Yuxuan Liang

Dr. Yuxuan Liang is currently an Assistant Professor at Intelligent Transportation Thrust, also affiliated with Data Science and Analytics Thrust, Hong Kong University of Science and Technology (Guangzhou). He is working on the research, development, and innovation of spatio-temporal data mining and AI, with a broad range of applications in smart cities. Prior to that, he obtained his PhD degree at School of Computing, National University of Singapore, supervised by Prof. Roger Zimmermann and Prof. David S. Rosenblum. He also worked closely with Dr. Yu Zheng and Dr. Junbo Zhang from JD Technology. He published 40+ papers in refereed journals (e.g., AI, TKDE) and conferences (such as KDD, NeurIPS, ICLR, WWW, ECCV, IJCAI, AAAI, and MM). His publications collectively gathered 2,600+ citations on Google Scholar, with h-index of 23 and i10-index of 35. Among them, three papers (GeoMAN, ST-MetaNet and STMTMVL) were selected as the most influential IJCAI/KDD papers according to PaperDigest, which indicates their significant impacts on both industry and academia. He also served as a PC member (or reviewer) for some prestigious conferences, including KDD, ICML, ICLR, NeurIPS, WWW, CVPR, ICCV, ECCV, IJCAI, AAAI, SIGSPATIAL, and Ubicomp.

He was recognized as 1 out of 10 most innovative and impactful PhD students focusing on Data Science in Singapore by Singapore Data Science Consortium (SDSC) in 2020. His research interests mainly lie in

Spatio-temporal (ST) data mining: ST representation learning, time series, ST imputation, AI for social good (e.g., transportation, human mobility, environment, climate), physics-informed learning.
Graph mining: learning graph representations (e.g., directed graphs, temporal graphs), GNN pruning.
Computer vision: video understanding, image recognition, image/video super-resolution.

Useful links: CityMind Lab, Google Scholar, DBLP, Linkedin

News

2023/09/23	LargeST, a large-scale traffic benchmark, was accepted by NeurIPS’23 DB Track. Congrats to Xu!
2023/09/23	Our paper about spatio-temporal causal inference was accepted by NeurIPS’23. Congrats to Yutong!
2023/09/09	Our paper about spatio-temporal diffusion model was accepted by SIGSPATIAL’23. Congrats to Haomin!
2023/07/26	One paper about geospatial cross-view matching was accepted by ACM MM’23. Congrats to Wenmiao!
2023/07/15	One paper about addressing spatio-temporal heterogeneity was accepted by TMC. Congrats to Zhengyang!
2023/06/30	One paper about spatio-temporal extrapolation was accepted by TNNLS. Congrats to Junfeng!
2023/06/15	We summarized recent advances in SSL for time series in our survey paper!
2023/05/17	Two papers about learning ST graphs were accepted by KDD’23. Congrats to Junfeng and Zhengyang!
2023/03/28	We summarized recent advances in Spatio-temporal Graph Neural Networks in our survey paper!
2023/02/28	An extension of AutoSTG was accepted by Artificial Intelligence (AI). Congrats to Songyu!
2023/02/08	One paper about contrastive learning on trajectories was accepted by ICDE’23. Congrats to Yanchuan!
2023/01/25	I successfully passed my PhD defense :-) Thanks Roger and David for their continuous support at NUS!
2023/01/21	One paper about GNN pruning was accepted as poster by ICLR’23. Congrats to Kun!
2022/11/20	One paper about large-scale air quality prediction via Transformer was accepted as oral presentation by AAAI’23.
2022/11/03	One paper about learning mixed-order relationships in ST graphs was accepted by TKDE.
2022/08/23	Two paper about periodic/contrastive learning for ST data were accepted as oral papers by SIGSPATIAL’22.
2022/08/03	One paper entitled Efficient Trajectory Classification using Transformer was accepted by CIKM’22.
2022/07/29	I was honored to receive the Dean’s Graduate Award from NUS. Thanks Roger for the nomination and supports!
2022/07/04	One paper about efficient video transformer was accepted by ECCV’22.
2022/07/01	One paper about geo-orientation was accepted by ACM MM’22.
2022/05/20	One paper about sequential recommendation was accepted by KDD’22.
2022/04/15	I was awarded The 23rd China Patent Excellence Award.
2022/03/01	Three papers were accepted by NAACL’22, IEEE Access and IJCNN’22.
2022/02/24	ST-MetaNet was selected as Most Influential KDD Papers.
2022/02/24	Two spatio-temporal AI papers (GeoMAN and stMTMVL) were selected as Most Influential IJCAI Papers.

Working experience

2023/06 - Present	Assistant Professor @ The Hong Kong University of Science and Technology (Guangzhou), China
2022/12 - 2023/05	Research Fellow @ National University of Singapore, Singapore
2021/07 - 2021/12	Research intern @ Sea AI Lab (SAIL), Singapore
2018/11 - 2019/04	Full-time research assistant @ National University of Singapore, Singapore
2018/01 - 2018/09	Algorithm engineer intern @ JD.COM, Beijing, China
2017/01 - 2018/01	Research intern @ Microsoft Research, Beijing, China
2015/12 - 2016/09	Research intern @ Microsoft Research, Beijing, China

Selected publications [See more]

* denotes corresponding author and + indicates equal contribution.

IJCAI’18

GeoMAN: Multi-Level Attention Networks for Geo-sensory Time Series Prediction.

Yuxuan Liang, Songyu Ke, Junbo Zhang, Xiuwen Yi, and Yu Zheng

In International Joint Conference on Artificial Intelligence, 2018

Bib PDF Code Cited by 450

@inproceedings{liang2018geoman,
  title = {GeoMAN: Multi-Level Attention Networks for Geo-sensory Time Series Prediction.},
  author = {Liang, Yuxuan and Ke, Songyu and Zhang, Junbo and Yi, Xiuwen and Zheng, Yu},
  booktitle = {International Joint Conference on Artificial Intelligence},
  volume = {2018},
  pages = {3428--3434},
  year = {2018}
}

KDD’19

Urban Traffic Prediction from Spatio-Temporal Data using Deep Meta Learning

Zheyi Pan, Yuxuan Liang, Weifeng Wang, Yong Yu, Yu Zheng, and Junbo Zhang

In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 2019

Bib PDF Code Cited by 378

@inproceedings{pan2019urban,
  title = {Urban Traffic Prediction from Spatio-Temporal Data using Deep Meta Learning},
  author = {Pan, Zheyi and Liang, Yuxuan and Wang, Weifeng and Yu, Yong and Zheng, Yu and Zhang, Junbo},
  booktitle = {Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery \& data mining},
  pages = {1720--1730},
  year = {2019}
}

IJCAI’16

Urban Water Quality Prediction based on Multi-Task Multi-View Learning

Ye Liu, Yu Zheng, Yuxuan Liang, Shuming Liu, and David S Rosenblum

In Proceedings of the 25th international joint conference on artificial intelligence, 2016

Bib PDF Code Cited by 219

@inproceedings{liu2016urban,
  title = {Urban Water Quality Prediction based on Multi-Task Multi-View Learning},
  author = {Liu, Ye and Zheng, Yu and Liang, Yuxuan and Liu, Shuming and Rosenblum, David S},
  booktitle = {Proceedings of the 25th international joint conference on artificial intelligence},
  year = {2016}
}

KDD’19

Urbanfm: Inferring Fine-Grained Urban Flows

Yuxuan Liang+, Kun Ouyang+, Lin Jing, Sijie Ruan, Ye Liu, Junbo Zhang, David S Rosenblum, and Yu Zheng

In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 2019

Bib PDF Code Cited by 99

@inproceedings{liang2019urbanfm,
  title = {Urbanfm: Inferring Fine-Grained Urban Flows},
  author = {Liang+, Yuxuan and Ouyang+, Kun and Jing, Lin and Ruan, Sijie and Liu, Ye and Zhang, Junbo and Rosenblum, David S and Zheng, Yu},
  booktitle = {Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery \& data mining},
  pages = {3132--3142},
  year = {2019}
}

KDD’20

Nodeaug: Semi-Supervised Node Classification with Data Augmentation

Yiwei Wang, Wei Wang, Yuxuan Liang, Yujun Cai, Juncheng Liu, and Bryan Hooi

In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020

Bib PDF Cited by 98

@inproceedings{wang2020nodeaug,
  title = {Nodeaug: Semi-Supervised Node Classification with Data Augmentation},
  author = {Wang, Yiwei and Wang, Wei and Liang, Yuxuan and Cai, Yujun and Liu, Juncheng and Hooi, Bryan},
  booktitle = {Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
  pages = {207--217},
  year = {2020}
}

NeurIPS’20

Digraph Inception Convolutional Networks

Zekun Tong, Yuxuan Liang, Changsheng Sun, Xinke Li, David Rosenblum, and Andrew Lim

Advances in neural information processing systems 2020

Bib PDF Cited by 68

@article{tong2020digraph,
  title = {Digraph Inception Convolutional Networks},
  author = {Tong, Zekun and Liang, Yuxuan and Sun, Changsheng and Li, Xinke and Rosenblum, David and Lim, Andrew},
  journal = {Advances in neural information processing systems},
  volume = {33},
  pages = {17907--17918},
  year = {2020}
}

ICLR’23

Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective

Kun Wang, Yuxuan Liang*, Pengkun Wang, Xu Wang, Pengfei Gu, Junfeng Fang, and Yang Wang*

In The International Conference on Learning Representations, 2023

Bib PDF

@inproceedings{wang2023searching,
  title = {Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective},
  author = {Wang, Kun and Liang*, Yuxuan and Wang, Pengkun and Wang, Xu and Gu, Pengfei and Fang, Junfeng and Wang*, Yang},
  booktitle = {The International Conference on Learning Representations},
  year = {2023}
}

AAAI’23

AirFormer: Predicting Nationwide Air Quality in China with Transformers

Yuxuan Liang, Yutong Xia, Songyu Ke, Yiwei Wang, Qingsong Wen, Junbo Zhang, Yu Zheng, and Roger Zimmermann

In Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

Bib PDF Code

@inproceedings{liang2023airformer,
  title = {AirFormer: Predicting Nationwide Air Quality in China with Transformers},
  author = {Liang, Yuxuan and Xia, Yutong and Ke, Songyu and Wang, Yiwei and Wen, Qingsong and Zhang, Junbo and Zheng, Yu and Zimmermann, Roger},
  booktitle = {Thirty-Seventh AAAI Conference on Artificial Intelligence},
  year = {2023}
}

SIGSPATIAL’22

When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?

Xu Liu+, Yuxuan Liang+, Chao Huang, Yu Zheng, Bryan Hooi, and Roger Zimmermann

In Proceedings of the 30th International Conference on Advances in Geographic Information Systems, 2022

Bib PDF Code

@inproceedings{liu2022contrastive,
  title = {When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?},
  author = {Liu+, Xu and Liang+, Yuxuan and Huang, Chao and Zheng, Yu and Hooi, Bryan and Zimmermann, Roger},
  booktitle = {Proceedings of the 30th International Conference on Advances in Geographic Information Systems},
  pages = {1--12},
  year = {2022}
}

WWW’21

Fine-grained Urban Flow Prediction

Yuxuan Liang, Kun Ouyang, Junkai Sun, Yiwei Wang, Junbo Zhang, Yu Zheng, David Rosenblum, and Roger Zimmermann

In Proceedings of the Web Conference, 2021

Bib PDF Cited by 32

@inproceedings{liang2021fine,
  title = {Fine-grained Urban Flow Prediction},
  author = {Liang, Yuxuan and Ouyang, Kun and Sun, Junkai and Wang, Yiwei and Zhang, Junbo and Zheng, Yu and Rosenblum, David and Zimmermann, Roger},
  booktitle = {Proceedings of the Web Conference},
  pages = {1833--1845},
  year = {2021}
}

Collaborators

I was really honored to closely work with the following researchers (in alphabetical order):

Chao Huang, Assistant Professor, University of Hong Kong
Kun Ouyang, Algorithm Engineer, Tencent
Sijie Ruan, Assistant Professor, Beijing Institute of Technology
Qingsong Wen, Staff Engineer/Manager, DAMO Academy, Alibaba Group (U.S.)
Wenmiao Hu, PhD candidate, National University of Singapore
Yiwei Wang, Applied Scientist, Amazon
Zekun Tong, National University of Singapore
Zhengyang Zhou, Associate Researcher, University of Science and Technology of China
Zheyi Pan, Doctor Management Trainee Program, JD.COM

For the students I mentored, please click here.