FD-GCL is an augmentation-free, negative-free graph contrastive learner that uses two fractional-diffusion encoders with different orders to generate local and global views, reporting state-of-the-art node classification on several heterophilic benchmarks.
Building on the BGRL framework, AFGRL eliminates the need for augmentations by generating positive samples directly from the original graph for each node
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
-
Simple Graph Contrastive Learning via Fractional-order Neural Diffusion Networks
FD-GCL is an augmentation-free, negative-free graph contrastive learner that uses two fractional-diffusion encoders with different orders to generate local and global views, reporting state-of-the-art node classification on several heterophilic benchmarks.