CMPGNN inserts learned cross-domain edges between source and target graphs so message passing aligns target nodes with source-domain classes, improving unsupervised graph domain adaptation under label shift.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Bridging Source and Target Domains via Link Prediction for Unsupervised Domain Adaptation on Graphs
CMPGNN inserts learned cross-domain edges between source and target graphs so message passing aligns target nodes with source-domain classes, improving unsupervised graph domain adaptation under label shift.