Yijun Su

AI Research Scientist at JD.com

Associate Researcher at University of Chinese Academy of Sciences

Focusing on LLMs, RS, ST AI, FL and GML

Bio

Dr. Yijun Su is now a AI Scientist at JD.com. He obtained his Ph.D. Degree in Artificial Intelligence from University of Chinese Academy of Sciences (UCAS), under the supervision of Prof. Ji Xiang. During his Ph.D., he mainly researched Technologies of Point-of-Interest Recommendation on Location-based Social Network. His current research interests span Large Language Model（Post Training and Agent）、Spatio-Temporal AI (Spatio-Temporal Recommendation and Spatio-Temporal Data Mining), Federated Learning (Federated Recommendation and Spatio-Temporal Federated Learning), and Graph Machine Learning (Graph Neural Network and Knowledge Graphs). He serves as the invited reviewer for conferences including WWW, KDD, AAAI, IJCAI, SDM, etc., and for journals including TKDE, WWWJ, TCYB, TIST, etc.

If you’d like to know more about my work or explore opportunities for collaboration, please get in touch!

Interests

Large Language Model
Spatio-Temporal AI
Federated Learning
Graph Machine Learning

Education

Ph.D in Artificial Intelligence, 2017-2020

University of Chinese Academy of Sciences
M.S in Artificial Intelligence, 2015-2017

University of Chinese Academy of Sciences

I am always open to collaborating with remote students and researchers who are interested in Recommendation Systems, LLMs, and AI Agents. Please feel free to contact me: suyijun.ucas [at] com

New!! We’re looking for talented full-time employees and interns to join our team working on JoyAI-G1 Large Models for Government Affairs and applying them to real-world scenarios. If you are interested, please feel free to contact me.

Publications

2026

Hepeng Gao, Funing Yang, Yijun Su, Xingliang Zhang, Yongjian Yang. Temporal-Aware Dynamic Graph Neural Networks for Next POI Recommendation. In Expert Systems with Applications, 2026.
Hepeng Gao, Funing Yang, Xingliang Zhang, Yijun Su, Yongjian Yang. Pre-Training Location Representations via Spatial-Temporal Trajectory Subgraph Contrastive Learning. In Tsinghua Science and Technology, 2026.

2025

Hepeng Gao, Funing Yang, Yongjian Yang, Yuanbo Xu, Yijun Su. Adaptive Receptive Field Graph Neural Networks. In Neural Networks, 2025.
Hepeng Gao, Yijun Su, Funing Yang, Yongjian Yang. Fine-Grained Data Inference via Incomplete Multi-Granularity Data. In The Web Conference 2025, 2025.

2024

Yantong Lai, Yijun Su, Lingwei Wei, Tianqi He, Haitao Wang, Gaode Chen, Daren Zha, Qiang Liu, Xingxing Wang. Disentangled Contrastive Hypergraph Learning for Next {POI} Recommendation. In SIGIR, 2024.
Yantong Lai, Yijun Su, Lingwei Wei, Tianci Wang, Daren Zha, Xin Wang. Adaptive Spatial-Temporal Hypergraph Fusion Learning for Next POI Recommendation. In ICASSP, 2024.

2023

Yantong Lai, Yijun Su, Lingwei Wei, Gaode Chen, Tianci Wang, Daren Zha. Multi-View Spatial-Temporal Enhanced Hypergraph Network for Next POI Recommendation. In Database Systems for Advanced Applications (DASFAA), 2023.
Gaode Chen, Xinghua Zhang, Yijun Su, Yantong Lai, Ji Xiang, Junbo Zhang, Yu Zheng. Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation. In Proceedings of The 37th AAAI Conference on Artificial Intelligence (AAAI), 2023.

2022

Gaode Chen, Yijun Su, Xinghua Zhang, Anmin Hu, Guochun Chen, Siyuan Feng, Ji Xiang, Junbo Zhang, Yu Zheng. A Cross-City Federated Transfer Learning Framework: A Case Study on Urban Region Profiling. arXiv:2206.00007, 2022.

2021 and Before

Yantong Lai, Yijun Su, Cong Xue, Daren Zha. Neural Demographic Prediction in Social Media with Deep Multi-View Multi-Task Learning. In Database Systems for Advanced Applications (DASFAA), 2021.
Xiang Li, Yijun Su, Neng Gao., Ji Xiang, Yuewu Wang. User Alignment with Jumping Seed Alignment Information Propagation. In International Joint Conference on Neural Networks (IJCNN), 2020.
Yijun Su, Jia-Dong Zhang, Xiang Li, Daren Zha, Ji Xiang, Wei Tang. FGRec: A Fine-Grained Point-of-Interest Recommendation Framework by Capturing Intrinsic Influences. In International Joint Conference on Neural Networks (IJCNN), 2020.
Yijun Su, Xiang Li, Baoping Liu, Daren Zha, Ji Xiang, Wei Tang, Neng Gao.. FGCRec: Fine-Grained Geographical Characteristics Modeling for Point-of-Interest Recommendation. In IEEE International Conference on Communications (ICC), 2020.
Wei Tang, Yiwen Jiang, Neng Gao., Ji Xiang, Jiahui Shen, Xiang Li, Yijun Su. Reducing Style Overfitting for Character Recognition via Parallel Neural Networks with Style to Content Connection. In * International Symposium on Parallel and Distributed Processing with Applications (ISPA)*, 2019.
Wei Tang, Yiwen Jiang, Neng Gao., Ji Xiang, Yijun Su, Xiang Li. SCS: Style and Content Supervision Network for Character Recognition with Unseen Font Style. In International Conference on Neural Information Processing(ICONIP), 2019.
Yijun Su, Xiang Li, Daren Zha, Wei Tang, Yiwen Jiang, Ji Xiang, Neng Gao.. HRec: Heterogeneous Graph Embedding-Based Personalized Point-of-Interest Recommendation. In International Conference on Neural Information Processing(ICONIP), 2019.
Yiwen Jiang, Wei Tang, Neng Gao., Ji Xiang, Yijun Su. Demographic Prediction from Purchase Data Based on Knowledge-Aware Embedding. In International Conference on Neural Information Processing (ICONIP), 2019.
Baoping Liu, Yijun Su, Daren Zha, Neng Gao., Ji Xiang. CARec: Content-Aware Point-of-Interest Recommendation via Adaptive Bayesian Personalized Ranking. In International Conference on Neural Information Processing(ICONIP), 2019.
Xiang Li, Yijun Su, Neng Gao., Wei Tang, Ji Xiang, Yuewu Wang. Anchor User Oriented Accordant Embedding for User Identity Linkage. In International Conference on Neural Information Processing (ICONIP), 2019.
Xiang Li, Yijun Su, Neng Gao., Wei Tang, Ji Xiang, Yuewu Wang. Aligning Users Across Social Networks by Joint User and Label Consistence Representation. In International Conference on Neural Information Processing(ICONIP), 2019.
Yijun Su, Xiang Li, Wei Tang, Daren Zha, Ji Xiang, Neng Gao.. Personalized Point-of-Interest Recommendation on Ranking with Poisson Factorization. In International Joint Conference on Neural Networks(IJCNN), 2019.
Wei Tang, Yijun Su, Xiang Li, Daren Zha, Weiyu Jiang, Neng Gao., Ji Xiang. CNN-Based Chinese Character Recognition with Skeleton Feature. In International Conference on Neural Information Processing (ICONIP), 2018.
Xiang Li, Yijun Su, Wei Tang, Neng Gao., Ji Xiang. User Identity Linkage with Accumulated Information from Neighbouring Anchor Links. In Web Information Systems Engineering (WISE), 2018.
Yijun Su, Xiang Li, Wei Tang, Ji Xiang, Yuanye He. Next Check-in Location Prediction via Footprints and Friendship on Location-Based Social Networks. In IEEE International Conference on Mobile Data Management (MDM), 2018.

Recent News

Oct 2026, I was selected for the Young Talent Support Program by the China Association for Science and Technology (CAST).

Sep 2026, I led the team that developed JoyAI-G1, a large model for government affairs, which was officially released at the JD Global Technology Explorers Conference.

Jul 2026, I was selected for the Beijing High-Level Innovation Talent Program by BAST.

May 2026, One paper about Temporal-Aware Dynamic Graph Neural Networks for Next POI Recommendation was accepted by Expert Systems with Applications 2026.

May 2025, One paper about Adaptive Receptive Field Graph Neural Networks was accepted by Neural Networks 2025.

Apr 2025, One paper about Pre-training Location Representations via Spatial-Temporal Trajectory Subgraph Contrastive Learning was accepted by TSC 2025.

Jan 2025, The jointly developed group standard, Data Governance Evaluation: Indicator System, was officially released.

Jan 2025, One paper about Fine-Grained Data Inference via Incomplete Multi-Granularity Data was accepted by WWW 2025.

Dec 2024, The industry white paper Data Security Governance Practice Guide was officially released.

Dec 2024, I led the team to receive the Excellence Award in the Beijing Division of the “Data Elements ×” Competition.

May 2024, I was invited to write a recommendation for AIGC-Powered Marketing: A Complete Guide, a new book by Cui Wenzhu, co-founder of Beijing Kuafu Technology.

May 2024, I was invited to give an academic talk, “Artificial Intelligence Empowering New Development in Smart Cities”, at the University of Chinese Academy of Sciences.

Mar 2024, One paper about Disentangled Contrastive Hypergraph Learning for Next POI Recommendation was accepted by SIGIR 2024.

Dec 2023, One paper about Adaptive Spatial-Temporal Hypergraph Fusion Learning for Next POI Recommendation was accepted by ICASSP 2024.

Dec 2023, I was invited to give an academic talk, “The Singularity Is Near: AIGC’s Technological Leap and Disruptive Impact”, at North China Electric Power University.

Jul 2023, I was invited to give an academic talk, “ChatGPT: The Singularity of Generative AI”, at Ningxia University.

Jan 2023, One paper about Multi-View Spatial-Temporal Enhanced Hypergraph Network for Next POI Recommendation was accepted by DASFAA 2023.

Nov 2022, One paper about A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation was accepted by AAAI 2023.

Jul 2022, I was invited to deliver a special talk, “Urban Computing and Spatio-Temporal Federated Learning: Enabling Innovative Smart City Applications,” at the CCF YOCSEF Changsha Technical Forum.

Oct 2021, I was invited to share “Spatio-Temporal Federation: When Spatio-Temporal Data Meets Federated Learning” at the CCF YOCSEF Chengdu “Qingcheng Inquiry” Closed Technical Forum.

Jul 2021, I was selected for the Yiqilin Excellent Talent Program, BEIJINGETOWN.

Jan 2021, One paper about Neural Demographic Prediction in Social Media with Deep Multi-View Multi-Task Learning was accepted by DASFAA 2021.