TY - JOUR
T1 - Robust cross-network node classification via constrained graph mutual information
AU - Yang, Shuiqiao
AU - Cai, Borui
AU - Cai, Taotao
AU - Song, Xiangyu
AU - Jiang, Jiaojiao
AU - Li, Bing
AU - Li, Jianxin
PY - 2022/12/5
Y1 - 2022/12/5
N2 - 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.
AB - 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.
KW - Graph domain adaptive learning
KW - Node classification
KW - Graph neural networks
KW - Mutual information
UR - http://www.scopus.com/inward/record.url?scp=85139078946&partnerID=8YFLogxK
U2 - 10.1016/j.knosys.2022.109852
DO - 10.1016/j.knosys.2022.109852
M3 - Article
AN - SCOPUS:85139078946
SN - 0950-7051
VL - 257
SP - 1
EP - 10
JO - Knowledge-Based Systems
JF - Knowledge-Based Systems
M1 - 109852
ER -