Graph Neural Networks with Adaptive Residual
Document Type
Conference Proceeding
Publication Date
1-1-2021
Abstract
Graph neural networks (GNNs) have shown the power in graph representation learning for numerous tasks. In this work, we discover an interesting phenomenon that although residual connections in the message passing of GNNs help improve the performance, they immensely amplify GNNs’ vulnerability against abnormal node features. This is undesirable because in real-world applications, node features in graphs could often be abnormal such as being naturally noisy or adversarially manipulated. We analyze possible reasons to understand this phenomenon and aim to design GNNs with stronger resilience to abnormal features. Our understandings motivate us to propose and derive a simple, efficient, interpretable, and adaptive message passing scheme, leading to a novel GNN with Adaptive residual, AirGNN1. Extensive experiments under various abnormal feature scenarios demonstrate the effectiveness of the proposed algorithm.
Identifier
85125027645 (Scopus)
ISBN
[9781713845393]
Publication Title
Advances in Neural Information Processing Systems
ISSN
10495258
First Page
9720
Last Page
9733
Volume
12
Grant
CNS1815636
Fund Ref
National Science Foundation
Recommended Citation
Liu, Xiaorui; Ding, Jiayuan; Jin, Wei; Xu, Han; Ma, Yao; Liu, Zitao; and Tang, Jiliang, "Graph Neural Networks with Adaptive Residual" (2021). Faculty Publications. 4563.
https://digitalcommons.njit.edu/fac_pubs/4563