CV

Education

• Honors Youth Program, Xi’an Jiaotong University: 2017 - 2019
• B.S. in Computer Science, Xi’an Jiaotong University: 2019 - 2023
• Ph.D. in Intelligence Science and Technology (Computer Science), Peking University: 2023 - 2028 (expected)

Experience

MuLab @ Peking University (PKU)

• Conducting research on Graph-Centric Relational Databases
• Supervisor: Prof. Muhan Zhang
• Dates: September 2022 - Present

Amazon AI Lab, Shanghai

• Remote intern, focusing on Relational Databases
• Supervisor: Prof. Muhan Zhang, Applied Scientist Minjie Wang
• Dates: November 2023 - June 2025

Luo Lab Undergraduate Division (LUD) @ Xi’an Jiaotong University (XJTU)

• Participated in Twibot-22 project as a team member
• Supervisor: Prof. Minnan Luo
• Dates: February 2022 - December 2022

Summer Workshop, School of Computing @ National University of Singapore (NUS)

• Attended lectures on Visual Computing and developed a traffic sign recognition pipeline
• Supervisor: Prof. Terence Sim
• Dates: May 2021 - August 2021

Publications

Reconsidering the Performance of GAE in Link Prediction [CIKM 2025 Best Full Paper]

• Authors: Weishuo Ma, Yanbo Wang, Xiyuan Wang, Muhan Zhang
• Description: This paper reevaluates the performance of Graph Autoencoders for link prediction, showing that with proper hyperparameter tuning, orthogonal embeddings, and linear propagation, a simple GAE can match SOTA GNNs in accuracy while being more efficient.
• Link: Arxiv

Efficient Neural Common Neighbor for Temporal Graph Link Prediction [LoG 2025 Oral]

• Authors: Xiaohui Zhang*, Yanbo Wang*, Xiyuan Wang, Muhan Zhang
• Description: This paper presents an efficient method for temporal graph link prediction, achieving state-of-the-art results on a large-scale temporal dataset (TGB).
• Link: Arxiv

Griffin: Towards a Graph-Centric Relational Database Foundation Model [ICML 2025]

• Authors: Yanbo Wang, Xiyuan Wang, Quan Gan, Minjie Wang, Qibin Yang, David Wipf, Muhan Zhang
• Description: This paper introduces Griffin, a novel graph-based foundation model that successfully tackles complex relational databases, showing strong predictive performance and transfer learning through its unified data handling, specialized graph neural network, and effective multi-stage pretraining.
• Link: Arxiv

4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs [NeurIPS 2024]

• Authors: Minjie Wang*, Quan Gan*, David Wipf, Zhenkun Cai, Ning Li, Jianheng Tang, Yanlin Zhang, Zizhao Zhang, Zunyao Mao, Yakun Song, Yanbo Wang, Jiahang Li, Han Zhang, Guang Yang, Xiao Qin, Chuan Lei, Muhan Zhang, Weinan Zhang, Christos Faloutsos, Zheng Zhang
• Description: This toolbox transforms any relational database tasks into graph-based tasks for predictive modeling.
• Link: Arxiv

An Empirical Study of Realized GNN Expressiveness [ICML 2024]

• Authors: Yanbo Wang, Muhan Zhang
• Description: This study investigates the capabilities of realized graph neural networks (GNNs), providing insights beyond the general GNN function space.
• Link: Arxiv

TwiBot-22: Towards Graph-Based Twitter Bot Detection [NeurIPS 2022]

• Authors: Shangbin Feng*, Zhaoxuan Tan*, Herun Wan*, Ningnan Wang*, Zilong Chen*, Binchi Zhang*, Qinghua Zheng, Wenqian Zhang, Zhenyu Lei, Shujie Yang, Xinshun Feng, Qingyue Zhang, Hongrui Wang, Yuhan Liu, Yuyang Bai, Heng Wang, Zijian Cai, Yanbo Wang, Lijing Zheng, Zihan Ma, Jundong Li, Minnan Luo
• Description: A comprehensive benchmark for detecting Twitter bots using graph-based approaches.
• Link: Twibot-22