LOHA directly contrasts low-pass and high-pass graph filters as mutual negatives and adds a spectral signal trend composite feature to reunite node features, improving self-supervised 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
-
LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views
LOHA directly contrasts low-pass and high-pass graph filters as mutual negatives and adds a spectral signal trend composite feature to reunite node features, improving self-supervised node classification.