Robust cross-network node classification via constrained graph mutual information

Shuiqiao Yang, Borui Cai, Taotao Cai, Xiangyu Song, Jiaojiao Jiang, Bing Li, Jianxin Li*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

27 Citations (Scopus)

Abstract

The recent methods for cross-network node classification mainly exploit graph neural networks (GNNs) as feature extractor to learn expressive graph representations across the source and target graphs. However, GNNs are vulnerable to noisy factors, such as adversarial attacks or perturbations on the node features or graph structure, which can cause a significant negative impact on their learning performance. To this end, we propose a robust graph domain adaptive learning framework RGDAL which exploits an information-theoretic principle to filter the noisy factors for cross-network node classification. Specifically, RGDAL utilizes graph convolutional network (GCN) with constrained graph mutual information and an adversarial learning component to learn noise-resistant and domain-invariant graph representations. To overcome the difficulties of estimating the mutual information for the non independent and identically distributed (non-i.i.d.) graph structured data, we design a dynamic neighborhood sampling strategy that can discretize the graph and incorporate the graph structural information for mutual information estimation. Experimental results on two real-world graph datasets demonstrate that RGDAL shows better robustness for cross-network node classification compared with the SOTA graph adaptive learning methods.

Original languageEnglish
Article number109852
Pages (from-to)1-10
Number of pages10
JournalKnowledge-Based Systems
Volume257
DOIs
Publication statusPublished - 5 Dec 2022

Keywords

  • Graph domain adaptive learning
  • Node classification
  • Graph neural networks
  • Mutual information

Fingerprint

Dive into the research topics of 'Robust cross-network node classification via constrained graph mutual information'. Together they form a unique fingerprint.

Cite this