Chao Li

Mitigating Dynamic Graph Distribution Shifts via Spectral Augmentation

This paper proposes a spectral-based graph augmentation framework designed to investigate and improve generalization behavior in dynamic graphs under distribution shifts and develops a multi-encoder architecture in which each encoder targets a specific spectral shift component to generate referential representations.

TcfDyG: Cryptocurrency Network Anomaly Detection Based on Time-aware Channel Fusion Dynamic Graph Neural Network

Adversarial Masked Graph Modeling for Robust Graph Autoencoders

This work designs a dual-consistency graph augmentation method that enriches the graph topology to mitigate structural vulnerabilities and presents an adversarial masked autoen-coder to mitigate model overfitting to the perturbed graph.