Self-measuring Similarity for Multi-task Gaussian Process

Kohei Hayashi, Takashi Takenouchi, Ryota Tomioka, Hisashi Kashima
Proceedings of ICML Workshop on Unsupervised and Transfer Learning, PMLR 27:145-153, 2012.

Abstract

Multi-task learning aims at transferring knowledge between similar tasks. The multi-task Gaussian process framework of Bonilla et al. models (incomplete) responses of $C$ data points for $R$ tasks (e.g., the responses are given by an $R \times C$ matrix) by using a Gaussian process; the covariance function takes its form as the product of a covariance function defined on input-specific features and an inter-task covariance matrix (which is empirically estimated as a model parameter). We extend this framework by incorporating a novel similarity measurement, which allows for the representation of much more complex data structures. The proposed framework also enables us to exploit additional information (e.g., the input-specific features) when constructing the covariance matrices by combining additional information with the covariance function. We also derive an efficient learning algorithm which uses an iterative method to make predictions. Finally, we apply our model to a real data set of recommender systems and show that the proposed method achieves the best prediction accuracy on the data set.

Cite this Paper


BibTeX
@InProceedings{pmlr-v27-hayashi12a, title = {Self-measuring Similarity for Multi-task Gaussian Process}, author = {Hayashi, Kohei and Takenouchi, Takashi and Tomioka, Ryota and Kashima, Hisashi}, booktitle = {Proceedings of ICML Workshop on Unsupervised and Transfer Learning}, pages = {145--153}, year = {2012}, editor = {Guyon, Isabelle and Dror, Gideon and Lemaire, Vincent and Taylor, Graham and Silver, Daniel}, volume = {27}, series = {Proceedings of Machine Learning Research}, address = {Bellevue, Washington, USA}, month = {02 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v27/hayashi12a/hayashi12a.pdf}, url = { http://proceedings.mlr.press/v27/hayashi12a.html }, abstract = {Multi-task learning aims at transferring knowledge between similar tasks. The multi-task Gaussian process framework of Bonilla et al. models (incomplete) responses of $C$ data points for $R$ tasks (e.g., the responses are given by an $R \times C$ matrix) by using a Gaussian process; the covariance function takes its form as the product of a covariance function defined on input-specific features and an inter-task covariance matrix (which is empirically estimated as a model parameter). We extend this framework by incorporating a novel similarity measurement, which allows for the representation of much more complex data structures. The proposed framework also enables us to exploit additional information (e.g., the input-specific features) when constructing the covariance matrices by combining additional information with the covariance function. We also derive an efficient learning algorithm which uses an iterative method to make predictions. Finally, we apply our model to a real data set of recommender systems and show that the proposed method achieves the best prediction accuracy on the data set.} }
Endnote
%0 Conference Paper %T Self-measuring Similarity for Multi-task Gaussian Process %A Kohei Hayashi %A Takashi Takenouchi %A Ryota Tomioka %A Hisashi Kashima %B Proceedings of ICML Workshop on Unsupervised and Transfer Learning %C Proceedings of Machine Learning Research %D 2012 %E Isabelle Guyon %E Gideon Dror %E Vincent Lemaire %E Graham Taylor %E Daniel Silver %F pmlr-v27-hayashi12a %I PMLR %P 145--153 %U http://proceedings.mlr.press/v27/hayashi12a.html %V 27 %X Multi-task learning aims at transferring knowledge between similar tasks. The multi-task Gaussian process framework of Bonilla et al. models (incomplete) responses of $C$ data points for $R$ tasks (e.g., the responses are given by an $R \times C$ matrix) by using a Gaussian process; the covariance function takes its form as the product of a covariance function defined on input-specific features and an inter-task covariance matrix (which is empirically estimated as a model parameter). We extend this framework by incorporating a novel similarity measurement, which allows for the representation of much more complex data structures. The proposed framework also enables us to exploit additional information (e.g., the input-specific features) when constructing the covariance matrices by combining additional information with the covariance function. We also derive an efficient learning algorithm which uses an iterative method to make predictions. Finally, we apply our model to a real data set of recommender systems and show that the proposed method achieves the best prediction accuracy on the data set.
RIS
TY - CPAPER TI - Self-measuring Similarity for Multi-task Gaussian Process AU - Kohei Hayashi AU - Takashi Takenouchi AU - Ryota Tomioka AU - Hisashi Kashima BT - Proceedings of ICML Workshop on Unsupervised and Transfer Learning DA - 2012/06/27 ED - Isabelle Guyon ED - Gideon Dror ED - Vincent Lemaire ED - Graham Taylor ED - Daniel Silver ID - pmlr-v27-hayashi12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 27 SP - 145 EP - 153 L1 - http://proceedings.mlr.press/v27/hayashi12a/hayashi12a.pdf UR - http://proceedings.mlr.press/v27/hayashi12a.html AB - Multi-task learning aims at transferring knowledge between similar tasks. The multi-task Gaussian process framework of Bonilla et al. models (incomplete) responses of $C$ data points for $R$ tasks (e.g., the responses are given by an $R \times C$ matrix) by using a Gaussian process; the covariance function takes its form as the product of a covariance function defined on input-specific features and an inter-task covariance matrix (which is empirically estimated as a model parameter). We extend this framework by incorporating a novel similarity measurement, which allows for the representation of much more complex data structures. The proposed framework also enables us to exploit additional information (e.g., the input-specific features) when constructing the covariance matrices by combining additional information with the covariance function. We also derive an efficient learning algorithm which uses an iterative method to make predictions. Finally, we apply our model to a real data set of recommender systems and show that the proposed method achieves the best prediction accuracy on the data set. ER -
APA
Hayashi, K., Takenouchi, T., Tomioka, R. & Kashima, H.. (2012). Self-measuring Similarity for Multi-task Gaussian Process. Proceedings of ICML Workshop on Unsupervised and Transfer Learning, in Proceedings of Machine Learning Research 27:145-153 Available from http://proceedings.mlr.press/v27/hayashi12a.html .

Related Material