This paper delves into the realm of stochastic optimization for compositional minimax optimization—a pivotal challenge across various machine learning domains, including deep AUC and reinforcement learning policy evaluation. Despite its significance, the problem of compositional minimax optimization is still under-explored. Adding to the complexity, current methods of compositional minimax optimization are plagued by sub-optimal complexities or heavy reliance on sizable batch sizes. To respond to these constraints, this paper introduces a novel method, called Nested STOchastic Recursive Momentum (NSTORM), which can achieve the optimal sample complexity and obtain the nearly accuracy solution, matching the existing minimax methods. We also demonstrate that NSTORM can achieve the same sample complexity under the Polyak-Lojasiewicz (PL)-condition—an insightful extension of its capabilities. Yet, NSTORM encounters an issue with its requirement for low learning rates, potentially constraining its real-world applicability in machine learning. To overcome this hurdle, we present ADAptive NSTORM (ADA-NSTORM) with adaptive learning rates. We demonstrate that ADA-NSTORM can achieve the same sample complexity but the experimental results show its more effectiveness. All the proposed complexities indicate that our proposed methods can match lower bounds to existing minimax optimizations, without requiring a large batch size in each iteration. Extensive experiments support the efficiency of our proposed methods.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
TimesURL: Self-Supervised Contrastive Learning for Universal Time Series Representation Learning
PDF ↗Learning universal time series representations applicable to various types of downstream tasks is challenging but valuable in real applications. Recently, researchers have attempted to leverage the success of self-supervised contrastive learning (SSCL) in Computer Vision(CV) and Natural Language Processing(NLP) to tackle time series representation. Nevertheless, due to the special temporal characteristics, relying solely on empirical guidance from other domains may be ineffective for time series and difficult to adapt to multiple downstream tasks. To this end, we review three parts involved in SSCL including 1) designing augmentation methods for positive pairs, 2) constructing (hard) negative pairs, and 3) designing SSCL loss. For 1) and 2), we find that unsuitable positive and negative pair construction may introduce inappropriate inductive biases, which neither preserve temporal properties nor provide sufficient discriminative features. For 3), just exploring segment- or instance-level semantics information is not enough for learning universal representation. To remedy the above issues, we propose a novel self-supervised framework named TimesURL. Specifically, we first introduce a frequency-temporal-based augmentation to keep the temporal property unchanged. And then, we construct double Universums as a special kind of hard negative to guide better contrastive learning. Additionally, we introduce time reconstruction as a joint optimization objective with contrastive learning to capture both segment-level and instance-level information. As a result, TimesURL can learn high-quality universal representations and achieve state-of-the-art performance in 6 different downstream tasks, including short- and long-term forecasting, imputation, classification, anomaly detection and transfer learning.
The learnware paradigm aims to establish a market of numerous well-performed machine learning models, enabling users to leverage existing helpful models for their tasks instead of starting from scratch. Each learnware in the market is a model submitted by its developer, associated with a specification generated with the help of learnware market, representing the model's specialty and utility and enabling it to be identified for new user tasks. As the market continuously scales up, accommodating an ever-increasing number of learnwares, the critical challenge of the learnware paradigm is to effectively and efficiently identify the most helpful learnware(s) for a new user task without accessing the user's raw data. In this paper, to achieve increasingly accurate learnware characterization and identification along with a growing number of learnwares in the market, we propose an approach called Evolvable Learnware Specification with Index (ELSI). Specifically, based on the key idea of leveraging the task information within learnware specifications, we tackle the challenge of ascertaining the capabilities of models beyond their original training tasks, thereby enabling learnware specifications and the entire market to evolve continuously. Furthermore, through organizing learnwares and constructing specification indexes, we design a practical procedure to accurately and efficiently identify helpful learnwares without examining the entire market. Theoretical analysis and extensive experiments on a learnware market prototype encompassing thousands of models and covering six real-world scenarios validate the effectiveness and efficiency of our approach.
As a promising approach to deal with distributed data, Federated Learning (FL) achieves major advancements in recent years. FL enables collaborative model training by exploiting the raw data dispersed in multiple edge devices. However, the data is generally non-independent and identically distributed, i.e., statistical heterogeneity, and the edge devices significantly differ in terms of both computation and communication capacity, i.e., system heterogeneity. The statistical heterogeneity leads to severe accuracy degradation while the system heterogeneity significantly prolongs the training process. In order to address the heterogeneity issue, we propose an Asynchronous Staleness-aware Model Update FL framework, i.e., FedASMU, with two novel methods. First, we propose an asynchronous FL system model with a dynamical model aggregation method between updated local models and the global model on the server for superior accuracy and high efficiency. Then, we propose an adaptive local model adjustment method by aggregating the fresh global model with local models on devices to further improve the accuracy. Extensive experimentation with 6 models and 5 public datasets demonstrates that FedASMU significantly outperforms baseline approaches in terms of accuracy (0.60% to 23.90% higher) and efficiency (3.54% to 97.98% faster).
Traditional channel-wise pruning methods by reducing network channels struggle to effectively prune efficient CNN models with depth-wise convolutional layers and certain efficient modules, such as popular inverted residual blocks. Prior depth pruning methods by reducing network depths are not suitable for pruning some efficient models due to the existence of some normalization layers. Moreover, finetuning subnet with directly removing activation layers would corrupt the original model weights, hindering the pruned model from achieving high performance. To address these issues, we propose a novel depth pruning method for efficient models. Our approach proposes a novel block pruning strategy and progressive training method for the subnet. Additionally, we extend our pruning method to vision transformer models. Experimental results demonstrate that our method consistently outperforms existing depth pruning methods across various pruning configurations. We obtained three pruned ConvNeXtV1 models with our method applying on ConvNeXtV1, which surpass most SOTA efficient models with comparable inference performance. Our method also achieves state-of-the-art pruning performance on the vision transformer model.
Federated Learning (FL) is an emerging paradigm that enables multiple users to collaboratively train a robust model in a privacy-preserving manner without sharing their private data. Most existing approaches of FL only consider traditional single-label image classification, ignoring the impact when transferring the task to multi-label image classification. Nevertheless, it is still challenging for FL to deal with user heterogeneity in their local data distribution in the real-world FL scenario, and this issue becomes even more severe in multi-label image classification. Inspired by the recent success of Transformers in centralized settings, we propose a novel FL framework for multi-label classification. Since partial label correlation may be observed by local clients during training, direct aggregation of locally updated models would not produce satisfactory performances. Thus, we propose a novel FL framework of Language-Guided Transformer (FedLGT) to tackle this challenging task, which aims to exploit and transfer knowledge across different clients for learning a robust global model. Through extensive experiments on various multi-label datasets (e.g., FLAIR, MS-COCO, etc.), we show that our FedLGT is able to achieve satisfactory performance and outperforms standard FL techniques under multi-label FL scenarios. Code is available at https://github.com/Jack24658735/FedLGT.
The audio spectrogram is a time-frequency representation that has been widely used for audio classification. One of the key attributes of the audio spectrogram is the temporal resolution, which depends on the hop size used in the Short-Time Fourier Transform (STFT). Previous works generally assume the hop size should be a constant value (e.g., 10 ms). However, a fixed temporal resolution is not always optimal for different types of sound. The temporal resolution affects not only classification accuracy but also computational cost. This paper proposes a novel method, DiffRes, that enables differentiable temporal resolution modeling for audio classification. Given a spectrogram calculated with a fixed hop size, DiffRes merges non-essential time frames while preserving important frames. DiffRes acts as a "drop-in" module between an audio spectrogram and a classifier and can be jointly optimized with the classification task. We evaluate DiffRes on five audio classification tasks, using mel-spectrograms as the acoustic features, followed by off-the-shelf classifier backbones. Compared with previous methods using the fixed temporal resolution, the DiffRes-based method can achieve the equivalent or better classification accuracy with at least 25% computational cost reduction. We further show that DiffRes can improve classification accuracy by increasing the temporal resolution of input acoustic features, without adding to the computational cost.
Attention-Induced Embedding Imputation for Incomplete Multi-View Partial Multi-Label Classification
PDF ↗As a combination of emerging multi-view learning methods and traditional multi-label classification tasks, multi-view multi-label classification has shown broad application prospects. The diverse semantic information contained in heterogeneous data effectively enables the further development of multi-label classification. However, the widespread incompleteness problem on multi-view features and labels greatly hinders the practical application of multi-view multi-label classification. Therefore, in this paper, we propose an attention-induced missing instances imputation technique to enhance the generalization ability of the model. Different from existing incomplete multi-view completion methods, we attempt to approximate the latent features of missing instances in embedding space according to cross-view joint attention, instead of recovering missing views in kernel space or original feature space. Accordingly, multi-view completed features are dynamically weighted by the confidence derived from joint attention in the late fusion phase. In addition, we propose a multi-view multi-label classification framework based on label-semantic feature learning, utilizing the statistical weak label correlation matrix and graph attention network to guide the learning process of label-specific features. Finally, our model is compatible with missing multi-view and partial multi-label data simultaneously and extensive experiments on five datasets confirm the advancement and effectiveness of our embedding imputation method and multi-view multi-label classification model.
Towards Inductive Robustness: Distilling and Fostering Wave-Induced Resonance in Transductive GCNs against Graph Adversarial Attacks
PDF ↗Graph neural networks (GNNs) have recently been shown to be vulnerable to adversarial attacks, where slight perturbations in the graph structure can lead to erroneous predictions. However, current robust models for defending against such attacks inherit the transductive limitations of graph convolutional networks (GCNs). As a result, they are constrained by fixed structures and do not naturally generalize to unseen nodes. Here, we discover that transductive GCNs inherently possess a distillable robustness, achieved through a wave-induced resonance process. Based on this, we foster this resonance to facilitate inductive and robust learning. Specifically, we first prove that the signal formed by GCN-driven message passing (MP) is equivalent to the edge-based Laplacian wave, where, within a wave system, resonance can naturally emerge between the signal and its transmitting medium. This resonance provides inherent resistance to malicious perturbations inflicted on the signal system. We then prove that merely three MP iterations within GCNs can induce signal resonance between nodes and edges, manifesting as a coupling between nodes and their distillable surrounding local subgraph. Consequently, we present Graph Resonance-fostering Network (GRN) to foster this resonance via learning node representations from their distilled resonating subgraphs. By capturing the edge-transmitted signals within this subgraph and integrating them with the node signal, GRN embeds these combined signals into the central node's representation. This node-wise embedding approach allows for generalization to unseen nodes. We validate our theoretical findings with experiments, and demonstrate that GRN generalizes robustness to unseen nodes, whilst maintaining state-of-the-art classification accuracy on perturbed graphs. Appendices can be found on arXiv version: https://arxiv.org/abs/2312.08651
Few-shot learning (FSL) aims to enable learning models with the ability to automatically adapt to novel (unseen) domains in open-world scenarios. Nonetheless, there exists a significant disparity between the vast number of new concepts encountered in the open world and the restricted available scale of existing FSL works, which primarily focus on a limited number of novel classes. Such a gap hinders the practical applicability of FSL in realistic scenarios. To bridge this gap, we propose a new problem named Few-Shot Learning with Many Novel Classes (FSL-MNC) by substantially enlarging the number of novel classes, exceeding the count in the traditional FSL setup by over 500-fold. This new problem exhibits two major challenges, including the increased computation overhead during meta-training and the degraded classification performance by the large number of classes during meta-testing. To overcome these challenges, we propose a Simple Hierarchy Pipeline (SHA-Pipeline). Due to the inefficiency of traditional protocols of EML, we re-design a lightweight training strategy to reduce the overhead brought by much more novel classes. To capture discriminative semantics across numerous novel classes, we effectively reconstruct and leverage the class hierarchy information during meta-testing. Experiments show that the proposed SHA-Pipeline significantly outperforms not only the ProtoNet baseline but also the state-of-the-art alternatives across different numbers of novel classes.
In recent years, Hypergraph Neural Networks (HGNNs) have achieved considerable success by manually designing architectures, which are capable of extracting effective patterns with high-order interactions from non-Euclidean data. However, such mechanism is extremely inefficient, demanding tremendous human efforts to tune diverse model parameters. In this paper, we propose a novel Hypergraph Neural Architecture Search (HyperNAS) to automatically design the optimal HGNNs. The proposed model constructs a search space suitable for hypergraphs, and derives hypergraph architectures through differentiable search strategies. A hypergraph structure-aware distance criterion is introduced as a guideline for obtaining an optimal hypergraph architecture via the leave-one-out method. Experimental results for node classification on benchmark Cora, Citeseer, Pubmed citation networks and hypergraph datasets show that HyperNAS outperforms existing HGNNs models and graph NAS methods.
ERL-TD: Evolutionary Reinforcement Learning Enhanced with Truncated Variance and Distillation Mutation
PDF ↗Recently, an emerging research direction called Evolutionary Reinforcement Learning (ERL) has been proposed, which combines evolutionary algorithm with reinforcement learning (RL) for tackling the tasks of sequential decision making. However, the recently proposed ERL algorithms often suffer from two challenges: the inaccuracy of policy estimation caused by the overestimation bias in RL and the insufficiency of exploration caused by inefficient mutations. To alleviate these problems, we propose an Evolutionary Reinforcement Learning algorithm enhanced with Truncated variance and Distillation mutation, called ERL-TD. We utilize multiple Q-networks to evaluate state-action pairs, so that multiple networks can provide more accurate evaluations for state-action pairs, in which the variance of evaluations can be adopted to control the overestimation bias in RL. Moreover, we propose a new distillation mutation to provide a promising mutation direction, which is different from traditional mutation generating a large number of random solutions. We evaluate ERL-TD on the continuous control benchmarks from the OpenAI Gym and DeepMind Control Suite. The experiments show that ERL-TD shows excellent performance and outperforms all baseline RL algorithms on the test suites.
Tactile signals collected by wearable electronics are essential in modeling and understanding human behavior. One of the main applications of tactile signals is action classification, especially in healthcare and robotics. However, existing tactile classification methods fail to capture the spatial and temporal features of tactile signals simultaneously, which results in sub-optimal performances. In this paper, we design Spatio-Temporal Aware tactility Transformer (STAT) to utilize continuous tactile signals for action classification. We propose spatial and temporal embeddings along with a new temporal pretraining task in our model, which aims to enhance the transformer in modeling the spatio-temporal features of tactile signals. Specially, the designed temporal pretraining task is to differentiate the time order of tubelet inputs to model the temporal properties explicitly. Experimental results on a public action classification dataset demonstrate that our model outperforms state-of-the-art methods in all metrics.
Real-world decision-making problems are usually accompanied by delayed rewards, which affects the sample efficiency of Reinforcement Learning, especially in the extremely delayed case where the only feedback is the episodic reward obtained at the end of an episode. Episodic return decomposition is a promising way to deal with the episodic-reward setting. Several corresponding algorithms have shown remarkable effectiveness of the learned step-wise proxy rewards from return decomposition. However, these existing methods lack either attribution or representation capacity, leading to inefficient decomposition in the case of long-term episodes. In this paper, we propose a novel episodic return decomposition method called Diaster (Difference of implicitly assigned sub-trajectory reward). Diaster decomposes any episodic reward into credits of two divided sub-trajectories at any cut point, and the step-wise proxy rewards come from differences in expectation. We theoretically and empirically verify that the decomposed proxy reward function can guide the policy to be nearly optimal. Experimental results show that our method outperforms previous state-of-the-art methods in terms of both sample efficiency and performance. The code is available at https://github.com/HxLyn3/Diaster.
Label noise poses an important challenge in machine learning, especially in deep learning, in which large models with high expressive power dominate the field. Models of that kind are prone to memorizing incorrect labels, thereby harming generalization performance. Many methods have been proposed to address this problem, including robust loss functions and more complex label correction approaches. Robust loss functions are appealing due to their simplicity, but typically lack flexibility, while label correction usually adds substantial complexity to the training setup. In this paper, we suggest to address the shortcomings of both methodologies by "ambiguating" the target information, adding additional, complementary candidate labels in case the learner is not sufficiently convinced of the observed training label. More precisely, we leverage the framework of so-called superset learning to construct set-valued targets based on a confidence threshold, which deliver imprecise yet more reliable beliefs about the ground-truth, effectively helping the learner to suppress the memorization effect. In an extensive empirical evaluation, our method demonstrates favorable learning behavior on synthetic and real-world noise, confirming the effectiveness in detecting and correcting erroneous training labels.
A crucial reason for the success of existing NeRF-based methods is to build a neural density field for the geometry representation via multiple perceptron layers (MLPs). MLPs are continuous functions, however, real geometry or density field is frequently discontinuous at the interface between the air and the surface. Such a contrary brings the problem of unfaithful geometry representation. To this end, this paper proposes spiking NeRF, which leverages spiking neurons and a hybrid Artificial Neural Network (ANN)-Spiking Neural Network (SNN) framework to build a discontinuous density field for faithful geometry representation. Specifically, we first demonstrate the reason why continuous density fields will bring inaccuracy. Then, we propose to use the spiking neurons to build a discontinuous density field. We conduct a comprehensive analysis for the problem of existing spiking neuron models and then provide the numerical relationship between the parameter of the spiking neuron and the theoretical accuracy of geometry. Based on this, we propose a bounded spiking neuron to build the discontinuous density field. Our method achieves SOTA performance. The source code and the supplementary material are available at https://github.com/liaozhanfeng/Spiking-NeRF.
In this paper, we study the mistake bound of online kernel learning on a budget. We propose a new budgeted online kernel learning model, called Ahpatron, which significantly improves the mistake bound of previous work and resolves an open problem related to upper bounds of hypothesis space constraints. We first present an aggressive variant of Perceptron, named AVP, a model without budget, which uses an active updating rule. Then we design a new budget maintenance mechanism, which removes a half of examples, and projects the removed examples onto a hypothesis space spanned by the remaining examples. Ahpatron adopts the above mechanism to approximate AVP. Theoretical analyses prove that Ahpatron has tighter mistake bounds, and experimental results show that Ahpatron outperforms the state-of-the-art algorithms on the same or a smaller budget.
Out-Of-Distribution (OOD) generalization is an essential topic in machine learning. However, recent research is only focusing on the corresponding methods for neural networks. This paper introduces a novel and effective solution for OOD generalization of decision tree models, named Invariant Decision Tree (IDT). IDT enforces a penalty term with regard to the unstable/varying behavior of a split across different environments during the growth of the tree. Its ensemble version, the Invariant Random Forest (IRF), is constructed. Our proposed method is motivated by a theoretical result under mild conditions, and validated by numerical tests with both synthetic and real datasets. The superior performance compared to non-OOD tree models implies that considering OOD generalization for tree models is absolutely necessary and should be given more attention.
Deep learning methods on graph data have achieved remarkable efficacy across a variety of real-world applications, such as social network analysis and transaction risk detection. Nevertheless, recent studies have illuminated a concerning fact: even the most expressive Graph Neural Networks (GNNs) are vulnerable to graph adversarial attacks. While several methods have been proposed to enhance the robustness of GNN models against adversarial attacks, few have focused on a simple yet realistic approach: valuing the adversarial risks and focused safeguards at the node level. This empowers defenders to allocate heightened security level to vulnerable nodes, while lower to robust nodes. With this new perspective, we propose a novel graph defense strategy RisKeeper, such that the adversarial risk can be directly kept in the input graph. We start at valuing the adversarial risk, by introducing a cost-aware projected gradient descent attack that takes into account both cost avoidance and compliance with costs budgets. Subsequently, we present a learnable approach to ascertain the ideal security level for each individual node by solving a bi-level optimization problem. Through extensive experiments on four real-world datasets, we demonstrate that our method achieves superior performance surpassing state-of-the-art methods. Our in-depth case studies provide further insights into vulnerable and robust structural patterns, serving as inspiration for practitioners to exercise heightened vigilance.
Neural architecture search-based multi-modal classification (NAS-MMC) methods can individually obtain the optimal classifier for different multi-modal data sets in an automatic manner. However, most existing NAS-MMC methods are dramatically time consuming due to the requirement for training and evaluating enormous models. In this paper, we propose an efficient evolutionary-based NAS-MMC method called divide-and-conquer neural architecture search (DC-NAS). Specifically, the evolved population is first divided into k+1 sub-populations, and then k sub-populations of them evolve on k small-scale data sets respectively that are obtained by splitting the entire data set using the k-fold stratified sampling technique; the remaining one evolves on the entire data set. To solve the sub-optimal fusion model problem caused by the training strategy of partial data, two kinds of sub-populations that are trained using partial data and entire data exchange the learned knowledge via two special knowledge bases. With the two techniques mentioned above, DC-NAS achieves the training time reduction and classification performance improvement. Experimental results show that DC-NAS achieves the state-of-the-art results in term of classification performance, training efficiency and the number of model parameters than the compared NAS-MMC methods on three popular multi-modal tasks including multi-label movie genre classification, action recognition with RGB and body joints and dynamic hand gesture recognition.