@inproceedings{meshgi-etal-2022-q,
title = "{Q}-Learning Scheduler for Multi Task Learning Through the use of Histogram of Task Uncertainty",
author = "Meshgi, Kourosh and
Sadat Mirzaei, Maryam and
Sekine, Satoshi",
booktitle = "Proceedings of the 7th Workshop on Representation Learning for NLP",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.repl4nlp-1.2",
doi = "10.18653/v1/2022.repl4nlp-1.2",
pages = "9--19",
abstract = "Simultaneous training of a multi-task learning network on different domains or tasks is not always straightforward. It could lead to inferior performance or generalization compared to the corresponding single-task networks. An effective training scheduling method is deemed necessary to maximize the benefits of multi-task learning. Traditional schedulers follow a heuristic or prefixed strategy, ignoring the relation of the tasks, their sample complexities, and the state of the emergent shared features. We proposed a deep Q-Learning Scheduler (QLS) that monitors the state of the tasks and the shared features using a novel histogram of task uncertainty, and through trial-and-error, learns an optimal policy for task scheduling. Extensive experiments on multi-domain and multi-task settings with various task difficulty profiles have been conducted, the proposed method is benchmarked against other schedulers, its superior performance has been demonstrated, and results are discussed.",
}
Markdown (Informal)
[Q-Learning Scheduler for Multi Task Learning Through the use of Histogram of Task Uncertainty](https://aclanthology.org/2022.repl4nlp-1.2) (Meshgi et al., RepL4NLP 2022)
ACL