Explaining Time Series via Contrastive and Locally Sparse Perturbations
Nanjing University（南京大学）；Ailibaba Group（阿里巴巴集团）；Pennsylvania State University（宾夕法尼亚州立大学）；Tsinghua University（清华大学）；Florida International University（佛罗里达国际大学）；New Jersey Institute of Technology（新泽西理工学院）；A*STAR（新加坡科技研究局）；The University of Hong Kong（香港大学）
Zichuan Liu, Yingying Zhang, Tianchun Wang, Zefan Wang, Dongsheng Luo, Mengnan Du, Min Wu, Yi Wang, Chunlin Chen, Lunting Fan, Qingsong Wen
Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns. Although previous saliency-based methods addressed the challenges, their perturbation may not alleviate the distribution shift issue, which is inevitable especially in heterogeneous samples. We present ContraLSP, a locally sparse model that introduces counterfactual samples to build uninformative perturbations but keeps distribution using contrastive learning. Furthermore, we incorporate sample-specific sparse gates to generate more binary-skewed and smooth masks, which easily integrate temporal trends and select the salient features parsimoniously. Empirical studies on both synthetic and real-world datasets show that ContraLSP outperforms state-of-the-art models, demonstrating a substantial improvement in explanation quality for time series data. The source code is available at \url{https://github.com/zichuan-liu/ContraLSP}.
Global Concept Explanations for Graphs by Contrastive Learning
Institute of Theoretical Informatics, Karlsruhe Insitute of Technology, Kaiserstr. 12, 76131 Karlsruhe, Germany Institute of Nanotechnology, Karlsruhe Insitute of Technology, Kaiserstr. 12, 76131 Karlsruhe, Germany
Evidential Spectrum-Aware Contrastive Learning for OOD Detection in Dynamic Graphs
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；Beijing Wuzi University（北京武术大学）
Cross-Subject EEG Emotion Recognition Based on Temporal Asynchronous Alignment Contrastive Learning
School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University（中山大学生物医学工程学院深圳校区）；School of Computer Science and Technology, Tianjin University（天津大学计算机科学与技术学院）
Contrastive Learning Meets Pseudo-label-assisted Mixup Augmentation: A Comprehensive Graph Representation Framework from Local to Global
School of Information Science and Technology, Beijing University of Technology（北京工业大学信息科学与技术学院）；The University of Sydney Business School, The University of Sydney（悉尼大学商学院）；College of Information Science and Technology, Beijing University of Chemical Technology（北京化工大学信息科学与技术学院）
VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection
Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI)（安达卢西亚数据科学与计算智能研究 institute）；Department of Computer Science and Artificial Intelligence (DECSAI), University of Granada（格拉纳达大学计算机科学与人工智能系）
FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularization
Hanoi University of Science and Technology（河内科学技术大学）；Nagoya University（名古屋大学）；Washington State University（华盛顿州立大学）；Swiss Federal Institute of Technology Lausanne（洛桑联邦理工学院）
