D^(2)-GCN:a graph convolutional network with dynamic disentanglement for node classification  

作　　者：Shangwei WU Yingtong XIONG Hui LIANG Chuliang WENG 

机构地区：[1]School of Data Science and Engineering,East China Normal University,Shanghai 200062,China

出　　处：《Frontiers of Computer Science》2025年第1期145-161,共17页计算机科学前沿(英文版)

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.62141214 and 62272171).

摘　　要：Classic Graph Convolutional Networks (GCNs) often learn node representation holistically, which ignores the distinct impacts from different neighbors when aggregating their features to update a node’s representation. Disentangled GCNs have been proposed to divide each node’s representation into several feature units. However, current disentangling methods do not try to figure out how many inherent factors the model should assign to help extract the best representation of each node. This paper then proposes D^(2)-GCN to provide dynamic disentanglement in GCNs and present the most appropriate factorization of each node’s mixed features. The convergence of the proposed method is proved both theoretically and experimentally. Experiments on real-world datasets show that D^(2)-GCN outperforms the baseline models concerning node classification results in both single- and multi-label tasks.

关 键 词：graph convolutional networks dynamic disentanglement label entropy node classification 

分 类 号：O15[理学—数学]