TY - GEN
T1 - Elastic Graph Neural Networks
AU - Liu, Xiaorui
AU - Jin, Wei
AU - Ma, Yao
AU - Li, Yaxin
AU - Liu, Hua
AU - Wang, Yiqi
AU - Yan, Ming
AU - Tang, Jiliang
N1 - Publisher Copyright:
Copyright © 2021 by the author(s)
PY - 2021
Y1 - 2021
N2 - While many existing graph neural networks (GNNs) have been proven to perform `2-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via `1-based graph smoothing. As a result, we introduce a family of GNNs (Elastic GNNs) based on `1 and `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 https://github.com/lxiaorui/ElasticGNN.
AB - While many existing graph neural networks (GNNs) have been proven to perform `2-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via `1-based graph smoothing. As a result, we introduce a family of GNNs (Elastic GNNs) based on `1 and `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 https://github.com/lxiaorui/ElasticGNN.
UR - http://www.scopus.com/inward/record.url?scp=85145615473&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85145615473&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85145615473
T3 - Proceedings of Machine Learning Research
SP - 6837
EP - 6849
BT - Proceedings of the 38th International Conference on Machine Learning, ICML 2021
PB - ML Research Press
T2 - 38th International Conference on Machine Learning, ICML 2021
Y2 - 18 July 2021 through 24 July 2021
ER -