EPAGCL derives degree-based edge augmentation probabilities from a new Error Passing Rate metric and reports state-of-the-art accuracy on seven graph datasets, while its core theoretical claim rests on a uniform per-node error assumption.
S.; Ribeiro, A.; and Sadler, B
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?
EPAGCL derives degree-based edge augmentation probabilities from a new Error Passing Rate metric and reports state-of-the-art accuracy on seven graph datasets, while its core theoretical claim rests on a uniform per-node error assumption.