Method finds communities in multilayer networks with varied connections
Degree-Corrected Joint Matrix Factorization for Multilayer Community Detection
Social and Information NetworksMachine Learning
Summary
Finding groups within networks is tricky when the same people or things connect differently in multiple situations or times. The authors developed a new technique that breaks down multiple network layers together, allowing them to find shared groups while still capturing unique connection patterns in each layer. Their method works better than others in many cases because it handles differences in how connected the nodes are and changes between layers. They tested it using simulated networks that mimic realistic variations and found it reliably identifies the correct groups.
What this means in practice
- •For social network analysts: Detect consistent community structures across different social platforms or time periods with varying user activity levels.
- •For telecommunications engineers: Identify stable user groups across multiple types of communication networks while accommodating varying connection intensities per network.
Authors
Alexandra Dache, Manon Rustin, Arnaud Vandaele, Nicolas Gillis
Abstract
Multilayer networks allow the modeling of interactions between the same entities across different contexts, such as temporal observations, varying settings, or interactions of different types. The goal of community detection in multilayer networks is to identify groups of nodes exhibiting similar connectivity patterns, which may vary across layers. We propose a method based on a joint nonnegative symmetric matrix trifactorization for community detection in multilayer networks, where each graph is approximated by a nonnegative symmetric matrix trifactorization. Our approach enforces constraints on the factor matrices so that communities are disjoint and shared across layers, while allowing each layer to have its own connectivity patterns and node degrees. This flexibility enables the model to capture both local and global structural variations across layers. We also develop an algorithm to efficiently solve this problem. We evaluate multilayer community detection methods using the multilayer degree-corrected stochastic block model (MDCBM), a flexible framework for generating realistic multilayer graphs with heterogeneous degrees and varying connectivity patterns. Experiments show that our method reliably detects communities across diverse regimes, whereas existing state-of-the-art approaches are often limited by restrictive structural assumptions.