Publication Type
Journal Article
Version
publishedVersion
Publication Date
1-2023
Abstract
Graph neural networks (GNNs) have witnessed widespread adoption due to their ability to learn superior representations for graph data. While GNNs exhibit strong discriminative power, they often fall short of learning the underlying node distribution for increased robustness. To deal with this, inspired by generative adversarial networks (GANs), we investigate the problem of adversarial learning on graph neural networks, and propose a novel framework named NAGNN (i.e., Neighbor-anchoring Adversarial Graph Neural Networks) for graph representation learning, which trains not only a discriminator but also a generator that compete with each other. In particular, we propose a novel neighbor-anchoring strategy, where the generator produces samples with explicit features and neighborhood structures anchored on a reference real node, so that the discriminator can perform neighborhood aggregation on the fake samples to learn superior representation. The advantage of our neighbor-anchoring strategy can be demonstrated both theoretically and empirically. Furthermore, as a by-product, our generator can synthesize realistic-looking features, enabling potential applications such as automatic content summarization. Finally, we conduct extensive experiments on four public benchmark datasets, and achieve promising results under both quantitative and qualitative evaluations.
Keywords
Neighbor-anchoring, generative adversarial network, graph neural network
Discipline
Databases and Information Systems
Research Areas
Data Science and Engineering; Intelligent Systems and Optimization
Publication
IEEE Transactions on Knowledge and Data Engineering
Volume
35
Issue
1
First Page
784
Last Page
795
ISSN
1041-4347
Identifier
10.1109/TKDE.2021.3087970
Publisher
Institute of Electrical and Electronics Engineers
Citation
LIU, Zemin; FANG, Yuan; LIU, Yong; and ZHENG, Vincent W..
Neighbor-anchoring adversarial graph neural networks. (2023). IEEE Transactions on Knowledge and Data Engineering. 35, (1), 784-795.
Available at: https://ink.library.smu.edu.sg/sis_research/8200
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
http://doi.org/10.1109/TKDE.2021.3087970