Quadratic Optimization based Clique Expansion for Overlapping Community Detection

TL;DR

QOCE is a scalable quadratic optimization-based algorithm for overlapping community detection in large networks, effectively balancing accuracy and efficiency.

Contribution

The paper introduces QOCE, a novel scalable algorithm that uses quadratic optimization for seed set expansion to detect overlapping communities.

Findings

QOCE outperforms four state-of-the-art algorithms in accuracy.

QOCE demonstrates high scalability on large networks.

QOCE achieves competitive detection performance across diverse datasets.

Abstract

Community detection is crucial for analyzing social and biological networks, and comprehensive approaches have been proposed in the last two decades. Nevertheless, finding all overlapping communities in large networks that could accurately approximate the ground-truth communities remains challenging. In this work, we present the QOCE (Quadratic Optimization based Clique Expansion), an overlapping community detection algorithm that could scale to large networks with hundreds of thousands of nodes and millions of edges. QOCE follows the popular seed set expansion strategy, regarding each high-quality maximal clique as the initial seed set and applying quadratic optimization for the expansion. We extensively evaluate our algorithm on 28 synthetic LFR networks and six real-world networks of various domains and scales, and compare QOCE with four state-of-the-art overlapping community detection algorithms. Empirical results demonstrate the competitive performance of the proposed approach in terms of detection accuracy, efficiency, and scalability.