让GNN聚类自动控制社区数，支持范围或精确值约束。
Bounded Graph Clustering with Graph Neural Networks
- 通过设定上下界约束，动态调节GNN聚类的社区数量。
- 在真实数据集上实现指定范围内社区数的高精度返回。
- 适合需要可控聚类数的社交网络、生物网络分析场景。
在社区发现任务中，许多方法需预先指定聚类数量，因对所有可能值进行穷举搜索计算成本过高。尽管一些经典算法可直接从数据中推断聚类数，但图神经网络（GNNs）通常不具备此能力：即使指定了目标聚类数，标准GNN方法也常无法准确返回。本文提出一种灵活且原理清晰的方法，以控制GNN发现的社区数量。无需假设真实聚类数已知，本框架允许用户指定一个合理的范围，并在训练过程中施加该约束。若用户希望获得确切的聚类数，亦可指定并可靠实现。
原文摘要 · Abstract (English)
In community detection, many methods require the user to specify the number of clusters in advance since an exhaustive search over all possible values is computationally infeasible. While some classical algorithms can infer this number directly from the data, this is typically not the case for graph neural networks (GNNs): even when a desired number of clusters is specified, standard GNN-based methods often fail to return the exact number due to the way they are designed. In this work, we address this limitation by introducing a flexible and principled way to control the number of communities discovered by GNNs. Rather than assuming the true number of clusters is known, we propose a framework that allows the user to specify a plausible range and enforce these bounds during training. However, if the user wants an exact number of clusters, it may also be specified and reliably returned.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。