Neural Collaborative Subspace Clustering

Tong Zhang, Pan Ji, Mehrtash Harandi, Wenbing Huang, Hongdong Li
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:7384-7393, 2019.

Abstract

We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces. In contrast to previous attempts, our model runs without the aid of spectral clustering. This makes our algorithm one of the kinds that can gracefully scale to large datasets. At its heart, our neural model benefits from a classifier which determines whether a pair of points lies on the same subspace or not. Essential to our model is the construction of two affinity matrices, one from the classifier and the other from a notion of subspace self-expressiveness, to supervise training in a collaborative scheme. We thoroughly assess and contrast the performance of our model against various state-of-the-art clustering algorithms including deep subspace-based ones.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-zhang19g, title = {Neural Collaborative Subspace Clustering}, author = {Zhang, Tong and Ji, Pan and Harandi, Mehrtash and Huang, Wenbing and Li, Hongdong}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {7384--7393}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/zhang19g/zhang19g.pdf}, url = {https://proceedings.mlr.press/v97/zhang19g.html}, abstract = {We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces. In contrast to previous attempts, our model runs without the aid of spectral clustering. This makes our algorithm one of the kinds that can gracefully scale to large datasets. At its heart, our neural model benefits from a classifier which determines whether a pair of points lies on the same subspace or not. Essential to our model is the construction of two affinity matrices, one from the classifier and the other from a notion of subspace self-expressiveness, to supervise training in a collaborative scheme. We thoroughly assess and contrast the performance of our model against various state-of-the-art clustering algorithms including deep subspace-based ones.} }
Endnote
%0 Conference Paper %T Neural Collaborative Subspace Clustering %A Tong Zhang %A Pan Ji %A Mehrtash Harandi %A Wenbing Huang %A Hongdong Li %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-zhang19g %I PMLR %P 7384--7393 %U https://proceedings.mlr.press/v97/zhang19g.html %V 97 %X We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces. In contrast to previous attempts, our model runs without the aid of spectral clustering. This makes our algorithm one of the kinds that can gracefully scale to large datasets. At its heart, our neural model benefits from a classifier which determines whether a pair of points lies on the same subspace or not. Essential to our model is the construction of two affinity matrices, one from the classifier and the other from a notion of subspace self-expressiveness, to supervise training in a collaborative scheme. We thoroughly assess and contrast the performance of our model against various state-of-the-art clustering algorithms including deep subspace-based ones.
APA
Zhang, T., Ji, P., Harandi, M., Huang, W. & Li, H.. (2019). Neural Collaborative Subspace Clustering. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:7384-7393 Available from https://proceedings.mlr.press/v97/zhang19g.html.

Related Material