MulSupConLD recovers a label distribution from binary multi-label data with RBF or contrastive weights and uses it to reweight supervised contrastive loss for multi-label 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
REJECT 1representative citing papers
citing papers explorer
-
Improving Multi-Label Contrastive Learning by Leveraging Label Distribution
MulSupConLD recovers a label distribution from binary multi-label data with RBF or contrastive weights and uses it to reweight supervised contrastive loss for multi-label classification.