Robust Multi-view Clustering Research Articles

Robust multi-view clustering via structure regularization concept factorization

Recently, many concept factorization-based multi-view clustering methods have been proposed and achieved promising results on text multi-view data. However, existing methods are limited in the following two aspects. (1) The Frobenius norm used in these methods is sensitive to noise and outliers; (2) These methods ignore the global structural information of the data. To address the above problems, we propose a robust concept factorization framework for multi-view clustering, which not only improves the robustness but also fully exploits the available information of multi-view data. Specifically, L2,1-norm is used to evaluate the error of the factorization, thus eliminating the effect of outliers and improving robustness. In addition, to retain more structure information of the original data, the global and local structure information are taken into consideration simultaneously, which makes the learned low-dimensional matrix more discriminative. Further, to make use of the complementary information of the different views, we introduce an adaptive weight learning strategy to assign weights for different views. An iterative updating algorithm is proposed to solve the proposed optimization problem. We compare the proposed method with state-of-the-art alternative methods on benchmark multi-view data sets. The extensive experimental results show the effectiveness and superiority of the proposed method.

Robust multi-view clustering via collaborative constraints and multi-layer concept factorization

Robust multi-view clustering via collaborative constraints and multi-layer concept factorization

Robust Multi-view Clustering via Graph-oriented High-order Correlations Learning

Robust Multi-view Clustering via Graph-oriented High-order Correlations Learning

Robust Multi-View Clustering Through Partition Integration on Stiefel Manifold

Multi-view clustering aims at integrating information from different views to improve clustering performance. Recent methods integrate multiple view-specific partition matrices to seek a consensus one and have demonstrated promising clustering performance in various applications. However, the clustering performance of such methods heavily relies on the consensus partition matrix estimated by the arithmetic mean in Euclidean space and thus is highly susceptible to noise corruption. To this end, this paper proposes to learn a consensus partition matrix through the geometric mean on the manifold to achieve robust clustering. Specifically, the multiple view-specific partition matrices can be regarded as points residing in the Stiefel manifold and enable a manifold-based integration. Consequently, the view-specific partition matrices are integrated by estimating a consensus partition matrix as the center point on the Stiefel manifold. Such a partition integration boils down to the Fréchet mean problem on a manifold, which is solved by the intrinsic manifold-based optimization and proves effective in providing a more robust estimation against noise. Experimental results on seven benchmark datasets demonstrate the effectiveness and noise-robustness of our proposed method in comparison to eight competitive methods.

Synthetic multi-view clustering with missing relationships and instances

Multi-view learning not only excavates the supplement information thoroughly, but also avoids noisy features and redundancies to improve down-stream tasks, e.g. Cluster, by constructing the fusing model. However, in practices, it is difficult to obtain complete multi-view data, which is summarized as both of Partially Sample-Missing Problem (PSP) originating from any view and Partially View-unaligned Problem (PVP). SURE (robust multi-view clustering with incomplete information) builds up the novel loss function to remove the noisy samples in the embedding space and presents the aligning method to solve both of PVP and PSP. However, generated instances and relationships contain relatively little discriminate information and semantic consistency, moreover, it needs a large size of complete samples to pre-train. Aiming to above problems, we propose the novel framework (termed Synthetic Multi-view Data Clustering, SMDC). For PSP problem, we induce feature-distillation in each feature-map level to generate features containing more semantic information helping with the guidance of complete feature-maps, furthermore, exploits self-distillation to strengthen the discriminability information of deeper levels supervised from the contrastive constraint in the embedding space. Moreover, for PVP problem, we leverage attention mechanism to adaptively fuse multi-view features and auto-align instances located in different views. The proposed model is verified in images and video clustering tasks, respectively. Comparing with popular methods achieve satisfactory performances. The code of model is published in: https://github.com/LNNU-computer-research-526/SMDC.