HCNA: Hyperbolic Contrastive Learning Framework for Self-Supervised Network Alignment

作者：

Highlights：

• A novel self-supervised contrastive learning-based technique to align entities across two networks.

• We introduce network specific guided augmentations to generate multiple graph views.

• We employ multi-order hyperbolic graph convolution networks to capture higher order hierarchical structures.

• Our extensive experiments show that HCNA consistently outperforms the baselines by at least 1–84% in terms of accuracy score.

摘要

•A novel self-supervised contrastive learning-based technique to align entities across two networks.•We introduce network specific guided augmentations to generate multiple graph views.•We employ multi-order hyperbolic graph convolution networks to capture higher order hierarchical structures.•Our extensive experiments show that HCNA consistently outperforms the baselines by at least 1–84% in terms of accuracy score.

论文关键词：Network alignment,Contrastive learning,Hyperbolic GCN

论文评审过程：Received 5 March 2022, Revised 21 May 2022, Accepted 1 July 2022, Available online 22 July 2022, Version of Record 22 July 2022.

论文官网地址：https://doi.org/10.1016/j.ipm.2022.103021