A node-wise multi-view ensemble distillation method lets plain MLPs match or beat multiplex GNN teachers on 5 of 6 datasets while running 35-89x faster.
arXiv preprint (2015)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Accurate, Efficient, and Interpretable MLPs on Multiplex Graphs via Node-wise Multi-View Ensemble Distillation
A node-wise multi-view ensemble distillation method lets plain MLPs match or beat multiplex GNN teachers on 5 of 6 datasets while running 35-89x faster.