HeTa learns relational importance weights on a surrogate HGNN, then attacks relations one by one with injected nodes and gradient-selected edges to transfer across target HGNNs.
Let graph be the go board: gradient-free node injection attack for graph neural networks via reinforce- ment learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HeTa: Relation-wise Heterogeneous Graph Foundation Attack Model
HeTa learns relational importance weights on a surrogate HGNN, then attacks relations one by one with injected nodes and gradient-selected edges to transfer across target HGNNs.