Automatic and Aligned Anchor Learning Strategy for Multi-View Clustering

Huimin Ma, Siwei Wang, Shengju Yu, Suyuan Liu, Jun-Jie Huang, Huijun Wu, Xinwang Liu, En Zhu

Abstract: Multi-view Clustering (MVC) generally utilizes the anchor technique to decrease the computational complexity so as to tackle large-scale scenarios. Existing researches generally are supposed to select anchors in advance to complete the next clustering task. Nevertheless, the number of anchors cannot be predetermined and must be selected as a parameter, which introduces additional time consumption for parameter search. Moreover, maintaining an identical number of anchors across each view is not reasonable, as it restricts the representational capacity of anchors in individual views. To address the above issues, we propose a view adaptive anchor multi-view clustering called Multi-view Clustering with Automatic and Aligned Anchor (3AMVC). We introduce the Hierarchical Bipartite Neighbor Clustering (HBNC) strategy to adaptively select a suitable number of representative anchors from the original samples of each view. Specifically, When the representative difference of anchors lies in a acceptable and satisfactory range, the HBNC process is halted and picks out the final anchors. In addition, in response to the varying quantities of anchors across different views, we propose an innovative anchor alignment strategy. This approach initially evaluates the quality of anchors on each view based on the intra-cluster distance criterion and then proceeds to align based on the view with the highest-quality anchors. The carefully organized experiments well validate the effectiveness and strengthens of 3AMVC.

Primary Subject Area: [Content] Multimodal Fusion

Secondary Subject Area: [Content] Multimodal Fusion

Relevance To Conference: This paper proposes a novel automatic anchor selection and alignment method for large-scale multi-view clustering tasks. It can automatically select the appropriate cluster center on a single view as the anchor for large-scale tasks without specifying the number of clusters. In addition, on the multi-view alignment task, this paper innovatively proposes a criterion for measuring the quality of view anchor graphs, so that other views can be aligned and then fused based on anchor graphs with better quality. The automatic selection of anchor points and the fusion operation after alignment make the method have a linear computational complexity with respect to the number of samples, and can be effectively used in large-scale multi-view scenarios. Compared with other large-scale multi-view clustering methods with limited anchors, it is more flexible. Extensive experiments demonstrate the effectiveness of this method from multiple aspects.

Submission Number: 3194