# Leveraging Multi-Task Learning for Multi-Label Power System Security Assessment

arXiv: https://arxiv.org/abs/2505.06207 · HTML: https://mlsanity.com/paper/2505.06207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 35 references that are in the map.
- First posted on arXiv 9 May 2025.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Neural Networks for Encoding Dynamic Security-Constrained Optimal Power Flow](https://mlsanity.com/paper/2003.07939/) (2020)
- [Efficient Database Generation for Data-driven Security Assessment of Power Systems](https://mlsanity.com/paper/1806.01074/) (2018)
- [Efficient Creation of Datasets for Data-Driven Power System Applications](https://mlsanity.com/paper/1910.01794/) (2019)
- [Ensemble Methods of Classification for Power Systems Security Assessment](https://mlsanity.com/paper/1601.01675/) (2016)
- [A Fast Certificate for Power System Small-Signal Stability](https://mlsanity.com/paper/2008.02263/) (2020)
- [Semi-Supervised Multi-Task Learning Based Framework for Power System Security Assessment](https://mlsanity.com/paper/2407.08886/) (2024)

## Abstract (arXiv)

This paper introduces a novel approach to the power system security assessment using Multi-Task Learning (MTL), and reformulating the problem as a multi-label classification task. The proposed MTL framework simultaneously assesses static, voltage, transient, and small-signal stability, improving both accuracy and interpretability with respect to the most state of the art machine learning methods. It consists of a shared encoder and multiple decoders, enabling knowledge transfer between stability tasks. Experiments on the IEEE 68-bus system demonstrate a measurable superior performance of the proposed method compared to the extant state-of-the-art approaches.