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.
Collaborative knowledge distillation for heterogeneous information network embedding
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
-
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.