AGU is an adaptive graph unlearning framework that combines task-specific edge and feature forgetting with GNN-specific affected-neighbor selection, and it reports state-of-the-art F1 and runtime on seven real-world graphs.
Inductive representation learning on large graphs
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
-
Adaptive Graph Unlearning
AGU is an adaptive graph unlearning framework that combines task-specific edge and feature forgetting with GNN-specific affected-neighbor selection, and it reports state-of-the-art F1 and runtime on seven real-world graphs.