Multi-Manifold Semi-Supervised Learning

Andrew Goldberg, Xiaojin Zhu, Aarti Singh, Zhiting Xu, Robert Nowak
Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, PMLR 5:169-176, 2009.

Abstract

We study semi-supervised learning when the data consists of multiple intersecting manifolds. We give a finite sample analysis to quantify the potential gain of using unlabeled data in this multi-manifold setting. We then propose a semi-supervised learning algorithm that separates different manifolds into decision sets, and performs supervised learning within each set. Our algorithm involves a novel application of Hellinger distance and size-constrained spectral clustering. Experiments demonstrate the benefit of our multi-manifold semi-supervised learning approach.

Cite this Paper


BibTeX
@InProceedings{pmlr-v5-goldberg09a, title = {Multi-Manifold Semi-Supervised Learning}, author = {Goldberg, Andrew and Zhu, Xiaojin and Singh, Aarti and Xu, Zhiting and Nowak, Robert}, booktitle = {Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics}, pages = {169--176}, year = {2009}, editor = {van Dyk, David and Welling, Max}, volume = {5}, series = {Proceedings of Machine Learning Research}, address = {Hilton Clearwater Beach Resort, Clearwater Beach, Florida USA}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v5/goldberg09a/goldberg09a.pdf}, url = {https://proceedings.mlr.press/v5/goldberg09a.html}, abstract = {We study semi-supervised learning when the data consists of multiple intersecting manifolds. We give a finite sample analysis to quantify the potential gain of using unlabeled data in this multi-manifold setting. We then propose a semi-supervised learning algorithm that separates different manifolds into decision sets, and performs supervised learning within each set. Our algorithm involves a novel application of Hellinger distance and size-constrained spectral clustering. Experiments demonstrate the benefit of our multi-manifold semi-supervised learning approach.} }
Endnote
%0 Conference Paper %T Multi-Manifold Semi-Supervised Learning %A Andrew Goldberg %A Xiaojin Zhu %A Aarti Singh %A Zhiting Xu %A Robert Nowak %B Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2009 %E David van Dyk %E Max Welling %F pmlr-v5-goldberg09a %I PMLR %P 169--176 %U https://proceedings.mlr.press/v5/goldberg09a.html %V 5 %X We study semi-supervised learning when the data consists of multiple intersecting manifolds. We give a finite sample analysis to quantify the potential gain of using unlabeled data in this multi-manifold setting. We then propose a semi-supervised learning algorithm that separates different manifolds into decision sets, and performs supervised learning within each set. Our algorithm involves a novel application of Hellinger distance and size-constrained spectral clustering. Experiments demonstrate the benefit of our multi-manifold semi-supervised learning approach.
RIS
TY - CPAPER TI - Multi-Manifold Semi-Supervised Learning AU - Andrew Goldberg AU - Xiaojin Zhu AU - Aarti Singh AU - Zhiting Xu AU - Robert Nowak BT - Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics DA - 2009/04/15 ED - David van Dyk ED - Max Welling ID - pmlr-v5-goldberg09a PB - PMLR DP - Proceedings of Machine Learning Research VL - 5 SP - 169 EP - 176 L1 - http://proceedings.mlr.press/v5/goldberg09a/goldberg09a.pdf UR - https://proceedings.mlr.press/v5/goldberg09a.html AB - We study semi-supervised learning when the data consists of multiple intersecting manifolds. We give a finite sample analysis to quantify the potential gain of using unlabeled data in this multi-manifold setting. We then propose a semi-supervised learning algorithm that separates different manifolds into decision sets, and performs supervised learning within each set. Our algorithm involves a novel application of Hellinger distance and size-constrained spectral clustering. Experiments demonstrate the benefit of our multi-manifold semi-supervised learning approach. ER -
APA
Goldberg, A., Zhu, X., Singh, A., Xu, Z. & Nowak, R.. (2009). Multi-Manifold Semi-Supervised Learning. Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 5:169-176 Available from https://proceedings.mlr.press/v5/goldberg09a.html.

Related Material