论文标题
通过自我表达的图形神经网络无监督的受约束社区检测
Unsupervised Constrained Community Detection via Self-Expressive Graph Neural Network
论文作者
论文摘要
图神经网络（GNN）能够在多个下游任务（例如节点分类和链接预测）上实现有希望的性能。对设计可以直接操作的GNN进行了相对较少的工作，该GNN可以直接在图形上进行社区检测。传统上，GNN经过半监督或自我监管的损失功能进行训练，然后应用聚类算法来检测社区。但是，这种脱钩的方法本质上是最佳的。设计无监督的损失功能来培训GNN并以综合方式提取社区是一个基本挑战。为了解决这个问题，我们将自我表达力的原则与自学图形神经网络的框架相结合，以便在文献中首次进行无监督的社区检测。我们的解决方案以端到端的方式进行了培训，并在多个可公开的数据集上实现了最先进的社区检测性能。
Graph neural networks (GNNs) are able to achieve promising performance on multiple graph downstream tasks such as node classification and link prediction. Comparatively lesser work has been done to design GNNs which can operate directly for community detection on graphs. Traditionally, GNNs are trained on a semi-supervised or self-supervised loss function and then clustering algorithms are applied to detect communities. However, such decoupled approaches are inherently sub-optimal. Designing an unsupervised loss function to train a GNN and extract communities in an integrated manner is a fundamental challenge. To tackle this problem, we combine the principle of self-expressiveness with the framework of self-supervised graph neural network for unsupervised community detection for the first time in literature. Our solution is trained in an end-to-end fashion and achieves state-of-the-art community detection performance on multiple publicly available datasets.
