MLDGG combines meta-learning with structure and representation learners to make GNNs generalize across graph domains, reporting accuracy gains over baselines on TWITCH, Facebook-100, and WebKB.
Algorithmic fairness generalization under covariate and dependence shifts simultaneously
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
-
MLDGG: Meta-Learning for Domain Generalization on Graphs
MLDGG combines meta-learning with structure and representation learners to make GNNs generalize across graph domains, reporting accuracy gains over baselines on TWITCH, Facebook-100, and WebKB.