ICML 2023 时序和时空论文总结

ICML 2023 时序和时空论文总结

ICML（International Conference on Machine Learning，国际机器学习会议）在7月23日-29日在美国夏威夷举行。今年，ICML 共收到 6538 份投稿，其中 1827 份被接收，接收率约为 27.9%。

本文总结了ICML 23有关时间序列和时空的相关论文，如有疏漏，欢迎大家补充。

部分内容参考知乎用户 @叶底藏花 文章：叶底藏花：ICML 2023 时序数据相关论文

时间序列（time series）

1. Probabilistic Imputation for Time-series Classification with Missing Data

论文链接：https://icml.cc/virtual/2023/poster/23522

作者：SeungHyun Kim · Hyunsu Kim · EungGu Yun · Hwangrae Lee · Jaehun Lee · Juho Lee

关键词：时间序列数据插补，概率模型，不确定性

2. Provably Convergent Schrödinger Bridge with Applications to Probabilistic Time Series Imputation

论文链接：https://icml.cc/virtual/2023/poster/24369

作者：Gerald Woo · Chenghao Liu · Doyen Sahoo · Akshat Kumar · Steven Hoi

关键词：时间序列插补、概率模型

3. Deep Latent State Space Models for Time-Series Generation

论文链接：https://icml.cc/virtual/2023/poster/24503

作者：Linqi Zhou · Michael Poli · Winnie Xu · Stefano Massaroli · Stefano Ermon

关键词：时间序列生成

4. Neural Stochastic Differential Games for Time-series Analysis

论文链接：https://icml.cc/virtual/2023/poster/25204

作者：Sungwoo Park · Byoungwoo Park · Moontae Lee · Changhee Lee

关键词：时间序列分析

5. Context Consistency Regularization for Label Sparsity in Time Series

论文链接：https://icml.cc/virtual/2023/poster/24019

作者：Yooju Shin · Susik Yoon · Hwanjun Song · Dongmin Park · Byunghyun Kim · Jae-Gil Lee · Byung Suk Lee

关键词：稀疏性，正则化

6. Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Series

论文链接：https://icml.cc/virtual/2023/poster/23522

作者：Aniruddh Raghu · Payal Chandak · Ridwan Alam · John Guttag · Collin Stultz

关键词：自监督、临床时序

7. SOM-CPC: Unsupervised Contrastive Learning with Self-Organizing Maps for Structured Representations of High-Rate Time Series

论文链接：https://icml.cc/virtual/2023/poster/24856

作者：SeungHyun Kim · Hyunsu Kim · EungGu Yun · Hwangrae Lee · Jaehun Lee · Juho Lee

关键词：无监督，对比学习，高频时序

8. Prototype-oriented unsupervised anomaly detection for multivariate time series

论文链接：https://icml.cc/virtual/2023/poster/24139

作者：yuxin li · Wenchao Chen · Bo Chen · Dongsheng Wang · Long Tian · Mingyuan Zhou

关键词：异常检测，多元时序，无监督

9. Learning Deep Time-index Models for Time Series Forecasting

论文链接：https://icml.cc/virtual/2023/poster/23522

作者：Gerald Woo · Chenghao Liu · Doyen Sahoo · Akshat Kumar · Steven Hoi

关键词：时间序列预测

10. Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series

论文链接：https://icml.cc/virtual/2023/poster/24923

作者：Abdul Fatir Ansari · Alvin Heng · Andre Lim · Harold Soh

关键词：不规则采样时间序列

11. Self-Interpretable Time Series Prediction with Counterfactual Explanations

论文链接：https://icml.cc/virtual/2023/poster/23975

作者：Jingquan Yan · Hao Wang

关键词：反事实，时间序列预测

12. Learning Perturbations to Explain Time Series Predictions

论文链接：https://icml.cc/virtual/2023/poster/24182

作者：Joseph Enguehard（独立一个作者太牛了！）

关键词：可解释性，时间序列预测

13. Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting

论文链接：https://icml.cc/virtual/2023/poster/23862

作者：Alex Reneau · Jerry Yao-Chieh Hu · Ammar Gilani · Han Liu

关键词：特征工程，多元时间序列预测

14. Theoretical Guarantees of Learning Ensembling Strategies with Applications to Time Series Forecasting

论文链接：https://icml.cc/virtual/2023/poster/24910

作者：Hilaf Hasson · Danielle Robinson · Yuyang Wang · Gaurav Gupta · Youngsuk Park

关键词：集成学习，时间序列预测

15. Sequential Predictive Conformal Inference for Time Series

论文链接：https://icml.cc/virtual/2023/poster/24627

作者：Chen Xu · Yao Xie

关键词：共形预测，不确定性

16. Non-autoregressive Conditional Diffusion Models for Time Series Prediction

论文链接：https://icml.cc/virtual/2023/poster/25084

作者：Lifeng Shen · James Kwok

关键词：扩散模型，时间序列预测

17. Sequential Monte Carlo Learning for Time Series Structure Discovery

论文链接：https://icml.cc/virtual/2023/poster/24520

作者：Feras Saad · Brian Patton · Matthew Hoffman · Rif Saurous · Vikash Mansinghka

关键词：蒙特卡洛方法，时间序列结构发现

18. Domain Adaptation for Time Series Under Feature and Label Shifts

论文链接：https://icml.cc/virtual/2023/poster/23456

作者：Gerald Woo · Chenghao Liu · Doyen Sahoo · Akshat Kumar · Steven Hoi

关键词：域适应，标签偏移

时空数据（spatial-temporal data）

19. NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition

论文链接：https://icml.cc/virtual/2023/poster/23962

作者：Xinquan Huang · Wenlei Shi · Qi Meng · Yue Wang · Xiaotian Gao · Jia Zhang · Tie-Yan Liu

关键词：神经偏微分方程，时空分解，AI4Science

20. Spatial Implicit Neural Representations for Global-Scale Species Mapping

论文链接：https://icml.cc/virtual/2023/poster/23767

作者：Gerald Woo · Chenghao Liu · Doyen Sahoo · Akshat Kumar · Steven Hoi

关键词：地理信息，稀疏性

21. Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation

（可能是最像时空数据挖掘的一篇了）

论文链接：https://icml.cc/virtual/2023/poster/24346

作者：Qianru Zhang · Chao Huang · Lianghao Xia · Zheng Wang · Siu Ming Yiu · Ruihua Han

关键词：时空图预测、对比学习

相关链接

ICML2023接受论文：ICML 2023 Papers

ICLR 2024投稿时空数据论文汇总

NeurIPS 2023 时间序列(Time Series)论文总结

NeurIPS 2023 时空数据论文总结

KDD 2023 时空数据论文

VLDB 2023 时空&时序论文汇总

ICDE 2023 时空数据论文

WWW 2023 时空数据论文

ECML PKDD 2023 时空数据论文

CIKM 2023 时空数据论文总结