Publications | Yuxuan Liang

Dr. Yuxuan Liang has published some papers in refereed journals and conferences, including DM venues (e.g., KDD*14, WWW*7, ICDE*3, TKDE*7, TMC*1), AI venues (e.g., TPAMI*2, AI Journal*2, NeurIPS*10, ICML*3, IJCAI*7, AAAI*5, ICLR*4), and CV venues (e.g., ECCV*1, MM*4). Here are some representative papers:

Spatio-Temporal (ST) Data Mining:
- ST/Urban + LLM: [KDD’24], [ICML’24a], [Survey’24], [WWW’24a], [WWW’24b], [ICLR’24]
- ST graph forecasting: [NeurIPS’23], [KDD’23], [SIGSPATIAL’23], [TKDE’22], [SIGSPATIAL’22], [TKDE’20], [KDD’19]
- ST grid modeling (e.g., earth science, crowd flow): [ICLR’24], [AAAI’24], [WWW’21], [TKDE’20], [TKDE’20], [KDD’19]
- ST Trajectory modeling: [IJCAI’24], [WWW’24], [ICDE’23], [CIKM’22], [IJCAI’21]
- AutoML for ST data: [AI’23], [WWW’21], [KDD’21]
- Applications: [AAAI’24], [KDD’23], [AAAI’23], [UBICOMP’21], [TVCG’21], [AAAI’20], [IJCAI’18], [SIGSPATIAL’17], [IJCAI’16]
Graph Mining:
- Graph learning: [TKDE’24], [ICML’24b], [ICML’24c], [TPAMI’24], [ICLR’24], [ICLR’23], [WWW’21], [NeurIPS’21], [NeurIPS’20]
- Graph augmentation: [WWW’21], [NeurIPS’21], [KDD’20]
- Applications: [KDD’22]
Multimodal Learning: [MM’24] [WWW’24a], [WWW’24b], [MM’23], [ECCV’22], [MM’22], [MM’21].
Survey Paper:
- LLMs/FMs + ST data:
  - [KDD’24] Foundation Models -> Time Series Analysis
  - [arXiv] Large Models -> Time Series and Spatio-Temporal Data
- ST Data Mining & Urban Computing:
  - [TKDE’23] Spatio-Temporal Graph Neural Networks -> Urban Computing
  - [arXiv] Deep Learning -> Trajectory Data Management and Mining
  - [arXiv] Deep Learning -> Cross-Domain Data Fusion in Urban Computing
  - [arXiv] Diffusion Models -> Time Series and Spatio-Temporal Data
  - [arXiv] Service Route and Time Prediction in Instant Delivery
- Time Series Analysis:
  - [TPAMI’24] Self-Supervised Learning -> Time Series Analysis
  - [arXiv] Deep Learning -> Multivariate Time Series Imputation

2024

KDD’25

[New] Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective

Yuchen Fang, Yuxuan Liang, Bo Hui, Zezhi Shao, Liwei Deng, Xu Liu, Xinke Jiang, and Kai Zheng

In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

Bib

@inproceedings{fang2025efficient,
  title = {Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective},
  author = {Fang, Yuchen and Liang, Yuxuan and Hui, Bo and Shao, Zezhi and Deng, Liwei and Liu, Xu and Jiang, Xinke and Zheng, Kai},
  booktitle = {Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  year = {2024}
}

KDD’25

[New] DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting

Hao Wu, Haomin Wen, Guibin Zhang, Yutong Xia, Yuxuan Liang, Yu Zheng, Qingsong Wen, and Kun Wang

In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024

Bib

@inproceedings{wu2025dynamic,
  title = {DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting},
  author = {Wu, Hao and Wen, Haomin and Zhang, Guibin and Xia, Yutong and Liang, Yuxuan and Zheng, Yu and Wen, Qingsong and Wang, Kun},
  booktitle = {Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
  year = {2024}
}

NeurIPS’24

[New] Attractor memory for long-term time series forecasting: A chaos perspective

Jiaxi Hu, Yuehong Hu, Wei Chen, Ming Jin, Shirui Pan, Qingsong Wen, and Yuxuan Liang*

In Advances in neural information processing systems, 2024

2024

2023

2022

2021

2020

2019

2018

2017

2016