Stability and Generalization of lp-Regularized Stochastic Learning for GCN

Shiyu Liu; Linsen Wei; Shaogao Lv; Ming Li

IJCAI 2023poster1 citations

Stability and Generalization of lp-Regularized Stochastic Learning for GCN

Shiyu Liu, Linsen Wei, Shaogao Lv, Ming Li

Abstract

Graph convolutional networks (GCN) are viewed as one of the most popular representations among the variants of graph neural networks over graph data and have shown powerful performance in empirical experiments. That l2-based graph smoothing enforces the global smoothness of GCN, while (soft) l1-based sparse graph learning tends to promote signal sparsity to trade for discontinuity. This paper aims to quantify the trade-off of GCN between smoothness and sparsity, with the help of a general lp-regularized (1

Uncertainty in AI: UAI: Graphical models

BibTeX

@inproceedings{ijcai2023p631,
  title     = {Stability and Generalization of lp-Regularized Stochastic Learning for GCN},
  author    = {Liu, Shiyu and Wei, Linsen and Lv, Shaogao and Li, Ming},
  booktitle = {Proceedings of the Thirty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-23}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Edith Elkind},
  pages     = {5685--5693},
  year      = {2023},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2023/631},
  url       = {https://doi.org/10.24963/ijcai.2023/631},
}