ABSTRACT
In this paper, we present a novel solution to multi-view clustering through a structured low-rank representation. When assuming similar samples can be linearly reconstructed by each other, the resulting representational matrix reflects the cluster structure and should ideally be block diagonal. We first impose low-rank constraint on the representational matrix to encourage better grouping effect. Then representational matrices under different views are allowed to communicate with each other and share their mutual cluster structure information. We develop an effective algorithm inspired by iterative re-weighted least squares for solving our formulation. During the optimization process, the intermediate representational matrix from one view serves as a cluster structure constraint for that from another view. Such mutual structural constraint fine-tunes the cluster structures from both views and makes them more and more agreeable. Extensive empirical study manifests the superiority and efficacy of the proposed method.
- http://archive.ics.uci.edu/ml/datasets/Multiple+Features.Google Scholar
- http://attributes.kyb.tuebingen.mpg.de/.Google Scholar
- http://membres-lig.imag.fr/grimal/data.html.Google Scholar
- http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2007/.Google Scholar
- U. Ahsan and I. Essa. Clustering social event images using kernel canonical correlation analysis. In IEEE Conference on CVPR Workshops, pages 814--819, 2014. Google ScholarDigital Library
- A. Argyriou, T. Evgeniou, and M. Pontil. Multi-task feature learning. In NIPS, 2007.Google ScholarDigital Library
- Y. Bengio, A. C. Courville, and P. Vincent. Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35:1798--1828, 2013. Google ScholarDigital Library
- E. Bruno and S. Marchand-Maillet. Multiview clustering: A late fusion approach using latent models. In ACM Conference on Research and Development in Information Retrieval, pages 736--737, 2009. Google ScholarDigital Library
- K. Chaudhuri, S. M. Kakade, K. Livescu, and K. Sridharan. Multi-view clustering via canonical correlation analysis. In International Conference on Machine Learning, pages 129--136, 2009. Google ScholarDigital Library
- W.-Y. Chen, Y. Song, H. Bai, C.-J. Lin, and E. Y. Chang. Parallel spectral clustering in distributed systems. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(3):568--586, 2011. Google ScholarDigital Library
- T.-S. Chua, J. Tang, R. Hong, H. Li, Z. Luo, and Y.-T. Zheng. Nus-wide: A real-world web image database from national university of singapore. In ACM Conference on Image and Video Retrieval, 2009. Google ScholarDigital Library
- E. Grave, G. Obozinski, and F. Bach. Trace lasso: a trace norm regularization for correlated designs. In NIPS, pages 2187--2195, 2011.Google ScholarDigital Library
- D. Greene and P. Cunningham. A matrix factorization approach for integrating multiple data views. In European Conference on Machine Learning and Knowledge Discovery in Databases, pages 423--438, 2009. Google ScholarDigital Library
- Y. Guo. Convex subspace representation learning from multi-view data. In AAAI, 2013.Google ScholarCross Ref
- A. Kumar and H. D. Iii. A co-training approach for multi-view spectral clustering. In International Conference on Machine Learning, pages 393--400, 2011.Google Scholar
- A. Kumar, P. Rai, and H. D. Iii. Co-regularized multiview spectral clustering. In Neural Information Processing Systems, pages 1413--1421, 2011.Google Scholar
- G. Liu, Z. Lin, S. Yan, J. Sun, Y. Yu, and Y. Ma. Robust recovery of subspace structures by low-rank representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1):171--184, 2013. Google ScholarDigital Library
- G. Liu, Z. Lin, and Y. Yu. Robust subspace segmentation by low-rank representation. In International Conference on Machine Learning, pages 663--670, 2010.Google ScholarDigital Library
- J. Liu, C. Wang, J. Gao, and J. Han. Multi-view clustering via joint nonnegative matrix factorization. In SIAM International Conference Data Mining, pages 252--260, 2013.Google ScholarCross Ref
- J. Shi and J. Malik. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):888--905, 2000. Google ScholarDigital Library
- W. Tang, R. Liu, Z. Su, and J. Zhang. Structure-constrained low-rank representation. IEEE Transactions on Neural Networks and Learning Systems, 2014.Google Scholar
- H. Wang, F. Nie, and H. Huang. Multi-view clustering and feature learning via structured sparsity. In International Conference on Machine Learning, pages 352--360, 2013.Google ScholarDigital Library
- C. Xu, D. Tao, and C. Xu. A survey on multi-view learning. arXiv preprint arXiv:1304.5634, 2013.Google Scholar
- Y. Zhang, Z. Jiang, and L. S. Davis. Learning structured low-rank representations for image classification. In Computer Vision and Pattern Recognition, pages 676--683, 2013. Google ScholarDigital Library
Index Terms
- Multi-view Clustering via Structured Low-rank Representation
Recommendations
Enhanced tensor low-rank representation learning for multi-view clustering
AbstractMulti-view subspace clustering (MSC), assuming the multi-view data are generated from a latent subspace, has attracted considerable attention in multi-view clustering. To recover the underlying subspace structure, a successful approach ...
Highlights- Capturing intrinsic high-order correlations underlying multi-view data.
- ...
Nonconvex low-rank and sparse tensor representation for multi-view subspace clustering
AbstractMulti-view subspace clustering has attracted significant attention due to the popularity of multi-view datasets. The effectiveness of the existing multi-view clustering methods highly depends on the quality of the affinity matrix. To derive a high ...
Semi-supervised Multi-view Clustering Based on Non-negative Matrix Factorization and Low-Rank Tensor Representation
AbstractMulti-view clustering methods aim to integrate the complementary information of different views to obtain accurate clustering results. However, the traditional multi-view clustering method is unsupervised which does not combine the label ...
Comments