Graph autoencoder with preserving node attribute similarity

Lin, Mugang, Wen, Kunhui, Zhu, Xuanying, Zhao, Huihuang and Sun, Xianfang ORCID: https://orcid.org/0000-0002-6114-0766 2023. Graph autoencoder with preserving node attribute similarity. Entropy 25 (4) , 567. 10.3390/e25040567

PDF - Published Version Available under License Creative Commons Attribution. Download (5MB)

Abstract

The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservation of the attribute information of nodes. Thus, the node attributes cannot be fully learned and the ability of the GAE to learn higher-quality representations is weakened. To address the issue, this paper proposes a novel GAE model that preserves node attribute similarity. The structural graph and the attribute neighbor graph, which is constructed based on the attribute similarity between nodes, are integrated as the encoder input using an effective fusion strategy. In the encoder, the attributes of the nodes can be aggregated both in their structural neighborhood and by their attribute similarity in their attribute neighborhood. This allows performing the fusion of the structural and node attribute information in the node representation by sharing the same encoder. In the decoder module, the adjacency matrix and the attribute similarity matrix of the nodes are reconstructed using dual decoders. The cross-entropy loss of the reconstructed adjacency matrix and the mean-squared error loss of the reconstructed node attribute similarity matrix are used to update the model parameters and ensure that the node representation preserves the original structural and node attribute similarity information. Extensive experiments on three citation networks show that the proposed method outperforms state-of-the-art algorithms in link prediction and node clustering tasks.

Item Type:	Article
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Additional Information:	License information from Publisher: LICENSE 1: URL: https://creativecommons.org/licenses/by/4.0/, Type: open-access
Publisher:	MDPI
Date of First Compliant Deposit:	6 April 2023
Date of Acceptance:	24 March 2023
Last Modified:	02 Jun 2023 21:56
URI:	https://orca.cardiff.ac.uk/id/eprint/158471

Actions (repository staff only)

Edit Item