Layered Division and Global Allocation for Community Detection in Multilayer Network

TL;DR

This paper introduces LDGA, a novel neural network-based method for community detection in multilayer networks that performs layer-wise division and global allocation, improving detection accuracy over existing methods.

Contribution

The paper proposes a new layered division and global allocation paradigm using a multi-head Transformer and community prototypes, enhancing multilayer community detection performance.

Findings

LDGA outperforms state-of-the-art methods in modularity scores.

The approach effectively captures layer-specific structural nuances.

Unsupervised training with a coupled loss function proves successful.

Abstract

Community detection in multilayer networks (CDMN) is to divide a set of entities with multiple relation types into a few disjoint subsets, which has many applications in the Web, transportation, and sociology systems. Recent neural network-based solutions to the CDMN task adopt a kind of representation fusion and global division paradigm: Each node is first learned a kind of layer-wise representations which are then fused for global community division. However, even with contrastive or attentive fusion mechanisms, the fused global representations often lack the discriminative power to capture structural nuances unique to each layer. In this paper, we propose a novel paradigm for the CDMN task: Layered Division and Global Allocation (LDGA). The core idea is to first perform layer-wise group division, based on which global community allocation is next performed. Concretely, LDGA employs a multi-head Transformer as the backbone representation encoder, where each head is for encoding node structural characteristics in each network layer. We integrate the Transformer with a community-latent encoder to capture community prototypes in each layer. A shared scorer performs layered division by generating layer-wise soft assignments, while global allocation assigns each node the community label with highest confidence across all layers to form the final consensus partition. We design a loss function that couples differentiable multilayer modularity with a cluster balance regularizer to train our model in an unsupervised manner. Extensive experiments on synthetic and real-world multilayer networks demonstrate that our LDGA outperforms the state-of-the-art competitors in terms of higher detected community modularities. Our code with parameter settings and datasets are available at https://anonymous.4open.science/r/LDGA-552B/.