A GRU-GAT model trained on limited grids achieves zero-shot transfer to unseen grids and identifies more vulnerable lines than structural or electrical baselines.
Gnns’ generalization improvement for large-scale power system analysis based on physics- informed self-supervised pre-training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Inductive Power Grid Cascading Failure Analysis with GRU-Gated Graph Attention
A GRU-GAT model trained on limited grids achieves zero-shot transfer to unseen grids and identifies more vulnerable lines than structural or electrical baselines.