Semi-supervised learning has been an effective paradigm for leveraging unlabeled data to reduce the reliance on labeled data. We propose CoMatch, a new semi-supervised learning method that unifies dominant approaches and addresses their limitations. CoMatch jointly learns two representations of the training data, their class probabilities and low-dimensional embeddings. The two representations interact with each other to jointly evolve. The embeddings impose a smoothness constraint on the class probabilities to improve the pseudo-labels, whereas the pseudo-labels regularize the structure of the embeddings through graph-based contrastive learning. CoMatch achieves state-of-the-art performance on multiple datasets. It achieves substantial accuracy improvements on the label-scarce CIFAR-10 and STL-10. On ImageNet with 1% labels, CoMatch achieves a top-1 accuracy of 66.0%, outperforming FixMatch by 12.6%. Furthermore, CoMatch achieves better representation learning performance on downstream tasks, outperforming both supervised learning and self-supervised learning. Code and pre-trained models are available at https://github.com/salesforce/CoMatch.
This paper introduces SelfMatch, a semi-supervised learning method that combines the power of contrastive self-supervised learning and consistency regularization. SelfMatch consists of two stages: (1) self-supervised pre-training based on contrastive learning and (2) semi-supervised fine-tuning based on augmentation consistency regularization. We empirically demonstrate that SelfMatch achieves the state-of-the-art results on standard benchmark datasets such as CIFAR-10 and SVHN. For example, for CIFAR-10 with 40 labeled examples, SelfMatch achieves 93.19% accuracy that outperforms the strong p…
Air Traffic Management Research Institute, Nanyang Technological University, Singapore（新加坡南洋理工大学航空交通管理研究所）；Center of AI Research, VinUniversity, Vietnam（越南Vin大学人工智能研究中心）
University of Western Ontario（西安大略大学）；ByteDance Inc.（字节跳动公司）；Vector Institute（向量研究所）
Deep neural networks are able to memorize noisy labels easily with a softmax cross-entropy (CE) loss. Previous studies attempted to address this issue focus on incorporating a noise-robust loss function to the CE loss. However, the memorization issue is alleviated but still remains due to the non-robust CE loss. To address this issue, we focus on learning robust contrastive representations of data on which the classifier is hard to memorize the label noise under the CE loss. We propose a novel contrastive regularization function to learn such representations over noisy data where label noise d…
Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization
National University of Singapore（新加坡国立大学）；RIKEN Center for Advanced Intelligence Project (AIP)（理化学研究所先进智能项目中心）；The University of Auckland（奥克兰大学）；The University of Melbourne（墨尔本大学）；The University of Tokyo（东京大学）
Zhejiang University（浙江大学）；IBM Research（IBM研究院）；Squirrel AI Learning（松鼠AI）
Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct efficient contrastive samples through data augmentation is key to its success. Unlike vision tasks, the data augmentation method for contrastive learning has not been investigated sufficiently in language tasks. In this paper, we propose a novel approach to construct contrastive samples for language tasks using text summarization. We use these samples for supervised contrastive learning to gain better text representa…
Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss that performs the prototypical regularization aggressively, e.g., the ProtoNCE loss, might cause the "coagulation" of examples in the embedding space. That is, the intra-prototype diversity of samples collapses to trivial solutions for their prototype being well-separated from others. Motivated by previous works, we propose to mitigate this phenomenon by learni…
Semantic search is an important task which objective is to find the relevant index from a database for query. It requires a retrieval model that can properly learn the semantics of sentences. Transformer-based models are widely used as retrieval models due to their excellent ability to learn semantic representations. in the meantime, many regularization methods suitable for them have also been proposed. In this paper, we propose a new regularization method: Regularized Contrastive Learning, which can help transformer-based models to learn a better representation of sentences. It firstly augmen…
University of Michigan（密歇根大学）；Amazon Web Services（亚马逊云科技）；Google Cloud AI（谷歌云人工智能）；KAIST（韩国科学技术院）；LG AI Research（LG人工智能研究院）
Contrastive representation learning has shown to be effective to learn representations from unlabeled data. However, much progress has been made in vision domains relying on data augmentations carefully designed using domain knowledge. In this work, we propose i-Mix, a simple yet effective domain-agnostic regularization strategy for improving contrastive representation learning. We cast contrastive learning as training a non-parametric classifier by assigning a unique virtual class to each data in a batch. Then, data instances are mixed in both the input and virtual label spaces, providing mor…
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）
DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of labeled data. They ignore the semantically similar and dissimilar constraints between different modalities, and cannot take advantage of unlabeled data. This paper proposes Cross-modal Deep Metric Learning with Multi-task Regularization (CDMLMR), which integrates quadruplet ranking loss and semi-supervised contrastive loss for modeling cross-modal semantic si…
Tsinghua University（清华大学）；Institute for Interdisciplinary Information Sciences（交叉信息研究院）
Is it possible to train several classifiers to perform meaningful crowd-sourcing to produce a better prediction label set without ground-truth annotation? This paper will modify the contrastive learning objectives to automatically train a self-complementing ensemble to produce a state-of-the-art prediction on the CIFAR10 and CIFAR100-20 tasks. This paper will present a straightforward method to modify a single unsupervised classification pipeline to automatically generate an ensemble of neural networks with varied decision boundaries to learn a more extensive feature set of classes. Loss Funct…
New York University（纽约大学）；Hyperfine Research（Hyperfine研究公司）；Yale University（耶鲁大学）
Establishing voxelwise semantic correspondence across distinct imaging modalities is a foundational yet formidable computer vision task. Current multi-modality registration techniques maximize hand-crafted inter-domain similarity functions, are limited in modeling nonlinear intensity-relationships and deformations, and may require significant re-engineering or underperform on new tasks, datasets, and domain pairs. This work presents ContraReg, an unsupervised contrastive representation learning approach to multi-modality deformable registration. By projecting learned multi-scale local patch fe…
Grid AI Labs（Grid人工智能实验室）；New York University（纽约大学）
Recent methods for self-supervised learning can be grouped into two paradigms: contrastive and non-contrastive approaches. Their success can largely be attributed to data augmentation pipelines which generate multiple views of a single input that preserve the underlying semantics. In this work, we introduce augmentation-augmented stochastic autoencoders (AASAE), yet another alternative to self-supervised learning, based on autoencoding. We derive AASAE starting from the conventional variational autoencoder (VAE), by replacing the KL divergence regularization, which is agnostic to the input dom…
University of Bonn（波恩大学）；ShanghaiTech University（上海科技大学）；Amazon Web Services（亚马逊云科技）
Contrastive learning has revolutionized self-supervised image representation learning field, and recently been adapted to video domain. One of the greatest advantages of contrastive learning is that it allows us to flexibly define powerful loss objectives as long as we can find a reasonable way to formulate positive and negative samples to contrast. However, existing approaches rely heavily on the short-range spatiotemporal salience to form clip-level contrastive signals, thus limit themselves from using global context. In this paper, we propose a new video-level contrastive learning method ba…
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）
Human beings can quickly adapt to environmental changes by leveraging learning experience. However, the poor ability of adapting to dynamic environments remains a major challenge for AI models. To better understand this issue, we study the problem of continual domain adaptation, where the model is presented with a labeled source domain and a sequence of unlabeled target domains. There are two major obstacles in this problem: domain shifts and catastrophic forgetting. In this work, we propose Gradient Regularized Contrastive Learning to solve the above obstacles. At the core of our method, grad…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
In this paper, we explore how to utilize pre-trained language model to perform few-shot text classification where only a few annotated examples are given for each class. Since using traditional cross-entropy loss to fine-tune language model under this scenario causes serious overfitting and leads to sub-optimal generalization of model, we adopt supervised contrastive learning on few labeled data and consistency-regularization on vast unlabeled data. Moreover, we propose a novel contrastive consistency to further boost model performance and refine sentence representation. After conducting exten…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University at Buffalo（布法罗大学）；Amazon（亚马逊）
Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open question how the modality alignment affects the downstream task performance. In this paper, based on an information-theoretic argument, we first prove that exact modality alignment is sub-optimal in general for downstream prediction tasks. Hence we advocate that the key of better performance lies in meaningful latent modality structures instead of perfect m…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carnegie Mellon University（卡内基梅隆大学）；Tencent（腾讯）
Graphs are powerful representations for relations among objects, which have attracted plenty of attention. A fundamental challenge for graph learning is how to train an effective Graph Neural Network (GNN) encoder without labels, which are expensive and time consuming to obtain. Contrastive Learning (CL) is one of the most popular paradigms to address this challenge, which trains GNNs by discriminating positive and negative node pairs. Despite the success of recent CL methods, there are still two under-explored problems. First, how to reduce the semantic error introduced by random topology bas…
Multi-label classification (MLC) is a prediction task where each sample can have more than one label. We propose a novel contrastive learning boosted multi-label prediction model based on a Gaussian mixture variational autoencoder (C-GMVAE), which learns a multimodal prior space and employs a contrastive loss. Many existing methods introduce extra complex neural modules like graph neural networks to capture the label correlations, in addition to the prediction modules. We find that by using contrastive learning in the supervised setting, we can exploit label information effectively in a data-d…
Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations. GCL can generate graph-level embeddings by maximizing the Mutual Information (MI) between different augmented views of the same graph (positive pairs). However, the GCL is limited by dimensional collapse, i.e., embedding vectors only occupy a low-dimensional subspace. In this paper, we show that the smoothing effect of the graph pooling and the implicit regularization of the graph convolution are two causes of the dimensional collapse in GCL. To…
Beyond Objective Expressivity: Geometry Preservation in Multimodal Contrastive Learning
Berlin Institute of Health, Charité - Universitätsmedizin Berlin（柏林健康研究院，柏林夏里特大学医学中心）；Department of Mathematics and Computer Science, Freie Universität Berlin（柏林自由大学数学与计算机科学系）；Intelligent Medicine Institute, Fudan University（复旦大学智能医学研究院）
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Contrastive representation learning seeks to acquire useful representations by estimating the shared information between multiple views of data. Here, the choice of data augmentation is sensitive to the quality of learned representations: as harder the data augmentations are applied, the views share more task-relevant information, but also task-irrelevant one that can hinder the generalization capability of representation. Motivated by this, we present a new robust contrastive learning scheme, coined RényiCL, which can effectively manage harder augmentations by utilizing Rényi divergence. Our …
Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）
Recent advances in contrastive learning have enlightened diverse applications across various semi-supervised fields. Jointly training supervised learning and unsupervised learning with a shared feature encoder becomes a common scheme. Though it benefits from taking advantage of both feature-dependent information from self-supervised learning and label-dependent information from supervised learning, this scheme remains suffering from bias of the classifier. In this work, we systematically explore the relationship between self-supervised learning and supervised learning, and study how self-super…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Google LLC（谷歌有限责任公司）；XaiPient
Pre-training representations (a.k.a. foundation models) has recently become a prevalent learning paradigm, where one first pre-trains a representation using large-scale unlabeled data, and then learns simple predictors on top of the representation using small labeled data from the downstream tasks. There are two key desiderata for the representation: label efficiency (the ability to learn an accurate classifier on top of the representation with a small amount of labeled data) and universality (usefulness across a wide range of downstream tasks). In this paper, we focus on one of the most popul…
Bootstrap Your Own Latent (BYOL) introduced an approach to self-supervised learning avoiding the contrastive paradigm and subsequently removing the computational burden of negative sampling associated with such methods. However, we empirically find that the image representations produced under the BYOL's self-distillation paradigm are poorly distributed in representation space compared to contrastive methods. This work empirically demonstrates that feature diversity enforced by contrastive losses is beneficial to image representation uniformity when employed in BYOL, and as such, provides grea…
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Amazon AWS AI（亚马逊云科技人工智能）
Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel regularization strategy to facilitate self-supervised speaker representation learning. Different from contrastive learning-based self-supervised learning methods, the proposed self-supervised regularization (SSReg) focuses exclusively on the similarity between the latent representations of positive data pairs. We also explore the effectiveness of alternative online dat…
Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
Aalborg University（奥尔堡大学）；University of Barcelona（巴塞罗那大学）；Computer Vision Center（计算机视觉中心）；Milestone Systems（里程碑系统公司）；Pioneer Center for Artificial Intelligence（先锋人工智能中心）
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Ant Group（蚂蚁集团）；University of Notre Dame（圣母大学）；Brandeis University（布兰迪斯大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）
This paper studies learning node representations with graph neural networks (GNNs) for unsupervised scenario. Specifically, we derive a theoretical analysis and provide an empirical demonstration about the non-steady performance of GNNs over different graph datasets, when the supervision signals are not appropriately defined. The performance of GNNs depends on both the node feature smoothness and the locality of graph structure. To smooth the discrepancy of node proximity measured by graph topology and node feature, we proposed SAIL - a novel \underline{S}elf-\underline{A}ugmented graph contra…
Breaking the Prototype Bias Loop: Confidence-Aware Federated Contrastive Learning for Highly Imbalanced Clients
Key Laboratory of Water Big Data Technology of Ministry of Water Resources, College of Computer Science and Software Engineering, Hohai University, Nanjing, China（水利部水大数据技术重点实验室，计算机科学与软件工程学院，河海大学，南京，中国）；Department of Computer Science, City University of Hong Kong, Hong Kong, China（计算机科学系，香港城市大学，香港，中国）；State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China（新型软件技术国家重点实验室，南京大学，南京，中国）；School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine, Nanjing, China（人工智能与信息技术学院，南京中医药大学，南京，中国）
Notable progress has been made in numerous fields of machine learning based on neural network-driven mutual information (MI) bounds. However, utilizing the conventional MI-based losses is often challenging due to their practical and mathematical limitations. In this work, we first identify the symptoms behind their instability: (1) the neural network not converging even after the loss seemed to converge, and (2) saturating neural network outputs causing the loss to diverge. We mitigate both issues by adding a novel regularization term to the existing losses. We theoretically and experimentally…
CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
Qwen Large Model Application Team, Alibaba Institute of Automation, Chinese Academy of Sciences（文勤大模型应用团队，阿里巴巴自动化研究所，中国科学院）；Qwen Large Model Application Team, Alibaba（文勤大模型应用团队，阿里巴巴）
University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming example is paired with ground-truth annotations. However, this clashes with many real-world applications: gathering labeled data, which is in itself tedious and expensive, becomes infeasible when data flow as a stream. This work explores Continual Semi-Supervised Learning (CSSL): here, only a small fraction of labeled input examples are shown to the learner. We assess how current CL methods (e.g.: EWC, LwF, iCaRL, ER, G…
Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high performance. In this study, we analyze that the consistency regularization restricts the propagation of labeling information due to the exclusion of samples with unconfident pseudo-labels in the model updates. Then, we propose contrastive regularization to improve both efficiency and accuracy of the consistency regularization by well-clustered features of unlabeled data. In specific, after strongly augmented samples ar…
Federated learning is widely used to perform decentralized training of a global model on multiple devices while preserving the data privacy of each device. However, it suffers from heterogeneous local data on each training device which increases the difficulty to reach the same level of accuracy as the centralized training. Supervised Contrastive Learning which outperform cross-entropy tries to minimizes the difference between feature space of points belongs to the same class and pushes away points from different classes. We propose Supervised Contrastive Federated Learning in which devices ca…
