基于图注意力机制和多距离分析的社区发现算法OA
Community Detection Algorithm Based on Graph Attention Mechanism and Multi-distance Analysis
针对大规模社交网络中节点关系复杂、社区结构隐蔽导致社区发现算法精度较低的问题,提出一种基于图注意力机制和多距离分析的社区发现算法.首先,在预训练部分引入多层感知机模块提高样本的识别精度.其次,提出基于图注意力机制的读出操作模块,通过自适应地学习节点在图表示学习中的贡献权重,实现加权聚合操作,从而增强图表示的判别能力,提升社区发现精度和鲁棒性.最后,设计一种多距离分析方法,增强对小目标的感知能力,提升检测准确率.实验结果表明,改进模型在多个数据集上均表现优异.Amazon 数据集上的 F1 值达到了90.22%,相比 CLARE 和 ProCom 模型分别提高了 11.33 个百分点和 5.86 个 百 分 点.Jaccard 相似度则达到了83.46%,相比 CLARE 和 ProCom 模型分别提高了 14.96 个百分点和 7.62 个百分点.
To address the low accuracy of community detection in large-scale social networks,which was caused by complex node relationships and hidden community structures,a community detection algorithm based on graph attention mechanisms and multi-distance analysis was proposed.Firstly,a multilayer per-ceptron(MLP)module was introduced during the pre-training phase so that the accuracy of sample rec-ognition could be improved.Secondly,a graph attention-based readout module was proposed,by which the contribution weights of nodes in graph representation learning were adaptively learned.The weighted aggregation was enabled,the discriminative power of graph-level representations was enhanced,and the accuracy and robustness of community detection were improved.Finally,a multi-distance analysis meth-od was designed to strengthen the detection of small communities and to further increase overall detection accuracy.It was demonstrated by experimental results that superior performance was delivered by the im-proved model across multiple datasets.On the Amazon dataset,the F1 score of 90.22%was achieved,which represented improvements of 11.33 and 5.86 percentage points over the CLARE and ProCom mod-els,respectively.For Jaccard similarity,a score of 83.46%was obtained,with improvements of 14.96 and 7.62 percentage points over CLARE and ProCom,respectively.
张震;吴国豪;张红霞;周麒
郑州大学 电气与信息工程学院 河南 郑州 450001郑州大学 电气与信息工程学院 河南 郑州 450001郑州人民医院 河南 郑州 450002郑州大学附属儿童医院 河南 郑州 450066
信息技术与安全科学
半监督社区发现多层感知机聚类图注意力机制多距离分析
semi-supervised community discoverymultilayer perceptron clusteringgraph attention mechanismmulti-distance analysis
《郑州大学学报(理学版)》 2026 (6)
9-16,8
河南省重点研发专项项目(231111211600)河南省重大公益专项项目(201300311200)
评论