Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning
Junlin Chen, Wenhao Wang, Junchao Xu +5
Graph Neural Networks (GNNs) excel on graph-structured data but suffer catastrophic forgetting when classes arrive sequentially. In class-incremental graph learning, predictions ar…
cs.LG2026
Rethinking Self-Distillation for Multi-Teacher Capability Merging
Roy Xie, Dan Friedman, Feng Nan +7
Combining capabilities of multiple expert models trained starting from the same base checkpoint has become increasingly common in frontier language-model post-training. Recent tren…