Shared-latent variable network alignment

The increasing popularity and diversity of social media sites, has encouraged many people to participate in different online social networks to enjoy a variety of services. Linking the same users across different social networks, also known as social network alignment, is a critical task of great research challenges. Many existing works usually focus on finding a projection function from one subspace to another for network alignment, however, the projection functions proposed in their papers are independent and updated individually, which could not effectively exploit the non-parallel data, and yield inferior alignment performance. In this paper, we propose a Shared-latent Variable Network Alignment (SVNA) architecture to effectively exploit the non-parallel data for network alignment, and jointly train projection functions and decoders in a unified framework with the shared latent variable z. Specifically, SVNA first employs the graph convolutional networks to preserve the structural information of the network. By introducing the shared latent variable z, SVNA simultaneously integrates two projection functions and two decoders for jointly training. Both projection functions and decoders share the same latent space, therefore both projection directions can learn from the non-parallel data more effectively. Thereafter, SVNA utilizes the Generative Adversarial Networks (GANs) framework to further train the projection functions, and adopts a probability-based semi-supervised method to achieve the network alignment. Experiments on three real-world datasets show that SVNA generally outperforms the state-of-the-art methods in network alignment task.