Yuanchen Bei

I am now a final-year master’s student in the College of Computer Science and Technology, Zhejiang University, advised by Prof. Sheng Zhou and Prof. Jiajun Bu. I also work closely with Dr. Hao Chen, Prof. Xiao Huang at PolyU and Prof. Feiran Huang at JNU.

“There should be (explicit/implicit) relations among real-world data.” My research interests currently include graph learning, relation foundation models, recommender systems, and multi-modal relation learning. In my free time, I am also interested in finance and economics. Please kindly reach out to me if you have any questions or cooperation interests.

👨‍💻‍ I am actively looking for Ph.D. opportunities in Summer/Fall 2025, and I sincerely appreciate any opportunity! It is my curriculum vitae.

News

• 2024.07:  📚 Invited as the reviewer for KDD 2025.
• 2024.05:  🎉 Our paper “Multi-Behavior Collaborative Filtering with Partial Order Graph Convolutional Networks” is accepted by KDD 2024.
• 2024.05:  📚 Invited as the reviewer for IEEE TII and IEEE TKDE.
• 2024.01:  🎉 Our paper “Macro Graph Neural Networks for Online Billion-Scale Recommender Systems” is accepted by TheWebConf 2024.
• 2023.12:  🎉 Our paper “CPDG: A Contrastive Pre-Training Method for Dynamic Graph Neural Networks” is accepted by ICDE 2024.
• 2023.09:  🎉 Our paper “Reinforcement Neighborhood Selection for Unsupervised Graph Anomaly Detection” is accepted by ICDM 2023.

Publications

Conference Papers (* equal-contributed):

• [6] Multi-Behavior Collaborative Filtering with Partial Order Graph Convolutional Networks. (KDD, 2024) [Applied in Alibaba Taobao]

  Yijie Zhang*, Yuanchen Bei*, Hao Chen*, Qijie Shen, Zheng Yuan, Huan Gong, Senzhang Wang, Feiran Huang, and Xiao Huang.

• [5] Macro Graph Neural Networks for Online Billion-Scale Recommender Systems. (TheWebConf, 2024) [Applied in Alibaba Taobao]

  Hao Chen*, Yuanchen Bei*, Qijie Shen, Yue Xu, Sheng Zhou, Wenbing Huang, Feiran Huang, Senzhang Wang, and Xiao Huang.

• [4] CPDG: A Contrastive Pre-Training Method for Dynamic Graph Neural Networks. (ICDE, 2024)

  Yuanchen Bei, Hao Xu, Sheng Zhou, Huixuan Chi, Haishuai Wang, Mengdi Zhang, Zhao Li, and Jiajun Bu.

• [3] Feedback Reciprocal Graph Collaborative Filtering. (CIKM, 2024)

  Weijun Chen*, Yuanchen Bei*, Qijie Shen, Hao Chen, Xiao Huang, and Feiran Huang.

• [2] Reinforcement Neighborhood Selection for Unsupervised Graph Anomaly Detection. (ICDM, 2023)

  Yuanchen Bei, Sheng Zhou, Qiaoyu Tan, Hao Xu, Hao Chen, Zhao Li, and Jiajun Bu.

• [1] Non-Recursive Cluster-Scale Graph Interacted Model for Click-Through Rate Prediction. (CIKM, 2023)

  Yuanchen Bei, Hao Chen, Shengyuan Chen, Xiao Huang, Sheng Zhou, and Feiran Huang.

Preprint Papers (* equal-contributed):

• [4] Revisiting the Message Passing in Heterophilous Graph Neural Networks.

  Zhuonan Zheng, Yuanchen Bei, Sheng Zhou, Yao Ma, Ming Gu, Hongjia Xu, Chengyu Lai, Jiawei Chen, and Jiajun Bu.

• [3] Better Late Than Never: Formulating and Benchmarking Recommendation Editing.

  Chengyu Lai, Sheng Zhou, Zhimeng Jiang, Qiaoyu Tan, Yuanchen Bei, Jiawei Chen, Ningyu Zhang, and Jiajun Bu.

• [2] Guarding Graph Neural Networks for Unsupervised Graph Anomaly Detection.

  Yuanchen Bei, Sheng Zhou, Jinke Shi, Yao Ma, Haishuai Wang, and Jiajun Bu.

• [1] Large Language Model Interaction Simulator for Cold-Start Item Recommendation.

  Feiran Huang, Zhenghang Yang*, Junyi Jiang*, Yuanchen Bei*, Yijie Zhang, and Hao Chen.

Workshop Papers:

• [3] Alleviating Behavior Data Imbalance for Multi-Behavior Graph Collaborative Filtering. (IWLKG@ICDM, 2023)

  Yijie Zhang, Yuanchen Bei, Shiqi Yang, Hao Chen, Zhiqing Li, Lijia Chen, and Feiran Huang.

• [2] Modeling Spatiotemporal Periodicity and Collaborative Signal for Local-Life Service Recommendation. (KDAH@CIKM, 2023)

  Huixuan Chi, Hao Xu, Mengya Liu, Yuanchen Bei, Sheng Zhou, Danyang Liu, and Mengdi Zhang.

• [1] Flattened Graph Convolutional Networks For Recommendation. (DLP@KDD, 2022)

  Yue Xu, Hao Chen, Zengde Deng, Yuanchen Bei, and Feiran Huang.

Patents:

• [2] Text Sentiment Analysis Method Based on Multi-Level Graph Pooling. (US Patent, No. 11,687,728, 2023)

  Feiran Huang, Zhiquan Liu, and Yuanchen Bei.

• [1] Social Recommendation Method Based on Multi-Feature Heterogeneous Graph Neural Networks. (US Patent, No. 11,631,147, 2023)

  Feiran Huang, Guan Liu, and Yuanchen Bei.

Selected Open-Source Project

• ColdRec: A Comprehensive Benchmark for Cold-Start Recommendation. (A Comprehensive Open-Source Toolkit for Cold-Start Recommendations)

  Include 20+ cold-start recommendation models with comprehensive evaluations.

• DreamerGPT: Chinese Instruction-tuning for Large Language Model. (Instruction Tuning for Open-Source LLMs with Chinese Corpus)

• Graph Pre-Training Library. (A Comprehensive Library of Graph Pre-Training Literature)

• Cold-Start Recommendation Library. (A Comprehensive Library of Cold-Start Recommendation Literature)

• DGraph-Fin Leaderboard. (A Large-Scale Dynamic Graph Anomaly Detection Leaderboard) 🥈 Top-2 Solution

Honors and Awards

• 2023.11, First Class Scholarship, Zhejiang University.
• 2022.06, Outstanding Undergraduate Student & Thesis.
• 2021.12, National Scholarship.
• 2020.05, First Class Scholarship, Jinan University.

Academic Services

• Conference Reviewer: KDD (2024, 2025), ECAI 2024.
• Journal Reviewer: ACM TKDD (Since 2023), IEEE TII (Since 2024), IEEE TKDE (Since 2024).

Experiences

• 2024.07 - 2024.09, Research Assistant, DEEP Lab@The Hong Kong Polytechnic University, Hong Kong SAR, China.
• 2022.09 - 2025.03, Research Assistant, Eagle Lab@Zhejiang University, Hangzhou, China.
• 2023.06 - 2023.11, Research Intern, CRO Security Technology Team@Alibaba Group, Hangzhou, China.
• 2022.02 - 2022.08, Research Intern, NLP Center@Meituan, Beijing, China.
• 2019.10 - 2022.01, Research Assistant, RecSys Group@Jinan University, Guangzhou, China.