Decoupled Representation Learning for Attributed Networks

Network representation learning or network embedding, which targets at learning the low-dimension representation of graph-based data, has attracted wide attention due to its effectiveness on various network-oriented applications in recent years. Though large efforts have been made on the joint analysis combining node attributes with the network structure, they usually model the interactions between nodes reflected by network structure and attributes in a coupled way and fail to address the common sparse attribute issues. To this end, in this article, we comprehensively study the problem of learning attributed network embedding, which focuses on characterizing different types of interactions among nodes and alleviating the sparse attribute problem as well. Specifically, we propose a novel DeCoupled Network Embedding (DCNE) model to learn node representations in a unified framework. We first respectively project both nodes and attributes into a low-dimensional vectorial space. Then, we introduce a novel "decoupled-fusion" learning process into each graph layer to iteratively generate node embeddings. In particular, we propose two adapted graph convolution modules to decouple the learning of network structure and attributes respectively, and a fusion module to adaptively aggregate the information. Next, we adopt a modified mini-batch algorithm to iteratively aggregate the higher-order information of both nodes and attributes within a multi-task learning framework. Extensive experiments on five public datasets demonstrate that DCNE could outperform state-of-the-art methods on multiple benchmark tasks. Moreover, several qualitative analyses further indicate DCNE can learn more robust and representative node embeddings than other comparison methods for attributed networks.