WSDM 2025 | 时间序列（time series）论文总结

WSDM 2025于2025年3月10号到14号在德国汉诺威举行（Hannover, Germany）

本文总结了WSDM 2024有关时间序列（time series）的相关论文，如有疏漏，欢迎大家补充。（从标题看是没有时空数据相关的论文）

时间序列Topic：异常检测，表示学习，分类。总计3篇。

点击文末阅读原文跳转笔者知乎链接（跳转论文链接更方便）。

1 Prospective Multi-Graph Cohesion for Multivariate Time Series Anomaly Detection

作者：iazhen Chen (University of Waterloo)*; Mingbin Feng (University of Waterloo); Tony S. Wirjanto (University of Waterloo)

关键词：时间序列异常检测

2 Cross-Domain Pre-training with Language Models for Transferable Time Series Representations

链接：https://arxiv.org/abs/2403.12372

作者：Mingyue Cheng (University of Science and Technology of China)*; Xiaoyu Tao (University of Science and Technology of China); Qi Liu (” University of Science and Technology of China, China”); Hao Zhang (University of Science and Technology of China); Yiheng Chen (USTC); Defu Lian (University of Science and Technology of China)

关键词：表示学习，自监督预训练

3 Empowering Time Series Classification with Multimodal Language Modeling

链接：https://arxiv.org/abs/2403.12371

作者：Mingyue Cheng (University of Science and Technology of China)*; Yiheng Chen (USTC); Qi Liu (” University of Science and Technology of China, China”); Zhiding Liu (University of Science and Technology of China); Yucong Luo (University of Science and Technology of China); Enhong Chen (University of Science and Technology of China)

关键词：时间序列分类，多模态

相关链接

WSDM 2025接受论文：https://www.wsdm-conference.org/2025/accepted-papers/