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 unknown, thereby rendering established community detection approaches ineffective without costly network topology acquisition. To tackle this challenge, we present META-CODE, a novel end-to-end solution for detecting overlapping communities in networks with unknown topology via exploratory learning aided by easy-to-collect node metadata. 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 comprehensive evaluations using five real-world datasets, we demonstrate that META-CODE exhibits (a) its superiority over benchmark community detection methods, (b) empirical evaluations as well as theoretical findings to see the effectiveness of our node query, (c) the influence of each module, and (d) its computational efficiency.

翻译：在社会网络中，社区结构的发现作为各类网络分析任务中的基础问题一直备受关注。然而，由于隐私顾虑或访问限制，网络结构往往是未知的，这使得若无高昂的网络拓扑获取成本，已有社区发现方法难以奏效。为应对这一挑战，我们提出了META-CODE——一种新颖的端到端解决方案，通过借助易于收集的节点元数据进行探索式学习，在拓扑未知的网络中检测重叠社区。具体而言，除初始网络推理步骤外，META-CODE包含三个迭代步骤：1）基于图神经网络（GNN）的节点级社区隶属嵌入，该网络通过我们新提出的重构损失进行训练；2）基于社区隶属关系的节点查询进行网络探索；3）利用边缘连通性孪生神经网络模型对已探索网络进行推理。通过使用五个真实数据集进行的综合评估，我们展示了META-CODE的（a）相较于基准社区发现方法的优越性，（b）验证节点查询有效性的实证评估与理论发现，（c）各模块的影响，以及（d）其计算效率。