IEEE Trans Cybern. 2017 Sep;47(9):2703-2716. doi: 10.1109/TCYB.2017.2711038. Epub 2017 Jun 13.
Designing multiobjective evolutionary algorithms (MOEAs) for community detection in complex networks has attracted much attention of researchers recently. However, most of the existing methods focus on addressing the task of nonoverlapping community detection, where each node must belong to one and only one community. In fact, communities are often overlapped with each other in many real-world networks, thus it is necessary to design overlapping community detection algorithms. To this end, this paper proposes a mixed representation-based MOEA (MR-MOEA) for overlapping community detection. In MR-MOEA, a mixed individual representation scheme is proposed to fast encode and decode the overlapping divisions of complex networks. Specifically, this mixed representation consists of two parts: one represents all potential overlapping nodes and the other delegates all nonoverlapping nodes. These two parts evolve together to detect the overlapping communities of networks based on different updating strategies suggested in MR-MOEA. We verify the effectiveness of the proposed algorithm MR-MOEA on ten real-world complex networks and the experimental results demonstrate that MR-MOEA is superior over six representative algorithms for overlapping community detection.
设计用于复杂网络社区发现的多目标进化算法（MOEAs）最近引起了研究人员的广泛关注。然而，大多数现有的方法都侧重于解决非重叠社区检测的任务，其中每个节点必须属于一个且仅属于一个社区。事实上，在许多现实世界的网络中，社区之间通常是重叠的，因此有必要设计重叠社区检测算法。为此，本文提出了一种基于混合表示的 MOEA（MR-MOEA）用于重叠社区检测。在 MR-MOEA 中，提出了一种混合个体表示方案，以快速编码和解码复杂网络的重叠分区。具体来说，这种混合表示由两部分组成：一部分表示所有潜在的重叠节点，另一部分代表所有非重叠节点。这两部分根据 MR-MOEA 中建议的不同更新策略共同进化，以检测网络的重叠社区。我们在十个真实的复杂网络上验证了所提出的算法 MR-MOEA 的有效性，实验结果表明，MR-MOEA 在重叠社区检测方面优于六个代表性算法。
