WWW 2026 | 时间序列（Time Series）论文总结（预测，生成，插补，分类，异常检测等）

时空探索之旅

发布于 2026-03-10 16:13:24

590

文章被收录于专栏：时空探索之旅时空探索之旅

WWW 2026将在2026年4月13日到17日于阿联酋迪拜（Dubai, United Arab Emirates）举行。

本文总结了WWW 2026上有关时间序列（time series）的相关论文，包含Research，industry和Web4Good3个Track的论文，总计27篇，如有疏漏，欢迎补充。

Research Track录用列表：https://www2026.thewebconf.org/accepted/research-tracks.html

Industry Track录用列表:

https://www2026.thewebconf.org/accepted/industry.html

Web4Good Track录用列表：https://www2026.thewebconf.org/accepted/web4good.html

Web4Good的介绍（Call for Papers, CFP）：https://www2026.thewebconf.org/calls/web4good.html（这个是收录了proceeding的，各个学校对该track是否是CCF A的认定，欢迎大家补充相关信息）

时间序列Topic：预测，分类，异常检测，插补，生成等任务，以及LLM，MLLM，VLM，KAN和Mamba等技术在上述任务中的应用。

Research1. EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysis2. Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning3. Cross-city Time Series Forecasting with Retrieval-Augmented Large Language Models4. Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification5. Automated Model Selection for Multivariate Time Series Forecasting6. SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting7. Dynamic Multi-period Experts for Online Time Series Forecasting8. Efficient High-Dimensional Time Series Forecasting with Transformers: A Channel Reordering Perspective9. Re-Diffusion: Modeling Latent Residuals with Diffusion for Time-Series Forecasting10. Time-TK: A Multi-Offset Temporal Interaction Framework Combining Transformer and Kolmogorov-Arnold Networks for Time Series Forecasting11. FedRMamba: Federated Residual Mamba for Multivariate Time-Series Forecasting12. QuiZSF: A Retrieval-Augmented Framework for Zero-Shot Time Series Forecasting13. GFMixer: Decoupled Temporal Gradient and Fourier-Aware Attention for Time Series Forecasting14. Byte-token Enhanced Language Models for Temporal Point Processes Analysis15. FSDI: Frequency-Shaped Diffusion For Time-Series Imputation16. TimeMar: Multi-Scale Autoregressive Modeling for Unconditional Time Series Generation17. Can Multimodal LLMs Perform Time Series Anomaly Detection?18. ViTs: Teaching Machines to See Time Series Anomalies Like Human Experts19. Evolving Proxy Kills Drift: Data-Efficient Streaming Time Series Anomaly Detection20. FedDiG: Frequency-Guided Diffusion Diversity for Generalizable Federated Time Series Classification21. We Need a More Robust Classifier: Dual Causal Learning Empowers Domain-Incremental Time Series Classification22. Predictability-Aware Compression and Decompression Framework for Multichannel Time Series Data with Latent Seasonality23. Interpretable Dynamic Network Modeling of Tensor Time Series via Kronecker Time-Varying Graphical Lasso24. Lifting Manifolds to Mitigate Pseudo-Alignment in LLM4TSIndustry25. Delay-Aware Graph Neural Stochastic Differential Equations for Financial Time Series Modeling and ForecastingWeb4Good26. Toward Green Computing: General Carbon Intensity Forecasting via Dual Graph Empowered Time Series Foundation Model 27. Energy-Efficient Training-Free Zero-Inflation Correction for Rainfall Forecasting with Time-Series Foundation Models

Research

1 EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysis

链接：https://arxiv.org/abs/2602.02551

作者：Hua Wang, Jinghao Lu and Fan Zhang

关键词：预测，优化器

2 Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning

链接：https://arxiv.org/abs/2601.07903

作者：Jianqi Zhang, Jingyao Wang, Wenwen Qiang, Fanjiang Xu and Changwen Zheng

关键词：预测，LLM，上下文学习

3 Cross-city Time Series Forecasting with Retrieval-Augmented Large Language Models

链接：https://arxiv.org/abs/2508.18635

作者：Yue Jiang, Chenxi Liu, Yile Chen, Qin Chao, Shuai Liu, Cheng Long and Gao Cong

关键词：跨城市时空预测，LLM，迁移学习

4 Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification

链接：https://arxiv.org/abs/2602.16224

作者：Xu Zhang, Peng Wang, Yichen Li and Wei Wang

关键词：预测，分类，摊销

5 Automated Model Selection for Multivariate Time Series Forecasting

作者：Xiaoxuan Fan, Jiaqi Sun, Xianjun Deng, Qiankun Zhang, Wei Xiang, Shenghao Liu and Lingzhi Yi

关键词：预测，模型选择

6 SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting

链接：https://arxiv.org/abs/2602.16220

作者：Xu Zhang, Qitong Wang, Peng Wang and Wei Wang

关键词：长时预测，MLP

7 Dynamic Multi-period Experts for Online Time Series Forecasting

作者：Seungha Hong, Sukang Chae, Suyeon Kim, Sanghwan Jang and Hwanjo Yu

关键词：在线预测，混合专家

8 Efficient High-Dimensional Time Series Forecasting with Transformers: A Channel Reordering Perspective

作者：Yuchen Fang, Shiyu Wang, Yuxuan Liang, Zhou Ye, Yang Xiang, Yan Zhao and Kai Zheng

关键词：高维预测，通道重排序

9 Re-Diffusion: Modeling Latent Residuals with Diffusion for Time-Series Forecasting

作者：Boning Zhang, Haishuai Wang, Zehong Hu, Jiajun Wang, Hongyi Zhang and Jia Jia

关键词：预测，扩散模型，残差

10 Time-TK: A Multi-Offset Temporal Interaction Framework Combining Transformer and Kolmogorov-Arnold Networks for Time Series Forecasting

链接：https://arxiv.org/abs/2602.11190

作者：Fan Zhang, Shiming Fan and Hua Wang

关键词：预测，KAN，表示学习

11 FedRMamba: Federated Residual Mamba for Multivariate Time-Series Forecasting

作者：Zhiwei Hu, Liang Zhang and Guangxu Zhu

关键词：预测，联邦学习，Mamba

12 QuiZSF: A Retrieval-Augmented Framework for Zero-Shot Time Series Forecasting

链接：https://arxiv.org/abs/2508.06915

作者：Shichao Ma, Zhengyang Zhou, Qihe Huang, Binwu Wang and Yang Wang

关键词：零样本预测，RAG

13 GFMixer: Decoupled Temporal Gradient and Fourier-Aware Attention for Time Series Forecasting

作者：Lin Zhang, Qing Li and Jingmei Zhao

关键词：预测，时域，频域

14 Byte-token Enhanced Language Models for Temporal Point Processes Analysis

链接：https://arxiv.org/abs/2502.07139

作者：Quyu Kong, Yixuan Zhang, Yang Liu, Panrong Tong, Enqi Liu and Feng Zhou

关键词：时间点过程，大模型，事件分析

15 FSDI: Frequency-Shaped Diffusion For Time-Series Imputation

作者：Wangmeng Shen, Hongfan Gao, Qingsong Zhong, Dingli Xu and Jilin Hu

关键词：插补，扩散，频域

16 TimeMar: Multi-Scale Autoregressive Modeling for Unconditional Time Series Generation

链接：https://arxiv.org/abs/2601.11184

作者：Xiangyu Xu, Qingsong Zhong and Jilin Hu

关键词：无条件时序生成，自回归

17 Can Multimodal LLMs Perform Time Series Anomaly Detection?

链接：https://arxiv.org/abs/2502.17812

作者：Xiongxiao Xu, Haoran Wang, Yueqing Liang, Philip S. Yu, Yue Zhao and Kai Shu

关键词：异常检测，多模态大模型

18 ViTs: Teaching Machines to See Time Series Anomalies Like Human Experts

链接：https://arxiv.org/abs/2510.04710

作者：Zexin Wang, Changhua Pei, Yang Liu, Hengyue Jiang, Quan Zhou, Haotian Si, Hang Cui, Jianhui Li, Gaogang Xie, Jingjing Li and Dan Pei

关键词：异常检测，视觉模型

19 Evolving Proxy Kills Drift: Data-Efficient Streaming Time Series Anomaly Detection

作者：Qing Wei, Hao Miao, Yan Zhao, Kai Zheng, Bin Yang, Volker Markl and Christian S. Jensen

关键词：异常检测，流式数据

20 FedDiG: Frequency-Guided Diffusion Diversity for Generalizable Federated Time Series Classification

作者：Haoran Shi, Junru Zhang, Cheng Peng, Xiaoli Tang, Longtao Huang and Han Yu

关键词：分类，频域，联邦

21 We Need a More Robust Classifier: Dual Causal Learning Empowers Domain-Incremental Time Series Classification

链接：https://arxiv.org/abs/2601.10312

作者：Zhipeng Liu, Peibo Duan, Xuan Tang, Haodong Jing, Mingyang Geng, Yongsheng Huang, Jialu Xu, Bin Zhang and Binwu Wang

关键词：分类，增量学习，稳健性

22 Predictability-Aware Compression and Decompression Framework for Multichannel Time Series Data with Latent Seasonality

链接：https://arxiv.org/abs/2506.00614

作者：Ziqi Liu, Pei Zeng and Yi Ding

关键词：季节性，压缩和解压

23 Interpretable Dynamic Network Modeling of Tensor Time Series via Kronecker Time-Varying Graphical Lasso

链接：https://arxiv.org/abs/2602.08197

作者：Shingo Higashiguchi, Koki Kawabata, Yasuko Matsubara and Yasushi Sakurai

关键词：张量时间序列、图形套索、网络推理

24 Lifting Manifolds to Mitigate Pseudo-Alignment in LLM4TS

链接：https://arxiv.org/abs/2510.12847

作者：Liangwei Nathan Zheng, Wenhao Liang, Wei Emma Zhang, Miao Xu, Olaf Maennel and Weitong Chen

关键词：LLM，伪对齐

Industry

25 Delay-Aware Graph Neural Stochastic Differential Equations for Financial Time Series Modeling and Forecasting

作者：Mingjie You:Tongji University;Dawei Cheng:Tongji University;Meilin Zhang:Tongji University;Peng Zhu:Tongji University;Yuqi Liang:Seek Data Group, Emoney Inc.

关键词：金融时序建模，图随机微分方程

Web4Good

26 Toward Green Computing: General Carbon Intensity Forecasting via Dual Graph Empowered Time Series Foundation Model

作者：Xiaoyang Zhang:Hong Kong Polytechnic University;Taiqi Zhou:Hong Kong Polytechnic University;Fang He:Hong Kong Polytechnic University;Yang Deng:Hong Kong Polytechnic University;Dan Wang:Hong Kong University of Science and Technology

关键词：基础模型，绿色计算

27 Energy-Efficient Training-Free Zero-Inflation Correction for Rainfall Forecasting with Time-Series Foundation Models

作者：Wentao Gao:Adelaide University;Xiaojing Du:Adelaide University;Xiongren Chen:Adelaide University;Yifan Guo:Adelaide University;Andres Mauricio Cifuentes-Bernal:Adelaide University;Renqiang Luo:Jilin University;Ziqi Xu:RMIT University

关键词：降雨预测，基础模型，节能