How can we find meaningful clusters in a graph robustly against noise edges? Graph clustering (i.e., dividing nodes into groups of similar ones) is a fundamental problem in graph analysis with applications in various fields. Recent studies have demonstrated that graph neural network (GNN) based approaches yield promising results for graph clustering. However, we observe that their performance degenerates significantly on graphs with noise edges, which are prevalent in practice. In this work, we propose MetaGC for robust GNN-based graph clustering. MetaGC employs a decomposable clustering loss function, which can be rephrased as a sum of losses over node pairs. We add a learnable weight to each node pair, and MetaGC adaptively adjusts the weights of node pairs using meta-weighting so that the weights of meaningful node pairs increase and the weights of less-meaningful ones (e.g., noise edges) decrease. We show empirically that MetaGC learns weights as intended and consequently outperforms the state-of-the-art GNN-based competitors, even when they are equipped with separate denoising schemes, on five real-world graphs under varying levels of noise. Our code and datasets are available at https://github.com/HyeonsooJo/MetaGC.

翻译：如何在没有噪声边的图中鲁棒地发现有意义的聚类？图聚类（即，将节点划分为相似组）是图分析中的一个基础问题，广泛应用于多个领域。近期研究表明，基于图神经网络的方法在图聚类中取得了令人满意的结果。然而，我们观察到这些方法在包含噪声边的图上性能显著下降，而噪声边在实际中普遍存在。为此，本文提出MetaGC，一种基于图神经网络的鲁棒图聚类方法。MetaGC采用可分解的聚类损失函数，该函数可重构为节点对损失之和。我们为每个节点对引入可学习的权重，并通过元加权自适应调整节点对权重，使得有意义的节点对权重增加，而意义较小的节点对（如噪声边）权重降低。实验证明，即使状态最先进的基于图神经网络的对比方法配备了独立的去噪机制，MetaGC仍能按照预期学习权重，并在五种不同噪声水平的真实世界图上取得更优性能。我们的代码和数据集可在https://github.com/HyeonsooJo/MetaGC获取。