IFL-GCL uses InfoNCE's similarity signal to resample semantically similar non-augmented pairs as positives and updates the contrastive loss, improving graph pre-training accuracy on several benchmarks.
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
REJECT 1representative citing papers
citing papers explorer
-
InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learning
IFL-GCL uses InfoNCE's similarity signal to resample semantically similar non-augmented pairs as positives and updates the contrastive loss, improving graph pre-training accuracy on several benchmarks.