M2D distillation augments input graphs with model-derived features and structure, letting simple student GNNs match teacher performance while exposing mechanisms such as attention and fairness directly in the data.
A comprehensive survey on graph reduction: Sparsification, coarsening, and condensation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Hamiltonian Graph Networks achieve 150-600x faster training via random feature parameter construction while retaining comparable accuracy and physical invariances on N-body systems up to 10,000 particles.
citing papers explorer
-
From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning
M2D distillation augments input graphs with model-derived features and structure, letting simple student GNNs match teacher performance while exposing mechanisms such as attention and fairness directly in the data.
-
Rapid training of Hamiltonian graph networks using random features
Hamiltonian Graph Networks achieve 150-600x faster training via random feature parameter construction while retaining comparable accuracy and physical invariances on N-body systems up to 10,000 particles.