HackGAN: Harmonious Cross-Network Mapping Using CycleGAN With Wasserstein–Procrustes Learning for Unsupervised Network Alignment

Network alignment (NA) that identifies equivalent nodes across networks is an effective tool for integrating knowledge from multiple networks. The state-of-the-art NA methods learn inter-network node similarities based on labeled anchor links, which are costly, time-consuming, and difficult to acquire. Therefore, a few unsupervised network alignment (UNA) methods propose solving NA problems without anchor links. However, most existing UNA methods rely on discriminative attributes to capture nodes’ similarities and are hard to obtain optimal one-to-one alignments. Toward these issues, this article proposes a novel method named HackGAN to solve the UNA problem solely based on the structural information. Specifically, HackGAN represents nodes with embeddings based on an unsupervised graph neural network (GNN) to capture their global and local structural features. After that, it initializes mapping functions to transform the embedding spaces of different networks into the same vector space by iteratively solving the Wasserstein–Procrustes problem. The mapping functions are then refined by an adversarial model with cycle-consistency and Sinkhorn distance losses to obtain optimized one-to-one mappings. Based on the distances between mapped embeddings, accurate and robust results are obtained with a collective alignment algorithm. Experimental comparisons on both synthetic and real-world datasets demonstrate the superiority of HackGAN.

I. Introduction

Networks are powerful structures for representing complex interconnections between entities. A large number of methods have been proposed for various network analysis tasks over a single network, including link prediction [1], [2], community detection [3], [4], and node classification [5], which provide deep insights into the underlying mechanism of complex network systems and benefit a lot of industrial applications. With a large number of networks regarding the same domain being developed by different organizations, entities appear in more than one network with increasing probabilities [6]. For example, people nowadays usually register more than one social application to enjoy diverse services.