Pentina_Curriculum_Learning_of_2015_CVPR_paper.pdf (1.05 MB)
Curriculum learning of multiple tasks
conference contribution
posted on 2023-06-10, 01:53 authored by Anastasia Pentina, Viktoriia SharmanskaViktoriia Sharmanska, Christoph H LampertSharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between the most related tasks. In this work we propose an approach that processes multiple tasks in a sequence with sharing between subsequent tasks instead of solving all tasks jointly. Subsequently, we address the question of curriculum learning of tasks, i.e. finding the best order of tasks to be learned. Our approach is based on a generalization bound criterion for choosing the task order that optimizes the average expected classification performance over all tasks. Our experimental results show that learning multiple related tasks sequentially can be more effective than learning them jointly, the order in which tasks are being solved affects the overall performance, and that our model is able to automatically discover a favourable order of tasks.
History
Publication status
- Published
File Version
- Published version
Journal
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)ISSN
1063-6919Publisher
IEEEExternal DOI
Page range
5492-5500Event name
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)Event location
Boston, MA, USAEvent type
conferenceEvent date
7 - 12 Jun 2015ISBN
9781467369633Department affiliated with
- Informatics Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2021-11-30First Open Access (FOA) Date
2021-11-30First Compliant Deposit (FCD) Date
2021-11-30Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC