Co-regularized Multi-view Subspace Clustering

Hong Yu, Tiantian Zhang, Yahong Lian, Yu Cai
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:17-32, 2018.

Abstract

For many clustering applications, Multi-view data sets are very common. Multi-view clustering aims to exploit information across views instead of individual views, which is promising to improve clustering performance. Note that a high-dimensional data set usually distributes on certain low-dimensional subspace. Thus, many multi-view subspace clustering algorithms have been developed. However, existing multi-view subspace clustering methods rarely perform clustering on the subspace representation of each view simultaneously as well as keep the indicator consistency among the representations, i.e., the same data point in different views should be assigned to the same cluster. In this paper, we propose a novel multi-view subspace clustering method. In our method, we use the indicator matrix to ensure that we perform clustering on the subspace representation of each view simultaneously. And at the same time, a co-regularized term is added to guarantee the consistency of the indicator matrices. Experiments on several real-world multi-view datasets demonstrate the effectiveness and superiority of our proposed method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v95-yu18a, title = {Co-regularized Multi-view Subspace Clustering}, author = {Yu, Hong and Zhang, Tiantian and Lian, Yahong and Cai, Yu}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {17--32}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/yu18a/yu18a.pdf}, url = {https://proceedings.mlr.press/v95/yu18a.html}, abstract = {For many clustering applications, Multi-view data sets are very common. Multi-view clustering aims to exploit information across views instead of individual views, which is promising to improve clustering performance. Note that a high-dimensional data set usually distributes on certain low-dimensional subspace. Thus, many multi-view subspace clustering algorithms have been developed. However, existing multi-view subspace clustering methods rarely perform clustering on the subspace representation of each view simultaneously as well as keep the indicator consistency among the representations, i.e., the same data point in different views should be assigned to the same cluster. In this paper, we propose a novel multi-view subspace clustering method. In our method, we use the indicator matrix to ensure that we perform clustering on the subspace representation of each view simultaneously. And at the same time, a co-regularized term is added to guarantee the consistency of the indicator matrices. Experiments on several real-world multi-view datasets demonstrate the effectiveness and superiority of our proposed method.} }
Endnote
%0 Conference Paper %T Co-regularized Multi-view Subspace Clustering %A Hong Yu %A Tiantian Zhang %A Yahong Lian %A Yu Cai %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-yu18a %I PMLR %P 17--32 %U https://proceedings.mlr.press/v95/yu18a.html %V 95 %X For many clustering applications, Multi-view data sets are very common. Multi-view clustering aims to exploit information across views instead of individual views, which is promising to improve clustering performance. Note that a high-dimensional data set usually distributes on certain low-dimensional subspace. Thus, many multi-view subspace clustering algorithms have been developed. However, existing multi-view subspace clustering methods rarely perform clustering on the subspace representation of each view simultaneously as well as keep the indicator consistency among the representations, i.e., the same data point in different views should be assigned to the same cluster. In this paper, we propose a novel multi-view subspace clustering method. In our method, we use the indicator matrix to ensure that we perform clustering on the subspace representation of each view simultaneously. And at the same time, a co-regularized term is added to guarantee the consistency of the indicator matrices. Experiments on several real-world multi-view datasets demonstrate the effectiveness and superiority of our proposed method.
APA
Yu, H., Zhang, T., Lian, Y. & Cai, Y.. (2018). Co-regularized Multi-view Subspace Clustering. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:17-32 Available from https://proceedings.mlr.press/v95/yu18a.html.

Related Material