PanDa: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation-Reference-Cited by-同舟云学术

PanDa: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation

Published:2024-09 Issue:9 Volume:36 Page:4835-4848
ISSN:1041-4347
Container-title:IEEE Transactions on Knowledge and Data Engineering
language:
Short-container-title:IEEE Trans. Knowl. Data Eng.

Author:

Zhong Qihuang¹^ORCID,Ding Liang²^ORCID,Liu Juhua¹^ORCID,Du Bo¹^ORCID,Tao Dacheng³^ORCID

Affiliation:

1. School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University, Wuhan, China

2. School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia

3. College of Computing & Data Science, Nanyang Technological University, Singapore

Funder

National Key Research and Development Program of China

National Natural Science Foundation of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/69/10629652/10475529.pdf?arnumber=10475529

Reference63 articles.

1. RoBERTa: A robustly optimized bert pretraining approach;Liu,2019

2. DeBERTa: Decoding-enhanced BERT with disentangled attention;He

3. Exploring the limits of transfer learning with a unified text-to-text transformer;Raffel;J. Mach. Learn. Res.,2020

4. Language models are few-shot learners;Brown

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

1. Few-shot class incremental learning via prompt transfer and knowledge distillation;Image and Vision Computing;2024-11

2. Generous teacher: Good at distilling knowledge for student learning;Image and Vision Computing;2024-10