IJCAI 2025 | 时间序列(Time Series)论文总结

IJCAI 2025将在2025年8月16日到8月22日于加拿大蒙特利尔（Montreal, Canada）和2025年8月28日到31日在中国广州（Guangzhou, China）举行。IJCAI 2025共有5404篇投稿，共录取了1042篇论文，录取率19.3%。

本文总结了2025 IJCAI上有关时间序列（time series）相关论文，共计26篇。

时间序列Topic：预测，异常检测，因果发现，时序分析，LLM应用，多模态等。其中23-26为Survey Track，1为蒙特利尔会场，其余Main Track论文为广州会场。

[Montreal]1. CASA: CNN Autoencoder-based Score Attention for Efficient Multivariate Long-term Time-series Forecasting

2. AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting

3. Non-collective Calibrating Strategy for Time Series Forecasting

4. TCDM: A Temporal Correlation-Empowered Diffusion Model for Time Series Forecasting

5. QuantileFormer: Probabilistic Time Series Forecasting with a Pattern-Mixture Decomposed VAE Transformer

6. Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern

7. Causal View of Time Series Imputation: Some Identification Results on Missing Mechanism

8. Conditional Information Bottleneck-Based Multivariate Time Series Forecasting

9. FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecasting

10. LLM-TPF: Multiscale Temporal Periodicity-Semantic Fusion LLMs for Time Series Forecasting

11. Learning to Extrapolate and Adjust: Two-Stage Meta-Learning for Concept Drift in Online Time Series Forecasting

12. MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning

13. T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models

14. State Feedback Enhanced Graph Differential Equations for Multivariate Time Series Forecasting

15. FreqLLM: Frequency-Aware Large Language Models for Time Series Forecasting

16. Efficient Constraint-based Window Causal Graph Discovery in Time Series with Multiple Time Lags

17. CRAFT: Time Series Forecasting with Cross-Future Behavior Awareness

18. MMNet: Missing-Aware and Memory-Enhanced Network for Multivariate Time Series Imputation

19. Conditional Denoising Meets Polynomial Modeling: A Flexible Decoupled Framework for Time Series Forecasting

20. DGraFormer: Dynamic Graph Learning Guided Multi-Scale Transformer for Multivariate Time Series Forecasting

21. RTdetector: Deep Transformer Networks for Time Series Anomaly Detection Based on Reconstruction Trend

22. General Incomplete Time Series Analysis via Patch Dropping Without Imputation

Survey Track

23. Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era

24. Deep Learning for Multivariate Time Series Imputation: A Survey

25. Harnessing Vision Models for Time Series Analysis: A Survey

26. Comprehensive Review of Neural Differential Equations for Time Series Analysis

说明:如果论文总结中有（模型）图，则论文已经在网络上公开（arXiv，OpenReview等）。

[Montreal]1 CASA: CNN Autoencoder-based Score Attention for Efficient Multivariate Long-term Time-series Forecasting

链接：https://arxiv.org/abs/2505.02011

作者：Minhyuk Lee, Hyekyung Yoon, MyungJoo Kang

关键词：多元时间序列预测，CNN，自编码器

2 AdaMixT: Adaptive Weighted Mixture of Multi-Scale Expert Transformers for Time Series Forecasting

作者：Huanyao Zhang, Jiaye Lin, Wentao Zhang, Haitao Yuan, Guoliang Li

关键词：预测，专家系统，Transformer

3 Non-collective Calibrating Strategy for Time Series Forecasting

链接：https://www.arxiv.org/abs/2506.03176

作者：Bin Wang, Yongqi Han, Minbo Ma, Tianrui Li, Junbo Zhang, Feng Hong, Yanwei Yu

关键词：预测，校准策略

4 TCDM: A Temporal Correlation-Empowered Diffusion Model for Time Series Forecasting

作者：Huibo Xu, Likang Wu, Xianquan Wang, Zhiding Liu, Qi Liu

关键词：预测，扩散模型，时间相关性

5 QuantileFormer: Probabilistic Time Series Forecasting with a Pattern-Mixture Decomposed VAE Transformer

作者：Yimiao Shao, Wenzhong Li, Kang Xia, Kaijie Lin, Mingkai Lin, Sanglu Lu

关键词：概率预测，分位数

6 Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern

作者：Jiahong Xiong, Chengsen Wang, Haifeng Sun, Yuhan Jing, Qi Qi, Zirui Zhuang, Lei Zhang, Jianxin Liao, Jingyu Wang

关键词：预测，多模态，LLM

7 Causal View of Time Series Imputation: Some Identification Results on Missing Mechanism

链接：https://www.arxiv.org/abs/2505.07180

作者：Ruichu Cai, Kaitao Zheng, Junxian Huang, Zijian Li, Zhengming Chen, Boyan Xu, Zhifeng Hao

关键词：插补，因果

8 Conditional Information Bottleneck-Based Multivariate Time Series Forecasting

作者：Xinhui Li, Liang Duan, Lixing Yu, Kun Yue, Yuehua Li

关键词：多元时间序列预测，信息瓶颈

9 FreEformer: Frequency Enhanced Transformer for Multivariate Time Series Forecasting

链接：https://arxiv.org/abs/2501.13989

作者：Wenzhen Yue, Yong Liu, Xianghua Ying, Bowei Xing, Ruohao Guo, Ji Shi

关键词：多元时间序列预测，频域增强

10 LLM-TPF: Multiscale Temporal Periodicity-Semantic Fusion LLMs for Time Series Forecasting

作者：Qihong Pan, Haofei Tan, Guojiang Shen, Xiangjie Kong, Mengmeng Wang, Chenyang Xu

关键词：预测，LLM，语义信息

11 Learning to Extrapolate and Adjust: Two-Stage Meta-Learning for Concept Drift in Online Time Series Forecasting

作者：Weiqi Chen, Zhaoyang Zhu, Yifan Zhang, Lefei Shen, Linxiao Yang, Qingsong Wen, Liang Sun

关键词：在线预测，元学习

12 MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning

链接：https://arxiv.org/abs/2406.06620

作者：Jiexia Ye, Weiqi Zhang, Ziyue Li, Jia Li, Meng Zhao, Fugee Tsung

关键词：医疗时序，多模态学习

13 T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models

链接：https://arxiv.org/abs/2505.02417

作者：Yunfeng Ge, Jiawei Li, Yiji Zhao, Haomin Wen, Zhao Li, Meikang Qiu, Hongyan Li, Ming Jin, Shirui Pan

关键词：多模态时间序列生成，扩散模型，多模态时序数据集

14 State Feedback Enhanced Graph Differential Equations for Multivariate Time Series Forecasting

作者：Jiaxu Cui, Qipeng Wang, Yiming Zhao, Bingyi Sun, Pengfei Wang, Bo Yang

关键词：多元时间序列预测，差分方程

15 FreqLLM: Frequency-Aware Large Language Models for Time Series Forecasting

作者：Shunnan Wang, Min Gao, Zongwei Wang, Yibing Bai, Feng Jiang, Guansong Pang

关键词：预测，LLM，频域感知

16 Efficient Constraint-based Window Causal Graph Discovery in Time Series with Multiple Time Lags

作者：Yewei Xia, Yixin Ren, Hong Cheng, Hao Zhang, Jihong Guan, Minchuan Xu, Shuigeng Zhou

关键词：因果图发现

17 CRAFT: Time Series Forecasting with Cross-Future Behavior Awareness

链接：https://arxiv.org/abs/2505.13896

作者：Yingwei Zhang, Ke Bu, Zhuoran Zhuang, Tao Xie, Yao Yu, Dong Li, Yang Guo, Detao Lv

关键词：预测，未来行为感知

18 MMNet: Missing-Aware and Memory-Enhanced Network for Multivariate Time Series Imputation

作者：Xiaoye Miao, Han Shi, Yi Yuan, Daozhan Pan, Yangyang Wu, Xiaohua Pan

关键词：插补，记忆增强

19 Conditional Denoising Meets Polynomial Modeling: A Flexible Decoupled Framework for Time Series Forecasting

链接：https://arxiv.org/abs/2410.13253

作者：Jintao Zhang, Mingyue Cheng, Xiaoyu Tao, Zhiding Liu, Daoyu Wang

关键词：预测，多项式建模

20 DGraFormer: Dynamic Graph Learning Guided Multi-Scale Transformer for Multivariate Time Series Forecasting

作者：Han Yan, Dongliang Chen, Guiyuan Jiang, Bin Wang, Lei Cao, Junyu Dong, Yanwei Yu

关键词：多元时间序列预测，动态图

21 RTdetector: Deep Transformer Networks for Time Series Anomaly Detection Based on Reconstruction Trend

作者：Xinhong Liu, Xiaoliang Li, Yangfan Li, Fengxiao Tang, Ming Zhao

关键词：异常检测，趋势重建

22 General Incomplete Time Series Analysis via Patch Dropping Without Imputation

作者：Yangyang Wu, Yi Yuan, Mengying Zhu, Xiaoye Miao, Meng Xi

关键词：不完整时序分析

Survey Track

23 Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era

链接：https://arxiv.org/abs/2505.02583

作者：Chenxi Liu, Shaowen Zhou, Qianxiong Xu, Hao Miao, Cheng Long, Ziyue Li, Rui Zhao

关键词：时序分析，跨模态，LLM

24 Deep Learning for Multivariate Time Series Imputation: A Survey

链接：https://arxiv.org/abs/2402.04059

作者：Jun Wang, Wenjie Du, Yiyuan Yang, Linglong Qian, Wei Cao, Keli Zhang, Wenjia Wang, Yuxuan Liang, Qingsong Wen

关键词：插补

25 Harnessing Vision Models for Time Series Analysis: A Survey

链接：https://arxiv.org/abs/2502.08869

作者：Jingchao Ni, Ziming Zhao, ChengAo Shen, Hanghang Tong, Dongjin Song, Wei Cheng, Dongsheng Luo, Haifeng Chen

关键词：视觉模型，多模态

26 Comprehensive Review of Neural Differential Equations for Time Series Analysis

链接：https://arxiv.org/abs/2502.09885

作者：YongKyung Oh, Seungsu Kam, Jonghun Lee, Dong-Young Lim, Sungil Kim, Alex A. T. Bui

关键词：时序分析，神经微分方程