Recall-Oriented Continual Learning with Generative Adversarial Meta-Model

ArXiv Pub Date : 2024-03-05 DOI:10.1609/aaai.v38i12.29202
Haneol Kang, Dong-Wan Choi
{"title":"Recall-Oriented Continual Learning with Generative Adversarial Meta-Model","authors":"Haneol Kang, Dong-Wan Choi","doi":"10.1609/aaai.v38i12.29202","DOIUrl":null,"url":null,"abstract":"The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the recalloriented continual learning framework to address this challenge. Inspired by the human brain’s ability to separate the mechanisms responsible for stability and plasticity, our framework consists of a two-level architecture where an inference network effectively acquires new knowledge and a generative network recalls past knowledge when necessary. In particular, to maximize the stability of past knowledge, we investigate the complexity of knowledge depending on different representations, and thereby introducing generative adversarial meta-model (GAMM) that incrementally learns task-specific parameters instead of input data samples of the task. Through our experiments, we show that our framework not only effectively learns new knowledge without any disruption but also achieves high stability of previous knowledge in both task-aware and task-agnostic learning scenarios. Our code is available at: https://github.com/bigdata-inha/recall-orientedcl-framework.","PeriodicalId":513202,"journal":{"name":"ArXiv","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ArXiv","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1609/aaai.v38i12.29202","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the recalloriented continual learning framework to address this challenge. Inspired by the human brain’s ability to separate the mechanisms responsible for stability and plasticity, our framework consists of a two-level architecture where an inference network effectively acquires new knowledge and a generative network recalls past knowledge when necessary. In particular, to maximize the stability of past knowledge, we investigate the complexity of knowledge depending on different representations, and thereby introducing generative adversarial meta-model (GAMM) that incrementally learns task-specific parameters instead of input data samples of the task. Through our experiments, we show that our framework not only effectively learns new knowledge without any disruption but also achieves high stability of previous knowledge in both task-aware and task-agnostic learning scenarios. Our code is available at: https://github.com/bigdata-inha/recall-orientedcl-framework.
以回忆为导向的持续学习与生成式对抗元模型
稳定性与可塑性的两难问题是持续学习中的一大挑战,因为它涉及到在学习新任务的同时保持以前任务的成绩这一相互冲突的目标之间取得平衡。在本文中,我们提出了以回忆为导向的持续学习框架来解决这一难题。受人脑将稳定性和可塑性机制分开的能力启发,我们的框架由两级架构组成,其中推理网络有效地获取新知识,而生成网络则在必要时回顾过去的知识。特别是,为了最大限度地提高过去知识的稳定性,我们研究了知识的复杂性取决于不同的表征,从而引入了生成对抗元模型(GAMM),该模型以增量方式学习特定任务的参数,而不是任务的输入数据样本。通过实验,我们发现我们的框架不仅能有效地学习新知识,而且在任务感知和任务无关的学习场景中都能实现先前知识的高度稳定性。我们的代码可在以下网址获取:https://github.com/bigdata-inha/recall-orientedcl-framework.
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信