VISTA: Unsupervised 2D Temporal Dependency Representations for Time Series Anomaly Detection
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；University of Glasgow（格拉斯哥大学）；University College London（伦敦大学学院）；Collaborative Innovation Center for Transport Studies, Dalian Maritime University（大连海事大学交通协同创新中心）；Department of Electric Engineering, Tsinghua University（清华大学电机工程系）；Shenzhen Skyworth AI Co. ,Ltd（深圳创维人工智能有限公司）
Sinchee Chin, Fan Zhang, Xiaochen Yang, Jing-Hao Xue, Wenming Yang, Peng Jia, Guijin Wang, Luo Yingqun
Time Series Anomaly Detection (TSAD) is essential for uncovering rare and potentially harmful events in unlabeled time series data. Existing methods are highly dependent on clean, high-quality inputs, making them susceptible to noise and real-world imperfections. Additionally, intricate temporal relationships in time series data are often inadequately captured in traditional 1D representations, leading to suboptimal modeling of dependencies. We introduce VISTA, a training-free, unsupervised TSAD algorithm designed to overcome these challenges. VISTA features three core modules: 1) Time Series Decomposition using Seasonal and Trend Decomposition via Loess (STL) to decompose noisy time series into trend, seasonal, and residual components; 2) Temporal Self-Attention, which transforms 1D time series into 2D temporal correlation matrices for richer dependency modeling and anomaly detection; and 3) Multivariate Temporal Aggregation, which uses a pretrained feature extractor to integrate cross-variable information into a unified, memory-efficient representation. VISTA's training-free approach enables rapid deployment and easy hyperparameter tuning, making it suitable for industrial applications. It achieves state-of-the-art performance on five multivariate TSAD benchmarks.
Unsupervised Dependency Parsing: Let's Use Supervised Parsers
Institute for Logic, Language, and Computation（逻辑、语言与计算研究所）；University of Amsterdam（阿姆斯特丹大学）
我们提出了一个自我训练的方法来无监督依存句法分析，重用现有的监督和无监督解析算法。我们的方法，被称为“迭代重排序”（IR），开始与依赖树生成的无监督解析器，并迭代地提高这些树使用更丰富的概率模型中使用的监督解析，反过来训练这些树。我们的系统在WSJ语料库上的准确率比Spitkovsky et al.（2013）的部分状态解析器高出1.8%。
Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behavior
School of Mechanical Engineering, Yonsei University（延世大学机械工程学院）；Department of Artificial Intelligence, Yonsei University（延世大学人工智能系）；Department of Mechanical Engineering, University of California, Berkeley（加州大学伯克利分校机械工程系）
Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition
National Laboratory of Pattern Recognition, CASIA, Beijing, China（中国科学院自动化研究所模式识别国家重点实验室，北京，中国）；CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China（中国科学院脑科学与智能技术卓越创新中心，北京，中国）；School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China（中国科学院大学人工智能学院，北京，中国）
Enhancing Node-Level Graph Domain Adaptation by Alleviating Local Dependency
Huazhong University of Science and Technology（华中科技大学）；School of Cyber Science and Engineering（网络科学与工程学院）；Hubei Key Laboratory of Distributed System Security（湖北省分布式系统安全重点实验室）；Hubei Engineering Research Center on Big Data Security（大数据安全工程研究中心）；Zhongguancun Academy（中关村学院）；Zu Chongzhi Center, Digital Innovation Research Center（祖冲之中心，数字创新研究中心）；Duke Kunshan University（杜克大学昆山分校）
Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation
Institute for Infocomm Research, A ∗ STAR, Singapore（信息与通信研究所，新加坡A ∗ STAR）；School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（电气与电子工程学院，南洋理工大学）；College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, China（人工智能学院，南京航空航天大学）；Fraunhofer Institute for Integrated Circuits, Germany（弗劳恩霍夫集成电路研究所，德国）；College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学）
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore（新加坡南洋理工大学电气与电子工程学院）；School of Computer Science and Engineering, Nanyang Technological University, Singapore（新加坡南洋理工大学计算机科学与工程学院）
