Architecture Knowledge Distillation for Evolutionary Generative Adversarial Network.

International journal of neural systems Pub Date : 2025-04-01 Epub Date: 2025-02-19 DOI:10.1142/S0129065725500133
Yu Xue, Yan Lin, Ferrante Neri
{"title":"Architecture Knowledge Distillation for Evolutionary Generative Adversarial Network.","authors":"Yu Xue, Yan Lin, Ferrante Neri","doi":"10.1142/S0129065725500133","DOIUrl":null,"url":null,"abstract":"<p><p>Generative Adversarial Networks (GANs) are effective for image generation, but their unstable training limits broader applications. Additionally, neural architecture search (NAS) for GANs with one-shot models often leads to insufficient subnet training, where subnets inherit weights from a supernet without proper optimization, further degrading performance. To address both issues, we propose Architecture Knowledge Distillation for Evolutionary GAN (AKD-EGAN). AKD-EGAN operates in two stages. First, architecture knowledge distillation (AKD) is used during supernet training to efficiently optimize subnetworks and accelerate learning. Second, a multi-objective evolutionary algorithm (MOEA) searches for optimal subnet architectures, ensuring efficiency by considering multiple performance metrics. This approach, combined with a strategy for architecture inheritance, enhances GAN stability and image quality. Experiments show that AKD-EGAN surpasses state-of-the-art methods, achieving a Fréchet Inception Distance (FID) of 7.91 and an Inception Score (IS) of 8.97 on CIFAR-10, along with competitive results on STL-10 (FID: 20.32, IS: 10.06). Code and models will be available at https://github.com/njit-ly/AKD-EGAN.</p>","PeriodicalId":94052,"journal":{"name":"International journal of neural systems","volume":" ","pages":"2550013"},"PeriodicalIF":0.0000,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International journal of neural systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/S0129065725500133","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/2/19 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Generative Adversarial Networks (GANs) are effective for image generation, but their unstable training limits broader applications. Additionally, neural architecture search (NAS) for GANs with one-shot models often leads to insufficient subnet training, where subnets inherit weights from a supernet without proper optimization, further degrading performance. To address both issues, we propose Architecture Knowledge Distillation for Evolutionary GAN (AKD-EGAN). AKD-EGAN operates in two stages. First, architecture knowledge distillation (AKD) is used during supernet training to efficiently optimize subnetworks and accelerate learning. Second, a multi-objective evolutionary algorithm (MOEA) searches for optimal subnet architectures, ensuring efficiency by considering multiple performance metrics. This approach, combined with a strategy for architecture inheritance, enhances GAN stability and image quality. Experiments show that AKD-EGAN surpasses state-of-the-art methods, achieving a Fréchet Inception Distance (FID) of 7.91 and an Inception Score (IS) of 8.97 on CIFAR-10, along with competitive results on STL-10 (FID: 20.32, IS: 10.06). Code and models will be available at https://github.com/njit-ly/AKD-EGAN.

生成对抗网络(GAN)对图像生成非常有效,但其不稳定的训练限制了其更广泛的应用。此外,使用单次模型对 GANs 进行神经架构搜索(NAS)往往会导致子网训练不足,子网会继承超级网的权重,而没有进行适当的优化,从而进一步降低性能。为了解决这两个问题,我们提出了进化式 GAN 的架构知识提炼(AKD-EGAN)。AKD-EGAN 分两个阶段运行。首先,在超级网络训练过程中使用架构知识蒸馏(AKD)来有效优化子网络并加速学习。其次,多目标进化算法(MOEA)搜索最佳子网架构,通过考虑多个性能指标确保效率。这种方法与架构继承策略相结合,提高了 GAN 的稳定性和图像质量。实验表明,AKD-EGAN 超越了最先进的方法,在 CIFAR-10 上达到了 7.91 的弗雷谢特起始距离(FID)和 8.97 的起始分数(IS),在 STL-10 上也取得了具有竞争力的结果(FID:20.32,IS:10.06)。代码和模型可在 https://github.com/njit-ly/AKD-EGAN 上查阅。
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