individuals generated using the genuine initialization method and featuring a limited number of features substantially improves the population's quality and, consequently, enhances the performance of the multi-objective algorithm.
Authors: Andrew Siyuan Chen
Abstract: In this paper, we introduce a probabilistic extension to Kolmogorov Arnold Networks (KANs) by incorporating Gaussian Process (GP) as non-linear neurons, which we refer to as GP-KAN. A fully analytical approach to handling the output distribution of one GP as an input to another GP is achieved by considering the function inner product of a GP function sample with the input distribution. These GP neurons exhibit robust non-linear modelling capabilities while using few parameters and can be easily and fully integrated in a feed-forward network structure. They provide inherent uncertainty estimates to the model prediction and can be trained directly on the log-likelihood objective function, without needing variational lower bounds or approximations. In the context of MNIST classification, a model based on GP-KAN of 80 thousand parameters achieved 98.5% prediction accuracy, compared to current state-of-the-art models with 1.5 million parameters.
Authors: Shiyu Wang, Zhixuan Chu, Yinbo Sun, Yu Liu, Yuliang Guo, Yang Chen, Huiyang Jian, Lintao Ma, Xingyu Lu, Jun Zhou
Abstract: Accurate workload forecasting is critical for efficient resource management in cloud computing systems, enabling effective scheduling and autoscaling. Despite recent advances with transformer-based forecasting models, challenges remain due to the non-stationary, nonlinear characteristics of workload time series and the long-term dependencies. In particular, inconsistent performance between long-term history and near-term forecasts hinders long-range predictions. This paper proposes a novel framework leveraging self-supervised multiscale representation learning to capture both long-term and near-term workload patterns. The long-term history is encoded through multiscale representations while the near-term observations are modeled via temporal flow fusion. These representations of different scales are fused using an attention mechanism and characterized with normalizing flows to handle non-Gaussian/non-linear distributions of time series. Extensive experiments on 9 benchmarks demonstrate superiority over existing methods.
Authors: Wei Wang, Qing Li
Abstract: Neural networks are increasingly evolving towards training large models with big data, a method that has demonstrated superior performance across many tasks. However, this approach introduces an urgent problem: current deep learning models are predominantly serial, meaning that as the number of network layers increases, so do the training and inference times. This is unacceptable if deep learning is to continue advancing. Therefore, this paper proposes a deep learning parallelization strategy based on the Universal Approximation Theorem (UAT). From this foundation, we designed a parallel network called Para-Former to test our theory. Unlike traditional serial models, the inference time of Para-Former does not increase with the number of layers, significantly accelerating the inference speed of multi-layer networks. Experimental results validate the effectiveness of this network.
Authors: Jy-yong Sohn, Dohyun Kwon, Seoyeon An, Kangwook Lee
Abstract: Fine-tuning large pre-trained models is a common practice in machine learning applications, yet its mathematical analysis remains largely unexplored. In this paper, we study fine-tuning through the lens of memorization capacity. Our new measure, the Fine-Tuning Capacity (FTC), is defined as the maximum number of samples a neural network can fine-tune, or equivalently, as the minimum number of neurons ($m$) needed to arbitrarily change $N$ labels among $K$ samples considered in the fine-tuning process. In essence, FTC extends the memorization capacity concept to the fine-tuning scenario. We analyze FTC for the additive fine-tuning scenario where the fine-tuned network is defined as the summation of the frozen pre-trained network $f$ and a neural network $g$ (with $m$ neurons) designed for fine-tuning. When $g$ is a ReLU network with either 2 or 3 layers, we obtain tight upper and lower bounds on FTC; we show that $N$ samples can be fine-tuned with $m=\Theta(N)$ neurons for 2-layer networks, and with $m=\Theta(\sqrt{N})$ neurons for 3-layer networks, no matter how large $K$ is. Our results recover the known memorization capacity results when $N = K$ as a special case.
Authors: Haohao Qu, Liangbo Ning, Rui An, Wenqi Fan, Tyler Derr, Xin Xu, Qing Li
Abstract: Deep learning, as a vital technique, has sparked a notable revolution in artificial intelligence. As the most representative architecture, Transformers have empowered numerous advanced models, especially the large language models that comprise billions of parameters, becoming a cornerstone in deep learning. Despite the impressive achievements, Transformers still face inherent limitations, particularly the time-consuming inference resulting from the quadratic computation complexity of attention calculation. Recently, a novel architecture named Mamba, drawing inspiration from classical state space models, has emerged as a promising alternative for building foundation models, delivering comparable modeling abilities to Transformers while preserving near-linear scalability concerning sequence length. This has sparked an increasing number of studies actively exploring Mamba's potential to achieve impressive performance across diverse domains. Given such rapid evolution, there is a critical need for a systematic review that consolidates existing Mamba-empowered models, offering a comprehensive understanding of this emerging model architecture. In this survey, we therefore conduct an in-depth investigation of recent Mamba-associated studies, covering from three main aspects: the advancements of Mamba-based models, the techniques of adapting Mamba to diverse data, and the applications where Mamba can excel. Specifically, we first recall the foundational knowledge of various representative deep learning models and the details of Mamba as preliminaries. Then, to showcase the significance of Mamba, we comprehensively review the related studies focusing on Mamba models' architecture design, data adaptability, and applications. Finally, we present an discussion of current limitations and explore various promising research directions to provide deeper insights for future investigations.
Authors: Absalom E. Ezugwu, Yuh-Shan Ho, Ojonukpe S. Egwuche, Olufisayo S. Ekundayo, Annette Van Der Merwe, Apu K. Saha, Jayanta Pal
Abstract: Machine learning (ML) has transformed numerous fields, but understanding its foundational research is crucial for its continued progress. This paper presents an overview of the significant classical ML algorithms and examines the state-of-the-art publications spanning twelve decades through an extensive bibliometric analysis study. We analyzed a dataset of highly cited papers from prominent ML conferences and journals, employing citation and keyword analyses to uncover critical insights. The study further identifies the most influential papers and authors, reveals the evolving collaborative networks within the ML community, and pinpoints prevailing research themes and emerging focus areas. Additionally, we examine the geographic distribution of highly cited publications, highlighting the leading countries in ML research. This study provides a comprehensive overview of the evolution of traditional learning algorithms and their impacts. It discusses challenges and opportunities for future development, focusing on the Global South. The findings from this paper offer valuable insights for both ML experts and the broader research community, enhancing understanding of the field's trajectory and its significant influence on recent advances in learning algorithms.
Authors: Qilei Li, Ahmed M. Abdelmoniem
Abstract: Federated Learning (FL) is a distributed machine learning diagram that enables multiple clients to collaboratively train a global model without sharing their private local data. However, FL systems are vulnerable to attacks that are happening in malicious clients through data poisoning and model poisoning, which can deteriorate the performance of aggregated global model. Existing defense methods typically focus on mitigating specific types of poisoning and are often ineffective against unseen types of attack. These methods also assume an attack happened moderately while is not always holds true in real. Consequently, these methods can significantly fail in terms of accuracy and robustness when detecting and addressing updates from attacked malicious clients. To overcome these challenges, in this work, we propose a simple yet effective framework to detect malicious clients, namely Confidence-Aware Defense (CAD), that utilizes the confidence scores of local models as criteria to evaluate the reliability of local updates. Our key insight is that malicious attacks, regardless of attack type, will cause the model to deviate from its previous state, thus leading to increased uncertainty when making predictions. Therefore, CAD is comprehensively effective for both model poisoning and data poisoning attacks by accurately identifying and mitigating potential malicious updates, even under varying degrees of attacks and data heterogeneity. Experimental results demonstrate that our method significantly enhances the robustness of FL systems against various types of attacks across various scenarios by achieving higher model accuracy and stability.
Authors: Victor Augusto Kich, Jair Augusto Bottega, Raul Steinmetz, Ricardo Bedin Grando, Ayano Yorozu, Akihisa Ohya
Abstract: Kolmogorov-Arnold Networks (KANs) have shown potential as an alternative to Multi-Layer Perceptrons (MLPs) in neural networks, providing universal function approximation with fewer parameters and reduced memory usage. In this paper, we explore the use of KANs as function approximators within the Proximal Policy Optimization (PPO) algorithm. We evaluate this approach by comparing its performance to the original MLP-based PPO using the DeepMind Control Proprio Robotics benchmark. Our results indicate that the KAN-based reinforcement learning algorithm can achieve comparable performance to its MLP-based counterpart, often with fewer parameters. These findings suggest that KANs may offer a more efficient option for reinforcement learning models.
Authors: Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, J\'anos Kram\'ar, Anca Dragan, Rohin Shah, Neel Nanda
Abstract: Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network's latent representations into seemingly interpretable features. Despite recent excitement about their potential, research applications outside of industry are limited by the high cost of training a comprehensive suite of SAEs. In this work, we introduce Gemma Scope, an open suite of JumpReLU SAEs trained on all layers and sub-layers of Gemma 2 2B and 9B and select layers of Gemma 2 27B base models. We primarily train SAEs on the Gemma 2 pre-trained models, but additionally release SAEs trained on instruction-tuned Gemma 2 9B for comparison. We evaluate the quality of each SAE on standard metrics and release these results. We hope that by releasing these SAE weights, we can help make more ambitious safety and interpretability research easier for the community. Weights and a tutorial can be found at https://huggingface.co/google/gemma-scope and an interactive demo can be found at https://www.neuronpedia.org/gemma-scope
URLs: https://huggingface.co/google/gemma-scope, https://www.neuronpedia.org/gemma-scope
Authors: Minh Lenhat, Viet Anh Nguyen, Khoa Nguyen, Duong Duc Hieu, Dao Huu Hung, Truong Son Hy
Abstract: The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training. Efficient transformers, on the other hand, often rely on clever data-modality-dependent construction to get over the quadratic complexity of transformers. This greatly hinders their applications on different data modalities, which is one of the pillars of contemporary foundational modeling. In this paper, we lay the groundwork for efficient foundational modeling by proposing SAMSA - SAMpling-Self-Attention, a context-aware linear complexity self-attention mechanism that works well on multiple data modalities. Our mechanism is based on a differentiable sampling without replacement method we discovered. This enables the self-attention module to attend to the most important token set, where the importance is defined by data. Moreover, as differentiability is not needed in inference, the sparse formulation of our method costs little time overhead, further lowering computational costs. In short, SAMSA achieved competitive or even SOTA results on many benchmarks, while being faster in inference, compared to other very specialized models. Against full self-attention, real inference time significantly decreases while performance ranges from negligible degradation to outperformance. We release our source code in the repository: https://github.com/HySonLab/SAMSA
Authors: Viet Anh Nguyen, Minh Lenhat, Khoa Nguyen, Duong Duc Hieu, Dao Huu Hung, Truong Son Hy
Abstract: The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training. To apply transformers across different data modalities, practitioners have to make specific clever data-modality-dependent constructions. In this paper, we propose Sampling Foundational Transformer (SFT) that can work on multiple data modalities (e.g., point cloud, graph, and sequence) and constraints (e.g., rotational-invariant). The existence of such model is important as contemporary foundational modeling requires operability on multiple data sources. For efficiency on large number of tokens, our model relies on our context aware sampling-without-replacement mechanism for both linear asymptotic computational complexity and real inference time gain. For efficiency, we rely on our newly discovered pseudoconvex formulation of transformer layer to increase model's convergence rate. As a model working on multiple data modalities, SFT has achieved competitive results on many benchmarks, while being faster in inference, compared to other very specialized models.
Authors: Sajjad Hashemian, Mohammad Saeed Arvenaghi, Ebrahim Ardeshir-Larijani
Abstract: In this paper, we introduce new algorithms for Principal Component Analysis (PCA) with outliers. Utilizing techniques from computational geometry, specifically higher-degree Voronoi diagrams, we navigate to the optimal subspace for PCA even in the presence of outliers. This approach achieves an optimal solution with a time complexity of $n^{d+\mathcal{O}(1)}\text{poly}(n,d)$. Additionally, we present a randomized algorithm with a complexity of $2^{\mathcal{O}(r(d-r))} \times \text{poly}(n, d)$. This algorithm samples subspaces characterized in terms of a Grassmannian manifold. By employing such sampling method, we ensure a high likelihood of capturing the optimal subspace, with the success probability $(1 - \delta)^T$. Where $\delta$ represents the probability that a sampled subspace does not contain the optimal solution, and $T$ is the number of subspaces sampled, proportional to $2^{r(d-r)}$. Our use of higher-degree Voronoi diagrams and Grassmannian based sampling offers a clearer conceptual pathway and practical advantages, particularly in handling large datasets or higher-dimensional settings.
Authors: Wangying Yang, Zitao Zheng, Shi Bo, Zhizhong Wu, Bo Zhang, Yuanfang Yang
Abstract: This study introduces a pioneering Dynamic Hypergraph Networks (DHCE) model designed to predict future medical diagnoses from electronic health records with enhanced accuracy. The DHCE model innovates by identifying and differentiating acute and chronic diseases within a patient's visit history, constructing dynamic hypergraphs that capture the complex, high-order interactions between diseases. It surpasses traditional recurrent neural networks and graph neural networks by effectively integrating clinical event data, reflected through medical language model-assisted encoding, into a robust patient representation. Through extensive experiments on two benchmark datasets, MIMIC-III and MIMIC-IV, the DHCE model exhibits superior performance, significantly outpacing established baseline models in the precision of sequential diagnosis prediction.
Authors: Shuo Yang, Ying Sheng, Joseph E. Gonzalez, Ion Stoica, Lianmin Zheng
Abstract: The inference process for large language models is slow and memory-intensive, with one of the most critical bottlenecks being excessive Key-Value (KV) cache accesses. This paper introduces "Double Sparsity," a novel post-training sparse attention technique designed to alleviate this bottleneck by reducing KV cache access. Double Sparsity combines token sparsity, which focuses on utilizing only the important tokens for computing self-attention, with channel sparsity, an approach that uses important feature channels for identifying important tokens. Our key insight is that the pattern of channel sparsity is relatively static, allowing us to use offline calibration to make it efficient at runtime, thereby enabling accurate and efficient identification of important tokens. Moreover, this method can be combined with offloading to achieve significant memory usage reduction. Experimental results demonstrate that Double Sparsity can achieve $\frac{1}{16}$ token and channel sparsity with minimal impact on accuracy across various tasks, including wiki-2 perplexity, key-value retrieval, and long context benchmarks with models including Llama-2-7B, Llama-2-70B, and Mixtral-8x7B. It brings up to a 14.1$\times$ acceleration in attention operations and a 1.9$\times$ improvement in end-to-end inference on GPUs. With offloading, it achieves a decoding speed acceleration of 16.3$\times$ compared to state-of-the-art solutions at a sequence length of 256K. Our code is publicly available at https://github.com/andy-yang-1/DoubleSparse.
Authors: Chang Dong, Liangwei Zheng, Weitong Chen, Wei Emma Zhang
Abstract: Kolmogorov-Arnold Networks (KAN) has recently attracted significant attention as a promising alternative to traditional Multi-Layer Perceptrons (MLP). Despite their theoretical appeal, KAN require validation on large-scale benchmark datasets. Time series data, which has become increasingly prevalent in recent years, especially univariate time series are naturally suited for validating KAN. Therefore, we conducted a fair comparison among KAN, MLP, and mixed structures. The results indicate that KAN can achieve performance comparable to, or even slightly better than, MLP across 128 time series datasets. We also performed an ablation study on KAN, revealing that the output is primarily determined by the base component instead of b-spline function. Furthermore, we assessed the robustness of these models and found that KAN and the hybrid structure MLP\_KAN exhibit significant robustness advantages, attributed to their lower Lipschitz constants. This suggests that KAN and KAN layers hold strong potential to be robust models or to improve the adversarial robustness of other models.
Authors: Milan Pape\v{z}, Martin Rektoris, Tom\'a\v{s} Pevn\'y, V\'aclav \v{S}m\'idl
Abstract: Daily internet communication relies heavily on tree-structured graphs, embodied by popular data formats such as XML and JSON. However, many recent generative (probabilistic) models utilize neural networks to learn a probability distribution over undirected cyclic graphs. This assumption of a generic graph structure brings various computational challenges, and, more importantly, the presence of non-linearities in neural networks does not permit tractable probabilistic inference. We address these problems by proposing sum-product-set networks, an extension of probabilistic circuits from unstructured tensor data to tree-structured graph data. To this end, we use random finite sets to reflect a variable number of nodes and edges in the graph and to allow for exact and efficient inference. We demonstrate that our tractable model performs comparably to various intractable models based on neural networks.
Authors: Rohan Baskar Prabhakar, Hengrui Zhang, David Wentzlaff
Abstract: Large Transformer networks are increasingly used in settings where low inference latency can improve the end-user experience and enable new applications. However, autoregressive inference is resource intensive and requires parallelism for efficiency. Parallelism introduces collective communication that is both expensive and represents a phase when hardware resources are underutilized. Towards mitigating this, Kraken is an evolution of the standard Transformer architecture that is designed to complement existing tensor parallelism schemes for efficient inference on multi-device systems. By introducing a fixed degree of intra-layer model parallelism, the architecture allows collective operations to be overlapped with compute, decreasing latency and increasing hardware utilization. When trained on OpenWebText, Kraken models reach a similar perplexity as standard Transformers while also preserving their language modeling capabilities when evaluated on the SuperGLUE benchmark. Importantly, when tested on multi-GPU systems using TensorRT-LLM engines, Kraken speeds up Time To First Token by a mean of 35.6% across a range of model sizes, context lengths, and degrees of tensor parallelism.
Authors: Xiaosheng Li, Wenjie Xi, Jessica Lin
Abstract: Neural networks are widely used in machine learning and data mining. Typically, these networks need to be trained, implying the adjustment of weights (parameters) within the network based on the input data. In this work, we propose a novel approach, RandomNet, that employs untrained deep neural networks to cluster time series. RandomNet uses different sets of random weights to extract diverse representations of time series and then ensembles the clustering relationships derived from these different representations to build the final clustering results. By extracting diverse representations, our model can effectively handle time series with different characteristics. Since all parameters are randomly generated, no training is required during the process. We provide a theoretical analysis of the effectiveness of the method. To validate its performance, we conduct extensive experiments on all of the 128 datasets in the well-known UCR time series archive and perform statistical analysis of the results. These datasets have different sizes, sequence lengths, and they are from diverse fields. The experimental results show that the proposed method is competitive compared with existing state-of-the-art methods.
Authors: Qizhen Zhang, Nikolas Gritsch, Dwaraknath Gnaneshwar, Simon Guo, David Cairuz, Bharat Venkitesh, Jakob Foerster, Phil Blunsom, Sebastian Ruder, Ahmet Ustun, Acyr Locatelli
Abstract: The Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance over dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive. Existing methods mitigate this by pre-training multiple dense expert models independently and using them to initialize an MoE. This is done by using experts' feed-forward network (FFN) to initialize the MoE's experts while merging other parameters. However, this method limits the reuse of dense model parameters to only the FFN layers, thereby constraining the advantages when "upcycling" these models into MoEs. We propose BAM (Branch-Attend-Mix), a simple yet effective method that addresses this shortcoming. BAM makes full use of specialized dense models by not only using their FFN to initialize the MoE layers but also leveraging experts' attention parameters fully by initializing them into a soft-variant of Mixture of Attention (MoA) layers. We explore two methods for upcycling attention parameters: 1) initializing separate attention experts from dense models including all attention parameters for the best model performance; and 2) sharing key and value parameters across all experts to facilitate for better inference efficiency. To further improve efficiency, we adopt a parallel attention transformer architecture to MoEs, which allows the attention experts and FFN experts to be computed concurrently. Our experiments on seed models ranging from 590 million to 2 billion parameters demonstrate that BAM surpasses baselines in both perplexity and downstream task performance, within the same computational and data constraints.
Authors: Ravi Raju, Swayambhoo Jain, Bo Li, Jonathan Li, Urmish Thakkar
Abstract: Large Language Models (LLMs) have revolutionized the landscape of machine learning, yet current benchmarks often fall short in capturing the diverse behavior of these models in real-world applications. A benchmark's usefulness is determined by its ability to clearly differentiate between models of varying capabilities (separability) and closely align with human preferences. Existing frameworks like Alpaca-Eval 2.0 LC \cite{dubois2024lengthcontrolledalpacaevalsimpleway} and Arena-Hard v0.1 \cite{li2024crowdsourced} are limited by their focus on general-purpose queries and lack of diversity across domains such as law, medicine, and multilingual contexts. In this paper, we address these limitations by introducing a novel data pipeline that curates diverse, domain-specific evaluation sets tailored for LLM-as-a-Judge frameworks. Our approach leverages a combination of manual curation, semi-supervised learning to generate clusters, and stratified sampling to ensure balanced representation across a wide range of domains and languages. The resulting evaluation set, which includes 1573 samples across 14 categories, demonstrates high separability (84\%) across ten top-ranked models, and agreement (84\%) with Chatbot Arena and (0.915) Spearman correlation. The agreement values are 9\% better than Arena Hard and 20\% better than AlpacaEval 2.0 LC, while the Spearman coefficient is 0.7 more than the next best benchmark, showcasing a significant improvement in the usefulness of the benchmark. We further provide an open-source evaluation tool that enables fine-grained analysis of model performance across user-defined categories, offering valuable insights for practitioners. This work contributes to the ongoing effort to enhance the transparency, diversity, and effectiveness of LLM evaluation methodologies.
Authors: Dimitris Fotakis, Evangelia Gergatsouli, Themis Gouleakis, Nikolas Patris, Thanos Tolias
Abstract: We consider Online Facility Location in the framework of learning-augmented online algorithms. In Online Facility Location (OFL), demands arrive one-by-one in a metric space and must be (irrevocably) assigned to an open facility upon arrival, without any knowledge about future demands. We focus on uniform facility opening costs and present an online algorithm for OFL that exploits potentially imperfect predictions on the locations of the optimal facilities. We prove that the competitive ratio decreases from sublogarithmic in the number of demands $n$ to constant as the so-called $\eta_1$ error, i.e., the sum of distances of the predicted locations to the optimal facility locations, decreases. E.g., our analysis implies that if for some $\varepsilon > 0$, $\eta_1 = \mathrm{OPT} / n^\varepsilon$, where $\mathrm{OPT}$ is the cost of the optimal solution, the competitive ratio becomes $O(1/\varepsilon)$. We complement our analysis with a matching lower bound establishing that the dependence of the algorithm's competitive ratio on the $\eta_1$ error is optimal, up to constant factors. Finally, we evaluate our algorithm on real world data and compare the performance of our learning-augmented approach against the performance of the best known algorithm for OFL without predictions.
Authors: Niclas Hildebrandt, Benedikt Boenninghoff, Dennis Orth, Christopher Schymura
Abstract: This paper presents the contribution of the Data Science Kitchen at GermEval 2021 shared task on the identification of toxic, engaging, and fact-claiming comments. The task aims at extending the identification of offensive language, by including additional subtasks that identify comments which should be prioritized for fact-checking by moderators and community managers. Our contribution focuses on a feature-engineering approach with a conventional classification backend. We combine semantic and writing style embeddings derived from pre-trained deep neural networks with additional numerical features, specifically designed for this task. Classifier ensembles are used to derive predictions for each subtask via a majority voting scheme. Our best submission achieved macro-averaged F1-scores of 66.8\%,\,69.9\% and 72.5\% for the identification of toxic, engaging, and fact-claiming comments.
Authors: Yixin Chen, Tonmoy Dey, Alan Kuhnle
Abstract: For the problem of maximizing a monotone, submodular function with respect to a cardinality constraint $k$ on a ground set of size $n$, we provide an algorithm that achieves the state-of-the-art in both its empirical performance and its theoretical properties, in terms of adaptive complexity, query complexity, and approximation ratio; that is, it obtains, with high probability, query complexity of $O(n)$ in expectation, adaptivity of $O(\log(n))$, and approximation ratio of nearly $1-1/e$. The main algorithm is assembled from two components which may be of independent interest. The first component of our algorithm, LINEARSEQ, is useful as a preprocessing algorithm to improve the query complexity of many algorithms. Moreover, a variant of LINEARSEQ is shown to have adaptive complexity of $O( \log (n / k) )$ which is smaller than that of any previous algorithm in the literature. The second component is a parallelizable thresholding procedure THRESHOLDSEQ for adding elements with gain above a constant threshold. Finally, we demonstrate that our main algorithm empirically outperforms, in terms of runtime, adaptive rounds, total queries, and objective values, the previous state-of-the-art algorithm FAST in a comprehensive evaluation with six submodular objective functions.
Authors: Sutanoy Dasgupta, Yabo Niu, Kishan Panaganti, Dileep Kalathil, Debdeep Pati, Bani Mallick
Abstract: We consider the off-policy evaluation (OPE) problem in contextual bandits, where the goal is to estimate the value of a target policy using the data collected by a logging policy. Most popular approaches to the OPE are variants of the doubly robust (DR) estimator obtained by combining a direct method (DM) estimator and a correction term involving the inverse propensity score (IPS). Existing algorithms primarily focus on strategies to reduce the variance of the DR estimator arising from large IPS. We propose a new approach called the Doubly Robust with Information borrowing and Context-based switching (DR-IC) estimator that focuses on reducing both bias and variance. The DR-IC estimator replaces the standard DM estimator with a parametric reward model that borrows information from the 'closer' contexts through a correlation structure that depends on the IPS. The DR-IC estimator also adaptively interpolates between this modified DM estimator and a modified DR estimator based on a context-specific switching rule. We give provable guarantees on the performance of the DR-IC estimator. We also demonstrate the superior performance of the DR-IC estimator compared to the state-of-the-art OPE algorithms on a number of benchmark problems.
Authors: Sourav Chatterjee, Mathukumalli Vidyasagar
Abstract: We consider the problem of estimating a large causal polytree from a relatively small i.i.d. sample. This is motivated by the problem of determining causal structure when the number of variables is very large compared to the sample size, such as in gene regulatory networks. We give an algorithm that recovers the tree with high accuracy in such settings. The algorithm works under essentially no distributional or modeling assumptions other than some mild non-degeneracy conditions.
Authors: Guang Li, Ren Togo, Takahiro Ogawa, Miki Haseyama
Abstract: In this study, we propose a novel method called region-guided masked image modeling (RGMIM) for learning meaningful representations from X-ray images. Our method adopts a new masking strategy that utilizes organ mask information to identify valid regions for learning more meaningful representations. We conduct quantitative evaluations on an open lung X-ray image dataset as well as masking ratio hyperparameter studies. When using the entire training set, RGMIM outperformed other comparable methods, achieving a 0.962 lung disease detection accuracy. Specifically, RGMIM significantly improved performance in small data volumes, such as 5% and 10% of the training set compared to other methods. RGMIM can mask more valid regions, facilitating the learning of discriminative representations and the subsequent high-accuracy lung disease detection. RGMIM outperforms other state-of-the-art self-supervised learning methods in experiments, particularly when limited training data is used.
Authors: David J. Chalmers
Abstract: There has recently been widespread discussion of whether large language models might be sentient. Should we take this idea seriously? I will break down the strongest reasons for and against. Given mainstream assumptions in the science of consciousness, there are significant obstacles to consciousness in current models: for example, their lack of recurrent processing, a global workspace, and unified agency. At the same time, it is quite possible that these obstacles will be overcome in the next decade or so. I conclude that while it is somewhat unlikely that current large language models are conscious, we should take seriously the possibility that successors to large language models may be conscious in the not-too-distant future.
Authors: Mohammad Vahid Jamali, Hamid Saber, Homayoon Hatami, Jung Hyun Bae
Abstract: While decades of theoretical research have led to the invention of several classes of error-correction codes, the design of such codes is an extremely challenging task, mostly driven by human ingenuity. Recent studies demonstrate that such designs can be effectively automated and accelerated via tools from machine learning (ML), thus enabling ML-driven classes of error-correction codes with promising performance gains compared to classical designs. A fundamental challenge, however, is that it is prohibitively complex, if not impossible, to design and train fully ML-driven encoder and decoder pairs for large code dimensions. In this paper, we propose Product Autoencoder (ProductAE) -- a computationally-efficient family of deep learning driven (encoder, decoder) pairs -- aimed at enabling the training of relatively large codes (both encoder and decoder) with a manageable training complexity. We build upon ideas from classical product codes and propose constructing large neural codes using smaller code components. ProductAE boils down the complex problem of training the encoder and decoder for a large code dimension $k$ and blocklength $n$ to less-complex sub-problems of training encoders and decoders for smaller dimensions and blocklengths. Our training results show successful training of ProductAEs of dimensions as large as $k = 300$ bits with meaningful performance gains compared to state-of-the-art classical and neural designs. Moreover, we demonstrate excellent robustness and adaptivity of ProductAEs to channel models different than the ones used for training.
Authors: Zhuoyuan Wang, Yorie Nakahira
Abstract: Accurate estimates of long-term risk probabilities and their gradients are critical for many stochastic safe control methods. However, computing such risk probabilities in real-time and in unseen or changing environments is challenging. Monte Carlo (MC) methods cannot accurately evaluate the probabilities and their gradients as an infinitesimal devisor can amplify the sampling noise. In this paper, we develop an efficient method to evaluate the probabilities of long-term risk and their gradients. The proposed method exploits the fact that long-term risk probability satisfies certain partial differential equations (PDEs), which characterize the neighboring relations between the probabilities, to integrate MC methods and physics-informed neural networks. We provide theoretical guarantees of the estimation error given certain choices of training configurations. Numerical results show the proposed method has better sample efficiency, generalizes well to unseen regions, and can adapt to systems with changing parameters. The proposed method can also accurately estimate the gradients of risk probabilities, which enables first- and second-order techniques on risk probabilities to be used for learning and control.
Authors: Jiarui Sun, Girish Chowdhary
Abstract: Stochastic Human Motion Prediction (HMP) aims to predict multiple possible future human pose sequences from observed ones. Most prior works learn motion distributions through encoding-decoding in the latent space, which does not preserve motion's spatial-temporal structure. While effective, these methods often require complex, multi-stage training and yield predictions that are inconsistent with the provided history and can be physically unrealistic. To address these issues, we propose CoMusion, a single-stage, end-to-end diffusion-based stochastic HMP framework. CoMusion is inspired from the insight that a smooth future pose initialization improves prediction performance, a strategy not previously utilized in stochastic models but evidenced in deterministic works. To generate such initialization, CoMusion's motion predictor starts with a Transformer-based network for initial reconstruction of corrupted motion. Then, a graph convolutional network (GCN) is employed to refine the prediction considering past observations in the discrete cosine transformation (DCT) space. Our method, facilitated by the Transformer-GCN module design and a proposed variance scheduler, excels in predicting accurate, realistic, and consistent motions, while maintaining appropriate diversity. Experimental results on benchmark datasets demonstrate that CoMusion surpasses prior methods across metrics, while demonstrating superior generation quality. Our Code is released at https://github.com/jsun57/CoMusion/ .
Authors: Yuqi Zhu, Xiaohan Wang, Jing Chen, Shuofei Qiao, Yixin Ou, Yunzhi Yao, Shumin Deng, Huajun Chen, Ningyu Zhang
Abstract: This paper presents an exhaustive quantitative and qualitative evaluation of Large Language Models (LLMs) for Knowledge Graph (KG) construction and reasoning. We engage in experiments across eight diverse datasets, focusing on four representative tasks encompassing entity and relation extraction, event extraction, link prediction, and question-answering, thereby thoroughly exploring LLMs' performance in the domain of construction and inference. Empirically, our findings suggest that LLMs, represented by GPT-4, are more suited as inference assistants rather than few-shot information extractors. Specifically, while GPT-4 exhibits good performance in tasks related to KG construction, it excels further in reasoning tasks, surpassing fine-tuned models in certain cases. Moreover, our investigation extends to the potential generalization ability of LLMs for information extraction, leading to the proposition of a Virtual Knowledge Extraction task and the development of the corresponding VINE dataset. Based on these empirical findings, we further propose AutoKG, a multi-agent-based approach employing LLMs and external sources for KG construction and reasoning. We anticipate that this research can provide invaluable insights for future undertakings in the field of knowledge graphs. The code and datasets are in https://github.com/zjunlp/AutoKG.
Authors: Zeyu Bian, Chengchun Shi, Zhengling Qi, Lan Wang
Abstract: This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inhomogeneities", we propose a class of latent factor models for the reward and observation transition functions, under which we develop a general OPE framework that consists of both model-based and model-free approaches. To our knowledge, this is the first paper that develops statistically sound OPE methods in offline RL with double inhomogeneities. It contributes to a deeper understanding of OPE in environments, where standard RL assumptions are not met, and provides several practical approaches in these settings. We establish the theoretical properties of the proposed value estimators and empirically show that our approach outperforms competing methods that ignore either temporal nonstationarity or individual heterogeneity. Finally, we illustrate our method on a data set from the Medical Information Mart for Intensive Care.
Authors: Varsha Kishore, Chao Wan, Justin Lovelace, Yoav Artzi, Kilian Q. Weinberger
Abstract: Differentiable Search Index is a recently proposed paradigm for document retrieval, that encodes information about a corpus of documents within the parameters of a neural network and directly maps queries to corresponding documents. These models have achieved state-of-the-art performances for document retrieval across many benchmarks. These kinds of models have a significant limitation: it is not easy to add new documents after a model is trained. We propose IncDSI, a method to add documents in real time (about 20-50ms per document), without retraining the model on the entire dataset (or even parts thereof). Instead we formulate the addition of documents as a constrained optimization problem that makes minimal changes to the network parameters. Although orders of magnitude faster, our approach is competitive with re-training the model on the whole dataset and enables the development of document retrieval systems that can be updated with new information in real-time. Our code for IncDSI is available at https://github.com/varshakishore/IncDSI.
Authors: Mateusz Krawczyk, Jaros{\l}aw Paw{\l}owski, Maciej M. Ma\'ska, Katarzyna Roszak
Abstract: We build a machine learning model to detect correlations in a three-qubit system using a neural network trained in an unsupervised manner on randomly generated states. The network is forced to recognize separable states, and correlated states are detected as anomalies. Quite surprisingly, we find that the proposed detector performs much better at distinguishing a weaker form of quantum correlations, namely, the quantum discord, than entanglement. In fact, it has a tendency to grossly overestimate the set of entangled states even at the optimal threshold for entanglement detection, while it underestimates the set of discordant states to a much lesser extent. In order to illustrate the nature of states classified as quantum-correlated, we construct a diagram containing various types of states -- entangled, as well as separable, both discordant and non-discordant. We find that the near-zero value of the recognition loss reproduces the shape of the non-discordant separable states with high accuracy, especially considering the non-trivial shape of this set on the diagram. The network architecture is designed carefully: it preserves separability, and its output is equivariant with respect to qubit permutations. We show that the choice of architecture is important to get the highest detection accuracy, much better than for a baseline model that just utilizes a partial trace operation.
Authors: Zengjie Zhang, Jayden Hong, Amir Soufi Enayati, Homayoun Najjaran
Abstract: Reinforcement learning (RL) for motion planning of multi-degree-of-freedom robots still suffers from low efficiency in terms of slow training speed and poor generalizability. In this paper, we propose a novel RL-based robot motion planning framework that uses implicit behavior cloning (IBC) and dynamic movement primitive (DMP) to improve the training speed and generalizability of an off-policy RL agent. IBC utilizes human demonstration data to leverage the training speed of RL, and DMP serves as a heuristic model that transfers motion planning into a simpler planning space. To support this, we also create a human demonstration dataset using a pick-and-place experiment that can be used for similar studies. Comparison studies in simulation reveal the advantage of the proposed method over the conventional RL agents with faster training speed and higher scores. A real-robot experiment indicates the applicability of the proposed method to a simple assembly task. Our work provides a novel perspective on using motion primitives and human demonstration to leverage the performance of RL for robot applications.
Authors: Minji Kim, Seong Jin Lee, Bumsik Kim
Abstract: In machine learning applications, distribution shifts between training and target environments can lead to significant drops in model performance. This study investigates the impact of such shifts on binary classification models within the Real-Time Bidding (RTB) market context, where selection bias contributes to these shifts. To address this challenge, we apply the Exponential Tilt Reweighting Alignment (ExTRA) algorithm, proposed by Maity et al. (2023). This algorithm estimates importance weights for the empirical risk by considering both covariate and label distributions, without requiring target label information, by assuming a specific weight structure. The goal of this study is to estimate weights that correct for the distribution shifts in RTB model and to evaluate the efficiency of the proposed model using simulated real-world data.
Authors: Jie Huang, Wei Ping, Peng Xu, Mohammad Shoeybi, Kevin Chen-Chuan Chang, Bryan Catanzaro
Abstract: In this paper, we investigate the in-context learning ability of retrieval-augmented encoder-decoder language models. We first conduct a comprehensive analysis of existing models and identify their limitations in in-context learning, primarily due to a mismatch between pretraining and inference, as well as a restricted context length. To address these issues, we propose RAVEN, a model that combines retrieval-augmented masked language modeling and prefix language modeling. We further introduce Fusion-in-Context Learning to enhance the few-shot performance by enabling the model to leverage more in-context examples without requiring additional training. Through extensive experiments, we demonstrate that our simple yet effective design significantly improves performance, achieving results comparable to the most advanced language models in certain scenarios, despite having substantially fewer parameters. Our work underscores the potential of retrieval-augmented encoder-decoder language models for in-context learning and encourages further research in this direction.
Authors: Elvis Han Cui, Zizhao Zhang, Culsome Junwen Chen, Weng Kee Wong
Abstract: Nature-inspired metaheuristic algorithms are important components of artificial intelligence, and are increasingly used across disciplines to tackle various types of challenging optimization problems. This paper demonstrates the usefulness of such algorithms for solving a variety of challenging optimization problems in statistics using a nature-inspired metaheuristic algorithm called competitive swarm optimizer with mutated agents (CSO-MA). This algorithm was proposed by one of the authors and its superior performance relative to many of its competitors had been demonstrated in earlier work and again in this paper. The main goal of this paper is to show a typical nature-inspired metaheuristic algorithmi, like CSO-MA, is efficient for tackling many different types of optimization problems in statistics. Our applications are new and include finding maximum likelihood estimates of parameters in a single cell generalized trend model to study pseudotime in bioinformatics, estimating parameters in the commonly used Rasch model in education research, finding M-estimates for a Cox regression in a Markov renewal model, performing matrix completion tasks to impute missing data for a two compartment model, and selecting variables optimally in an ecology problem in China. To further demonstrate the flexibility of metaheuristics, we also find an optimal design for a car refueling experiment in the auto industry using a logistic model with multiple interacting factors. In addition, we show that metaheuristics can sometimes outperform optimization algorithms commonly used in statistics.
Authors: Shokirbek Shermukhamedov, Dilorom Mamurjonova, Michael Probst
Abstract: We introduce the elEmBERT model for chemical classification tasks. It is based on deep learning techniques, such as a multilayer encoder architecture. We demonstrate the opportunities offered by our approach on sets of organic, inorganic and crystalline compounds. In particular, we developed and tested the model using the Matbench and Moleculenet benchmarks, which include crystal properties and drug design-related benchmarks. We also conduct an analysis of vector representations of chemical compounds, shedding light on the underlying patterns in structural data. Our model exhibits exceptional predictive capabilities and proves universally applicable to molecular and material datasets. For instance, on the Tox21 dataset, we achieved an average precision of 96%, surpassing the previously best result by 10%.
Authors: Rafael-Edy Menadil, Mariana-Iuliana Georgescu, Radu Tudor Ionescu
Abstract: Learning Using Privileged Information is a particular type of knowledge distillation where the teacher model benefits from an additional data representation during training, called privileged information, improving the student model, which does not see the extra representation. However, privileged information is rarely available in practice. To this end, we propose a text classification framework that harnesses text-to-image diffusion models to generate artificial privileged information. The generated images and the original text samples are further used to train multimodal teacher models based on state-of-the-art transformer-based architectures. Finally, the knowledge from multimodal teachers is distilled into a text-based (unimodal) student. Hence, by employing a generative model to produce synthetic data as privileged information, we guide the training of the student model. Our framework, called Learning Using Generated Privileged Information (LUGPI), yields noticeable performance gains on four text classification data sets, demonstrating its potential in text classification without any additional cost during inference.
Authors: Zeyuan Song, Zheyu Jiang
Abstract: Root-zone soil moisture monitoring is essential for sensor-based smart irrigation and agricultural drought prevention. Modeling the spatiotemporal water flow dynamics in porous media such as soil is typically achieved by solving an agro-hydrological model, the most important of which being the Richards equation. In this paper, we present a novel data-driven solution algorithm named the DRW (Data-driven global Random Walk) algorithm, which holistically integrates adaptive linearization scheme, neural networks, and global random walk in a finite volume discretization framework. We discuss the need and benefits of introducing these components to achieve synergistic improvements in solution accuracy and numerical stability. We show that the DRW algorithm can accurately solve $n$-dimensional Richards equation with guaranteed convergence under reasonable assumptions. Through examples, we also demonstrate that the DRW algorithm can better preserve the underlying physics and mass conservation of the Richards equation compared to state-of-the-art solution algorithms and commercial solver.
Authors: Changhe Chen, Mozhgan Pourkeshavarz, Amir Rasouli
Abstract: Benchmarking is a common method for evaluating trajectory prediction models for autonomous driving. Existing benchmarks rely on datasets, which are biased towards more common scenarios, such as cruising, and distance-based metrics that are computed by averaging over all scenarios. Following such a regiment provides a little insight into the properties of the models both in terms of how well they can handle different scenarios and how admissible and diverse their outputs are. There exist a number of complementary metrics designed to measure the admissibility and diversity of trajectories, however, they suffer from biases, such as length of trajectories. In this paper, we propose a new benChmarking paRadIgm for evaluaTing trajEctoRy predIction Approaches (CRITERIA). Particularly, we propose 1) a method for extracting driving scenarios at varying levels of specificity according to the structure of the roads, models' performance, and data properties for fine-grained ranking of prediction models; 2) A set of new bias-free metrics for measuring diversity, by incorporating the characteristics of a given scenario, and admissibility, by considering the structure of roads and kinematic compliancy, motivated by real-world driving constraints. 3) Using the proposed benchmark, we conduct extensive experimentation on a representative set of the prediction models using the large scale Argoverse dataset. We show that the proposed benchmark can produce a more accurate ranking of the models and serve as a means of characterizing their behavior. We further present ablation studies to highlight contributions of different elements that are used to compute the proposed metrics.
Authors: Tianjiao Li, Guanghui Lan
Abstract: Line search (or backtracking) procedures have been widely employed into first-order methods for solving convex optimization problems, especially those with unknown problem parameters (e.g., Lipschitz constant). In this paper, we show that line search is superfluous in attaining the optimal rate of convergence for solving a convex optimization problem whose parameters are not given a priori. In particular, we present a novel accelerated gradient descent type algorithm called auto-conditioned fast gradient method (AC-FGM) that can achieve an optimal $\mathcal{O}(1/k^2)$ rate of convergence for smooth convex optimization without requiring the estimate of a global Lipschitz constant or the employment of line search procedures. We then extend AC-FGM to solve convex optimization problems with H\"{o}lder continuous gradients and show that it automatically achieves the optimal rates of convergence uniformly for all problem classes with the desired accuracy of the solution as the only input. Finally, we report some encouraging numerical results that demonstrate the advantages of AC-FGM over the previously developed parameter-free methods for convex optimization.
Authors: Benjamin Feuer, Yurong Liu, Chinmay Hegde, Juliana Freire
Abstract: Existing deep-learning approaches to semantic column type annotation (CTA) have important shortcomings: they rely on semantic types which are fixed at training time; require a large number of training samples per type and incur large run-time inference costs; and their performance can degrade when evaluated on novel datasets, even when types remain constant. Large language models have exhibited strong zero-shot classification performance on a wide range of tasks and in this paper we explore their use for CTA. We introduce ArcheType, a simple, practical method for context sampling, prompt serialization, model querying, and label remapping, which enables large language models to solve CTA problems in a fully zero-shot manner. We ablate each component of our method separately, and establish that improvements to context sampling and label remapping provide the most consistent gains. ArcheType establishes a new state-of-the-art performance on zero-shot CTA benchmarks (including three new domain-specific benchmarks which we release along with this paper), and when used in conjunction with classical CTA techniques, it outperforms a SOTA DoDuo model on the fine-tuned SOTAB benchmark. Our code is available at https://github.com/penfever/ArcheType.
Authors: Wenqian Xing, Jungho Lee, Chong Liu, Shixiang Zhu
Abstract: Black-box optimization (BBO) has become increasingly relevant for tackling complex decision-making problems, especially in public policy domains such as police redistricting. However, its broader application in public policymaking is hindered by the complexity of defining feasible regions and the high-dimensionality of decisions. This paper introduces a novel BBO framework, termed as the Conditional And Generative Black-box Optimization (CageBO). This approach leverages a conditional variational autoencoder to learn the distribution of feasible decisions, enabling a two-way mapping between the original decision space and a simplified, constraint-free latent space. The CageBO efficiently handles the implicit constraints often found in public policy applications, allowing for optimization in the latent space while evaluating objectives in the original space. We validate our method through a case study on large-scale police redistricting problems in Atlanta, Georgia. Our results reveal that our CageBO offers notable improvements in performance and efficiency compared to the baselines.
Authors: Xiaochen Wang, Xiao Xiao, Ruhan Zhang, Xuan Zhang, Taesik Na, Tejaswi Tenneti, Haixun Wang, Fenglong Ma
Abstract: Efficient and accurate product relevance assessment is critical for user experiences and business success. Training a proficient relevance assessment model requires high-quality query-product pairs, often obtained through negative sampling strategies. Unfortunately, current methods introduce pooling bias by mistakenly sampling false negatives, diminishing performance and business impact. To address this, we present Bias-mitigating Hard Negative Sampling (BHNS), a novel negative sampling strategy tailored to identify and adjust for false negatives, building upon our original False Negative Estimation algorithm. Our experiments in the Instacart search setting confirm BHNS as effective for practical e-commerce use. Furthermore, comparative analyses on public dataset showcase its domain-agnostic potential for diverse applications.
Authors: Shumin Deng, Ningyu Zhang, Nay Oo, Bryan Hooi
Abstract: Large Language Models (LLMs) employing Chain-of-Thought (CoT) prompting have broadened the scope for improving multi-step reasoning capabilities. We generally divide multi-step reasoning into two phases: path generation to generate the reasoning path(s); and answer calibration post-processing the reasoning path(s) to obtain a final answer. However, the existing literature lacks systematic analysis on different answer calibration approaches. In this paper, we summarize the taxonomy of recent answer calibration techniques and break them down into step-level and path-level strategies. We then conduct a thorough evaluation on these strategies from a unified view, systematically scrutinizing step-level and path-level answer calibration across multiple paths. Experimental results reveal that integrating the dominance of both strategies tends to derive optimal outcomes. Our study holds the potential to illuminate key insights for optimizing multi-step reasoning with answer calibration.
Authors: Xiaoyue Mi, Fan Tang, Yepeng Weng, Danding Wang, Juan Cao, Sheng Tang, Peng Li, Yang Liu
Abstract: Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i.e., accuracy on natural samples has reduced significantly. In this study, we reveal that natural accuracy degradation is highly related to the disruption of the natural sample topology in the representation space by quantitative and qualitative experiments. Based on this observation, we propose Topology-pReserving Adversarial traINing (TRAIN) to alleviate the problem by preserving the topology structure of natural samples from a standard model trained only on natural samples during adversarial training. As an additional regularization, our method can be combined with various popular adversarial training algorithms, taking advantage of both sides. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny ImageNet show that our proposed method achieves consistent and significant improvements over various strong baselines in most cases. Specifically, without additional data, TRAIN achieves up to 8.86% improvement in natural accuracy and 6.33% improvement in robust accuracy.
Authors: Fengfan Zhou, Qianyu Zhou, Bangjie Yin, Hui Zheng, Xuequan Lu, Lizhuang Ma, Hefei Ling
Abstract: Face Recognition (FR) systems can be easily deceived by adversarial examples that manipulate benign face images through imperceptible perturbations. Adversarial attacks on FR encompass two types: impersonation (targeted) attacks and dodging (untargeted) attacks. Previous methods often achieve a successful impersonation attack on FR, however, it does not necessarily guarantee a successful dodging attack on FR in the black-box setting. In this paper, our key insight is that the generation of adversarial examples should perform both impersonation and dodging attacks simultaneously. To this end, we propose a novel attack method termed as Adversarial Pruning (Adv-Pruning), to fine-tune existing adversarial examples to enhance their dodging capabilities while preserving their impersonation capabilities. Adv-Pruning consists of Priming, Pruning, and Restoration stages. Concretely, we propose Adversarial Priority Quantification to measure the region-wise priority of original adversarial perturbations, identifying and releasing those with minimal impact on absolute model output variances. Then, Biased Gradient Adaptation is presented to adapt the adversarial examples to traverse the decision boundaries of both the attacker and victim by adding perturbations favoring dodging attacks on the vacated regions, preserving the prioritized features of the original perturbations while boosting dodging performance. As a result, we can maintain the impersonation capabilities of original adversarial examples while effectively enhancing dodging capabilities. Comprehensive experiments demonstrate the superiority of our method compared with state-of-the-art adversarial attack methods.
Authors: Pascal Pernot
Abstract: Average calibration of the (variance-based) prediction uncertainties of machine learning regression tasks can be tested in two ways: one is to estimate the calibration error (CE) as the difference between the mean absolute error (MSE) and the mean variance (MV); the alternative is to compare the mean squared z-scores (ZMS) to 1. The problem is that both approaches might lead to different conclusions, as illustrated in this study for an ensemble of datasets from the recent machine learning uncertainty quantification (ML-UQ) literature. It is shown that the estimation of MV, MSE and their confidence intervals becomes unreliable for heavy-tailed uncertainty and error distributions, which seems to be a frequent feature of ML-UQ datasets. By contrast, the ZMS statistic is less sensitive and offers the most reliable approach in this context, still acknowledging that datasets with heavy-tailed z-scores distributions should be considered with great care. Unfortunately, the same problem is expected to affect also conditional calibrations statistics, such as the popular ENCE, and very likely post-hoc calibration methods based on similar statistics. Several solutions to circumvent the outlined problems are proposed.
Authors: Cristiano M. Garcia, Alceu de Souza Britto Jr, Jean Paul Barddal
Abstract: Initially supported by Twitter, hashtags are now used on several social media platforms. Hashtags are helpful for tagging, tracking, and grouping posts on similar topics. In this paper, based on a hashtag stream regarding the hashtag #mybodymychoice, we analyze hashtag drifts over time using concepts from graph analysis and textual data streams using the Girvan-Newman method to uncover hashtag communities in annual snapshots between 2018 and 2022. In addition, we offer insights about some correlated hashtags found in the study. Our approach can be useful for monitoring changes over time in opinions and sentiment patterns about an entity on social media. Even though the hashtag #mybodymychoice was initially coupled with women's rights, abortion, and bodily autonomy, we observe that it suffered drifts during the studied period across topics such as drug legalization, vaccination, political protests, war, and civil rights. The year 2021 was the most significant drifting year, in which the communities detected and their respective sizes suggest that #mybodymychoice had a significant drift to vaccination and Covid-19-related topics.
Authors: Johnny Tian-Zheng Wei, Ryan Yixiang Wang, Robin Jia
Abstract: Detecting whether copyright holders' works were used in LLM pretraining is poised to be an important problem. This work proposes using data watermarks to enable principled detection with only black-box model access, provided that the rightholder contributed multiple training documents and watermarked them before public release. By applying a randomly sampled data watermark, detection can be framed as hypothesis testing, which provides guarantees on the false detection rate. We study two watermarks: one that inserts random sequences, and another that randomly substitutes characters with Unicode lookalikes. We first show how three aspects of watermark design -- watermark length, number of duplications, and interference -- affect the power of the hypothesis test. Next, we study how a watermark's detection strength changes under model and dataset scaling: while increasing the dataset size decreases the strength of the watermark, watermarks remain strong if the model size also increases. Finally, we view SHA hashes as natural watermarks and show that we can robustly detect hashes from BLOOM-176B's training data, as long as they occurred at least 90 times. Together, our results point towards a promising future for data watermarks in real world use.
Authors: Tao Li, Kim Hammar, Rolf Stadler, Quanyan Zhu
Abstract: Asymmetric information stochastic games (AISGs) arise in many complex socio-technical systems, such as cyber-physical systems and IT infrastructures. Existing computational methods for AISGs are primarily offline and can not adapt to equilibrium deviations. Further, current methods are limited to particular information structures to avoid belief hierarchies. Considering these limitations, we propose conjectural online learning (COL), an online learning method under generic information structures in AISGs. COL uses a forecaster-actor-critic (FAC) architecture, where subjective forecasts are used to conjecture the opponents' strategies within a lookahead horizon, and Bayesian learning is used to calibrate the conjectures. To adapt strategies to nonstationary environments based on information feedback, COL uses online rollout with cost function approximation (actor-critic). We prove that the conjectures produced by COL are asymptotically consistent with the information feedback in the sense of a relaxed Bayesian consistency. We also prove that the empirical strategy profile induced by COL converges to the Berk-Nash equilibrium, a solution concept characterizing rationality under subjectivity. Experimental results from an intrusion response use case demonstrate COL's {faster convergence} over state-of-the-art reinforcement learning methods against nonstationary attacks.
Authors: Tian Gao, Soroush Nasiriany, Huihan Liu, Quantao Yang, Yuke Zhu
Abstract: Imitation learning has shown great potential for enabling robots to acquire complex manipulation behaviors. However, these algorithms suffer from high sample complexity in long-horizon tasks, where compounding errors accumulate over the task horizons. We present PRIME (PRimitive-based IMitation with data Efficiency), a behavior primitive-based framework designed for improving the data efficiency of imitation learning. PRIME scaffolds robot tasks by decomposing task demonstrations into primitive sequences, followed by learning a high-level control policy to sequence primitives through imitation learning. Our experiments demonstrate that PRIME achieves a significant performance improvement in multi-stage manipulation tasks, with 10-34% higher success rates in simulation over state-of-the-art baselines and 20-48% on physical hardware.
Authors: Shuhei Watanabe, Neeratyoy Mallik, Edward Bergman, Frank Hutter
Abstract: While deep learning has celebrated many successes, its results often hinge on the meticulous selection of hyperparameters (HPs). However, the time-consuming nature of deep learning training makes HP optimization (HPO) a costly endeavor, slowing down the development of efficient HPO tools. While zero-cost benchmarks, which provide performance and runtime without actual training, offer a solution for non-parallel setups, they fall short in parallel setups as each worker must communicate its queried runtime to return its evaluation in the exact order. This work addresses this challenge by introducing a user-friendly Python package that facilitates efficient parallel HPO with zero-cost benchmarks. Our approach calculates the exact return order based on the information stored in file system, eliminating the need for long waiting times and enabling much faster HPO evaluations. We first verify the correctness of our approach through extensive testing and the experiments with 6 popular HPO libraries show its applicability to diverse libraries and its ability to achieve over 1000x speedup compared to a traditional approach. Our package can be installed via pip install mfhpo-simulator.
Authors: Yakir Yehuda, Itzik Malkiel, Oren Barkan, Jonathan Weill, Royi Ronen, Noam Koenigstein
Abstract: Despite the many advances of Large Language Models (LLMs) and their unprecedented rapid evolution, their impact and integration into every facet of our daily lives is limited due to various reasons. One critical factor hindering their widespread adoption is the occurrence of hallucinations, where LLMs invent answers that sound realistic, yet drift away from factual truth. In this paper, we present a novel method for detecting hallucinations in large language models, which tackles a critical issue in the adoption of these models in various real-world scenarios. Through extensive evaluations across multiple datasets and LLMs, including Llama-2, we study the hallucination levels of various recent LLMs and demonstrate the effectiveness of our method to automatically detect them. Notably, we observe up to 87% hallucinations for Llama-2 in a specific experiment, where our method achieves a Balanced Accuracy of 81%, all without relying on external knowledge.
Authors: Dovile Juodelyte, Yucheng Lu, Amelia Jim\'enez-S\'anchez, Sabrina Bottazzi, Enzo Ferrante, Veronika Cheplygina
Abstract: Transfer learning has become an essential part of medical imaging classification algorithms, often leveraging ImageNet weights. The domain shift from natural to medical images has prompted alternatives such as RadImageNet, often showing comparable classification performance. However, it remains unclear whether the performance gains from transfer learning stem from improved generalization or shortcut learning. To address this, we conceptualize confounders by introducing the Medical Imaging Contextualized Confounder Taxonomy (MICCAT) and investigate a range of confounders across it -- whether synthetic or sampled from the data -- using two public chest X-ray and CT datasets. We show that ImageNet and RadImageNet achieve comparable classification performance, yet ImageNet is much more prone to overfitting to confounders. We recommend that researchers using ImageNet-pretrained models reexamine their model robustness by conducting similar experiments. Our code and experiments are available at https://github.com/DovileDo/source-matters.
Authors: Sukhbinder Singh, Saeed S. Jahromi, Roman Orus
Abstract: Convolutional neural networks (CNNs) are one of the most widely used neural network architectures, showcasing state-of-the-art performance in computer vision tasks. Although larger CNNs generally exhibit higher accuracy, their size can be effectively reduced by ``tensorization'' while maintaining accuracy, namely, replacing the convolution kernels with compact decompositions such as Tucker, Canonical Polyadic decompositions, or quantum-inspired decompositions such as matrix product states, and directly training the factors in the decompositions to bias the learning towards low-rank decompositions. But why doesn't tensorization seem to impact the accuracy adversely? We explore this by assessing how \textit{truncating} the convolution kernels of \textit{dense} (untensorized) CNNs impact their accuracy. Specifically, we truncated the kernels of (i) a vanilla four-layer CNN and (ii) ResNet-50 pre-trained for image classification on CIFAR-10 and CIFAR-100 datasets. We found that kernels (especially those inside deeper layers) could often be truncated along several cuts resulting in significant loss in kernel norm but not in classification accuracy. This suggests that such ``correlation compression'' (underlying tensorization) is an intrinsic feature of how information is encoded in dense CNNs. We also found that aggressively truncated models could often recover the pre-truncation accuracy after only a few epochs of re-training, suggesting that compressing the internal correlations of convolution layers does not often transport the model to a worse minimum. Our results can be applied to tensorize and compress CNN models more effectively.
Authors: Renrui Zhang, Dongzhi Jiang, Yichi Zhang, Haokun Lin, Ziyu Guo, Pengshuo Qiu, Aojun Zhou, Pan Lu, Kai-Wei Chang, Peng Gao, Hongsheng Li
Abstract: The remarkable progress of Multi-modal Large Language Models (MLLMs) has garnered unparalleled attention, due to their superior performance in visual contexts. However, their capabilities in visual math problem-solving remain insufficiently evaluated and understood. We investigate current benchmarks to incorporate excessive visual content within textual questions, which potentially assist MLLMs in deducing answers without truly interpreting the input diagrams. To this end, we introduce MathVerse, an all-around visual math benchmark designed for an equitable and in-depth evaluation of MLLMs. We meticulously collect 2,612 high-quality, multi-subject math problems with diagrams from publicly available sources. Each problem is then transformed by human annotators into six distinct versions, each offering varying degrees of information content in multi-modality, contributing to 15K test samples in total. This approach allows MathVerse to comprehensively assess whether and how much MLLMs can truly understand the visual diagrams for mathematical reasoning. In addition, we propose a Chain-of-Thought (CoT) evaluation strategy for a fine-grained assessment of the output answers. Rather than naively judging True or False, we employ GPT-4(V) to adaptively extract crucial reasoning steps, and then score each step with detailed error analysis, which can reveal the intermediate CoT reasoning quality by MLLMs. We hope the MathVerse benchmark may provide unique insights to guide the future development of MLLMs. Project page: https://mathverse-cuhk.github.io
Authors: Yue Ding, Sen Yan, Maqsood Hussain Shah, Hongyuan Fang, Ji Li, Mingming Liu
Abstract: The escalating challenges of traffic congestion and environmental degradation underscore the critical importance of embracing E-Mobility solutions in urban spaces. In particular, micro E-Mobility tools such as E-scooters and E-bikes, play a pivotal role in this transition, offering sustainable alternatives for urban commuters. However, the energy consumption patterns for these tools are a critical aspect that impacts their effectiveness in real-world scenarios and is essential for trip planning and boosting user confidence in using these. To this effect, recent studies have utilised physical models customised for specific mobility tools and conditions, but these models struggle with generalization and effectiveness in real-world scenarios due to a notable absence of open datasets for thorough model evaluation and verification. To fill this gap, our work presents an open dataset, collected in Dublin, Ireland, specifically designed for energy modelling research related to E-Scooters and E-Bikes. Furthermore, we provide a comprehensive analysis of energy consumption modelling based on the dataset using a set of representative machine learning algorithms and compare their performance against the contemporary mathematical models as a baseline. Our results demonstrate a notable advantage for data-driven models in comparison to the corresponding mathematical models for estimating energy consumption. Specifically, data-driven models outperform physical models in accuracy by up to 83.83% for E-Bikes and 82.16% for E-Scooters based on an in-depth analysis of the dataset under certain assumptions.
Authors: Joel Ruben Antony Moniz, Soundarya Krishnan, Melis Ozyildirim, Prathamesh Saraf, Halim Cagri Ates, Yuan Zhang, Hong Yu
Abstract: Reference resolution is an important problem, one that is essential to understand and successfully handle context of different kinds. This context includes both previous turns and context that pertains to non-conversational entities, such as entities on the user's screen or those running in the background. While LLMs have been shown to be extremely powerful for a variety of tasks, their use in reference resolution, particularly for non-conversational entities, remains underutilized. This paper demonstrates how LLMs can be used to create an extremely effective system to resolve references of various types, by showing how reference resolution can be converted into a language modeling problem, despite involving forms of entities like those on screen that are not traditionally conducive to being reduced to a text-only modality. We demonstrate large improvements over an existing system with similar functionality across different types of references, with our smallest model obtaining absolute gains of over 5% for on-screen references. We also benchmark against GPT-3.5 and GPT-4, with our smallest model achieving performance comparable to that of GPT-4, and our larger models substantially outperforming it.
Authors: Alexander Nemecek, Yuzhou Jiang, Erman Ayday
Abstract: The indistinguishability of text generated by large language models (LLMs) from human-generated text poses significant challenges. Watermarking algorithms are potential solutions by embedding detectable signatures within LLM-generated outputs. However, current watermarking schemes lack robustness to a range of attacks such as text substitution or manipulation, undermining their reliability. This paper proposes a novel topic-based watermarking algorithm for LLMs, designed to enhance the robustness of watermarking in LLMs. Our approach leverages the topics extracted from input prompts or outputs of non-watermarked LLMs in the generation process of watermarked text. We dynamically utilize token lists on identified topics and adjust token sampling weights accordingly. By using these topic-specific token biases, we embed a topic-sensitive watermarking into the generated text. We outline the theoretical framework of our topic-based watermarking algorithm and discuss its potential advantages in various scenarios. Additionally, we explore a comprehensive range of attacks against watermarking algorithms, including discrete alterations, paraphrasing, and tokenizations. We demonstrate that our proposed watermarking scheme classifies various watermarked text topics with 99.99% confidence and outperforms existing algorithms in terms of z-score robustness and the feasibility of modeling text degradation by potential attackers, while considering the trade-offs between the benefits and losses of watermarking LLM-generated text.
Authors: Baoxing Jiang, Yujie Wan, Shenggen Ju
Abstract: Few-Shot Aspect-Based Sentiment Analysis (FSABSA) is an indispensable and highly challenging task in natural language processing. However, methods based on Pre-trained Language Models (PLMs) struggle to accommodate multiple sub-tasks, and methods based on Generative Pre-trained Transformers (GPTs) perform poorly. To address the above issues, the paper designs a Heuristic-enhanced Candidates Selection (HCS) strategy and further proposes All in One (AiO) model based on it. The model works in a two-stage, which simultaneously accommodates the accuracy of PLMs and the generalization capability of GPTs. Specifically, in the first stage, a backbone model based on PLMs generates rough heuristic candidates for the input sentence. In the second stage, AiO leverages LLMs' contextual learning capabilities to generate precise predictions. The study conducted comprehensive comparative and ablation experiments on five benchmark datasets. The experimental results demonstrate that the proposed model can better adapt to multiple sub-tasks, and also outperforms the methods that directly utilize GPTs.
Authors: Youngbin Lee, Yejin Kim, Javier Sanz-Cruzado, Richard McCreadie, Yongjae Lee
Abstract: Recommender systems can be helpful for individuals to make well-informed decisions in complex financial markets. While many studies have focused on predicting stock prices, even advanced models fall short of accurately forecasting them. Additionally, previous studies indicate that individual investors often disregard established investment theories, favoring their personal preferences instead. This presents a challenge for stock recommendation systems, which must not only provide strong investment performance but also respect these individual preferences. To create effective stock recommender systems, three critical elements must be incorporated: 1) individual preferences, 2) portfolio diversification, and 3) the temporal dynamics of the first two. In response, we propose a new model, Portfolio Temporal Graph Network Recommender, PfoTGNRec, which can handle time-varying collaborative signals and incorporates diversification-enhancing sampling. On real-world individual trading data, our approach demonstrates superior performance compared to state-of-the-art baselines, including cutting-edge dynamic embedding models and existing stock recommendation models. Indeed, we show that PfoTGNRec is an effective solution that can balance customer preferences with the need to suggest portfolios with high Return-on-Investment. The source code and data are available at https://anonymous.4open.science/r/ICAIF2024-E23E.
Authors: Runtao Liu, Ashkan Khakzar, Jindong Gu, Qifeng Chen, Philip Torr, Fabio Pizzati
Abstract: With the ability to generate high-quality images, text-to-image (T2I) models can be exploited for creating inappropriate content. To prevent misuse, existing safety measures are either based on text blacklists, which can be easily circumvented, or harmful content classification, requiring large datasets for training and offering low flexibility. Hence, we propose Latent Guard, a framework designed to improve safety measures in text-to-image generation. Inspired by blacklist-based approaches, Latent Guard learns a latent space on top of the T2I model's text encoder, where it is possible to check the presence of harmful concepts in the input text embeddings. Our proposed framework is composed of a data generation pipeline specific to the task using large language models, ad-hoc architectural components, and a contrastive learning strategy to benefit from the generated data. The effectiveness of our method is verified on three datasets and against four baselines. Code and data will be shared at https://latentguard.github.io/.
Authors: Yuzhen Huang, Jinghan Zhang, Zifei Shan, Junxian He
Abstract: There is a belief that learning to compress well will lead to intelligence. Recently, language modeling has been shown to be equivalent to compression, which offers a compelling rationale for the success of large language models (LLMs): the development of more advanced language models is essentially enhancing compression which facilitates intelligence. Despite such appealing discussions, little empirical evidence is present for the interplay between compression and intelligence. In this work, we examine their relationship in the context of LLMs, treating LLMs as data compressors. Given the abstract concept of "intelligence", we adopt the average downstream benchmark scores as a surrogate, specifically targeting intelligence related to knowledge and commonsense, coding, and mathematical reasoning. Across 12 benchmarks, our study brings together 31 public LLMs that originate from diverse organizations. Remarkably, we find that LLMs' intelligence -- reflected by average benchmark scores -- almost linearly correlates with their ability to compress external text corpora. These results provide concrete evidence supporting the belief that superior compression indicates greater intelligence. Furthermore, our findings suggest that compression efficiency, as an unsupervised metric derived from raw text corpora, serves as a reliable evaluation measure that is linearly associated with the model capabilities. We open-source our compression datasets as well as our data collection pipelines to facilitate future researchers to assess compression properly.
Authors: Jun Wang, Yufei Cui, Yu Mao, Nan Guan, Chun Jason Xue
Abstract: Pre-processing whole slide images (WSIs) can impact classification performance. Our study shows that using fixed hyper-parameters for pre-processing out-of-domain WSIs can significantly degrade performance. Therefore, it is critical to search domain-specific hyper-parameters during inference. However, searching for an optimal parameter set is time-consuming. To overcome this, we propose SSAPT, a novel Similarity-based Simulated Annealing approach for fast parameter tuning to enhance inference performance on out-of-domain data. The proposed SSAPT achieves 5\% to 50\% improvement in accuracy with $\times5$ times faster parameter searching speed on average.
Authors: Md Adnan Arefeen, Biplob Debnath, Md Yusuf Sarwar Uddin, Srimat Chakradhar
Abstract: Retrieval-augmented generation (RAG) systems combine the strengths of language generation and information retrieval to power many real-world applications like chatbots. Use of RAG for understanding of videos is appealing but there are two critical limitations. One-time, upfront conversion of all content in large corpus of videos into text descriptions entails high processing times. Also, not all information in the rich video data is typically captured in the text descriptions. Since user queries are not known apriori, developing a system for video to text conversion and interactive querying of video data is challenging. To address these limitations, we propose an incremental RAG system called iRAG, which augments RAG with a novel incremental workflow to enable interactive querying of a large corpus of videos. Unlike traditional RAG, iRAG quickly indexes large repositories of videos, and in the incremental workflow, it uses the index to opportunistically extract more details from select portions of the videos to retrieve context relevant to an interactive user query. Such an incremental workflow avoids long video to text conversion times, and overcomes information loss issues due to conversion of video to text, by doing on-demand query-specific extraction of details in video data. This ensures high quality of responses to interactive user queries that are often not known apriori. To the best of our knowledge, iRAG is the first system to augment RAG with an incremental workflow to support efficient interactive querying of a large corpus of videos. Experimental results on real-world datasets demonstrate 23x to 25x faster video to text ingestion, while ensuring that latency and quality of responses to interactive user queries is comparable to responses from a traditional RAG where all video data is converted to text upfront before any user querying.
Authors: Myeung Suk Oh, Anindya Bijoy Das, Taejoon Kim, David J. Love, Christopher G. Brinton
Abstract: Recently, deep learning approaches have provided solutions to difficult problems in wireless positioning (WP). Although these WP algorithms have attained excellent and consistent performance against complex channel environments, the computational complexity coming from processing high-dimensional features can be prohibitive for mobile applications. In this work, we design a novel positioning neural network (P-NN) that utilizes the minimum description features to substantially reduce the complexity of deep learning-based WP. P-NN's feature selection strategy is based on maximum power measurements and their temporal locations to convey information needed to conduct WP. We improve P-NN's learning ability by intelligently processing two different types of inputs: sparse image and measurement matrices. Specifically, we implement a self-attention layer to reinforce the training ability of our network. We also develop a technique to adapt feature space size, optimizing over the expected information gain and the classification capability quantified with information-theoretic measures on signal bin selection. Numerical results show that P-NN achieves a significant advantage in performance-complexity tradeoff over deep learning baselines that leverage the full power delay profile (PDP). In particular, we find that P-NN achieves a large improvement in performance for low SNR, as unnecessary measurements are discarded in our minimum description features.
Authors: Yifan Guo, Zhongqiang Ren, Chen Wang
Abstract: This paper considers a Min-Max Multiple Traveling Salesman Problem (MTSP), where the goal is to find a set of tours, one for each agent, to collectively visit all the cities while minimizing the length of the longest tour. Though MTSP has been widely studied, obtaining near-optimal solutions for large-scale problems is still challenging due to its NP-hardness. Recent efforts in data-driven methods face challenges of the need for hard-to-obtain supervision and issues with high variance in gradient estimations, leading to slow convergence and highly suboptimal solutions. We address these issues by reformulating MTSP as a bilevel optimization problem, using the concept of imperative learning (IL). This involves introducing an allocation network that decomposes the MTSP into multiple single-agent traveling salesman problems (TSPs). The longest tour from these TSP solutions is then used to self-supervise the allocation network, resulting in a new self-supervised, bilevel, end-to-end learning framework, which we refer to as imperative MTSP (iMTSP). Additionally, to tackle the high-variance gradient issues during the optimization, we introduce a control variate-based gradient estimation algorithm. Our experiments showed that these innovative designs enable our gradient estimator to converge 20% faster than the advanced reinforcement learning baseline and find up to 80% shorter tour length compared with Google OR-Tools MTSP solver, especially in large-scale problems (e.g. 1000 cities and 15 agents).
Authors: Zexuan Zhong, Mengzhou Xia, Danqi Chen, Mike Lewis
Abstract: Mixture-of-experts (MoE) models facilitate efficient scaling; however, training the router network introduces the challenge of optimizing a non-differentiable, discrete objective. Recently, a fully-differentiable MoE architecture, SMEAR, was proposed (Muqeeth et al., 2023), which softly merges experts in the parameter space; nevertheless, its effectiveness was only demonstrated in downstream fine-tuning on classification tasks. In this paper, we present Lory, the first approach that scales such architectures to autoregressive language model pre-training. Lory introduces two key techniques: (1) a causal segment routing strategy that achieves high efficiency for expert merging operations while preserving the autoregressive nature of language models; (2) a similarity-based data batching method that encourages expert specialization by grouping similar documents in training instances. We pre-train a series of Lory models on 150B tokens from scratch, with up to 32 experts and 30B (1.5B active) parameters. Experimental results show significant performance gains over parameter-matched dense models on both perplexity (+13.9%) and a variety of downstream tasks (+1.5%-11.1%). Despite segment-level routing, Lory models achieve competitive performance compared to state-of-the-art MoE models with token-level routing. We further demonstrate that the trained experts in Lory capture domain-level specialization without supervision. Our work highlights the potential of fully-differentiable MoE architectures for language model pre-training and advocates future research in this area.
Authors: Kris Sankaran
Abstract: Society's capacity for algorithmic problem-solving has never been greater. Artificial Intelligence is now applied across more domains than ever, a consequence of powerful abstractions, abundant data, and accessible software. As capabilities have expanded, so have risks, with models often deployed without fully understanding their potential impacts. Interpretable and interactive machine learning aims to make complex models more transparent and controllable, enhancing user agency. This review synthesizes key principles from the growing literature in this field. We first introduce precise vocabulary for discussing interpretability, like the distinction between glass box and explainable models. We then explore connections to classical statistical and design principles, like parsimony and the gulfs of interaction. Basic explainability techniques -- including learned embeddings, integrated gradients, and concept bottlenecks -- are illustrated with a simple case study. We also review criteria for objectively evaluating interpretability approaches. Throughout, we underscore the importance of considering audience goals when designing interactive data-driven systems. Finally, we outline open challenges and discuss the potential role of data science in addressing them. Code to reproduce all examples can be found at https://go.wisc.edu/3k1ewe.
Authors: Daniel Freedman, Eyal Rozenberg, Alex Bronstein
Abstract: A central problem in quantum mechanics involves solving the Electronic Schrodinger Equation for a molecule or material. The Variational Monte Carlo approach to this problem approximates a particular variational objective via sampling, and then optimizes this approximated objective over a chosen parameterized family of wavefunctions, known as the ansatz. Recently neural networks have been used as the ansatz, with accompanying success. However, sampling from such wavefunctions has required the use of a Markov Chain Monte Carlo approach, which is inherently inefficient. In this work, we propose a solution to this problem via an ansatz which is cheap to sample from, yet satisfies the requisite quantum mechanical properties. We prove that a normalizing flow using the following two essential ingredients satisfies our requirements: (a) a base distribution which is constructed from Determinantal Point Processes; (b) flow layers which are equivariant to a particular subgroup of the permutation group. We then show how to construct both continuous and discrete normalizing flows which satisfy the requisite equivariance. We further demonstrate the manner in which the non-smooth nature ("cusps") of the wavefunction may be captured, and how the framework may be generalized to provide induction across multiple molecules. The resulting theoretical framework entails an efficient approach to solving the Electronic Schrodinger Equation.
Authors: Wei Ji, Li Li, Zheqi Lv, Wenqiao Zhang, Mengze Li, Zhen Wan, Wenqiang Lei, Roger Zimmermann
Abstract: In our increasingly interconnected world, where intelligent devices continually amass copious personalized multi-modal data, a pressing need arises to deliver high-quality, personalized device-aware services. However, this endeavor presents a multifaceted challenge to prevailing artificial intelligence (AI) systems primarily rooted in the cloud. As these systems grapple with shifting data distributions between the cloud and devices, the traditional approach of fine-tuning-based adaptation (FTA) exists the following issues: the costly and time-consuming data annotation required by FTA and the looming risk of model overfitting. To surmount these challenges, we introduce a Universal On-Device Multi-modal Model Adaptation Framework, revolutionizing on-device model adaptation by striking a balance between efficiency and effectiveness. The framework features the Fast Domain Adaptor (FDA) hosted in the cloud, providing tailored parameters for the Lightweight Multi-modal Model on devices. To enhance adaptability across multi-modal tasks, the AnchorFrame Distribution Reasoner (ADR) minimizes communication costs. Our contributions, encapsulated in the Cloud-Device Collaboration Multi-modal Parameter Generation (CDC-MMPG) framework, represent a pioneering solution for on-Device Multi-modal Model Adaptation (DMMA). Extensive experiments validate the efficiency and effectiveness of our method, particularly in video question answering and retrieval tasks, driving forward the integration of intelligent devices into our daily lives.
Authors: Arvi Jonnarth, Ola Johansson, Michael Felsberg
Abstract: Sim-to-real transfer presents a difficult challenge, where models trained in simulation are to be deployed in the real world. The distribution shift between the two settings leads to biased representations of the dynamics, and thus to suboptimal predictions in the real-world environment. In this work, we tackle the challenge of sim-to-real transfer of reinforcement learning (RL) agents for coverage path planning (CPP). In CPP, the task is for a robot to find a path that covers every point of a confined area. Specifically, we consider the case where the environment is unknown, and the agent needs to plan the path online while mapping the environment. We bridge the sim-to-real gap through a semi-virtual environment, including a real robot and real-time aspects, while utilizing a simulated sensor and obstacles to enable environment randomization and automated episode resetting. We investigate what level of fine-tuning is needed for adapting to a realistic setting, comparing to an agent trained solely in simulation. We find that a high inference frequency allows first-order Markovian policies to transfer directly from simulation, while higher-order policies can be fine-tuned to further reduce the sim-to-real gap. Moreover, they can operate at a lower frequency, thus reducing computational requirements. In both cases, our approaches transfer state-of-the-art results from simulation to the real domain, where direct learning would take in the order of weeks with manual interaction, that is, it would be completely infeasible.
Authors: Cong Zeng, Shengkun Tang, Xianjun Yang, Yuanzhou Chen, Yiyou Sun, zhiqiang xu, Yao Li, Haifeng Chen, Wei Cheng, Dongkuan Xu
Abstract: The advent of Large Language Models (LLMs) has revolutionized text generation, producing outputs that closely mimic human writing. This blurring of lines between machine- and human-written text presents new challenges in distinguishing one from the other a task further complicated by the frequent updates and closed nature of leading proprietary LLMs. Traditional logits-based detection methods leverage surrogate models for identifying LLM-generated content when the exact logits are unavailable from black-box LLMs. However, these methods grapple with the misalignment between the distributions of the surrogate and the often undisclosed target models, leading to performance degradation, particularly with the introduction of new, closed-source models. Furthermore, while current methodologies are generally effective when the source model is identified, they falter in scenarios where the model version remains unknown, or the test set comprises outputs from various source models. To address these limitations, we present Distribution-Aligned LLMs Detection (DALD), an innovative framework that redefines the state-of-the-art performance in black-box text detection even without logits from source LLMs. DALD is designed to align the surrogate model's distribution with that of unknown target LLMs, ensuring enhanced detection capability and resilience against rapid model iterations with minimal training investment. By leveraging corpus samples from publicly accessible outputs of advanced models such as ChatGPT, GPT-4 and Claude-3, DALD fine-tunes surrogate models to synchronize with unknown source model distributions effectively.
Authors: Jo\~ao A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva, Carolina Scarton
Abstract: This work introduces EUvsDisinfo, a multilingual dataset of disinformation articles originating from pro-Kremlin outlets, along with trustworthy articles from credible / less biased sources. It is sourced directly from the debunk articles written by experts leading the EUvsDisinfo project. Our dataset is the largest to-date resource in terms of the overall number of articles and distinct languages. It also provides the largest topical and temporal coverage. Using this dataset, we investigate the dissemination of pro-Kremlin disinformation across different languages, uncovering language-specific patterns targeting certain disinformation topics. We further analyse the evolution of topic distribution over an eight-year period, noting a significant surge in disinformation content before the full-scale invasion of Ukraine in 2022. Lastly, we demonstrate the dataset's applicability in training models to effectively distinguish between disinformation and trustworthy content in multilingual settings.
Authors: Wentao Shi, Mengqi Yuan, Junkang Wu, Qifan Wang, Fuli Feng
Abstract: Adapting Large Language Models (LLMs) for agent tasks is critical in developing language agents. Direct Preference Optimization (DPO) is a promising technique for this adaptation with the alleviation of compounding errors, offering a means to directly optimize Reinforcement Learning (RL) objectives. However, applying DPO to multi-turn tasks presents challenges due to the inability to cancel the partition function. Overcoming this obstacle involves making the partition function independent of the current state and addressing length disparities between preferred and dis-preferred trajectories. In this light, we replace the policy constraint with the state-action occupancy measure constraint in the RL objective and add length normalization to the Bradley-Terry model, yielding a novel loss function named DMPO for multi-turn agent tasks with theoretical explanations. Extensive experiments on three multi-turn agent task datasets confirm the effectiveness and superiority of the DMPO loss.
Authors: Qiuhao Lu, Rui Li, Andrew Wen, Jinlian Wang, Liwei Wang, Hongfang Liu
Abstract: Large Language Models (LLMs) have revolutionized various sectors, including healthcare where they are employed in diverse applications. Their utility is particularly significant in the context of rare diseases, where data scarcity, complexity, and specificity pose considerable challenges. In the clinical domain, Named Entity Recognition (NER) stands out as an essential task and it plays a crucial role in extracting relevant information from clinical texts. Despite the promise of LLMs, current research mostly concentrates on document-level NER, identifying entities in a more general context across entire documents, without extracting their precise location. Additionally, efforts have been directed towards adapting ChatGPT for token-level NER. However, there is a significant research gap when it comes to employing token-level NER for clinical texts, especially with the use of local open-source LLMs. This study aims to bridge this gap by investigating the effectiveness of both proprietary and local LLMs in token-level clinical NER. Essentially, we delve into the capabilities of these models through a series of experiments involving zero-shot prompting, few-shot prompting, retrieval-augmented generation (RAG), and instruction-fine-tuning. Our exploration reveals the inherent challenges LLMs face in token-level NER, particularly in the context of rare diseases, and suggests possible improvements for their application in healthcare. This research contributes to narrowing a significant gap in healthcare informatics and offers insights that could lead to a more refined application of LLMs in the healthcare sector.
Authors: Wei Wang, Qing Li
Abstract: Language models have emerged as a critical area of focus in artificial intelligence, particularly with the introduction of groundbreaking innovations like ChatGPT. Large-scale Transformer networks have quickly become the leading approach for advancing natural language processing algorithms. Built on the Transformer architecture, these models enable interactions that closely mimic human communication and, equipped with extensive knowledge, can even assist in guiding human tasks. Despite their impressive capabilities and growing complexity, a key question remains-the theoretical foundations of large language models (LLMs). What makes Transformer so effective for powering intelligent language applications, such as translation and coding? What underlies LLMs' ability for In-Context Learning (ICL)? How does the LoRA scheme enhance the fine-tuning of LLMs? And what supports the practicality of pruning LLMs? To address these critical questions and explore the technological strategies within LLMs, we leverage the Universal Approximation Theory (UAT) to offer a theoretical backdrop, shedding light on the mechanisms that underpin these advancements.
Authors: John Payne, Aishwaryaprajna, Peter R. Lewis
Abstract: The sustainable foraging problem is a dynamic environment testbed for exploring the forms of agent cognition in dealing with social dilemmas in a multi-agent setting. The agents need to resist the temptation of individual rewards through foraging and choose the collective long-term goal of sustainability. We investigate methods of online learning in Neuro-Evolution and Deep Recurrent Q-Networks to enable agents to attempt the problem one-shot as is often required by wicked social problems. We further explore if learning temporal dependencies with Long Short-Term Memory may be able to aid the agents in developing sustainable foraging strategies in the long term. It was found that the integration of Long Short-Term Memory assisted agents in developing sustainable strategies for a single agent, however failed to assist agents in managing the social dilemma that arises in the multi-agent scenario.
Authors: Ariel D. Procaccia, Benjamin Schiffer, Shirley Zhang
Abstract: We consider the problem of online fair division of indivisible goods to players when there are a finite number of types of goods and player values are drawn from distributions with unknown means. Our goal is to maximize social welfare subject to allocating the goods fairly in expectation. When a player's value for an item is unknown at the time of allocation, we show that this problem reduces to a variant of (stochastic) multi-armed bandits, where there exists an arm for each player's value for each type of good. At each time step, we choose a distribution over arms which determines how the next item is allocated. We consider two sets of fairness constraints for this problem: envy-freeness in expectation and proportionality in expectation. Our main result is the design of an explore-then-commit algorithm that achieves $\tilde{O}(T^{2/3})$ regret while maintaining either fairness constraint. This result relies on unique properties fundamental to fair-division constraints that allow faster rates of learning, despite the restricted action space. We also prove a lower bound of $\tilde{\Omega}(T^{2/3})$ regret for our setting, showing that our results are tight.
Authors: Jike Wang, Rui Qin, Mingyang Wang, Meijing Fang, Yangyang Zhang, Yuchen Zhu, Qun Su, Qiaolin Gou, Chao Shen, Odin Zhang, Zhenxing Wu, Dejun Jiang, Xujun Zhang, Huifeng Zhao, Xiaozhe Wan, Zhourui Wu, Liwei Liu, Yu Kang, Chang-Yu Hsieh, Tingjun Hou
Abstract: Significant interests have recently risen in leveraging sequence-based large language models (LLMs) for drug design. However, most current applications of LLMs in drug discovery lack the ability to comprehend three-dimensional (3D) structures, thereby limiting their effectiveness in tasks that explicitly involve molecular conformations. In this study, we introduced Token-Mol, a token-only 3D drug design model. This model encodes all molecular information, including 2D and 3D structures, as well as molecular property data, into tokens, which transforms classification and regression tasks in drug discovery into probabilistic prediction problems, thereby enabling learning through a unified paradigm. Token-Mol is built on the transformer decoder architecture and trained using random causal masking techniques. Additionally, we proposed the Gaussian cross-entropy (GCE) loss function to overcome the challenges in regression tasks, significantly enhancing the capacity of LLMs to learn continuous numerical values. Through a combination of fine-tuning and reinforcement learning (RL), Token-Mol achieves performance comparable to or surpassing existing task-specific methods across various downstream tasks, including pocket-based molecular generation, conformation generation, and molecular property prediction. Compared to existing molecular pre-trained models, Token-Mol exhibits superior proficiency in handling a wider range of downstream tasks essential for drug design. Notably, our approach improves regression task accuracy by approximately 30% compared to similar token-only methods. Token-Mol overcomes the precision limitations of token-only models and has the potential to integrate seamlessly with general models such as ChatGPT, paving the way for the development of a universal artificial intelligence drug design model that facilitates rapid and high-quality drug design by experts.
Authors: Nicola Muca Cirone, Jad Hamdan, Cristopher Salvi
Abstract: We present a unified approach to obtain scaling limits of neural networks using the genus expansion technique from random matrix theory. This approach begins with a novel expansion of neural networks which is reminiscent of Butcher series for ODEs, and is obtained through a generalisation of Fa\`a di Bruno's formula to an arbitrary number of compositions. In this expansion, the role of monomials is played by random multilinear maps indexed by directed graphs whose edges correspond to random matrices, which we call operator graphs. This expansion linearises the effect of the activation functions, allowing for the direct application of Wick's principle to compute the expectation of each of its terms. We then determine the leading contribution to each term by embedding the corresponding graphs onto surfaces, and computing their Euler characteristic. Furthermore, by developing a correspondence between analytic and graphical operations, we obtain similar graph expansions for the neural tangent kernel as well as the input-output Jacobian of the original neural network, and derive their infinite-width limits with relative ease. Notably, we find explicit formulae for the moments of the limiting singular value distribution of the Jacobian. We then show that all of these results hold for networks with more general weights, such as general matrices with i.i.d. entries satisfying moment assumptions, complex matrices and sparse matrices.
Authors: Tom Fischer, Yaoyao Liu, Artur Jesslen, Noor Ahmed, Prakhar Kaushik, Angtian Wang, Alan Yuille, Adam Kortylewski, Eddy Ilg
Abstract: Different from human nature, it is still common practice today for vision tasks to train deep learning models only initially and on fixed datasets. A variety of approaches have recently addressed handling continual data streams. However, extending these methods to manage out-of-distribution (OOD) scenarios has not effectively been investigated. On the other hand, it has recently been shown that non-continual neural mesh models exhibit strong performance in generalizing to such OOD scenarios. To leverage this decisive property in a continual learning setting, we propose incremental neural mesh models that can be extended with new meshes over time. In addition, we present a latent space initialization strategy that enables us to allocate feature space for future unseen classes in advance and a positional regularization term that forces the features of the different classes to consistently stay in respective latent space regions. We demonstrate the effectiveness of our method through extensive experiments on the Pascal3D and ObjectNet3D datasets and show that our approach outperforms the baselines for classification by $2-6\%$ in the in-domain and by $6-50\%$ in the OOD setting. Our work also presents the first incremental learning approach for pose estimation. Our code and model can be found at https://github.com/Fischer-Tom/iNeMo.
Authors: Hao Wang, Xiangyu Yang, Yichen Zhu
Abstract: This paper explores a specific type of nonconvex sparsity-promoting regularization problems, namely those involving $\ell_p$-norm regularization, in conjunction with a twice continuously differentiable loss function. We propose a novel second-order algorithm designed to effectively address this class of challenging nonconvex and nonsmooth problems, showcasing several innovative features: (i) The use of an alternating strategy to solve a reweighted $\ell_1$ regularized subproblem and the subspace approximate Newton step. (ii) The reweighted $\ell_1$ regularized subproblem relies on a convex approximation to the nonconvex regularization term, enabling a closed-form solution characterized by the soft-thresholding operator. This feature allows our method to be applied to various nonconvex regularization problems. (iii) Our algorithm ensures that the iterates maintain their sign values and that nonzero components are kept away from 0 for a sufficient number of iterations, eventually transitioning to a perturbed Newton method. (iv) We provide theoretical guarantees of global convergence, local superlinear convergence in the presence of the Kurdyka-\L ojasiewicz (KL) property, and local quadratic convergence when employing the exact Newton step in our algorithm. We also showcase the effectiveness of our approach through experiments on a diverse set of model prediction problems.
Authors: Partha Chakraborty, Mahmoud Alfadel, Meiyappan Nagappan
Abstract: Software bugs require developers to exert significant effort to identify and resolve them, often consuming about one-third of their time. Bug localization, the process of pinpointing the exact source code files that need modification, is crucial in reducing this effort. Existing bug localization tools, typically reliant on deep learning techniques, face limitations in cross-project applicability and effectiveness in multi-language environments. Recent advancements with Large Language Models (LLMs) offer detailed representations for bug localization. However, they encounter challenges with limited context windows and mapping accuracy. To address these issues, we propose BLAZE, an approach that employs dynamic chunking and hard example learning. First, BLAZE dynamically segments source code to minimize continuity loss. Then, BLAZE fine-tunes a GPT-based model using challenging bug cases, in order to enhance cross-project and cross-language bug localization. To support the capability of BLAZE, we create the BEETLEBOX dataset, which comprises 26,321 bugs from 29 large and thriving open-source projects across five different programming languages (Java, C++, Python, Go, and JavaScript). Our evaluations of BLAZE on three benchmark datasets BEETLEBOX, SWE-Bench, and Ye et al. demonstrate substantial improvements compared to six state-of-the-art baselines. Specifically, BLAZE achieves up to an increase of 120% in Top 1 accuracy, 144% in Mean Average Precision (MAP), and 100% in Mean Reciprocal Rank (MRR). An extensive ablation study confirms the contributions of our pipeline components to the overall performance enhancement.
Authors: Santosh V. Patapati
Abstract: Major Depressive Disorder (MDD) is a pervasive mental health condition that affects 300 million people worldwide. This work presents a novel, BiLSTM-based tri-modal model-level fusion architecture for the binary classification of depression from clinical interview recordings. The proposed architecture incorporates Mel Frequency Cepstral Coefficients, Facial Action Units, and uses a two-shot learning based GPT-4 model to process text data. This is the first work to incorporate large language models into a multi-modal architecture for this task. It achieves impressive results on the DAIC-WOZ AVEC 2016 Challenge cross-validation split and Leave-One-Subject-Out cross-validation split, surpassing all baseline models and multiple state-of-the-art models. In Leave-One-Subject-Out testing, it achieves an accuracy of 91.01%, an F1-Score of 85.95%, a precision of 80%, and a recall of 92.86%.
Authors: Matthijs de Jong, Jan Viebahn, Yuliya Shapovalova
Abstract: Power grid operation is becoming increasingly complex due to the increase in generation of renewable energy. The recent series of Learning To Run a Power Network (L2RPN) competitions have encouraged the use of artificial agents to assist human dispatchers in operating power grids. In this paper we study the performance of imitation learning for day-ahead power grid operation through topology actions. In particular, we consider two rule-based expert agents: a greedy agent and a N-1 agent. While the latter is more computationally expensive since it takes N-1 safety considerations into account, it exhibits a much higher operational performance. We train a fully-connected neural network (FCNN) on expert state-action pairs and evaluate it in two ways. First, we find that classification accuracy is limited despite extensive hyperparameter tuning, due to class imbalance and class overlap. Second, as a power system agent, the FCNN performs only slightly worse than expert agents. Furthermore, hybrid agents, which incorporate minimal additional simulations, match expert agents' performance with significantly lower computational cost. Consequently, imitation learning shows promise for developing fast, high-performing power grid agents, motivating its further exploration in future L2RPN studies.
Authors: Mingzhi Chen, Yiyu Gui, Yuqi Su, Yuesheng Zhu, Guibo Luo, Yuchao Yang
Abstract: Electroencephalogram (EEG) classification has been widely used in various medical and engineering applications, where it is important for understanding brain function, diagnosing diseases, and assessing mental health conditions. However, the scarcity of EEG data severely restricts the performance of EEG classification networks, and generative model-based data augmentation methods have emerged as potential solutions to overcome this challenge. There are two problems with existing methods: (1) The quality of the generated EEG signals is not high; (2) The enhancement of EEG classification networks is not effective. In this paper, we propose a Transformer-based denoising diffusion probabilistic model and a generated data-based augmentation method to address the above two problems. For the characteristics of EEG signals, we propose a constant-factor scaling method to preprocess the signals, which reduces the loss of information. We incorporated Multi-Scale Convolution and Dynamic Fourier Spectrum Information modules into the model, improving the stability of the training process and the quality of the generated data. The proposed augmentation method randomly reassemble the generated data with original data in the time-domain to obtain vicinal data, which improves the model performance by minimizing the empirical risk and the vicinal risk. We verify the proposed augmentation method on four EEG datasets for four tasks and observe significant accuracy performance improvements: 14.00% on the Bonn dataset; 6.38% on the SleepEDF-20 dataset; 9.42% on the FACED dataset; 2.5% on the Shu dataset. We will make the code of our method publicly accessible soon.
Authors: Ali Abdollahi, Mahdi Ghaznavi, Mohammad Reza Karimi Nejad, Arash Mari Oriyad, Reza Abbasi, Ali Salesi, Melika Behjati, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah
Abstract: Vision-language models (VLMs) are intensively used in many downstream tasks, including those requiring assessments of individuals appearing in the images. While VLMs perform well in simple single-person scenarios, in real-world applications, we often face complex situations in which there are persons of different genders doing different activities. We show that in such cases, VLMs are biased towards identifying the individual with the expected gender (according to ingrained gender stereotypes in the model or other forms of sample selection bias) as the performer of the activity. We refer to this bias in associating an activity with the gender of its actual performer in an image or text as the Gender-Activity Binding (GAB) bias and analyze how this bias is internalized in VLMs. To assess this bias, we have introduced the GAB dataset with approximately 5500 AI-generated images that represent a variety of activities, addressing the scarcity of real-world images for some scenarios. To have extensive quality control, the generated images are evaluated for their diversity, quality, and realism. We have tested 12 renowned pre-trained VLMs on this dataset in the context of text-to-image and image-to-text retrieval to measure the effect of this bias on their predictions. Additionally, we have carried out supplementary experiments to quantify the bias in VLMs' text encoders and to evaluate VLMs' capability to recognize activities. Our experiments indicate that VLMs experience an average performance decline of about 13.2% when confronted with gender-activity binding bias.
Authors: Zhehan Zhang, Meihua Qian, Li Luo, Ripon Saha, Qianyi Gao, Xinxin Song
Abstract: Assessing artistic creativity has long challenged researchers, with traditional methods proving time-consuming. Recent studies have applied machine learning to evaluate creativity in drawings, but not paintings. Our research addresses this gap by developing a CNN model to automatically assess the creativity of human paintings. Using a dataset of six hundred paintings by professionals and children, our model achieved 90% accuracy and faster evaluation times than human raters. This approach demonstrates the potential of machine learning in advancing artistic creativity assessment, offering a more efficient alternative to traditional methods.
Authors: Jacob K Christopher, Brian R Bartoldson, Bhavya Kailkhura, Ferdinando Fioretto
Abstract: Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique has facilitated notable speed improvements by enabling parallel sequence verification, its efficiency remains inherently limited by the reliance on incremental token generation in existing draft models. To overcome this limitation, this paper proposes an adaptation of speculative decoding which uses discrete diffusion models to generate draft sequences. This allows parallelization of both the drafting and verification steps, providing significant speed-ups to the inference process. Our proposed approach, Speculative Diffusion Decoding (SpecDiff), is validated on standard language generation benchmarks and empirically demonstrated to provide a up to 8.7x speed-up over standard generation processes and up to 2.5x speed-up over existing speculative decoding approaches.
Authors: Taewoon Kim, Vincent Fran\c{c}ois-Lavet, Michael Cochez
Abstract: Humans observe only part of their environment at any moment but can still make complex, long-term decisions thanks to our long-term memory. To test how an AI can learn and utilize its long-term memory, we have developed a partially observable Markov decision processes (POMDP) environment, where the agent has to answer questions while navigating a maze. The environment is completely knowledge graph (KG) based, where the hidden states are dynamic KGs. A KG is both human- and machine-readable, making it easy to see what the agents remember and forget. We train and compare agents with different memory systems, to shed light on how human brains work when it comes to managing its own memory. By repurposing the given learning objective as learning a memory management policy, we were able to capture the most likely hidden state, which is not only interpretable but also reusable.
Authors: Jiaojiao Guan, Yongxin Ji, Cheng Peng, Wei Zou, Xubo Tang, Jiayu Shang, Yanni Sun
Abstract: Bacteriophages are viruses that target bacteria, playing a crucial role in microbial ecology. Phage proteins are important in understanding phage biology, such as virus infection, replication, and evolution. Although a large number of new phages have been identified via metagenomic sequencing, many of them have limited protein function annotation. Accurate function annotation of phage proteins presents several challenges, including their inherent diversity and the scarcity of annotated ones. Existing tools have yet to fully leverage the unique properties of phages in annotating protein functions. In this work, we propose a new protein function annotation tool for phages by leveraging the modular genomic structure of phage genomes. By employing embeddings from the latest protein foundation models and Transformer to capture contextual information between proteins in phage genomes, PhaGO surpasses state-of-the-art methods in annotating diverged proteins and proteins with uncommon functions by 6.78% and 13.05% improvement, respectively. PhaGO can annotate proteins lacking homology search results, which is critical for characterizing the rapidly accumulating phage genomes. We demonstrate the utility of PhaGO by identifying 688 potential holins in phages, which exhibit high structural conservation with known holins. The results show the potential of PhaGO to extend our understanding of newly discovered phages.
Authors: Nayely V\'elez-Cruz, Manfred D. Laubichler
Abstract: The ubiquity of multiscale interactions in complex systems is well-recognized, with development and heredity serving as a prime example of how processes at different temporal scales influence one another. This work introduces a novel multiscale state-space model to explore the dynamic interplay between systems interacting across different time scales, with feedback between each scale. We propose a Bayesian learning framework to estimate unknown states by learning the unknown process noise covariances within this multiscale model. We develop a Particle Gibbs with Ancestor Sampling (PGAS) algorithm for inference and demonstrate through simulations the efficacy of our approach.
Authors: Majid Daliri, Christopher Musco, Ananda Theertha Suresh
Abstract: Suppose Alice has a distribution $P$ and Bob has a distribution $Q$. Alice wants to generate a sample $a\sim P$ and Bob a sample $b \sim Q$ such that $a = b$ with has as high of probability as possible. It is well-known that, by sampling from an optimal coupling between the distributions, Alice and Bob can achieve $Pr[a = b] = 1 - D_{TV}(P,Q)$, where $D_{TV}(P,Q)$ is the total variation distance. What if Alice and Bob must solve this same problem without communicating at all? Perhaps surprisingly, with access to public randomness, they can still achieve $Pr[a=b] \geq \frac{1-D_{TV}(P,Q)}{1+D_{TV}(P,Q)} \geq 1-2D_{TV}(P,Q)$. In fact, this bound can be obtained using a simple protocol based on the Weighted MinHash algorithm. In this work, we explore the communication-free coupling problem in greater depth. First, we show that an equally simple protocol based on Gumbel sampling matches the worst-case guarantees of the Weighted MinHash approach, but tends to perform better in practice. Conversely, we prove that both approaches are actually sharp: no communication-free protocol can achieve $Pr[a=b]>\frac{1-D_{TV}(P,Q)}{1+D_{TV}(P,Q)}$ in the worst-case. Finally, we prove that, for distributions over $n$ items, there exists a scheme that uses just $O(\log(n/\epsilon))$ bits of communication to achieve $Pr[a = b] = 1 - D_{TV}(P,Q) - \epsilon$, i.e. to essentially match optimal coupling. Beyond our theoretical results, we demonstrate an application of communication-free coupling to speculative decoding, a recent method for accelerating autoregressive large language models [Leviathan, Kalman, Matias, ICML 2023]. We show that communication-free protocols yield a variant of speculative decoding that we call Drafter-Invariant Speculative Decoding, which has the desirable property that the output of the method is fixed given a fixed random seed, regardless of what drafter is used for speculation.
Authors: Brandon J. O'Connell, Max D. Champneys, Timothy J. Rogers
Abstract: In the field of operational modal analysis (OMA), obtained modal information is frequently used to assess the current state of aerospace, mechanical, offshore and civil structures. However, the stochasticity of operational systems and the lack of forcing information can lead to inconsistent results. Quantifying the uncertainty of the recovered modal parameters through OMA is therefore of significant value. In this article, a new perspective on Bayesian OMA is proposed: a Bayesian stochastic subspace identification (SSI) algorithm. Distinct from existing approaches to Bayesian OMA, a hierarchical probabilistic model is embedded at the core of covariance-driven SSI. Through substitution of canonical correlation analysis with a Bayesian equivalent, posterior distributions over the modal properties are obtained. Two inference schemes are presented for the proposed Bayesian formulation: Markov Chain Monte Carlo and variational Bayes. Two case studies are then explored. The first is benchmark study using data from a simulated, multi degree-of-freedom, linear system. Following application of Bayesian SSI, it is shown that the same posterior is targeted and recovered by both inference schemes, with good agreement between the posterior mean and the conventional SSI result. The second study applies the variational form to data obtained from an in-service structure: The Z24 bridge. The results of this study are presented at single model orders, and then using a stabilisation diagram. The recovered posterior uncertainty is presented and compared to the classic SSI result. It is observed that the posterior distributions with mean values coinciding with the natural frequencies exhibit lower variance than values situated away from the natural frequencies.
Authors: Sumanth Prabhu
Abstract: Self-ensembling techniques with diverse reasoning paths such as Self-Consistency have demonstrated remarkable performance gains in text generation with Large Language Models (LLMs). However, such techniques depend on the availability of an accurate answer extraction process to aggregate across multiple outputs. Moreover, they acquire higher inference cost, in comparison to Greedy Decoding, due to generation of relatively higher number of output tokens. Research has shown that the free form text outputs from Self-Consistency can be aggregated reliably using LLMs to produce the final output. Additionally, recent advancements in LLM inference have demonstrated that usage of diverse exemplars in prompts have the ability to induce diversity in the LLM outputs. Such proven techniques can be easily extended to self-ensembling based approaches to achieve enhanced results in text generation. In this paper, we introduce PEDAL (Prompts based on Exemplar Diversity Aggregated using LLMs), a hybrid self-ensembling approach, that combines the strengths of diverse exemplar based prompts and LLM based aggregation to achieve improvement in overall performance. On the publicly available SVAMP and ARC datasets, our experiments reveal that PEDAL can achieve better accuracy than Greedy Decoding based strategies with lower inference cost compared to Self Consistency based approaches.