arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.11174cs.AI
收藏

深度残差GCN中基于动态膨胀聚合的重叠社区检测

Overlapping Community Detection using Dynamic Dilated Aggregation in Deep Residual GCN

Bangladesh University of Engineering and Technology(孟加拉工程技术大学);University of Arizona(亚利桑那大学)

Md Nurul Muttakin, Md Iqbal Hossain, Md Saidur Rahman

AI总结:

本文提出深度动态残差图卷积网络DynaResGCN,结合动态膨胀聚合与Bernoulli-Poisson解码器,在无标签、人工标注及大规模合著网络上均显著提升重叠社区检测性能。

摘要:

重叠社区检测是图挖掘中的一个关键问题。一些研究已考虑应用图卷积网络(GCN)来解决该问题。然而,在一般不规则图的情况下,融合深度图卷积网络仍然具有挑战性。在本研究中,我们基于新颖的动态膨胀聚合机制以及统一的端到端编码器-解码器框架,设计了一个深度动态残差图卷积网络(DynaResGCN),用于检测网络中的重叠社区。深度DynaResGCN模型被用作编码器,而我们引入Bernoulli-Poisson(BP)模型作为解码器。因此,我们将所提出的重叠社区检测框架应用于一个没有真实标签的研究主题数据集、一组具有可靠(人工标注)真实标签的Facebook网络,以及一组具有经验性(非人工标注)真实标签的超大规模合著网络。我们在这些数据集上的实验表明,与许多最先进的方法相比,该方法在网络重叠社区检测方面具有显著优越的性能。

英文摘要:

Overlapping community detection is a key problem in graph mining. Some research has considered applying graph convolutional networks (GCN) to tackle the problem. However, it is still challenging to incorporate deep graph convolutional networks in the case of general irregular graphs. In this study, we design a deep dynamic residual graph convolutional network (DynaResGCN) based on our novel dynamic dilated aggregation mechanisms and a unified end-to-end encoder-decoder-based framework to detect overlapping communities in networks. The deep DynaResGCN model is used as the encoder, whereas we incorporate the Bernoulli-Poisson (BP) model as the decoder. Consequently, we apply our overlapping community detection framework in a research topics dataset without having ground truth, a set of networks from Facebook having a reliable (hand-labeled) ground truth, and in a set of very large co-authorship networks having empirical (not hand-labeled) ground truth. Our experimentation on these datasets shows significantly superior performance over many state-of-the-art methods for the detection of overlapping communities in networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑