Dual Label-Guided Graph Refinement for Multi-View Graph Clustering
Dual Label-Guided Graph Refinement for Multi-View Graph Clustering
复制标题
DOI：
10.1609/aaai.v37i7.26057
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Yawen Ling;Jianpeng Chen;Yazhou Ren;X. Pu;Jie Xu;Xiao-lan Zhu;Lifang He
中科院分区：
文献类型：
--
作者：
Yawen Ling;Jianpeng Chen;Yazhou Ren;X. Pu;Jie Xu;Xiao-lan Zhu;Lifang He
随着多视图图数据量的增加，无需标签监督就能发现隐藏簇的多视图图聚类（MVGC）越来越受到研究者的关注。现有的MVGC方法通常对给定的图敏感，特别是受低质量图的影响，即，它们往往受到同质性假设的限制。然而，广泛的现实世界的数据很难满足同质性假设。这个差距限制了现有MVGC方法在低同亲图上的性能。为了减轻这种限制，我们的动机是提取高层次的视图共同信息，用于细化每个视图的图，并减少非同质边缘的影响。为此，我们提出了双标签引导图细化多视图图聚类（DuaLGR），以减轻在面对低同质图的脆弱性。具体来说，DuaLGR由两个模块组成，分别是双标签引导图细化模块和图编码模块。第一个模块被设计为从节点特征和图中提取软标签，然后学习细化矩阵。在第二个模块的伪标签的合作下，这些图被细化，并以不同的顺序自适应地聚合。随后，可以在伪标签的指导下生成共识图。最后，图编码器模块将共识图沿着节点特征一起编码，以产生用于迭代聚类的高级伪标签。实验结果表明，该算法在处理低同调图形数据时具有上级性能。DuaLGR的源代码可在https://github.com/YwL-zhufeng/DuaLGR上获得。
With the increase of multi-view graph data, multi-view graph clustering (MVGC) that can discover the hidden clusters without label supervision has attracted growing attention from researchers. Existing MVGC methods are often sensitive to the given graphs, especially influenced by the low quality graphs, i.e., they tend to be limited by the homophily assumption. However, the widespread real-world data hardly satisfy the homophily assumption. This gap limits the performance of existing MVGC methods on low homophilous graphs. To mitigate this limitation, our motivation is to extract high-level view-common information which is used to refine each view's graph, and reduce the influence of non-homophilous edges. To this end, we propose dual label-guided graph refinement for multi-view graph clustering (DuaLGR), to alleviate the vulnerability in facing low homophilous graphs. Specifically, DuaLGR consists of two modules named dual label-guided graph refinement module and graph encoder module. The first module is designed to extract the soft label from node features and graphs, and then learn a refinement matrix. In cooperation with the pseudo label from the second module, these graphs are refined and aggregated adaptively with different orders. Subsequently, a consensus graph can be generated in the guidance of the pseudo label. Finally, the graph encoder module encodes the consensus graph along with node features to produce the high-level pseudo label for iteratively clustering. The experimental results show the superior performance on coping with low homophilous graph data. The source code for DuaLGR is available at https://github.com/YwL-zhufeng/DuaLGR.