# Inductive Power Grid Cascading Failure Analysis with GRU-Gated Graph Attention

arXiv: https://arxiv.org/abs/2605.07010 · HTML: https://mlsanity.com/paper/2605.07010/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 7 of 7)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [A Review of Graph Neural Networks and Their Applications in Power Systems](https://mlsanity.com/paper/2101.10025/) (2021)
- [Power Flow Balancing with Decentralized Graph Neural Networks](https://mlsanity.com/paper/2111.02169/) (2021)
- [Power Failure Cascade Prediction using Graph Neural Networks](https://mlsanity.com/paper/2404.16134/) (2024)
- [Cascading Blackout Severity Prediction with Statistically-Augmented Graph Neural Networks](https://mlsanity.com/paper/2403.15363/) (2024)
- [A Dual Power Grid Cascading Failure Model for the Vulnerability Analysis](https://mlsanity.com/paper/2405.11311/) (2024)

## Abstract (arXiv)

Identifying vulnerable transmission lines in power grids before a cascading failure occurs is challenging: existing methods can learn inter-line failure correlations from cascade data, but they are trained and evaluated on a single grid, and transferring the learned knowledge to an unseen grid remains an open problem. We address this by training a single Gated Recurrent Unit (GRU)-gated Graph Attention Network on combined cascading failure data from limited training grids and applying it directly to any unseen grid without retraining. A GRU gate controls what information each node retains or discards at each cascade iteration. Empirical evaluation shows that the model transfers zero-shot to multiple new grids spanning inter-time and inter-domain settings. Using information extracted from the trained model, we consistently identify more vulnerable lines than established structural and electrical baselines.