Advisors

• Bryan Hooi

  PhD advisor · until 2026 · National University of Singapore

  From a thesis record ↗

• GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner

  Zhenyu Hou, Yufei He, Yukuo Cen, Xiao Liu, Yuxiao Dong, Evgeny Kharlamov, Jie Tang

  ACM Web Conference (WWW) · 2023

  A masked self-supervised learning framework to impose regularization on feature reconstruction for graph SSL by designing the strategies of multi-view random re-mask decoding and latent representation prediction to regularize the feature reconstruction.

  243
• UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs

  Yufei He, Yuan Sui, Xiaoxin He, Bryan Hooi

  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · 2025

  The UniGraph framework, designed to learn a foundation model for TAGs, which is capable of generalizing to unseen graphs and tasks across diverse domains, and the first pre-training algorithm specifically designed for large-scale self-supervised learning on TAGs, based on Masked Graph Modeling are presented.

  82
• UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs

  Yufei He, Yuan Sui, Xiaoxin He, Yue Liu, Yifei Sun, Bryan Hooi

  Proceedings of the ACM on Web Conference 2025 · 2025

  UniGraph2 is proposed, a novel cross-domain graph foundation model that enables general representation learning on MMGs, providing a unified embedding space that captures both the multimodal information and the underlying graph structure.

  68
• NTSFormer: A Self-Teaching Graph Transformer for Multimodal Isolated Cold-Start Node Classification

  Jun Hu, Yufei He, Yuan Li, Bryan Hooi, Bingsheng He

  Proceedings of the AAAI Conference on Artificial Intelligence · 2026

  Neighbor-to-Self Graph Transformer (NTSFormer) is proposed, a unified Graph Transformer framework that jointly tackles the isolation and missing-modality issues via a self-teaching paradigm and achieves superior performance for multimodal isolated cold-start node classification.

  12
• SGKD: A Scalable and Effective Knowledge Distillation Framework for Graph Representation Learning

  Yufei He, Yao Ma

  IEEE ... International Conference on Data Mining workshops · 2022

  4
• Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning

  Jun Hu, Shangheng Chen, Yufei He, Yuan Li, Bryan Hooi, Bingsheng He

  Proceedings of the AAAI Conference on Artificial Intelligence · 2026

  –