ClustGDD distills large graphs by clustering node embeddings and refining synthetic attributes, achieving state-of-the-art node classification accuracy at orders of magnitude lower time cost.
Title resolution pending
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
-
Simple yet Effective Graph Distillation via Clustering
ClustGDD distills large graphs by clustering node embeddings and refining synthetic attributes, achieving state-of-the-art node classification accuracy at orders of magnitude lower time cost.