Adversarial Capsule Learning for Network Embedding

The purpose of network embedding is to learn a low-dimensional representation for each node in the network. One can then use this low-dimensional representation to solve some network analysis tasks, such as node classification and node clustering. At present, there are several network embedding learning methods based on GAN (Generative Adversarial Networks) to enhance the robustness of representations. However, these methods have two drawbacks. First, they are often too difficult to be trained stably. Second, they only learn the robust representations by matching the posterior distribution of the latent representations to the given priors. On the contrary, Capsule Networks can learn a more equivariant representation of images that is more robust to the changes in pose and spatial relationships of parts of objects in images. However, there is still no research using Capsule Network for network embedding since the social network is essentially different from images. For this problem, we propose a new approach of adversarial capsule learning (ACL) for network embedding, which is the first time to use Capsule Network in the network analysis tasks. To be specific, the new model consists of two parts, a generator and discriminator. We use Graph Convolutional Networks (GCN) as the generator to learn the embedding of nodes, and use Capsule Network as the discriminator to distinguish between the real and fake samples as accurately as possible. The experimental results demonstrate the effectiveness of the proposed new method.