AnchorRM: Parallel Intra-Batch State Reconstruction with Anchor-Based Residual Memory for Temporal Graph Neural Networks
AnchorRM, an anchor-based residual memory mechanism that reconstructs event-specific intra-batch node states without executing sequential recurrent updates, substantially improves the scalability and training efficiency of memory-based temporal graph learning while maintaining competitive predictive performance.
Haroon Gharwi, Kai Shu, Yue Dai
· 0 citations