Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering
Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering
复制标题
DOI：
10.1609/aaai.v37i7.25960
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Zongmo Huang;Yazhou Ren;X. Pu;Shudong Huang;Zenglin Xu;Lifang He
中科院分区：
文献类型：
--
作者：
Zongmo Huang;Yazhou Ren;X. Pu;Shudong Huang;Zenglin Xu;Lifang He
多视图聚类（MVC）作为无监督学习领域的重要研究课题之一，在过去的十年中得到了广泛的研究，并开发了许多MVC方法。在这些方法中，最近出现的图神经网络（Graph Neural Networks， GNN）将拓扑结构和节点属性以图的形式建模，以指导统一的嵌入学习和聚类。然而，现有的基于gnn的MVC方法的有效性仍然有限，主要原因是对自监督信息和图信息的利用考虑不足，这可以从以下两个方面体现出来：1)这些模型大多只是使用自监督信息来指导特征学习，没有意识到这些信息也可以应用于图学习和样本加权；2)在这些模型中，图信息的使用通常局限于特征聚合，但它也为检测噪声样本提供了有价值的证据。为此，本文提出了用于深度加权多视图聚类的自监督图注意网络（SGDMC），通过充分利用自监督信息和图信息，提高了基于gnn的深度MVC模型的性能。具体而言，提出了一种同时考虑节点属性相似性和自监督信息的注意力分配方法，以综合评价不同节点之间的相关性。同时，为了减轻样本噪声和聚类结构差异带来的负面影响，我们进一步设计了基于注意力图和全局伪标签与局部聚类分配差异的样本加权策略。在多个真实数据集上的实验结果证明了我们的方法比现有方法的有效性。
As one of the most important research topics in the unsupervised learning field, Multi-View Clustering (MVC) has been widely studied in the past decade and numerous MVC methods have been developed. Among these methods, the recently emerged Graph Neural Networks (GNN) shine a light on modeling both topological structure and node attributes in the form of graphs, to guide unified embedding learning and clustering. However, the effectiveness of existing GNN-based MVC methods is still limited due to the insufficient consideration in utilizing the self-supervised information and graph information, which can be reflected from the following two aspects: 1) most of these models merely use the self-supervised information to guide the feature learning and fail to realize that such information can be also applied in graph learning and sample weighting; 2) the usage of graph information is generally limited to the feature aggregation in these models, yet it also provides valuable evidence in detecting noisy samples. To this end, in this paper we propose Self-Supervised Graph Attention Networks for Deep Weighted Multi-View Clustering (SGDMC), which promotes the performance of GNN-based deep MVC models by making full use of the self-supervised information and graph information. Specifically, a novel attention-allocating approach that considers both the similarity of node attributes and the self-supervised information is developed to comprehensively evaluate the relevance among different nodes. Meanwhile, to alleviate the negative impact caused by noisy samples and the discrepancy of cluster structures, we further design a sample-weighting strategy based on the attention graph as well as the discrepancy between the global pseudo-labels and the local cluster assignment. Experimental results on multiple real-world datasets demonstrate the effectiveness of our method over existing approaches.