DRSA provides a plug-and-play alignment framework that decouples features and relations to prevent type collapse and relation confusion in heterogeneous graph foundation models.
Hetgpt: Harnessing the power of prompt tuning in pre-trained heterogeneous graph neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
CP-GBA distills a queryable repository of promptable subgraph triggers via graph prompt learning to achieve transferable backdoor attacks on GNNs with state-of-the-art success rates across paradigms and defenses.
citing papers explorer
-
Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment
DRSA provides a plug-and-play alignment framework that decouples features and relations to prevent type collapse and relation confusion in heterogeneous graph foundation models.
-
Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers
CP-GBA distills a queryable repository of promptable subgraph triggers via graph prompt learning to achieve transferable backdoor attacks on GNNs with state-of-the-art success rates across paradigms and defenses.