用于高效生成式排练的渐进潜重放

Stanislaw Pawlak, Filip Szatkowski, Michał Bortkiewicz, Jan Dubi'nski, T. Trzci'nski
{"title":"用于高效生成式排练的渐进潜重放","authors":"Stanislaw Pawlak, Filip Szatkowski, Michał Bortkiewicz, Jan Dubi'nski, T. Trzci'nski","doi":"10.48550/arXiv.2207.01562","DOIUrl":null,"url":null,"abstract":"We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network. While replay strategies mitigate the effects of catastrophic forgetting in neural networks, recent works on generative replay show that performing the rehearsal only on the deeper layers of the network improves the performance in continual learning. However, the generative approach introduces additional computational overhead, limiting its applications. Motivated by the observation that earlier layers of neural networks forget less abruptly, we propose to update network layers with varying frequency using intermediate-level features during replay. This reduces the computational burden by omitting computations for both deeper layers of the generator and earlier layers of the main model. We name our method Progressive Latent Replay and show that it outperforms Internal Replay while using significantly fewer resources.","PeriodicalId":281152,"journal":{"name":"International Conference on Neural Information Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Progressive Latent Replay for efficient Generative Rehearsal\",\"authors\":\"Stanislaw Pawlak, Filip Szatkowski, Michał Bortkiewicz, Jan Dubi'nski, T. Trzci'nski\",\"doi\":\"10.48550/arXiv.2207.01562\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network. While replay strategies mitigate the effects of catastrophic forgetting in neural networks, recent works on generative replay show that performing the rehearsal only on the deeper layers of the network improves the performance in continual learning. However, the generative approach introduces additional computational overhead, limiting its applications. Motivated by the observation that earlier layers of neural networks forget less abruptly, we propose to update network layers with varying frequency using intermediate-level features during replay. This reduces the computational burden by omitting computations for both deeper layers of the generator and earlier layers of the main model. We name our method Progressive Latent Replay and show that it outperforms Internal Replay while using significantly fewer resources.\",\"PeriodicalId\":281152,\"journal\":{\"name\":\"International Conference on Neural Information Processing\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-07-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Neural Information Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2207.01562\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Neural Information Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2207.01562","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

我们介绍了一种内部重放的新方法,该方法根据网络的深度来调节排练的频率。虽然重放策略减轻了神经网络中灾难性遗忘的影响,但最近关于生成重放的研究表明,只在网络的较深层进行排练可以提高持续学习的性能。然而,生成方法引入了额外的计算开销,限制了它的应用。由于观察到早期神经网络层的遗忘不那么突然,我们建议在重播期间使用中级特征以不同的频率更新网络层。这省去了对生成器的较深层和主模型的较早期层的计算,从而减少了计算负担。我们将我们的方法命名为渐进潜伏重放,并表明它在使用更少的资源的同时优于内部重放。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Progressive Latent Replay for efficient Generative Rehearsal
We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network. While replay strategies mitigate the effects of catastrophic forgetting in neural networks, recent works on generative replay show that performing the rehearsal only on the deeper layers of the network improves the performance in continual learning. However, the generative approach introduces additional computational overhead, limiting its applications. Motivated by the observation that earlier layers of neural networks forget less abruptly, we propose to update network layers with varying frequency using intermediate-level features during replay. This reduces the computational burden by omitting computations for both deeper layers of the generator and earlier layers of the main model. We name our method Progressive Latent Replay and show that it outperforms Internal Replay while using significantly fewer resources.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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