HyFi improves hypergraph contrastive learning by weighting nodes that share hyperedges as 'weak positives' and using feature noise instead of topology corruption for augmentation.
Hypergraph neural net- works,
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
-
Closer through commonality: Enhancing hypergraph contrastive learning with shared groups
HyFi improves hypergraph contrastive learning by weighting nodes that share hyperedges as 'weak positives' and using feature noise instead of topology corruption for augmentation.