Multi-view clustering is widely applied in engineering and scientific research. It helps reveal the underlying structures and correlations behind complex multi-view data. Graph-based multi-view clustering stands as a prominent research frontier within the multi-view clustering field, yet faces persistent challenges. Firstly, typically constructed initial input graphs for each view yields sparse clustering structure, hindering clustering performance. Secondly, as data sources proliferate, algorithms encounter escalating time complexities, notably in methods relying on n×n fully connected graphs. Thirdly, prevailing graph fusion strategies struggle to mitigate the impact of low-quality graphs, impeding overall efficacy. In this paper, we present a novel Multi-View Clustering method based on High-Order Bipartite Graph fusion (MCHBG). For the first two challenges, the introduced high-order bipartite graphs in MCHBG reveal richer clustering structures, effectively alleviating sparse clustering structure of the input graph, while keeping the overall algorithm’s computational complexity controlled within O(n). For the third challenge, our graph fusion mechanism selectively integrates high-order bipartite graphs, and implicitly weights the selected bipartite graphs to mitigate the impact of low-quality bipartite graphs. MCHBG learns a structured fusion bipartite graph under the Laplacian rank constraint, which directly indicates the clusters of data. Extensive experimental results demonstrate the effectiveness and superiority of MCHBG. Code available: https://anonymous.4open.science/r/MCHBG.

中文翻译：

---

通过高阶二部图融合进行多视图聚类


多视图聚类在工程和科学研究中有着广泛的应用。它有助于揭示复杂多视图数据背后的底层结构和相关性。基于图的多视图聚类是多视图聚类领域的一个突出的研究前沿，但面临着持续的挑战。首先，通常为每个视图构建的初始输入图会产生稀疏的聚类结构，从而阻碍聚类性能。其次，随着数据源的激增，算法的时间复杂度不断增加，尤其是依赖于 n×n 全连接图的方法。第三，流行的图融合策略难以减轻低质量图的影响，从而阻碍了整体效率。在本文中，我们提出了一种基于高阶二部图融合（MCHBG）的新颖的多视图聚类方法。针对前两个挑战，MCHBG中引入的高阶二部图揭示了更丰富的聚类结构，有效缓解了输入图的稀疏聚类结构，同时将整体算法的计算复杂度控制在O(n)以内。对于第三个挑战，我们的图融合机制选择性地集成高阶二分图，并隐式对所选二分图进行加权，以减轻低质量二分图的影响。 MCHBG 在拉普拉斯秩约束下学习结构化融合二部图，它直接指示数据的簇。大量的实验结果证明了 MCHBG 的有效性和优越性。可用代码：https://anonymous.4open.science/r/MCHBG。