Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach
Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；ByteDance（字节跳动）；National Institute of Health Data Science, Peking University（北京大学国家健康数据科学研究院）
并非所有正样本对都对时间序列对比学习有益。本文研究了两种可能损害通过对比学习所学时间序列表示质量的不良正样本对：噪声正样本对和错误正样本对。我们观察到，当存在噪声正样本对时，模型倾向于简单地学习噪声模式（噪声对齐）。同时，当出现错误正样本对时，模型会浪费大量精力去对齐不具代表性的模式（错误对齐）。为了解决这一问题，我们提出了一种动态坏正样本对挖掘（Dynamic Bad Pair Mining，DBPM）算法，该算法能够可靠地识别并抑制时间序列对比学习中的不良正样本对。具体而言，DBPM利用一个记忆模块在训练过程中动态跟踪每个正样本对的训练行为。这使我们能够在每个epoch根据其历史训练行为识别潜在的不良正样本对。随后，识别出的不良样本对通过一个变换模块被降权，从而减轻其对表示学习过程的负面影响。DBPM是一种简单的算法，被设计为无需可学习参数的轻量级插件，用于提升现有最先进方法的性能。通过在四个大规模真实世界时间序列数据集上进行的大量实验，我们证明了DBPM在减轻不良正样本对不利影响方面的有效性。
英文摘要：
Not all positive pairs are beneficial to time series contrastive learning. In this paper, we study two types of bad positive pairs that can impair the quality of time series representation learned through contrastive learning: the noisy positive pair and the faulty positive pair. We observe that, with the presence of noisy positive pairs, the model tends to simply learn the pattern of noise (Noisy Alignment). Meanwhile, when faulty positive pairs arise, the model wastes considerable amount of effort aligning non-representative patterns (Faulty Alignment). To address this problem, we propose a Dynamic Bad Pair Mining (DBPM) algorithm, which reliably identifies and suppresses bad positive pairs in time series contrastive learning. Specifically, DBPM utilizes a memory module to dynamically track the training behavior of each positive pair along training process. This allows us to identify potential bad positive pairs at each epoch based on their historical training behaviors. The identified bad pairs are subsequently down-weighted through a transformation module, thereby mitigating their negative impact on the representation learning process. DBPM is a simple algorithm designed as a lightweight plug-in without learnable parameters to enhance the performance of existing state-of-the-art methods. Through extensive experiments conducted on four large-scale, real-world time series datasets, we demonstrate DBPM's efficacy in mitigating the adverse effects of bad positive pairs.
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Emory University（埃默里大学）
Recently, heterogeneous Graph Neural Networks (GNNs) have become a de facto model for analyzing HGs, while most of them rely on a relative large number of labeled data. In this work, we investigate Contrastive Learning (CL), a key component in self-supervised approaches, on HGs to alleviate the label scarcity problem. We first generate multiple semantic views according to metapaths and network schemas. Then, by pushing node embeddings corresponding to different semantic views close to each other (positives) and pulling other embeddings apart (negatives), one can obtain informative representati…
Beijing Jiaotong University（北京交通大学）；Beijing Key Laboratory of Traffic Data Analysis and Mining（交通数据分析与挖掘北京市重点实验室）
The objective of this paper is to learn semantic representations for sleep stage classification from raw physiological time series. Although supervised methods have gained remarkable performance, they are limited in clinical situations due to the requirement of fully labeled data. Self-supervised learning (SSL) based on contrasting semantically similar (positive) and dissimilar (negative) pairs of samples have achieved promising success. However, existing SSL methods suffer the problem that many semantically similar positives are still uncovered and even treated as negatives. In this paper, we…
Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between Proteins
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）；Institute of Artificial Intelligence, Huazhong University of Science and Technology（华中科技大学人工智能研究院）；Hubei Key Laboratory of Brain-Inspired Intelligent Systems, Huazhong University of Science and Technology（华中科技大学湖北省类脑智能系统重点实验室）；Key Laboratory of Image Processing and Intelligent Control (Huazhong University of Science and Technology), Ministry of Education（华中科技大学图像信息处理与智能控制教育部重点实验室）
Query-based video grounding is an important yet challenging task in video understanding, which aims to localize the target segment in an untrimmed video according to a sentence query. Most previous works achieve significant progress by addressing this task in a fully-supervised manner with segment-level labels, which require high labeling cost. Although some recent efforts develop weakly-supervised methods that only need the video-level knowledge, they generally match multiple pre-defined segment proposals with query and select the best one, which lacks fine-grained frame-level details for dis…
In deep metric learning, the Triplet Loss has emerged as a popular method to learn many computer vision and natural language processing tasks such as facial recognition, object detection, and visual-semantic embeddings. One issue that plagues the Triplet Loss is network collapse, an undesirable phenomenon where the network projects the embeddings of all data onto a single point. Researchers predominately solve this problem by using triplet mining strategies. While hard negative mining is the most effective of these strategies, existing formulations lack strong theoretical justification for the…
Affinity Uncertainty-based Hard Negative Mining in Graph Contrastive Learning
Australian Artificial Intelligence Institute, University of Technology Sydney（悉尼科技大学澳大利亚人工智能研究院）；School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院）
Recently, learning from vast unlabeled data, especially self-supervised learning, has been emerging and attracted widespread attention. Self-supervised learning followed by the supervised fine-tuning on a few labeled examples can significantly improve label efficiency and outperform standard supervised training using fully annotated data. In this work, we present a novel self-supervised deep learning paradigm based on online hard negative pair mining. Specifically, we design a student-teacher network to generate multi-view of the data for self-supervised learning and integrate hard negative pa…
A lot of recent advances in unsupervised feature learning are based on designing features which are invariant under semantic data augmentations. A common way to do this is contrastive learning, which uses positive and negative samples. Some recent works however have shown promising results for non-contrastive learning, which does not require negative samples. However, the non-contrastive losses have obvious "collapsed" minima, in which the encoders output a constant feature embedding, independent of the input. A folk conjecture is that so long as these collapsed solutions are avoided, the prod…
Deep anomaly detection methods learn representations that separate between normal and anomalous images. Although self-supervised representation learning is commonly used, small dataset sizes limit its effectiveness. It was previously shown that utilizing external, generic datasets (e.g. ImageNet classification) can significantly improve anomaly detection performance. One approach is outlier exposure, which fails when the external datasets do not resemble the anomalies. We take the approach of transferring representations pre-trained on external datasets for anomaly detection. Anomaly detection…
La Trobe University（乐卓博大学）；Monash University（蒙纳士大学）
Anomaly detection from graph data has drawn much attention due to its practical significance in many critical applications including cybersecurity, finance, and social networks. Existing data mining and machine learning methods are either shallow methods that could not effectively capture the complex interdependency of graph data or graph autoencoder methods that could not fully exploit the contextual information as supervision signals for effective anomaly detection. To overcome these challenges, in this paper, we propose a novel method, Self-Supervised Learning for Graph Anomaly Detection (S…
Seoul National University（首尔国立大学）；Korea Institute of Energy Technology（韩国能源技术研究院）
Graph contrastive learning has become a powerful technique for several graph mining tasks. It learns discriminative representation from different perspectives of augmented graphs. Ubiquitous in our daily life, singed-directed graphs are the most complex and tricky to analyze among various graph types. That is why singed-directed graph contrastive learning has not been studied much yet, while there are many contrastive studies for unsigned and undirected. Thus, this paper proposes a novel signed-directed graph contrastive learning, SDGCL. It makes two different structurally perturbed graph view…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Standigm；Samsung Electronics（三星电子）；Samsung Advanced Institute of Technology (SAIT)（三星先进技术研究院）；AITRICS
Retrosynthesis, of which the goal is to find a set of reactants for synthesizing a target product, is an emerging research area of deep learning. While the existing approaches have shown promising results, they currently lack the ability to consider availability (e.g., stability or purchasability) of the reactants or generalize to unseen reaction templates (i.e., chemical reaction rules). In this paper, we propose a new approach that mitigates the issues by reformulating retrosynthesis into a selection problem of reactants from a candidate set of commercially available molecules. To this end, …
Many recent successes in sentence representation learning have been achieved by simply fine-tuning on the Natural Language Inference (NLI) datasets with triplet loss or siamese loss. Nevertheless, they share a common weakness: sentences in a contradiction pair are not necessarily from different semantic categories. Therefore, optimizing the semantic entailment and contradiction reasoning objective alone is inadequate to capture the high-level semantic structure. The drawback is compounded by the fact that the vanilla siamese or triplet losses only learn from individual sentence pairs or triple…
Xidian University（西安电子科技大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Embedded topic models are able to learn interpretable topics even with large and heavy-tailed vocabularies. However, they generally hold the Euclidean embedding space assumption, leading to a basic limitation in capturing hierarchical relations. To this end, we present a novel framework that introduces hyperbolic embeddings to represent words and topics. With the tree-likeness property of hyperbolic space, the underlying semantic hierarchy among words and topics can be better exploited to mine more interpretable topics. Furthermore, due to the superiority of hyperbolic geometry in representing…
National University of Singapore（新加坡国立大学）；Chinese Academy of Sciences（中国科学院）；SEA AI Lab（SEA AI实验室）
Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative visual features that are uniformly scattered in the feature space. During deployment, the common practice is to directly fine-tune CSL models with cross-entropy, which however may not be the best strategy in practice. Although cross-entropy tends to separate inter-class features, the resulting models still have limited capability for reducing intra-class feature scattering that exists in CSL models. In this paper, we in…
National University of Defense Technology（国防科技大学）；University of Science and Technology of China（中国科学技术大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Benefiting from the intrinsic supervision information exploitation capability, contrastive learning has achieved promising performance in the field of deep graph clustering recently. However, we observe that two drawbacks of the positive and negative sample construction mechanisms limit the performance of existing algorithms from further improvement. 1) The quality of positive samples heavily depends on the carefully designed data augmentations, while inappropriate data augmentations would easily lead to the semantic drift and indiscriminative positive samples. 2) The constructed negative samp…
Learning Robust Representations for Malicious Content Detection via Contrastive Sampling and Uncertainty Estimation
1 College of Engineering；Computer Science, University of Central Florida, Orlando, USA, 2 Department of Computer Science \& Engineering, Mississippi State University, MS State, USA , 3 Department of Computer Science, University of Nevada, Las Vegas, USA
University of Chinese Academy of Sciences（中国科学院大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph representations without human annotations. Although remarkable progress has been witnessed recently, the success behind GCL is still left somewhat mysterious. In this work, we first identify several critical design considerations within a general GCL paradigm, including augmentation functions, contrasting modes, contrastive objectives, and negative mining techniques. Then, to understand the interplay of different GCL components, we conduct extensive, controlled experiments over a set of benchmark tasks on datasets a…
Queen’s University Belfast（贝尔法斯特女王大学）；Anyvision Research Team（Anyvision研究团队）
Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large fraction of trivial samples. Therefore, most existing methods generally resort to sample mining strategies for selecting nontrivial samples to accelerate convergence and improve performance. In this work, we identify two critical limitations of the sample mining methods, and provide solutions for both of them. First, previous mining methods assign one binary s…
Fudan University（复旦大学）；ByteDance AI Lab（字节跳动人工智能实验室）；Tongji University（同济大学）
The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events, etc. However, existing methods commonly process the frames of a video as individual images or short clips, making the modeling of long-range semantic dependencies difficult. In this paper, we propose TCA (Temporal Context Aggregation for Video Retrieval), a video representation learning framework that incorporates long-range temporal information between frame-level features using the self-attention mechanism. To tr…
North University of China（中北大学）；Dalian University of Technology（大连理工大学）
Predicting medications is a crucial task in many intelligent healthcare systems. It can assist doctors in making informed medication decisions for patients according to electronic medical records (EMRs). However, medication prediction is a challenging data mining task due to the complex relations between medical codes. Most existing studies focus on utilizing inherent relations between homogeneous codes of medical ontology graph to enhance their representations using supervised methods, and few studies pay attention to the valuable relations between heterogeneous or homogeneous medical codes f…
North China Electric Power University（华北电力大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Beihang University（北京航空航天大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
Virginia Tech（弗吉尼亚理工大学）；Space Dynamics Laboratory（空间动力学实验室）
The availability of wide-ranging third-party intellectual property (3PIP) cores enables integrated circuit (IC) designers to focus on designing high-level features in ASICs/SoCs. The massive proliferation of ICs brings with it an increased number of bad actors seeking to exploit those circuits for various nefarious reasons. This is not surprising as integrated circuits affect every aspect of society. Thus, malicious logic (Hardware Trojans, HT) being surreptitiously injected by untrusted vendors into 3PIP cores used in IC design is an ever present threat. In this paper, we explore methods for …
University of Pittsburgh（匹兹堡大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
Recently brain networks have been widely adopted to study brain dynamics, brain development and brain diseases. Graph representation learning techniques on brain functional networks can facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative diseases. However, current graph learning techniques have several issues on brain network mining. Firstly, most current graph learning models are designed for unsigned graph, which hinders the analysis of many signed network data (e.g., brain functional networks). Meanwhile, the insufficiency of brain network data limits …
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Recent years have witnessed growing interests in multimedia recommendation, which aims to predict whether a user will interact with an item with multimodal contents. Previous studies focus on modeling user-item interactions with multimodal features included as side information. However, this scheme is not well-designed for multimedia recommendation. Firstly, only collaborative item-item relationships are implicitly modeled through high-order item-user-item co-occurrences. We argue that the latent semantic item-item structures underlying these multimodal contents could be beneficial for learnin…
College of Computer, National University of Defense Technology（国防科技大学计算机学院）；College of Intelligence Science and Technology, National University of Defense Technology（国防科技大学智能科学学院）；Northwestern Polytechnical University（西北工业大学）；Beijing Information Science and Technology University（北京信息科技大学）
Contrastive deep graph clustering, which aims to divide nodes into disjoint groups via contrastive mechanisms, is a challenging research spot. Among the recent works, hard sample mining-based algorithms have achieved great attention for their promising performance. However, we find that the existing hard sample mining methods have two problems as follows. 1) In the hardness measurement, the important structural information is overlooked for similarity calculation, degrading the representativeness of the selected hard negative samples. 2) Previous works merely focus on the hard negative sample …
Enhancing Ethereum Fraud Detection via Generative and Contrastive Self-supervision
Zhejiang University of Technology（浙江工业大学）；Binjiang Institute of Artificial Intelligence, ZJUT（浙江工业大学滨江人工智能研究院）；Science and Technology on Communication Information Security Control Laboratory（通信信息安全控制技术实验室）
