DCOM-GNN: A Deep Clustering Optimization Method for Graph Neural Networks

doi:10.1016/j.knosys.2023.110961

2023-11-01

PRE

Junli Wang

Rui Duan

Chungang Yan

DOI：10.1016/j.knosys.2023.110961

原文链接

原文求助

摘要

En 中文

Deep clustering plays an important role in data analysis, and with the prevalence of graph data nowadays, various deep clustering models on graph are constantly proposed. However, due to the lack of more adequate clustering guidance, the discriminability of feature representation learned from these models for the clustering task is limited. Therefore, for the purpose of enabling the output of these models to be more cluster-oriented, we propose a Deep Clustering Optimization Method for Graph Neural Networks (DCOM-GNN), which can be attached to the original model architecture conveniently. For DCOM-GNN, it contains two components, one is the inter-cluster distance optimization module, whose role is to further adjust the distance between clusters of the original model output rationally. Another one is the intra-cluster distance optimization module, which aims to improve the cohesiveness of the original model output. Comprehensive experiments show that the performance of various deep clustering models on graph can be significantly improved after adding DCOM-GNN.(c) 2023 Elsevier B.V. All rights reserved.

Keyword:

Deep clustering

Graph neural networks

Inter-cluster distance

Intra-cluster distance

Optimization method