A simple Laplacian smoothing loss applied to the target graph, with random-walk neighbor sampling, improves unsupervised graph domain adaptation on citation networks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation
A simple Laplacian smoothing loss applied to the target graph, with random-walk neighbor sampling, improves unsupervised graph domain adaptation on citation networks.