Unsupervised Adversarial Graph Alignment with Graph Embedding

TL;DR

This paper introduces an unsupervised adversarial framework for aligning graphs without any labeled anchor links, using embedding space alignment and iterative refinement to improve accuracy and applicability in social network analysis.

Contribution

The paper proposes the first fully unsupervised adversarial method for graph alignment that does not require any anchor links or attribute information, with an iterative extension for improved accuracy.

Findings

Effective in aligning graphs without anchor links

Improves embedding quality and alignment accuracy through iterative refinement

Beneficial for link prediction in social networks

Abstract

Graph alignment, also known as network alignment, is a fundamental task in social network analysis. Many recent works have relied on partially labeled cross-graph node correspondences, i.e., anchor links. However, due to the privacy and security issue, the manual labeling of anchor links for diverse scenarios may be prohibitive. Aligning two graphs without any anchor links is a crucial and challenging task. In this paper, we propose an Unsupervised Adversarial Graph Alignment (UAGA) framework to learn a cross-graph alignment between two embedding spaces of different graphs in a fully unsupervised fashion (\emph{i.e.,} no existing anchor links and no users' personal profile or attribute information is available). The proposed framework learns the embedding spaces of each graph, and then attempts to align the two spaces via adversarial training, followed by a refinement procedure. We further extend our UAGA method to incremental UAGA (iUAGA) that iteratively reveals the unobserved user links based on the pseudo anchor links. This can be used to further improve both the embedding quality and the alignment accuracy. Moreover, the proposed methods will benefit some real-world applications, \emph{e.g.,} link prediction in social networks. Comprehensive experiments on real-world data demonstrate the effectiveness of our proposed approaches UAGA and iUAGA for unsupervised graph alignment.