Unsupervised Deep Embedding for Clustering Analysis

Junyuan Xie, Ross Girshick, Ali Farhadi
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:478-487, 2016.

Abstract

Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns feature representations and cluster assignments using deep neural networks. DEC learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods.

Cite this Paper


BibTeX
@InProceedings{pmlr-v48-xieb16, title = {Unsupervised Deep Embedding for Clustering Analysis}, author = {Xie, Junyuan and Girshick, Ross and Farhadi, Ali}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {478--487}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/xieb16.pdf}, url = {https://proceedings.mlr.press/v48/xieb16.html}, abstract = {Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns feature representations and cluster assignments using deep neural networks. DEC learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Unsupervised Deep Embedding for Clustering Analysis %A Junyuan Xie %A Ross Girshick %A Ali Farhadi %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-xieb16 %I PMLR %P 478--487 %U https://proceedings.mlr.press/v48/xieb16.html %V 48 %X Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns feature representations and cluster assignments using deep neural networks. DEC learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods.
RIS
TY - CPAPER TI - Unsupervised Deep Embedding for Clustering Analysis AU - Junyuan Xie AU - Ross Girshick AU - Ali Farhadi BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-xieb16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 478 EP - 487 L1 - http://proceedings.mlr.press/v48/xieb16.pdf UR - https://proceedings.mlr.press/v48/xieb16.html AB - Clustering is central to many data-driven application domains and has been studied extensively in terms of distance functions and grouping algorithms. Relatively little work has focused on learning representations for clustering. In this paper, we propose Deep Embedded Clustering (DEC), a method that simultaneously learns feature representations and cluster assignments using deep neural networks. DEC learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective. Our experimental evaluations on image and text corpora show significant improvement over state-of-the-art methods. ER -
APA
Xie, J., Girshick, R. & Farhadi, A.. (2016). Unsupervised Deep Embedding for Clustering Analysis. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:478-487 Available from https://proceedings.mlr.press/v48/xieb16.html.

Related Material