Kangyang Luo, Shuai Wang, Yexuan Fu, Renrong Shao, Xiang Li, Yunshi Lan, Ming Gao, Jinlong Shu
{"title":"DFDG:用于单次联合学习的无数据双生成器逆向精馏法","authors":"Kangyang Luo, Shuai Wang, Yexuan Fu, Renrong Shao, Xiang Li, Yunshi Lan, Ming Gao, Jinlong Shu","doi":"arxiv-2409.07734","DOIUrl":null,"url":null,"abstract":"Federated Learning (FL) is a distributed machine learning scheme in which\nclients jointly participate in the collaborative training of a global model by\nsharing model information rather than their private datasets. In light of\nconcerns associated with communication and privacy, one-shot FL with a single\ncommunication round has emerged as a de facto promising solution. However,\nexisting one-shot FL methods either require public datasets, focus on model\nhomogeneous settings, or distill limited knowledge from local models, making it\ndifficult or even impractical to train a robust global model. To address these\nlimitations, we propose a new data-free dual-generator adversarial distillation\nmethod (namely DFDG) for one-shot FL, which can explore a broader local models'\ntraining space via training dual generators. DFDG is executed in an adversarial\nmanner and comprises two parts: dual-generator training and dual-model\ndistillation. In dual-generator training, we delve into each generator\nconcerning fidelity, transferability and diversity to ensure its utility, and\nadditionally tailor the cross-divergence loss to lessen the overlap of dual\ngenerators' output spaces. In dual-model distillation, the trained dual\ngenerators work together to provide the training data for updates of the global\nmodel. At last, our extensive experiments on various image classification tasks\nshow that DFDG achieves significant performance gains in accuracy compared to\nSOTA baselines.","PeriodicalId":501422,"journal":{"name":"arXiv - CS - Distributed, Parallel, and Cluster Computing","volume":"30 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"DFDG: Data-Free Dual-Generator Adversarial Distillation for One-Shot Federated Learning\",\"authors\":\"Kangyang Luo, Shuai Wang, Yexuan Fu, Renrong Shao, Xiang Li, Yunshi Lan, Ming Gao, Jinlong Shu\",\"doi\":\"arxiv-2409.07734\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Federated Learning (FL) is a distributed machine learning scheme in which\\nclients jointly participate in the collaborative training of a global model by\\nsharing model information rather than their private datasets. In light of\\nconcerns associated with communication and privacy, one-shot FL with a single\\ncommunication round has emerged as a de facto promising solution. However,\\nexisting one-shot FL methods either require public datasets, focus on model\\nhomogeneous settings, or distill limited knowledge from local models, making it\\ndifficult or even impractical to train a robust global model. To address these\\nlimitations, we propose a new data-free dual-generator adversarial distillation\\nmethod (namely DFDG) for one-shot FL, which can explore a broader local models'\\ntraining space via training dual generators. DFDG is executed in an adversarial\\nmanner and comprises two parts: dual-generator training and dual-model\\ndistillation. In dual-generator training, we delve into each generator\\nconcerning fidelity, transferability and diversity to ensure its utility, and\\nadditionally tailor the cross-divergence loss to lessen the overlap of dual\\ngenerators' output spaces. In dual-model distillation, the trained dual\\ngenerators work together to provide the training data for updates of the global\\nmodel. At last, our extensive experiments on various image classification tasks\\nshow that DFDG achieves significant performance gains in accuracy compared to\\nSOTA baselines.\",\"PeriodicalId\":501422,\"journal\":{\"name\":\"arXiv - CS - Distributed, Parallel, and Cluster Computing\",\"volume\":\"30 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Distributed, Parallel, and Cluster Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07734\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Distributed, Parallel, and Cluster Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07734","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
联合学习(FL)是一种分布式机器学习方案,其中客户通过共享模型信息而非其私有数据集,共同参与全局模型的协作训练。考虑到与通信和隐私相关的问题,只有一轮通信的单次 FL 已成为事实上有前途的解决方案。然而,现有的单次 FL 方法要么需要公共数据集,要么专注于模型同构设置,要么从局部模型中提炼出有限的知识,这使得训练一个稳健的全局模型变得困难甚至不切实际。为了解决这些局限性,我们提出了一种新的无数据双生成器对抗性提炼方法(即 DFDG),它可以通过训练双生成器来探索更广阔的局部模型训练空间。DFDG 以对抗方式执行,包括两个部分:双发电机训练和双模型蒸馏。在双生成器训练中,我们对每个生成器的保真度、可转移性和多样性进行深入研究,以确保其实用性,此外,我们还对交叉发散损失进行了调整,以减少双生成器输出空间的重叠。在双模型蒸馏过程中,经过训练的双生成器共同为全局模型的更新提供训练数据。最后,我们在各种图像分类任务中进行的大量实验表明,与 SOTA 基线相比,DFDG 在准确率方面取得了显著的性能提升。
DFDG: Data-Free Dual-Generator Adversarial Distillation for One-Shot Federated Learning
Federated Learning (FL) is a distributed machine learning scheme in which
clients jointly participate in the collaborative training of a global model by
sharing model information rather than their private datasets. In light of
concerns associated with communication and privacy, one-shot FL with a single
communication round has emerged as a de facto promising solution. However,
existing one-shot FL methods either require public datasets, focus on model
homogeneous settings, or distill limited knowledge from local models, making it
difficult or even impractical to train a robust global model. To address these
limitations, we propose a new data-free dual-generator adversarial distillation
method (namely DFDG) for one-shot FL, which can explore a broader local models'
training space via training dual generators. DFDG is executed in an adversarial
manner and comprises two parts: dual-generator training and dual-model
distillation. In dual-generator training, we delve into each generator
concerning fidelity, transferability and diversity to ensure its utility, and
additionally tailor the cross-divergence loss to lessen the overlap of dual
generators' output spaces. In dual-model distillation, the trained dual
generators work together to provide the training data for updates of the global
model. At last, our extensive experiments on various image classification tasks
show that DFDG achieves significant performance gains in accuracy compared to
SOTA baselines.