Minglai Shao

Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning

2024

Graph representation learning has become a mainstream method for fraud detection due to its strong expressive power, which focuses on enhancing node representations through improved neighborhood knowledge capture. However, the focus on local interactions leads …

FADE: Towards Fairness-aware Data Generation for Domain Generalization via Classifier-Guided Score-based Diffusion Models

2024

Fairness-aware domain generalization (FairDG) has emerged as a critical challenge for deploying trustworthy AI systems, particularly in scenarios involving distribution shifts. Traditional methods for addressing fairness have failed in domain generalization due to their lack …

GDDA: Semantic OOD Detection on Graphs under Covariate Shift via Score-Based Diffusion Models

2024 · arXiv (Cornell University)

Out-of-distribution (OOD) detection poses a significant challenge for Graph Neural Networks (GNNs), particularly in open-world scenarios with varying distribution shifts. Most existing OOD detection methods on graphs primarily focus on identifying instances in test data …

Evidence-Based Out-of-Distribution Detection on Multi-Label Graphs

2025 · Society for Industrial and Applied Mathematics eBooks

The Out-of-Distribution (OOD) problem in graph-structured data is becoming increasingly important in various areas of research and applications, including social network recommendation [36], protein function detection[9, 21], etc. Furthermore, owing to the inherent multi-label properties …

Addressing Graph Anomaly Detection via Causal Edge Separation and Spectrum

2025 · arXiv (Cornell University)

In the real world, anomalous entities often add more legitimate connections while hiding direct links with other anomalous entities, leading to heterophilic structures in anomalous networks that most GNN-based techniques fail to address. Several works …

Mitigating Message Imbalance in Fraud Detection with Dual-View Graph Representation Learning

2025 · arXiv (Cornell University)

Graph representation learning has become a mainstream method for fraud detection due to its strong expressive power, which focuses on enhancing node representations through improved neighborhood knowledge capture. However, the focus on local interactions leads …