Modularity Based Community Detection in Hypergraphs
This work addresses community detection in hypergraphs, which is important for analyzing complex relational data in fields like social networks and biology, but it is incremental as it builds on existing Louvain methodology.
The paper tackles the problem of community detection in hypergraphs by proposing h-Louvain, a scalable algorithm that adapts the classical Louvain method to optimize hypergraph modularity, addressing issues where direct application fails. The method uses a dynamically tuned linear combination of graph and hypergraph modularity, guided by Bayesian optimization, and shows improved results on synthetic and real-world networks.
In this paper, we propose a scalable community detection algorithm using hypergraph modularity function, h-Louvain. It is an adaptation of the classical Louvain algorithm in the context of hypergraphs. We observe that a direct application of the Louvain algorithm to optimize the hypergraph modularity function often fails to find meaningful communities. We propose a solution to this issue by adjusting the initial stage of the algorithm via carefully and dynamically tuned linear combination of the graph modularity function of the corresponding two-section graph and the desired hypergraph modularity function. The process is guided by Bayesian optimization of the hyper-parameters of the proposed procedure. Various experiments on synthetic as well as real-world networks are performed showing that this process yields improved results in various regimes.