Is Multi-Task Learning an Upper Bound for Continual Learning?-Reference-Cited by-同舟云学术

Is Multi-Task Learning an Upper Bound for Continual Learning?

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Wu Zihao¹,Tran Huy¹,Pirsiavash Hamed²,Kolouri Soheil¹

Affiliation:

1. Vanderbilt University,Department of Computer Science,Nashville,TN

2. University of California,Department of Computer Science,Davis,CA

Funder

Defense Advanced Research Projects Agency

Publisher

IEEE

Link

Reference21 articles.

1. Supermasks in superposition;wortsman;Advances in neural information processing systems,2020

3. Barlow twins: Self-supervised learning via redundancy reduction;zbontar;International Conference on Machine Learning,2021

5. Linear mode connectivity in multitask and continual learning;mirzadeh;International Conference on Learning Representations,2020

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

2. Exploring Soft Prompt Initialization Strategy for Few-Shot Continual Text Classification;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14