Multi-component Similarity Graphs for Cross-network Node Classification
点击次数：
发表刊物：IEEE TRANSACTIONS ON ARTIFICIAL INTELLIGENCE
关键字：Cross-network node classification aims to train a classifier for unlabeled target network using a source network with rich labels. In applications, the degree of nodes mostly conforms to the long-tail distribution, i.e., most nodes in the network are tail nodes with sparse neighborhoods. The established methods focus on either the discrepancy cross network or the long tail in single network. As for the cross-network node classification under long tail, the co-existence of sparsity of tail nodes and the discrepancy cross network challenges existing methods for long-tail or methods for cross-network node classification. To this end, a Multi-component Similarity Graphs for Cross-network Node Classification (MS-CNC) is proposed in this paper. Specifically, in order to address the sparsity of the tail nodes, multiple component similarity graphs, including attribute and structure similarity graphs, are constructed for each network to enrich the neighborhoods of the tail nodes and alleviate the long tail phenomenon. Then multiple representations are learned from the multiple similarity graphs separately. Based on the multi-component representations, a two-level adversarial model is designed to address the distribution difference across networks. One level is used to learn the invariant representations cross network in view of structure and attribute components separately, and the other level is used to learn the invariant representations in view of the fused structure and attribute graphs. Extensive experimental results show that MS-CNC outperforms the stateof-the-art methods.
是否译文：否