Semi-Supervised Learning with Adaptive Spectral Transform

Hanxiao Liu, Yiming Yang
; Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, PMLR 51:902-910, 2016.

Abstract

This paper proposes a novel nonparametric framework for semi-supervised learning and for optimizing the Laplacian spectrum of the data manifold simultaneously. Our formulation leads to a convex optimization problem that can be efficiently solved via the bundle method, and can be interpreted as to asymptotically minimize the generalization error bound of semi-supervised learning with respect to the graph spectrum. Experiments over benchmark datasets in various domains show advantageous performance of the proposed method over strong baselines.

Cite this Paper


BibTeX
@InProceedings{pmlr-v51-liu16, title = {Semi-Supervised Learning with Adaptive Spectral Transform}, author = {Hanxiao Liu and Yiming Yang}, booktitle = {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics}, pages = {902--910}, year = {2016}, editor = {Arthur Gretton and Christian C. Robert}, volume = {51}, series = {Proceedings of Machine Learning Research}, address = {Cadiz, Spain}, month = {09--11 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v51/liu16.pdf}, url = {http://proceedings.mlr.press/v51/liu16.html}, abstract = {This paper proposes a novel nonparametric framework for semi-supervised learning and for optimizing the Laplacian spectrum of the data manifold simultaneously. Our formulation leads to a convex optimization problem that can be efficiently solved via the bundle method, and can be interpreted as to asymptotically minimize the generalization error bound of semi-supervised learning with respect to the graph spectrum. Experiments over benchmark datasets in various domains show advantageous performance of the proposed method over strong baselines.} }
Endnote
%0 Conference Paper %T Semi-Supervised Learning with Adaptive Spectral Transform %A Hanxiao Liu %A Yiming Yang %B Proceedings of the 19th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2016 %E Arthur Gretton %E Christian C. Robert %F pmlr-v51-liu16 %I PMLR %J Proceedings of Machine Learning Research %P 902--910 %U http://proceedings.mlr.press %V 51 %W PMLR %X This paper proposes a novel nonparametric framework for semi-supervised learning and for optimizing the Laplacian spectrum of the data manifold simultaneously. Our formulation leads to a convex optimization problem that can be efficiently solved via the bundle method, and can be interpreted as to asymptotically minimize the generalization error bound of semi-supervised learning with respect to the graph spectrum. Experiments over benchmark datasets in various domains show advantageous performance of the proposed method over strong baselines.
RIS
TY - CPAPER TI - Semi-Supervised Learning with Adaptive Spectral Transform AU - Hanxiao Liu AU - Yiming Yang BT - Proceedings of the 19th International Conference on Artificial Intelligence and Statistics PY - 2016/05/02 DA - 2016/05/02 ED - Arthur Gretton ED - Christian C. Robert ID - pmlr-v51-liu16 PB - PMLR SP - 902 DP - PMLR EP - 910 L1 - http://proceedings.mlr.press/v51/liu16.pdf UR - http://proceedings.mlr.press/v51/liu16.html AB - This paper proposes a novel nonparametric framework for semi-supervised learning and for optimizing the Laplacian spectrum of the data manifold simultaneously. Our formulation leads to a convex optimization problem that can be efficiently solved via the bundle method, and can be interpreted as to asymptotically minimize the generalization error bound of semi-supervised learning with respect to the graph spectrum. Experiments over benchmark datasets in various domains show advantageous performance of the proposed method over strong baselines. ER -
APA
Liu, H. & Yang, Y.. (2016). Semi-Supervised Learning with Adaptive Spectral Transform. Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, in PMLR 51:902-910

Related Material