Exploring Cohesive Subgraphs in Hypergraphs: The (k,g)-core Approach

TL;DR

This paper introduces the (k,g)-core, a new cohesive subgraph model for hypergraphs that considers both neighbor relationships and co-occurrence frequency, with efficient algorithms and applications in various domains.

Contribution

It proposes the (k,g)-core model for hypergraphs, combining neighbor and co-occurrence factors, and extends algorithms to efficiently identify these subgraphs.

Findings

The (k,g)-core effectively captures cohesive structures in hypergraphs.

The extended algorithm demonstrates high efficiency in experiments.

Applications include recommendation systems, network analysis, and fraud detection.

Abstract

Identifying cohesive subgraphs in hypergraphs is a fundamental problem that has received recent attention in data mining and engineering fields. Existing approaches mainly focus on a strongly induced subhypergraph or edge cardinality, overlooking the importance of the frequency of co-occurrence. In this paper, we propose a new cohesive subgraph named (k,g)-core, which considers both neighbour and co-occurrence simultaneously. The $(k,g)$-core has various applications including recommendation system, network analysis, and fraud detection. To the best of our knowledge, this is the first work to combine these factors. We extend an existing efficient algorithm to find solutions for $(k,g)$-core. Finally, we conduct extensive experimental studies that demonstrate the efficiency and effectiveness of our proposed algorithm.