Dual adaptive learning multi-task multi-view for graph network representation learning. (May 2023)

• Record Type: Journal Article
• Authors: Han, Beibei; Wei, Yingmei; Wang, Qingyong; Wan, Shanshan
• Is Part Of: Neural networks. Volume 162(2023)
• Page Start: 297
• Page End: 308
• Publication Date: 2023-05
• Subjects: Graph network analysis -- Multi-view graph network -- Multi-task learning -- Adaptive graph network represent learning; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2023.02.026
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Graph network analysis, which achieves widely application, is to explore and mine the graph structure data. However, existing graph network analysis methods with graph representation learning technique ignore the correlation between multiple graph network analysis tasks, and they need massive repeated calculation to obtain each graph network analysis results. Or they cannot adaptively balance the relative importance of multiple graph network analysis tasks, that lead to weak model fitting. Besides, most of existing methods ignore multiplex views semantic information and global graph information, which fail to learn robust node embeddings resulting in unsatisfied graph analysis results. To solve these issues, we propose a m ulti-task m ulti-view a daptive g raph network representation l earning model, called M 2 agl. The highlights of M 2 agl are as follows: (1) Graph convolutional network with the linear combination of the adjacency matrix and PPMI (positive point-wise mutual information) matrix is utilized as encoder to extract the local and global intra-view graph feature information of the multiplex graph network. Each intra-view graph information of the multiplex graph network can adaptively learn the parameters of graph encoder. (2) We use regularization to capture the interaction information among different graph views, and the importance of different graph views are learned by view attention mechanism for further inter-view graph network fusion. (3) The model is trained oriented by multiple graph network analysis tasks. The relative importance of multiple graph network analysis tasks are adjusted adaptively with the homoscedastic uncertainty. The regularization can be considered as an auxiliary task to further boost the performance. Experiments on real-worlds attributed multiplex graph networks demonstrate the effectiveness of M 2 agl in comparison with other competing approaches.