ICDM 2024于2024年12月9号-12月12号在阿联酋阿布扎比（Abu Dhabi, UAE）举行。

本文总结了ICDM 2024有关时间序列（time series）的相关论文，如有疏漏，欢迎大家补充。

时间序列Topic：分类，预测，异常检测，基础模型等内容。总计9篇，其中regular4篇，short4篇，Demo1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）。

Regular

1. HyperTime: A Dynamic Hypergraph Approach for Time Series Classification
2. Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder
3. EMIT - Event Based Masked Auto Encoding for Irregular Time Series
4. Feature Map Purification for Enhancing Adversarial Robustness of Deep Timeseries Classifiers

Short

1. Matrix Profile for Anomaly Detection on Multidimensional Time Series
2. Interdependency Matters: Graph Alignment for Multivariate Time Series Anomaly Detection
3. ExoTST: Exogenous-Aware Temporal Sequence Transformer for Time Series Prediction
4. Rank Supervised Contrastive Learning for Time Series Classification

Demo

1. BiTSA: Leveraging Time Series Foundation Model for Building Energy Analytics

Regular

1 HyperTime: A Dynamic Hypergraph Approach for Time Series Classification

作者：Raneen Younis and Zahra Ahmadi

关键词：Time series classification, Dynamic hypergraph, Graph neural networks

2 Improving Time Series Encoding with Noise-Aware Self-Supervised Learning and an Efficient Encoder

链接：https://arxiv.org/abs/2306.06579

作者：Duy Nguyen Anh, Trang Tran, Hieu Pham Huy, Le Nguyen Phi, and Lam Nguyen Minh

关键词：Time series representation learning, Noise-resiliency training strategy, Inception

3 EMIT - Event Based Masked Auto Encoding for Irregular Time Series

链接：https://arxiv.org/abs/2409.16554

作者：Hrishikesh Patel, Ruihong Qiu, Adam Irwin, Shazia Sadiq, and Sen Wang

关键词：Irregular time series, Self-supervised learning, Healthcare

4 Feature Map Purification for Enhancing Adversarial Robustness of Deep Timeseries Classifiers

作者：Mubarak Abdu-Aguye, Zaigham Zaheer, and Karthik Nandakumar

关键词：adversarial robustness, feature maps, purification, timeseries, wavelets

Short

5 Matrix Profile for Anomaly Detection on Multidimensional Time Series

链接：https://arxiv.org/abs/2409.09298

作者：Chin-Chia Michael Yeh, Audrey Der, Uday Singh Saini, Vivian Lai, Yan Zheng, Junpeng Wang, Xin Dai, Zhongfang Zhuang, Yujie Fan, Huiyuan Chen, Prince Aboagye, Liang Wang, Wei Zhang, and Eamonn Keogh

关键词：time series, anomaly detection, multidimensionality

6 Interdependency Matters: Graph Alignment for Multivariate Time Series Anomaly Detection

链接：https://arxiv.org/abs/2410.08877

作者：Yuanyi Wang, Haifeng Sun, Chengsen Wang, Mengde Zhu, Wei Tang, Jingyu Wang, Qi Qi, Zirui Zhuang, and Jianxin Liao

关键词：multivariate time series, anomaly detection, graph alignment, unsupervised learning

7 ExoTST: Exogenous-Aware Temporal Sequence Transformer for Time Series Prediction

链接：https://arxiv.org/abs/2410.12184

作者：Kshitij Tayal, Arvind Renganathan, Xiaowei Jia, Vipin Kumar, and Dan Lu

关键词：Exogenous Variables, Modality Fusion

8 Rank Supervised Contrastive Learning for Time Series Classification

链接：https://arxiv.org/abs/2401.18057

作者：Qianying Ren, Dongsheng Luo, and Dongjin Song

关键词：time series classification, representation learning, contrastive learning

Demo

9 BiTSA: Leveraging Time Series Foundation Model for Building Energy Analytics

链接：https://arxiv.org/abs/2412.14175

作者：Xiachong Lin, Arian Prabowo, Imran Razzak, Hao Xue, Matthew Amos, Sam Behrens, and Flora Salim

关键词：基础模型， 能源时间序列 

相关链接

ICDM 2024接受论文：https://icdm2024.org/accepted_papers/

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。