30 citations · 47 across the 17 of their papers we have counts for
18 papers
FRACTION: Fraud Explanation Generation via Agentic Graph Context Navigation
Cecelia Soh, Jun Hu, Yuan Li +6
Graph fraud explanation generation emerges as an important task, which requires jointly leveraging graph structure and content information to produce human-readable explanations fo…
NodeImport: Imbalanced Node Classification with Node Importance Assessment
Nan Chen, Zemin Liu, Bryan Hooi +3
In real-world applications, node classification on graphs often faces the challenge of class imbalance, where majority classes dominate training, resulting in biased model performa…
Multi-Label Node Classification with Label Influence Propagation
Yifei Sun, Zemin Liu, Bryan Hooi +4
Graphs are a complex and versatile data structure used across various domains, with possibly multi-label nodes playing a particularly crucial role. Examples include proteins in PPI…
Robust Multimodal Recommendation via Graph Retrieval-Enhanced Modality Completion
Yuan Li, Jun Hu, Jiaxin Jiang +2
Multimodal data plays a critical role in web-based recommendation systems, where information from diverse modalities such as vision and text enhances representation learning. Howev…
EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning
Yufei He, Juncheng Liu, Zhiyuan Hu +9
Prevailing medical AI operates on an unrealistic ''one-shot'' model, diagnosing from a complete patient file. However, real-world diagnosis is an iterative inquiry where Clinicians…
Autonomous Chain-of-Thought Distillation for Graph-Based Fraud Detection
Yuan Li, Jun Hu, Bryan Hooi +2
Graph-based fraud detection on text-attributed graphs (TAGs) requires jointly modeling rich textual semantics and relational dependencies. However, existing LLM-enhanced GNN approa…
Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning
Jun Hu, Shangheng Chen, Yufei He +3
Heterogeneous Graph Neural Networks (HGNNs) are widely used for deep learning on heterogeneous graphs. Typical end-to-end HGNNs require repetitive message passing during training,…
Beyond Brainstorming: What Drives High-Quality Scientific Ideas? Lessons from Multi-Agent Collaboration
Nuo Chen, Yicheng Tong, Jiaying Wu +5
While AI agents show potential in scientific ideation, most existing frameworks rely on single-agent refinement, limiting creativity due to bounded knowledge and perspective. Inspi…
DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs
Yuan Li, Jun Hu, Bryan Hooi +2
Real-world fraud detection applications benefit from graph learning techniques that jointly exploit node features, often rich in textual data, and graph structural information. Rec…
NTSFormer: A Self-Teaching Graph Transformer for Multimodal Isolated Cold-Start Node Classification
Jun Hu, Yufei He, Yuan Li +2
Isolated cold-start node classification on multimodal graphs is challenging because such nodes have no edges and often have missing modalities (e.g., absent text or image features)…
JudgeLRM: Large Reasoning Models as a Judge
Nuo Chen, Zhiyuan Hu, Qingyun Zou +4
Large Language Models (LLMs) are increasingly adopted as evaluators, offering a scalable alternative to human annotation. However, existing supervised fine-tuning (SFT) approaches…
RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs
Yuan Li, Jun Hu, Jiaxin Jiang +3
Recent advances in graph learning have paved the way for innovative retrieval-augmented generation (RAG) systems that leverage the inherent relational structures in graph data. How…
Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation
Jun Hu, Bryan Hooi, Bingsheng He +1
Multimodal recommendation systems can learn users' preferences from existing user-item interactions as well as the semantics of multimodal data associated with items. Many existing…
Partitioning Message Passing for Graph Fraud Detection
Wei Zhuo, Zemin Liu, Bryan Hooi +4
Label imbalance and homophily-heterophily mixture are the fundamental problems encountered when applying Graph Neural Networks (GNNs) to Graph Fraud Detection (GFD) tasks. Existing…
Efficient Heterogeneous Graph Learning via Random Projection
Jun Hu, Bryan Hooi, Bingsheng He
Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Typical HGNNs require repetitive message passing during training, limiting…
A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions
Zemin Liu, Yuan Li, Nan Chen +3
Graphs represent interconnected structures prevalent in a myriad of real-world scenarios. Effective graph analytics, such as graph learning methods, enables users to gain profound…
Spade: A Real-Time Fraud Detection Framework on Evolving Graphs (Complete Version)
Jiaxin Jiang, Yuan Li, Bingsheng He +3
Real-time fraud detection is a challenge for most financial and electronic commercial platforms. To identify fraudulent communities, Grab, one of the largest technology companies i…
PathEnum: Towards Real-Time Hop-Constrained s-t Path Enumeration
Shixuan Sun, Yuhang Chen, Bingsheng He +1
We study the hop-constrained s-t path enumeration (HcPE) problem, which takes a graph , two distinct vertices and a hop constraint as input, and outputs all paths from…