Graph contrastive learning's advantage over untrained and handcrafted baselines is size-dependent: baselines win on small datasets, GCL wins modestly past a few thousand graphs, then plateaus.
A fair comparison of graph neural networks for graph classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size
Graph contrastive learning's advantage over untrained and handcrafted baselines is size-dependent: baselines win on small datasets, GCL wins modestly past a few thousand graphs, then plateaus.