A unifying framework for vector-valued manifold regularization and multi-view learning

Minh Hà Quang, Loris Bazzani, Vittorio Murino
Proceedings of the 30th International Conference on Machine Learning, PMLR 28(2):100-108, 2013.

Abstract

This paper presents a general vector-valued reproducing kernel Hilbert spaces (RKHS) formulation for the problem of learning an unknown functional dependency between a structured input space and a structured output space, in the Semi-Supervised Learning setting. Our formulation includes as special cases Vector-valued Manifold Regularization and Multi-view Learning, thus provides in particular a unifying framework linking these two important learning approaches. In the case of least square loss function, we provide a closed form solution with an efficient implementation. Numerical experiments on challenging multi-class categorization problems show that our multi-view learning formulation achieves results which are comparable with state of the art and are significantly better than single-view learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v28-haquang13, title = {A unifying framework for vector-valued manifold regularization and multi-view learning}, author = {Hà Quang, Minh and Bazzani, Loris and Murino, Vittorio}, booktitle = {Proceedings of the 30th International Conference on Machine Learning}, pages = {100--108}, year = {2013}, editor = {Dasgupta, Sanjoy and McAllester, David}, volume = {28}, number = {2}, series = {Proceedings of Machine Learning Research}, address = {Atlanta, Georgia, USA}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v28/haquang13.pdf}, url = {https://proceedings.mlr.press/v28/haquang13.html}, abstract = {This paper presents a general vector-valued reproducing kernel Hilbert spaces (RKHS) formulation for the problem of learning an unknown functional dependency between a structured input space and a structured output space, in the Semi-Supervised Learning setting. Our formulation includes as special cases Vector-valued Manifold Regularization and Multi-view Learning, thus provides in particular a unifying framework linking these two important learning approaches. In the case of least square loss function, we provide a closed form solution with an efficient implementation. Numerical experiments on challenging multi-class categorization problems show that our multi-view learning formulation achieves results which are comparable with state of the art and are significantly better than single-view learning. } }
Endnote
%0 Conference Paper %T A unifying framework for vector-valued manifold regularization and multi-view learning %A Minh Hà Quang %A Loris Bazzani %A Vittorio Murino %B Proceedings of the 30th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2013 %E Sanjoy Dasgupta %E David McAllester %F pmlr-v28-haquang13 %I PMLR %P 100--108 %U https://proceedings.mlr.press/v28/haquang13.html %V 28 %N 2 %X This paper presents a general vector-valued reproducing kernel Hilbert spaces (RKHS) formulation for the problem of learning an unknown functional dependency between a structured input space and a structured output space, in the Semi-Supervised Learning setting. Our formulation includes as special cases Vector-valued Manifold Regularization and Multi-view Learning, thus provides in particular a unifying framework linking these two important learning approaches. In the case of least square loss function, we provide a closed form solution with an efficient implementation. Numerical experiments on challenging multi-class categorization problems show that our multi-view learning formulation achieves results which are comparable with state of the art and are significantly better than single-view learning.
RIS
TY - CPAPER TI - A unifying framework for vector-valued manifold regularization and multi-view learning AU - Minh Hà Quang AU - Loris Bazzani AU - Vittorio Murino BT - Proceedings of the 30th International Conference on Machine Learning DA - 2013/05/13 ED - Sanjoy Dasgupta ED - David McAllester ID - pmlr-v28-haquang13 PB - PMLR DP - Proceedings of Machine Learning Research VL - 28 IS - 2 SP - 100 EP - 108 L1 - http://proceedings.mlr.press/v28/haquang13.pdf UR - https://proceedings.mlr.press/v28/haquang13.html AB - This paper presents a general vector-valued reproducing kernel Hilbert spaces (RKHS) formulation for the problem of learning an unknown functional dependency between a structured input space and a structured output space, in the Semi-Supervised Learning setting. Our formulation includes as special cases Vector-valued Manifold Regularization and Multi-view Learning, thus provides in particular a unifying framework linking these two important learning approaches. In the case of least square loss function, we provide a closed form solution with an efficient implementation. Numerical experiments on challenging multi-class categorization problems show that our multi-view learning formulation achieves results which are comparable with state of the art and are significantly better than single-view learning. ER -
APA
Hà Quang, M., Bazzani, L. & Murino, V.. (2013). A unifying framework for vector-valued manifold regularization and multi-view learning. Proceedings of the 30th International Conference on Machine Learning, in Proceedings of Machine Learning Research 28(2):100-108 Available from https://proceedings.mlr.press/v28/haquang13.html.

Related Material