DAWN: Domain Generalization Based Network Alignment

Network alignment aims to discover nodes in different networks belonging to the same identity. In recent years, the network alignment problem has aroused significant attentions in both industry and academia. With the rapid growth of information, the sizes of networks are usually very large and in most cases we only focus on the alignment of partial networks. However, under this circumstances, the collected network data may be highly biased, and the training and testing data are no longer i.i.d. (identically and independently distributed). Thus, it is difficult for the trained alignment model to have a good performance in the test set. To bridge this gap, in this paper, we propose a novel Domain generAlization based netWork aligNment approach termed as DAWN. Specifically, in DAWN, we first design a novel invariant feature extraction model which leverages adversarial learning to extract domain-invariant features. Then, we design a novel invariant network alignment model which can achieve global optimum and local optimum simultaneously to learn domain-invariant alignment patterns. Finally, we conduct extensive experiments on the benchmark dataset of Facebook-Twitter, and results show that DAWN can averagely achieve 14.01% higher Hits@k and 10.63% higher MRR@k compared with the state-of-the-art methods.

Automated summary

Network alignment aims to discover nodes of the same identity in different networks. This paper proposes a novel Domain generAlization based netWork aligNment approach (DAWN) that leverages adversarial learning to extract domain-invariant features and achieve global and local optimum alignment patterns. Experimental results on the Facebook-Twitter benchmark dataset show that DAWN outperforms state-of-the-art methods with an average improvement of 14.01% in Hits@k and 10.63% in MRR@k.