Multi-task learning with labeled and unlabeled tasks

Pentina A, Lampert C. 2017. Multi-task learning with labeled and unlabeled tasks. ICML: International Conference on Machine Learning, PMLR, vol. 70, 2807–2816.

Download (ext.)
OA https://arxiv.org/abs/1602.06518 [Submitted Version]
Conference Paper | Published | English

Scopus indexed
Department
Series Title
PMLR
Abstract
In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data must be available for all tasks, we consider a new setting, in which for some tasks, potentially most of them, only unlabeled training data is provided. Consequently, to solve all tasks, information must be transferred between tasks with labels and tasks without labels. Focusing on an instance-based transfer method we analyze two variants of this setting: when the set of labeled tasks is fixed, and when it can be actively selected by the learner. We state and prove a generalization bound that covers both scenarios and derive from it an algorithm for making the choice of labeled tasks (in the active case) and for transferring information between the tasks in a principled way. We also illustrate the effectiveness of the algorithm on synthetic and real data.
Publishing Year
Date Published
2017-06-08
Publisher
ML Research Press
Volume
70
Page
2807 - 2816
Conference
ICML: International Conference on Machine Learning
Conference Location
Sydney, Australia
Conference Date
2017-08-06 – 2017-08-11
IST-REx-ID
999

Cite this

Pentina A, Lampert C. Multi-task learning with labeled and unlabeled tasks. In: Vol 70. ML Research Press; 2017:2807-2816.
Pentina, A., & Lampert, C. (2017). Multi-task learning with labeled and unlabeled tasks (Vol. 70, pp. 2807–2816). Presented at the ICML: International Conference on Machine Learning, Sydney, Australia: ML Research Press.
Pentina, Anastasia, and Christoph Lampert. “Multi-Task Learning with Labeled and Unlabeled Tasks,” 70:2807–16. ML Research Press, 2017.
A. Pentina and C. Lampert, “Multi-task learning with labeled and unlabeled tasks,” presented at the ICML: International Conference on Machine Learning, Sydney, Australia, 2017, vol. 70, pp. 2807–2816.
Pentina A, Lampert C. 2017. Multi-task learning with labeled and unlabeled tasks. ICML: International Conference on Machine Learning, PMLR, vol. 70, 2807–2816.
Pentina, Anastasia, and Christoph Lampert. Multi-Task Learning with Labeled and Unlabeled Tasks. Vol. 70, ML Research Press, 2017, pp. 2807–16.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data ISTA Research Explorer

Web of Science

View record in Web of Science®

Search this title in

Google Scholar
ISBN Search