2 papers
cs.LG2025
A Batch-Insensitive Dynamic GNN Approach to Address Temporal Discontinuity in Graph Streams
Yang Zhou, Xiaoning Ren
In dynamic graphs, preserving temporal continuity is critical. However, Memory-based Dynamic Graph Neural Networks (MDGNNs) trained with large batches often disrupt event sequences…
cs.LG2025
Robust OOD Graph Learning via Mean Constraints and Noise Reduction
Yang Zhou, Xiaoning Ren
Graph Out-of-Distribution (OOD) classification often suffers from sharp performance drops, particularly under category imbalance and structural noise. This work tackles two pressin…