Gu Xiang, Huang Qiwei, Yang Jie
School of Artificial Intelligence and Computer Science, Nantong University, Nantong 226019, China.
School of Information Science and Technology, Nantong University, Nantong 226019, China.
Sensors (Basel). 2025 Apr 20;25(8):2601. doi: 10.3390/s25082601.
Community detection is particularly important in vehicular social networks because it helps identify closely connected groups of vehicles within the network. Community structures with overlapping relationships are identified through network topology and vehicle attribute information, thereby optimizing communication efficiency, supporting resource allocation, and enhancing privacy protection. However, most existing community detection methods focus on non-overlapping communities, usually only considering the topological structure of the network, and often ignoring the attribute information of nodes. To address these problems, this paper proposes a semi-supervised overlapping community detection method based on graph attention autoencoder (CDGAAE). The method consists of three key components: graph attention autoencoder module, modularity optimization enhancement module, and semi-supervised clustering module. First, the graph attention autoencoder module fuses topological information and node attribute information and encodes nodes using a graph attention mechanism. Second, the modularity optimization enhancement module effectively captures the structure of overlapping communities. Finally, the semi-supervised clustering module combines prior information to improve the accuracy of community detection. CDGAAE is comprehensively evaluated on multiple real and synthetic datasets, and experimental results show that CDGAAE outperforms other competing methods.
社区检测在车载社交网络中尤为重要，因为它有助于识别网络内紧密相连的车辆群组。通过网络拓扑和车辆属性信息识别具有重叠关系的社区结构，从而优化通信效率、支持资源分配并加强隐私保护。然而，大多数现有的社区检测方法侧重于非重叠社区，通常只考虑网络的拓扑结构，并且常常忽略节点的属性信息。为了解决这些问题，本文提出了一种基于图注意力自动编码器的半监督重叠社区检测方法（CDGAAE）。该方法由三个关键组件组成：图注意力自动编码器模块、模块化优化增强模块和半监督聚类模块。首先，图注意力自动编码器模块融合拓扑信息和节点属性信息，并使用图注意力机制对节点进行编码。其次，模块化优化增强模块有效地捕捉重叠社区的结构。最后，半监督聚类模块结合先验信息以提高社区检测的准确性。在多个真实和合成数据集上对CDGAAE进行了全面评估，实验结果表明CDGAAE优于其他竞争方法。
