Graph domain adaptation fails more when source and target graphs have different local homophily profiles, and the proposed HGDA filters and aligns homophily, heterophily, and attribute signals to improve cross-graph node classification.
Demystifying structural disparity in graph neural networks: Can one size fit all?Advances in neural information processing systems, 36, 2024a
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Homophily Enhanced Graph Domain Adaptation
Graph domain adaptation fails more when source and target graphs have different local homophily profiles, and the proposed HGDA filters and aligns homophily, heterophily, and attribute signals to improve cross-graph node classification.