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.
This is likely related to the degree distribution [Zhanget al., 2024; Zouet al., 2021 ], as DBLP has a high proportion of nodes with low degrees
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.