Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning

Vishakh Padmakumar, Leonard Lausen, Miguel Ballesteros, Sheng Zha, He He, George Karypis


Abstract
Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of intermediate tasks can heavily affect downstream task performance. In this work, we aim to disentangle the effect of scale and relatedness of tasks in multi-task representation learning. We find that, on average, increasing the scale of multi-task learning, in terms of the number of tasks, indeed results in better learned representations than smaller multi-task setups. However, if the target tasks are known ahead of time, then training on a smaller set of related tasks is competitive to the large-scale multi-task training at a reduced computational cost.
Anthology ID:
2022.naacl-main.183
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2542–2550
Language:
URL:
https://aclanthology.org/2022.naacl-main.183
DOI:
10.18653/v1/2022.naacl-main.183
Bibkey:
Cite (ACL):
Vishakh Padmakumar, Leonard Lausen, Miguel Ballesteros, Sheng Zha, He He, and George Karypis. 2022. Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2542–2550, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning (Padmakumar et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.183.pdf
Data
GLUENCBI DiseaseSuperGLUEWNUT 2017