Time series analysis has achieved great success in diverse applications such as network security, environmental monitoring, and medical informatics. Learning similarities among different time series is a crucial problem since it serves as the foundation for downstream analysis such as clustering and anomaly detection. It often remains unclear what kind of distance metric is suitable for similarity learning due to the complex temporal dynamics of the time series generated from event-triggered sensing, which is common in diverse applications, including automated driving, interactive healthcare, and smart home automation. The overarching goal of this paper is to develop an unsupervised learning framework that is capable of learning task-aware similarities among unlabeled event-triggered time series. From the machine learning vantage point, the proposed framework harnesses the power of both hierarchical multi-scale sequence autoencoders and Gaussian Mixture Model (GMM) to effectively learn the low-dimensional representations from the time series. Finally, the obtained similarity measure can be easily visualized for explaining. The proposed framework aspires to offer a stepping stone that gives rise to a systematic approach to model and learn similarities among a multitude of event-triggered time series. Through extensive qualitative and quantitative experiments, it is revealed that the proposed method outperforms state-of-the-art methods considerably.
Locality-Aware Redundancy Pruning for LLM Depth Compression
University of Southern California(美国南加州大学);Neural Superintelligence Lab, MODULABS(MODULABS神经超级智能实验室);Seoul National University(首尔国立大学);Inha University(釜山大学)
Cluster-Aware Similarity Diffusion for Instance Retrieval
University of Science and Technology of China(中国科学技术大学);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)
Similarity-based context aware continual learning for spiking neural networks
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);Chinese Academy of Sciences(中国科学院);Center for Long-term Artificial Intelligence(长期人工智能中心)
Structure-aware Hybrid-order Similarity Learning for Multi-view Unsupervised Feature Selection
Joint Laboratory of Data Science and Business Intelligence, School of Statistics and Data Science, Southwestern University of Finance and Economics(数据科学与商务智能联合实验室,统计与数据科学学院,西南财经大学);Big Data Laboratory on Financial Security and Behavior, SWUFE (Laboratory of Philosophy and Social Sciences, Ministry of Education)(金融安全与行为大数据实验室,SWUFE(哲学社会科学实验室,教育部));Department of Electrical Engineering and Computer Science, University of Kansas(电气与计算机工程系,堪萨斯大学);School of Computing and Artificial Intelligence, Southwest Jiaotong University(计算与人工智能学院,西南交通大学)
Structural-Aware Sentence Similarity with Recursive Optimal Transport
Research Institute of Information Technology(信息技术研究所);Beijing National Research Center for Information Science and Technology (BNRist)(北京信息科学与技术国家研究中心);Tsinghua University(清华大学)
H+: An Efficient Similarity-Aware Aggregation for Byzantine Resilient Federated Learning
Beijing Institute of Technology(北京理工大学);Southwest University(西南大学);Sun Yat-Sen University(中山大学);The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳))
TagBO: LLM-Driven Task-Aware Graph Bayesian Optimization for Scientific Discovery
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Harbin Institute of Technology(哈尔滨工业大学);Fudan University(复旦大学);Shenzhen Loop Area Institute(深圳河套学院);Shanghai Jiao Tong University(上海交通大学);Central South University(中南大学);Huazhong Agricultural University(华中农业大学)
Human-Centric Aware UAV Trajectory Planning in Search and Rescue Missions Employing Multi-Objective Reinforcement Learning with AHP and Similarity-Based Experience Replay
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg(卢森堡大学安全、可靠性与信任跨学科中心);University of Luxembourg(卢森堡大学)
有效检测假新闻最近引起了极大的关注。目前的研究在预测假新闻方面做出了重大贡献,但较少关注利用新闻文章中文本和视觉信息之间的关系(相似性)。重视这种相似性有助于识别假新闻故事,例如,试图使用不相关的图像来吸引读者的注意力。在这项工作中,我们提出了一个$\mathsf{S}$ imilarity- $\mathsf{A}$ ware $\mathsf{F}$ ak $\mathsf{E}$新闻检测方法($\mathsf{SAFE}$),调查多模态(文本和视觉)信息的新闻文章。首先,采用神经网络分别提取新闻文本和视觉特征。我们进一步研究跨模态提取的特征之间的关系。新闻文本和视觉信息的这种表示及其关系被联合学习并用于预测假新闻。提出的方法有助于识别虚假的新闻文章的基础上,他们的文字,图像,或他们的“不匹配”。“我们对大规模的真实数据进行了广泛的实验,证明了所提出的方法的有效性。
Dynamic Graph with Similarity-Aware Attention Graph Neural Network for Recommender Systems
Department of Computer Science and Engineering(计算机科学与工程系);SRM University Andhra Pradesh(安得拉邦SRM大学);Mangalagiri, Andhra Pradesh 522502, India(安得拉邦马加拉加里522502, 印度)
Hierarchy-Aware Neural Subgraph Matching with Enhanced Similarity Measure
College of Computer Science and Technology, National University of Defense Technology(计算机科学与技术学院,国防科技大学);College of Information and Communication, National University of Defense Technology(信息与通信学院,国防科技大学)
TieFake: Title-Text Similarity and Emotion-Aware Fake News Detection
University of Electronic Science and Technology of China(电子科技大学);th Research Institute of China Electronics Technology Group Corporation(中国电子科技集团公司第三十研究所)
Beyond Pixel Similarity: Task-Aware Evaluation of GAN-Based Synthetic Sonar Data for Robotic Perception
XITASO GmbH IT & Software Solutions(XITASO信息技术与软件解决方案有限公司);National University of Sciences and Technology (NUST)(国立科技大学);Technical University of Kaiserslautern(凯泽斯劳滕工业大学)