Low-rank tensor approximation with local structure for multi-view intrinsic subspace clustering

Recently, multi-view learning has captured widespread attention in the machine learning area, yet it is still crucial and challenging to exploit beneficial patterns from multi-view data. Specifically, very limited work has been devoted to multi-view semi-supervised learning, where only a small number of labeled data points are available for model training. Therefore, a simple yet efficient seeded random walk scheme is proposed in this paper to address the multi-view semi-supervised classification problem, where known labeled data points serve as random seeds to be walked with certain probability. In this scheme, the semi-supervised classification indicator is obtained based primarily on an arrival probability and a reward matrix, which are computed by leveraging an initial distribution from some random seeds. Besides, theoretical analyses are then provided to indicate a connection of the proposed model with the existing manifold ranking method. Finally, comprehensive experiments on eight publicly available data sets demonstrate the superiority of the proposed model against compared state-of-the-art semi-supervised methods and fully supervised classifiers. Furthermore, experimental results also suggest that the proposed method comes with positive robustness and promising generalization capability in terms of data classification.

Seeded random walk for multi-view semi-supervised classification

/pdf/multilayer-graph-contrastive-clustering-network-1ayuun79.pdf

Multilayer graph contrastive clustering network

Multi-view subspace clustering with inter-cluster consistency and intra-cluster diversity among views

With advances in information acquisition technologies, multi-view data are increasing dramatically in a variety of real-world applications, whereas such data is usually corrupted by noises and outliers. Many existing multi-view graph clustering (MVGC) methods usually learn a consensus affinity graph using a late-fusion scheme in semantic space, which compound the challenge of leveraging the underlying relationships among corrupted multi-view data. In this paper, we propose a novel clustering method for handing corrupted multi-view data, hereafter referred to as Latent Low-Rank Proxy Graph Learning (LLPGL). Specifically, by projecting the multi-view data into a low-dimension proxy feature space, LLPGL can learn a low-dimension yet low-rank latent proxy from corrupted view data. Meanwhile, by employing the adaptive neighbor graph learning over the clean proxy, a high-quality affinity graph can be learned for clustering purpose. Then, an effective optimization algorithm is proposed to solve the model of LLPGL. Experimental results on five widely used real-world benchmarks validate the effectiveness of the proposed method.Consequently, the proposed method can be used to cluster the corrupted multi-view data for real-life applications.

Multi-view Clustering with Latent Low-rank Proxy Graph Learning

With the increasing popularity of multi-view data, multi-view subspace clustering (MVSC) has attracted intensive attention. However, the curse of dimensionality of the high-dimensional multi-view data constantly obsesses the development of multi-view method. Together with the curse of dimensionality, the existence of noise and outliers further obstructs the ability of MVSC to exploit the underlying subspace structure. To solve these challenging problems, in this paper, we propose a novel MVSC method, namely robust energy preserving embedding (REPE), which aims to exploit the underlying subspace structure of multi-view data through energy preserving embedding projection and low-rank constraint. In a different manner than before, we use dictionary learning to integrate self-expressiveness learning and embedded subspace learning together, ensure the preservation of energy by restoring the data in embedding space to the original space. Moreover, Schatten p -norm is introduced to better approximate the low-rank constraint. So that we can reduce the dimension of the data while maintain the major energy of the original view data. Thereby, a high quality affinity graph can be learned, such that the promising clustering results can subsequently be obtained. Extensive experiments on five benchmarks have validated the effectiveness of the proposed method, by comparing it with the state of arts.

Xingfeng Li

Papers

Robust energy preserving embedding for multi-view subspace clustering

Robust multi-view graph clustering in latent energy-preserving embedding space

Multiple kernel clustering with pure graph learning scheme