An attentional-walk-based autoencoder for community detection

The purpose of community detection is to discover closely connected groups of entities in complex networks such as interest groups, proteins and vehicles in social, biological and transportation networks. Recently, autoencoders have become a popular technique to extract nonlinear relationships between nodes by learning their representation vectors through an encoder-decoder neural structure, which is beneficial to discovering communities with vague boundaries. However, most of the existing autoencoders take restoring a network's adjacency matrix as their objective, which puts emphasis on the first-order relationships between the nodes and neglects their higher-order relationships that may be more useful for community detection. In this paper, we propose a novel attentional-walk-based autoencoder (AWBA) which integrates random walk considering attentional coefficients between each pair of nodes into the encoder to mine their high-order relationships. First, the attention layers are added to the encoder to learn the influence of a node's different neighbors on it in encoding. Second, we develop a new random walk strategy that embeds the attention coefficients and the community membership of the nodes obtained by a seed-expansion-based clustering algorithm into the computation of the transition probability matrix to instill both low and high order relationships between the nodes into the representation vectors. The experimental results on synthetic and real-world networks verify the superiority of our algorithm over the baseline algorithms.

Automated summary

This paper presents a novel attentional-walk-based autoencoder (AWBA) that integrates random walk with attentional coefficients to mine high-order relationships between nodes, aiming to improve community detection. Experimental results demonstrate the superior performance of our algorithm compared to baseline algorithms.