Factorial Multi-Task Learning : A Bayesian Nonparametric Approach

Sunil Gupta, Dinh Phung, Svetha Venkatesh
Proceedings of the 30th International Conference on Machine Learning, PMLR 28(3):657-665, 2013.

Abstract

Multi-task learning is a paradigm shown to improve the performance of related tasks through their joint learning. However, for real-world data, it is usually difficult to assess the task relatedness and joint learning with unrelated tasks may lead to serious performance degradations. To this end, we propose a framework that groups the tasks based on their relatedness in a low dimensional subspace and allows a varying degree of relatedness among tasks by sharing the subspace bases across the groups. This provides the flexibility of no sharing when two sets of tasks are unrelated and partial/total sharing when the tasks are related. Importantly, the number of task-groups and the subspace dimensionality are automatically inferred from the data. This feature keeps the model beyond a specific set of parameters. To realize our framework, we present a novel Bayesian nonparametric prior that extends the traditional hierarchical beta process prior using a Dirichlet process to permit potentially infinite number of child beta processes. We apply our model for multi-task regression and classification applications. Experimental results using several synthetic and real-world datasets show the superiority of our model to other recent state-of-the-art multi-task learning methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v28-gupta13a, title = {Factorial Multi-Task Learning : A Bayesian Nonparametric Approach}, author = {Gupta, Sunil and Phung, Dinh and Venkatesh, Svetha}, booktitle = {Proceedings of the 30th International Conference on Machine Learning}, pages = {657--665}, year = {2013}, editor = {Dasgupta, Sanjoy and McAllester, David}, volume = {28}, number = {3}, series = {Proceedings of Machine Learning Research}, address = {Atlanta, Georgia, USA}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v28/gupta13a.pdf}, url = {https://proceedings.mlr.press/v28/gupta13a.html}, abstract = {Multi-task learning is a paradigm shown to improve the performance of related tasks through their joint learning. However, for real-world data, it is usually difficult to assess the task relatedness and joint learning with unrelated tasks may lead to serious performance degradations. To this end, we propose a framework that groups the tasks based on their relatedness in a low dimensional subspace and allows a varying degree of relatedness among tasks by sharing the subspace bases across the groups. This provides the flexibility of no sharing when two sets of tasks are unrelated and partial/total sharing when the tasks are related. Importantly, the number of task-groups and the subspace dimensionality are automatically inferred from the data. This feature keeps the model beyond a specific set of parameters. To realize our framework, we present a novel Bayesian nonparametric prior that extends the traditional hierarchical beta process prior using a Dirichlet process to permit potentially infinite number of child beta processes. We apply our model for multi-task regression and classification applications. Experimental results using several synthetic and real-world datasets show the superiority of our model to other recent state-of-the-art multi-task learning methods.} }
Endnote
%0 Conference Paper %T Factorial Multi-Task Learning : A Bayesian Nonparametric Approach %A Sunil Gupta %A Dinh Phung %A Svetha Venkatesh %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-gupta13a %I PMLR %P 657--665 %U https://proceedings.mlr.press/v28/gupta13a.html %V 28 %N 3 %X Multi-task learning is a paradigm shown to improve the performance of related tasks through their joint learning. However, for real-world data, it is usually difficult to assess the task relatedness and joint learning with unrelated tasks may lead to serious performance degradations. To this end, we propose a framework that groups the tasks based on their relatedness in a low dimensional subspace and allows a varying degree of relatedness among tasks by sharing the subspace bases across the groups. This provides the flexibility of no sharing when two sets of tasks are unrelated and partial/total sharing when the tasks are related. Importantly, the number of task-groups and the subspace dimensionality are automatically inferred from the data. This feature keeps the model beyond a specific set of parameters. To realize our framework, we present a novel Bayesian nonparametric prior that extends the traditional hierarchical beta process prior using a Dirichlet process to permit potentially infinite number of child beta processes. We apply our model for multi-task regression and classification applications. Experimental results using several synthetic and real-world datasets show the superiority of our model to other recent state-of-the-art multi-task learning methods.
RIS
TY - CPAPER TI - Factorial Multi-Task Learning : A Bayesian Nonparametric Approach AU - Sunil Gupta AU - Dinh Phung AU - Svetha Venkatesh BT - Proceedings of the 30th International Conference on Machine Learning DA - 2013/05/26 ED - Sanjoy Dasgupta ED - David McAllester ID - pmlr-v28-gupta13a PB - PMLR DP - Proceedings of Machine Learning Research VL - 28 IS - 3 SP - 657 EP - 665 L1 - http://proceedings.mlr.press/v28/gupta13a.pdf UR - https://proceedings.mlr.press/v28/gupta13a.html AB - Multi-task learning is a paradigm shown to improve the performance of related tasks through their joint learning. However, for real-world data, it is usually difficult to assess the task relatedness and joint learning with unrelated tasks may lead to serious performance degradations. To this end, we propose a framework that groups the tasks based on their relatedness in a low dimensional subspace and allows a varying degree of relatedness among tasks by sharing the subspace bases across the groups. This provides the flexibility of no sharing when two sets of tasks are unrelated and partial/total sharing when the tasks are related. Importantly, the number of task-groups and the subspace dimensionality are automatically inferred from the data. This feature keeps the model beyond a specific set of parameters. To realize our framework, we present a novel Bayesian nonparametric prior that extends the traditional hierarchical beta process prior using a Dirichlet process to permit potentially infinite number of child beta processes. We apply our model for multi-task regression and classification applications. Experimental results using several synthetic and real-world datasets show the superiority of our model to other recent state-of-the-art multi-task learning methods. ER -
APA
Gupta, S., Phung, D. & Venkatesh, S.. (2013). Factorial Multi-Task Learning : A Bayesian Nonparametric Approach. Proceedings of the 30th International Conference on Machine Learning, in Proceedings of Machine Learning Research 28(3):657-665 Available from https://proceedings.mlr.press/v28/gupta13a.html.

Related Material