PILOT: a pre-trained model-based continual learning toolbox

被引：0

作者：

HaiLong SUN ^{[1
,2
]}

DaWei ZHOU ^{[1
,2
]}

DeChuan ZHAN ^{[1
,2
]}

HanJia YE ^{[1
,2
]}

机构：

[1] School of Artificial Intelligence, Nanjing University

[2] National Key Laboratory for Novel Software Technology, Nanjing

来源：

Science China(Information Sciences) | 2025年 / 68卷 / 04期

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

<正>The rapid advancements in deep learning have resulted in significant achievements across various fields. However, our ever-changing world often presents training data in a streaming format from an open environment. For example, while ChatGPT demonstrates exceptional inference capabilities,it struggles to provide users with the most up-to-date information. This challenge arises from the high costs associated with retraining a GPT model on new data daily.

引用

页码：383 / 384

页数：2

共 50 条

[1] PILOT: a pre-trained model-based continual learning toolbox
Sun, Hai-Long
Zhou, Da-Wei
Zhan, De-Chuan
Ye, Han-Jia
SCIENCE CHINA-INFORMATION SCIENCES, 2025, 68 (04)
[2] Continual learning with Bayesian model based on a fixed pre-trained feature extractor
Yang Yang
Zhiying Cui
Junjie Xu
Changhong Zhong
Wei-Shi Zheng
Ruixuan Wang
Visual Intelligence, 1 (1):
[3] Continual Learning with Bayesian Model Based on a Fixed Pre-trained Feature Extractor
Yang, Yang
Cui, Zhiying
Xu, Junjie
Zhong, Changhong
Wang, Ruixuan
Zheng, Wei-Shi
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT V, 2021, 12905 : 397 - 406
[4] Continual Learning with Pre-Trained Models: A Survey
Zhou, Da-Wei
Sun, Hai-Long
Ning, Jingyi
Ye, Han-Jia
Zhan, De-Chuan
PROCEEDINGS OF THE THIRTY-THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2024, 2024, : 8363 - 8371
[5] SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
Zhang, Gengwei
Wang, Liyuan
Kang, Guoliang
Chen, Ling
Wei, Yunchao
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 19091 - 19101
[6] RanPAC: Random Projections and Pre-trained Models for Continual Learning
McDonnell, Mark D.
Gong, Dong
Parveneh, Amin
Abbasnejad, Ehsan
van den Hengel, Anton
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[7] Do Pre-trained Models Benefit Equally in Continual Learning?
Lee, Kuan-Ying
Zhong, Yuanyi
Wang, Yu-Xiong
2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 6474 - 6482
[8] Pre-Trained Language Model-Based Deep Learning for Sentiment Classification of Vietnamese Feedback
Loc, Cu Vinh
Viet, Truong Xuan
Viet, Tran Hoang
Thao, Le Hoang
Viet, Nguyen Hoang
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS, 2023, 22 (03)
[9] Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
Zhou, Da-Wei
Sun, Hai-Long
Ye, Han-Jia
Zhan, De-Chuan
2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2024, : 23554 - 23564
[10] Pre-trained Language Model-based Retrieval and Ranking forWeb Search
Zou, Lixin
Lu, Weixue
Liu, Yiding
Cai, Hengyi
Chu, Xiaokai
Ma, Dehong
Shi, Daiting
Sun, Yu
Cheng, Zhicong
Gu, Simiu
Wang, Shuaiqiang
Yin, Dawei
ACM TRANSACTIONS ON THE WEB, 2023, 17 (01)

← 1 2 3 4 5 →