Detecting User Community in Sparse Domain via Cross-Graph Pairwise Learning

TL;DR

This paper introduces PCCD, a novel method for detecting user communities in sparse bipartite graphs by leveraging cross-graph user information and pairwise community closeness estimation.

Contribution

The paper proposes a new approach that uses external graph knowledge and pairwise user closeness to improve community detection in sparse heterogeneous graphs.

Findings

PCCD outperforms several strong baseline methods.

The model is robust across different levels of graph sparsity.

Extensive experiments validate the effectiveness of the approach.

Abstract

Cyberspace hosts abundant interactions between users and different kinds of objects, and their relations are often encapsulated as bipartite graphs. Detecting user community in such heterogeneous graphs is an essential task to uncover user information needs and to further enhance recommendation performance. While several main cyber domains carrying high-quality graphs, unfortunately, most others can be quite sparse. However, as users may appear in multiple domains (graphs), their high-quality activities in the main domains can supply community detection in the sparse ones, e.g., user behaviors on Google can help thousands of applications to locate his/her local community when s/he uses Google ID to login those applications. In this paper, our model, Pairwise Cross-graph Community Detection (PCCD), is proposed to cope with the sparse graph problem by involving external graph knowledge to learn user pairwise community closeness instead of detecting direct communities. Particularly in our model, to avoid taking excessive propagated information, a two-level filtering module is utilized to select the most informative connections through both community and node level filters. Subsequently, a Community Recurrent Unit (CRU) is designed to estimate pairwise user community closeness. Extensive experiments on two real-world graph datasets validate our model against several strong alternatives. Supplementary experiments also validate its robustness on graphs with varied sparsity scales.