AAAI 2025将在2025年2月25日到3月4日于美国费城（ Philadelphia, Pennsylvania, USA）举行。AAAI 2025共有12,957篇投稿（Main Technical Track），共录取了3032篇论文，录取率23.4%。

本文总结了2025 AAAI上有关时间序列（time series）相关论文，共计55篇。如有疏漏，欢迎大家补充。

时间序列Topic：预测，分类，异常检测，表示学习，因果发现，非平稳时序，LLM应用，Mamba等。其中10，19，49，51为Oral。

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. Language Pre-training Guided Masking Representation Learning for Time Series Classification
2. Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning
3. Hierarchical Classification Auxiliary Network for Time Series Forecasting
4. TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
5. Neural Conformal Control for Time Series Forecasting
6. Probabilistic Forecasting of Irregularly Sampled Time Series with Missing Values via Conditional Normalizing Flows
7. Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting
8. Times2D: Multi-Period Decomposition and Derivative Mapping for General Time Series Forecasting
9. VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting
10. [Oral] Unlocking the Power of Patch: Patch-Based MLP for Long-Term Time Series Forecasting
11. Amplifier: Bringing Attention to Neglected Low-Energy Components in Time Series Forecasting
12. Unlocking the Power of LSTM for Long Term Time Series Forecasting
13. Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting
14. Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation
15. Auto-Regressive Moving Diffusion Models for Time Series Forecasting
16. xPatch: Dual-Stream Time Series Forecasting with Exponential Seasonal-Trend Decomposition
17. Affirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting
18. A Lightweight Sparse Interaction Network for Time Series Forecasting
19. [Oral] HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting
20. HyperMixer: Specializable Hypergraph Channel Mixing for Long-term Multivariate Time Series Forecasting
21. FilterTS: Comprehensive Frequency Filtering for Multivariate Time Series Forecasting
22. WaveletMixer: A Multi-resolution Wavelets Based MLP-Mixer For Multivariate Long-term Time Series Forecasting
23. TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data
24. WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecasting
25. Revisiting Attention for Multivariate Time Series Forecasting
26. Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences
27. CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning
28. CSformer: Combining Channel Independence and Mixing for Robust Multivariate Time Series Forecasting
29. Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting
30. Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine
31. GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causality
32. TAIL-MIL: Time-Aware and Instance-Learnable Multiple Instance Learning for Multivariate Time Series Anomaly Detection
33. Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection
34. Content-aware Balanced Spectrum Encoding in Masked Modeling for Time Series Classification
35. MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification
36. SPACETIME: Causal Discovery from Non-Stationary Time Series
37. STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis
38. TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis
39. DualDynamics: Synergizing Implicit and Explicit Methods for Robust Irregular Time Series Analysis
40. InteDisUX: Interpretation-Guided Discriminative User-Centric Explanation For Time Series
41. Enhancing Masked Time-Series Modeling via Dropping Patches
42. Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarios
43. Real-time Calibration Model for Low-cost Sensor in Fine-grained Time series
44. Learning to Generate Multi-Domain Time Series with Domain Prompts
45. KernelMatmul: Scaling Gaussian Processes to Large Time Series
46. TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents
47. Motif-aware Graph Neural Networks for Networked Time Series Imputation
48. Modeling Latent Non-Linear Dynamical System over Time Series
49. [Oral] Time Series Supplier Allocation via Deep Black-Litterman Model
50. Federated Foundation Models on Heterogeneous Time Series
51. [Oral] ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
52. Integrating Sequence and Image Modeling in Irregular Medical Time Series through Self-Supervised Learning
53. Mixture of Online and Offline Experts for Non-stationary Time Series
54. Population Aware Diffusion for Time Series Generation
55. Enhancing Multivariate Time-Series Domain Adaptation via Contrastive Frequency Graph Discovery and Language-Guided Adversary Alignment

1 Language Pre-training Guided Masking Representation Learning for Time Series Classification

作者：Liaoyuan Tang,Zheng Wang,Jie Wang,guanxiong he,Zhezheng Hao,Rong Wang,Feiping Nie

关键词：分类，语言模型

2 Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning

链接：https://arxiv.org/abs/2412.20790

作者：En Fu,Yanyan Hu

关键词：频率掩码，表示学习

3 Hierarchical Classification Auxiliary Network for Time Series Forecasting

链接：https://arxiv.org/abs/2405.18975

作者：Yanru Sun,Zongxia Xie,Dongyue Chen,Emadeldeen Eldele,Qinghua Hu

关键词：分类，辅助网络

4 TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment

链接：https://arxiv.org/abs/2406.01638

作者：Chenxi Liu,Qianxiong Xu,Hao Miao,Sun Yang,Lingzheng Zhang,Cheng Long,Ziyue Li,Rui Zhao

关键词：大模型，预测，对齐

5 Neural Conformal Control for Time Series Forecasting

链接：https://arxiv.org/abs/2412.18144

作者：Ruipu Li,Alexander Rodríguez

关键词：预测，共形

6 Probabilistic Forecasting of Irregularly Sampled Time Series with Missing Values via Conditional Normalizing Flows

链接：https://arxiv.org/abs/2402.06293

作者：Vijaya Krishna Yalavarthi,Randolf Scholz,Stefan Born,Lars Schmidt-Thieme

关键词：概率预测，缺失值

7 Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting

链接：https://arxiv.org/abs/2406.03751

作者：Yifan Hu,Peiyuan Liu,Peng Zhu,Dawei Cheng,Tao Dai

关键词：预测，自适应多尺度分解

8 Times2D: Multi-Period Decomposition and Derivative Mapping for General Time Series Forecasting

作者：Reza nematirad,Anil Pahwa,Bala Natarajan

关键词：预测

9 VarDrop: Enhancing Training Efficiency by Reducing Variate Redundancy in Periodic Time Series Forecasting

作者：Junhyeok Kang,Yooju Shin,Jae-Gil Lee

关键词：高效训练，剔除冗余

10 [Oral]Unlocking the Power of Patch: Patch-Based MLP for Long-Term Time Series Forecasting

链接：https://arxiv.org/abs/2405.13575

作者：Peiwang Tang,Weitai Zhang

关键词：预测，Patch

11 Amplifier: Bringing Attention to Neglected Low-Energy Components in Time Series Forecasting

作者：Jingru Fei,Kun Yi,Wei Fan,Qi Zhang,Zhendong Niu

关键词：预测

12 Unlocking the Power of LSTM for Long Term Time Series Forecasting

链接：https://arxiv.org/abs/2408.10006

作者：Yaxuan Kong,Zepu Wang,Yuqi Nie,Tian Zhou,Stefan Zohren,Yuxuan Liang,Peng Sun,Qingsong Wen

关键词：预测，xLSTM

13 Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting

链接：https://arxiv.org/abs/2412.12226

作者：Tianyi YIN,Jingwei Wang,Yunlong Ma,Han Wang,Chenze Wang,Yukai Zhao,Min Liu,Weiming Shen

关键词：预测，量化

14 Battling the Non-stationarity in Time Series Forecasting via Test-time Adaptation

链接：https://arxiv.org/abs/2501.04970

作者：HyunGi Kim,Siwon Kim,Jisoo Mok,Sungroh Yoon

关键词：非平稳时序，测试时适应

15 Auto-Regressive Moving Diffusion Models for Time Series Forecasting

链接：https://arxiv.org/abs/2412.09328

作者：Jiaxin Gao,Qinglong Cao,Yuntian Chen

关键词：预测，自回归扩散

16 xPatch: Dual-Stream Time Series Forecasting with Exponential Seasonal-Trend Decomposition

链接：https://arxiv.org/abs/2412.17323

作者：Artyom Stitsyuk,Jaesik Choi

关键词：预测，指数季节趋势分解，双流结构

17 Affirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting

作者：Yuhan Wu,Xiyu Meng,Huajin Hu,Junru Zhang,Yabo Dong,Dongming Lu

关键词：预测，Mamba，傅里叶过滤

18 A Lightweight Sparse Interaction Network for Time Series Forecasting

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

关键词：预测，轻量化

19 [Oral]HDT: Hierarchical Discrete Transformer for Multivariate Time Series Forecasting

作者：FENG SHIBO,Peilin Zhao,Liu Liu,Pengcheng Wu,Zhiqi Shen

关键词：预测

20 HyperMixer: Specializable Hypergraph Channel Mixing for Long-term Multivariate Time Series Forecasting

作者：Changyuan Tian,Zhicong Lu,Zequn Zhang,Heming Yang,Wei Cao,Zhi Guo,Xian Sun,Li Jin

关键词：长时预测，超图

21 FilterTS: Comprehensive Frequency Filtering for Multivariate Time Series Forecasting

作者：Yulong Wang,Yushuo Liu,Xiaoyi Duan,Kai Wang

关键词：预测，频域过滤

22 WaveletMixer: A Multi-resolution Wavelets Based MLP-Mixer For Multivariate Long-term Time Series Forecasting

作者：Zichi Zhang,Tuan Dung Pham,Yimeng An,Ngoc Phu Doan,Majed Alsharari,Viet-Hung Tran,Tuan Hoang,Hans Vandierendonck,Son T. Mai

关键词：长时预测，小波，多分辨率

23 TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data

作者：Ege Onur Taga,Muhammed Emrullah Ildiz,Samet Oymak

关键词：预测，合成数据

24 WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecasting

链接：https://arxiv.org/abs/2412.17176

作者：Md Mahmuddun Nabi Murad,Mehmet Aktukmak,Yasin Yilmaz

关键词：长时预测，小波，多分辨率

25 Revisiting Attention for Multivariate Time Series Forecasting

链接：https://arxiv.org/abs/2407.13806

作者：Haixiang Wu

关键词：预测，注意力机制

26 Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences

链接：https://arxiv.org/abs/2501.02735

作者：Xiwen Chen,Peijie Qiu,Wenhui Zhu,Huayu Li,Hao Wang,Aristeidis Sotiras,Yalin Wang,Abolfazl Razi

关键词：预测，注意力机制

27 CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning

链接：https://arxiv.org/abs/2403.07300

作者：Peiyuan Liu,Hang Guo,Tao Dai,Naiqi Li,Jigang Bao,Xudong Ren,Yong Jiang,Shu-Tao Xia

关键词：预测，对齐，跨模态微调

28 CSformer: Combining Channel Independence and Mixing for Robust Multivariate Time Series Forecasting

链接：https://arxiv.org/abs/2312.06220

作者：Haoxin Wang,Yipeng Mo,Kunlan Xiang,Nan Yin,Honghe Dai,Bixiong Li,Songhai Fan,Site Mo

关键词：预测，通道独立（混合）

29 Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting

作者：Ruichu Cai,Haiqin Huang,Zhifan Jiang,Zijian Li,changze zhou,Yuequn Liu,Yuming Liu,Zhifeng Hao

关键词：在线预测

30 Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine

链接：https://arxiv.org/abs/2412.14435

作者：Luis Roque,Vitor Cerqueira,Carlos Soares,Luís Torgo

关键词：评测

31 GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causality

作者：Zehao Liu,Mengzhou Gao,Pengfei Jiao

关键词：异常检测

32 TAIL-MIL: Time-Aware and Instance-Learnable Multiple Instance Learning for Multivariate Time Series Anomaly Detection

作者：Jaeseok Jang,HYUK-YOON KWON

关键词：异常检测

33 Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection

链接：https://arxiv.org/abs/2412.19108

作者：Xiaoyu Huang,Weidong Chen,Bo Hu,Zhendong Mao

关键词：异常检测，混合专家系统

34 Content-aware Balanced Spectrum Encoding in Masked Modeling for Time Series Classification

链接：https://arxiv.org/abs/2412.13232

作者：Yudong Han,Haocong Wang,Yupeng Hu,Yongshun Gong,Xuemeng Song,Weili Guan

关键词：分类，内容感知

35 MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification

作者：Yang Mu,Muhammad Shahzad,Xiao Xiang Zhu

关键词：分类，局部-全局

36 SPACETIME: Causal Discovery from Non-Stationary Time Series

链接：https://arxiv.org/abs/2501.10235

作者：Sarah Mameche, Lénaïg Cornanguer, Urmi Ninad, Jilles Vreeken

关键词：因果发现，非平稳

37 STEM-LTS: Integrating Semantic-Temporal Dynamics in LLM-driven Time Series Analysis

作者：Zhe Zhao,Pengkun Wang,HaiBin Wen,ShuangWang,Liheng Yu,Yang Wang

关键词：时序分析，LLM

38 TimeCHEAT: A Channel Harmony Strategy for Irregularly Sampled Multivariate Time Series Analysis

链接：https://arxiv.org/abs/2412.12886

作者：Jiexi Liu,Meng Cao,Songcan Chen

关键词：不规则时序，通道依赖独立

39 DualDynamics: Synergizing Implicit and Explicit Methods for Robust Irregular Time Series Analysis

链接：https://arxiv.org/abs/2401.04979

作者：YongKyung Oh,Dongyoung Lim,Sungil Kim

关键词：不规则时序，神经微分方程

40 InteDisUX: Intepretation-Guided Discriminative User-Centric Explanation For Time Series

作者：Viet-Hung Tran,Zichi Zhang,Tuan Dung Pham,Ngoc Phu Doan,Anh-Tuan Hoang,Peixin Li,Hans Vandierendonck,Ira Assent,Son T. Mai

关键词：分类，可解释性

41 Enhancing Masked Time-Series Modeling via Dropping Patches

链接：https://arxiv.org/abs/2412.15315

作者：Tianyu Qiu,Yi Xie,Yun Xiong,Hao Niu,Xiaofeng Gao

关键词：预测，patch丢弃

42 Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarios

作者：Mohammad Rafid Ul Islam,Prasad Tadepalli,Alan Fern

关键词：插补，停电场景

43 Real-time Calibration Model for Low-cost Sensor in Fine-grained Time series

链接：https://arxiv.org/abs/2412.20170

作者：Seokho Ahn,Hyungjin Kim,Sungbok Shin,Young-Duk Seo

关键词：传感器时序数据

44 Learning to Generate Multi-Domain Time Series with Domain Prompts

链接：https://arxiv.org/abs/2501.05403

作者：Yu-Hao Huang,Chang Xu,Yueying Wu,Wu-Jun Li,Jiang Bian

关键词：生成，领域提示

45 KernelMatmul: Scaling Gaussian Processes to Large Time Series

作者：Tilman Hoffbauer,Holger Hoos,Jakob Bossek

关键词：高斯过程

46 TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents

作者：Geon Lee,Wenchao Yu,Kijung Shin,Wei Cheng,Haifeng Chen

关键词：智能体，时间序列事件

47 Motif-aware Graph Neural Networks for Networked Time Series Imputation

作者：Nourhan Ahmed,Vijaya Krishna Yalavarthi,Lars Schmidt-Thieme

关键词：插补，GNN

48 Modeling Latent Non-Linear Dynamical System over Time Series

链接：https://arxiv.org/abs/2412.08114

作者：Ren Fujiwara,Yasuko Matsubara,Yasushi Sakurai

关键词：非线性系统

49 [Oral] Time Series Supplier Allocation via Deep Black-Litterman Model

链接：https://arxiv.org/abs/2401.17350

作者：Xinke Jiang,WentaoZhang,Yuchen Fang,Xiaowei Gao,Hao Chen,Haoyu Zhang,Dingyi Zhuang,Jiayuan Luo

关键词：时间序列供应商分配

50 Federated Foundation Models on Heterogeneous Time Series

链接：https://arxiv.org/abs/2412.08906

作者：Shengchao Chen,Guodong Long,Jing Jiang,Chengqi Zhang

关键词：基础模型，联邦学习

51 [Oral]ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data

链接：https://arxiv.org/abs/2412.11376

作者：Chengsen Wang,Qi Qi,Jingyu Wang,Haifeng Sun,Zirui Zhuang,Jinming Wu,Lei Zhang,Jianxin Liao

关键词：多模态问答，时间序列基础模型

AAAI 2025 | ChatTime：首个理解与生成统一的时序文本多模态基础模型

52 Integrating Sequence and Image Modeling in Irregular Medical Time Series through Self-Supervised Learning

作者：Liuqing Chen,Shuhong Xiao,Shixian Ding,Shanhai Hu,Lingyun Sun

关键词：多模态，医疗时序

53 Mixture of Online and Offline Experts for Non-stationary Time Series

链接：https://arxiv.org/abs/2202.05996

作者：Zhilin Zhao,Longbing Cao,Yuanyu Wan

关键词：非平稳时序，在线离线场景

54 Population Aware Diffusion for Time Series Generation

链接：https://arxiv.org/abs/2501.00910

作者：Yang Li,Han Meng,Zhenyu Bi,Ingolv T. Urnes,Haipeng Chen

关键词：生成，扩散

55 Enhancing Multivariate Time-Series Domain Adaptation via Contrastive Frequency Graph Discovery and Language-Guided Adversary Alignment

作者：Guo Haoren,Zhu Haiyue,Jiahui Wang,Prahlad Vadakkepat,Weng Khuen Ho,Tong Heng LEE

关键词：时间序列域自适应

欢迎各位作者投稿近期有关时空数据和时间序列录用的顶级会议和期刊的优秀文章解读，我们将竭诚为您宣传,共同学习进步。如有意愿,请通过后台私信与我们联系。