A hardness-aware reweighted contrastive loss that uses labels and similarity to upweight hard positives and negatives reduces degree bias in graph node classification.
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
-
Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning
A hardness-aware reweighted contrastive loss that uses labels and similarity to upweight hard positives and negatives reduces degree bias in graph node classification.