GCAL combines information-maximization adaptation with variational memory graph generation to prevent catastrophic forgetting in unsupervised continual graph domain adaptation.
Using our framework demonstrates remarkable enhancements, showing the effectiveness of our proposed techniques
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
-
GCAL: Adapting Graph Models to Evolving Domain Shifts
GCAL combines information-maximization adaptation with variational memory graph generation to prevent catastrophic forgetting in unsupervised continual graph domain adaptation.