D2MoE dynamically allocates expert resources in graph MoEs via difficulty-driven top-p routing based on predictive entropy, yielding higher accuracy and lower memory/time costs on node classification benchmarks.
Beyond homophily in graph neural networks: current limitations and effective designs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node Classification
D2MoE dynamically allocates expert resources in graph MoEs via difficulty-driven top-p routing based on predictive entropy, yielding higher accuracy and lower memory/time costs on node classification benchmarks.