Elastic Graph Neural Networks

# Elastic Graph Neural Networks

**arXiv ID:** 2107.06996
**Authors:** Xiaorui Liu, Wei Jin, Yao Ma, Yaxin Li, Hua Liu, Yiqi Wang, Ming Yan, Jiliang Tang
**Published:** 2021-07-05T01:36:01Z
**Abstract:**
While many existing graph neural networks (GNNs) have been proven to perform $\ell_2$-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via $\ell_1$-based graph smoothing. As a result, we introduce a family of GNNs (Elastic GNNs) based on $\ell_1$ and $\ell_2$-based graph smoothing. In particular, we propose a novel and general message passing scheme into GNNs. This message passing algorithm is not only friendly to back-propagation training but also achieves the desired smoothing properties with a theoretical convergence guarantee. Experiments on semi-supervised learning tasks demonstrate that the proposed Elastic GNNs obtain better adaptivity on benchmark datasets and are significantly robust to graph adversarial attacks. The implementation of Elastic GNNs is available at \url{https://github.com/lxiaorui/ElasticGNN}.

## Skill Description

This skill is generated from the arXiv paper: Elastic Graph Neural Networks (2107.06996).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2107.06996](http://arxiv.org/abs/2107.06996v1)