A Model-Agnostic Approach to Mitigate Gradient Interference for Multi-Task Learning-Reference-Cited by-同舟云学术

A Model-Agnostic Approach to Mitigate Gradient Interference for Multi-Task Learning

Published:2022 Issue: Volume: Page:1-14
ISSN:2168-2267
Container-title:IEEE Transactions on Cybernetics
language:
Short-container-title:IEEE Trans. Cybern.

Author:

Chai Heyan¹^ORCID,Yin Zhe¹,Ding Ye²^ORCID,Liu Li³^ORCID,Fang Binxing¹,Liao Qing¹^ORCID

Affiliation:

1. Department of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China

2. School of Cyberspace Security, Dongguan University of Technology, Dongguan, China

3. College of System Engineering, National University of Defense Technology, Changsha, China

Funder

National Key Research and Development Program of China

National Natural Science Foundation of China

Guangdong Major Project of Basic and Applied Basic Research

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Computer Science Applications,Human-Computer Interaction,Information Systems,Control and Systems Engineering,Software

Link

http://xplorestaging.ieee.org/ielx7/6221036/6352949/09970586.pdf?arnumber=9970586

Cited by 10 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

1. TGGS network: A multi-task learning network for gradient-guided knowledge sharing;Knowledge-Based Systems;2024-10

2. A novel tree-based method for interpretable reinforcement learning;ACM Transactions on Knowledge Discovery from Data;2024-09-09

3. Multi-Instance Multi-Task Learning for Joint Clinical Outcome and Genomic Profile Predictions From the Histopathological Images;IEEE Transactions on Medical Imaging;2024-06

4. SGCL: Semantic-aware Graph Contrastive Learning with Lipschitz Graph Augmentation;2024 IEEE 40th International Conference on Data Engineering (ICDE);2024-05-13

5. Towards Task-Conflicts Momentum-Calibrated Approach for Multi-task Learning;2024 IEEE 40th International Conference on Data Engineering (ICDE);2024-05-13