拓扑不确定性下探索式学习辅助社区发现的统一框架
A Unified Framework for Exploratory Learning-Aided Community Detection Under Topological Uncertainty
AI总结：
本文提出统一框架 META-CODE，在网络拓扑未知或部分已知时，结合节点元数据、图神经网络嵌入、节点查询探索和孪生网络推断，迭代检测重叠社区，并在多个真实数据集上验证了其显著优于基准方法。
摘要：
在社交网络中，社区结构的发现作为各类网络分析任务中的基础问题受到了广泛关注。然而，由于隐私顾虑或访问限制，网络结构往往是不确定的，这使得已有的社区发现方法在未付出高昂网络拓扑获取代价的情况下难以奏效。为应对这一挑战，我们提出了 META-CODE，这是一个统一框架，用于在网络拓扑未知（或仅部分已知）时，借助易于收集的节点元数据，通过探索式学习来检测重叠社区。具体而言，除初始网络推断步骤外，META-CODE 由三个迭代步骤组成：1）基于图神经网络（GNN）的节点级社区归属嵌入，该 GNN 由我们新提出的重构损失训练；2）通过基于社区归属的节点查询进行网络探索；3）利用基于边连通性的孪生神经网络模型，从已探索的网络中进行网络推断。通过在三个真实世界数据集（包括两个大规模网络）上的大量实验，我们证明了：(a) META-CODE 相较于基准社区发现方法的优越性，在 Facebook 数据集上，就归一化互信息（NMI）而言，相比我们所选竞争方法中的最佳竞争者取得了高达 65.55% 的显著提升；(b) META-CODE 中每个模块的影响；(c) 基于实证评估和理论发现，META-CODE 中节点查询的有效性；以及 (d) 所推断网络的收敛性。
英文摘要：
In social networks, the discovery of community structures has received considerable attention as a fundamental problem in various network analysis tasks. However, due to privacy concerns or access restrictions, the network structure is often uncertain, thereby rendering established community detection approaches ineffective without costly network topology acquisition. To tackle this challenge, we present META-CODE, a unified framework for detecting overlapping communities via exploratory learning aided by easy-to-collect node metadata when networks are topologically unknown (or only partially known). Specifically, META-CODE consists of three iterative steps in addition to the initial network inference step: 1) node-level community-affiliation embeddings based on graph neural networks (GNNs) trained by our new reconstruction loss, 2) network exploration via community-affiliation-based node queries, and 3) network inference using an edge connectivity-based Siamese neural network model from the explored network. Through extensive experiments on three real-world datasets including two large networks, we demonstrate: (a) the superiority of META-CODE over benchmark community detection methods, achieving remarkable gains up to 65.55% on the Facebook dataset over the best competitor among our selected competitive methods in terms of normalized mutual information (NMI), (b) the impact of each module in META-CODE, (c) the effectiveness of node queries in META-CODE based on empirical evaluations and theoretical findings, and (d) the convergence of the inferred network.
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。
