Xiucheng Li (李修成)

Assistant Professor of School of Computer Science and Technology at Harbin Institute of Technology, Shenzhen.

• Previously: PhD, School of Computer Science and Engineering, Nanyang Technological University
• Advisor: Gao Cong
• Office: Info-Tech Building 1906, HIT Campus, University Town of Shenzhen
• Email: lixiucheng [at] hit.edu.cn; xli055 [at] e.ntu.edu.sg

---

Research Interests

My research interests fall into machine learning and its applications. I am particularly interested in spatiotemporal data modeling and developing machine learning models for various scientific learning problems (also known as AI4Science) by exploring the underlying geometry and symmetry, the topics include:

• Spatiotemporal (time series) data modeling.
• Machine learning for partial differential equations (ML4PDEs).
• Graph machine learning and probabilistic generative models.

You can learn more about my interests from my posts.

Students and Alumni

I am very glad to work with some excellent students at HITSZ. Self-motivated undergraduate students with strong programming skills and solid math background are welcome, feel free to drop me an email and attach your cv if you are interested in the above topics.

Yunfeng Liao	(廖云峰)	class of 2022@HITSZ
Haokun Gui	(桂昊坤)\(\dagger\)	class of 2020@HITSZ	→ PhD@HKUST
Yuhang Xie	(谢宇航)\(\dagger\)	class of 2020@HITSZ	→ PhD@CUHK
Xinya Liu	(刘欣雅)	class of 2020@HITSZ	→ PhD@CityU HK
Hongyi Chen	(陈弘毅)	class of 2020@HITSZ	→ Master@HITSZ
Yilun Ji	(纪一仑)	class of 2020@HITSZ	→ Master@HITSZ
Hualong Wu	(吴华龙)	class of 2019@HITSZ	→ Master@HITSZ

\(\dagger\) co-supervised with Prof. Xinyang Chen.

---

Teaching

• Discrete Mathematics, 2024@HITSZ.

---

Publications

• Curvature-aware Graph Attention for PDEs on Manifolds
  Yunfeng Liao, Jiawen Guan, Xiucheng Li✉
  International Conference on Machine Learning (ICML), 2025 [PDF] [Code]

• Spatio-Temporal LLM for Few Shot Time Series Forecasting
  Yue Jiang, Yile Chen, Xiucheng Li, Qin Chao, Shuai Liu, Gao Cong
  International Conference on Machine Learning (ICML), 2025 [PDF]

• Handling Imbalanced Pseudolabels for Vision-Language Models with Concept Alignment and Confusion-Aware Calibrated Margin
  Yuchen Wang, Xuefeng Bai, Xiucheng Li, Weili Guan, Liqiang Nie, Xinyang Chen
  International Conference on Machine Learning (ICML), 2025 [PDF] [Code]

• Disentangling Dynamics: Advanced, Scalable and Explainable Imputation for Multivariate Time Series
  Shuai Liu, Xiucheng Li, Yile Chen, Yue Jiang, Gao Cong
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025 [PDF]

• Semantic-Enhanced Representation Learning for Road Networks with Temporal Dynamics
  Yile Chen, Xiucheng Li, Gao Cong, Zhifeng Bao, Cheng Long
  IEEE Transactions on Mobile Computing (TMC), 2025 [PDF]

• Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics
  Xiaodan Chen, Xiucheng Li✉, Xinyang Chen, Zhijun Li✉
  Neural Information Processing Systems (NeurIPS), 2024 [PDF] [Code]

• Boosting Transferability and Discriminability for Time Series Domain Adaptation
  Mingyang Liu, Xinyang Chen✉, Yang Shu✉, Xiucheng Li✉, Weili Guan, Liqiang Nie
  Neural Information Processing Systems (NeurIPS), 2024 [PDF] [Code]

• Vector Quantization Pretraining for EEG Time Series with Random Projection and Phase Alignment
  Haokun Gui, Xiucheng Li✉, Xinyang Chen✉
  International Conference on Machine Learning (ICML), 2024 [PDF] [Code]

• Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values
  Xiaodan Chen, Xiucheng Li✉, Bo Liu, Zhijun Li✉
  International Conference on Learning Representations (ICLR), 2024 [PDF] [Code]

• A Scalable Adaptive Graph Diffusion Forecasting Network for Multivariate Time Series Forecasting
  Yue Jiang, Xiucheng Li✉, Yile Chen, Shuai Liu, Weilong Kong, Gao Cong
  IEEE International Conference on Data Engineering (ICDE), 2024 [PDF] [Code]

• Optimizing Smartphone App Usage Prediction: A Click-Through Rate Ranking Approach
  Yuqi Zhang, Meiying Kang, Xiucheng Li✉, Yu Qiu, Zhijun Li✉
  ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2024 [PDF]

• Multi-Label Action Anticipation for Real-World Videos with Scene Understanding
  Yuqi Zhang, Xiucheng Li✉, Hao Xie, Weijun Zhuang, Shihui Guo, Zhijun Li✉
  IEEE Transactions on Image Processing (TIP), 2024 [PDF]

• DeepMeshCity: A Deep Learning Model for Urban Grid Prediction
  Chi Zhang, Linhao Cai, Meng Chen, Xiucheng Li✉, Gao Cong
  ACM Transactions on Knowledge Discovery from Data (TKDD), 2024 [PDF]

• Spatial-Temporal Cross-View Contrastive Pre-training for Check-in Sequence Representation Learning
  Letian Gong, Huaiyu Wan, Shengnan Guo, Xiucheng Li, Yan Lin, E. Zheng, T. Wang, Z. Zhou, Y. Lin
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2024 [PDF]

• Multivariate Time-series Imputation with Disentangled Temporal Representations
  Shuai Liu, Xiucheng Li✉, Gao Cong, Yile Chen, Yue Jiang
  International Conference on Learning Representations (ICLR), 2023 [PDF][Code]

• Points-of-Interest Relationship Inference with Spatial-enriched Graph Neural Networks
  Yile Chen, Xiucheng Li, Gao Cong, Cheng Long, Zhifeng Bao, Shang Liu, Wanli Gu, Fuzheng Zhang
  International Conference on Very Large Data Bases (VLDB), 2022 [PDF]

• Robust Road Network Representation Learning: When Traffic Patterns Meet Traveling Semantics
  Yile Chen, Xiucheng Li, Gao Cong, Cheng Long, Zhifeng Bao
  The Conference on Information and Knowledge Management (CIKM), 2021 [PDF]

• Similar Trajectory Search with Spatio-temporal Deep Representation Learning
  David A. Tedjopurnomo, Xiucheng Li, Zhifeng Bao, Gao Cong, Farhana Choudhury, Kai Qin
  ACM Transactions on Intelligent Systems and Technology (TIST), 2021 [PDF]

• Sinkhorn Collaborative Filtering
  Xiucheng Li, Jin Yao Chin, Yile Chen, Gao Cong
  International World Wide Web Conference (WWW), 2021 [PDF] [Code]

• Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting
  Shengnan Guo, Youfang Lin, Huaiyu Wan, Xiucheng Li, Gao Cong
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021 [PDF]

• Spatial Transition Learning on Road Networks with Deep Probabilistic Models
  Xiucheng Li, Gao Cong, Yun Cheng
  IEEE International Conference on Data Engineering (ICDE), 2021 [PDF] [Code]

• PGeoTopic: A Distributed Solution for Mining Geographical Topic Models
  Kaiqi Zhao, Gao Cong, Xiucheng Li
  IEEE Transactions on Knowledge and Data Engineering (TKDE), 2020 [PDF]

• Learning Travel Time Distributions with Deep Generative Models
  Xiucheng Li, Gao Cong, Aixin Sun, Yun Cheng
  International World Wide Web Conference (WWW), 2019 [PDF] [Code]

• Deep Representation Learning for Trajectory Similarity Computation
  Xiucheng Li, Kaiqi Zhao, Gao Cong, Christian S. Jensen, Wei Wei
  IEEE International Conference on Data Engineering (ICDE), 2018 [PDF] [Code]

• Latent Representation Model for Social Influence Embedding
  Shanshan Feng, Gao Cong, Arijit Khan, Xiucheng Li, Yong Liu, Chee Yeow Meng
  IEEE International Conference on Data Engineering (ICDE), 2018 [PDF]

• Discovering Pollution Sources and Propagation Patterns in Urban Area
  Xiucheng Li, Yun Cheng, Gao Cong, Lisi Chen
  ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2017 [PDF]

• Finding Dynamic Co-evolving Zones in Spatial-Temporal Time Series Data
  Yun Cheng, Xiucheng Li, Yan Li
  European Conference on Machine Learning and Data Mining (ECML-PKDD), 2016 [PDF]

• AirCloud: A Cloud-based Air-Quality Monitoring System for Everyone
  Yun Cheng, Xiucheng Li, Zhijun Li, Shouxu Jiang, YiLong Li, Jia Ji, Xiaofan (Fred) Jiang
  ACM Conference on Embedded Networked Sensor Systems (SenSys), 2014 [PDF]