Learnable random-walk path sampling with a kernel-density mutual information loss improves node classification under distribution shifts, outperforming prior graph OOD methods on seven benchmarks.
Learning causally invariant representations for out-of- distribution generalization on graphs
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
-
Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective
Learnable random-walk path sampling with a kernel-density mutual information loss improves node classification under distribution shifts, outperforming prior graph OOD methods on seven benchmarks.