English

glassoformer: a query-sparse transformer for post-fault power grid voltage prediction

Machine Learning 2022-01-25 v1 Signal Processing

Abstract

We propose GLassoformer, a novel and efficient transformer architecture leveraging group Lasso regularization to reduce the number of queries of the standard self-attention mechanism. Due to the sparsified queries, GLassoformer is more computationally efficient than the standard transformers. On the power grid post-fault voltage prediction task, GLassoformer shows remarkably better prediction than many existing benchmark algorithms in terms of accuracy and stability.

Keywords

Cite

@article{arxiv.2201.09145,
  title  = {glassoformer: a query-sparse transformer for post-fault power grid voltage prediction},
  author = {Yunling Zheng and Carson Hu and Guang Lin and Meng Yue and Bao Wang and Jack Xin},
  journal= {arXiv preprint arXiv:2201.09145},
  year   = {2022}
}
R2 v1 2026-06-24T08:58:48.888Z