SPACE: fully decentralised distributed learning for tradeoff of privacy, accuracy, communication complexity, and efficiency
SPACE:完全去中心化的分布式学习,以权衡隐私、准确性、通信复杂性和效率
基本信息
- 批准号:10046257
- 负责人:
- 金额:$ 7.14万
- 依托单位:
- 依托单位国家:英国
- 项目类别:CR&D Bilateral
- 财政年份:2022
- 资助国家:英国
- 起止时间:2022 至 无数据
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Training data of a machine learning application may be collected from geographically different places, but transferring distributed data to a central server for training can be legally or practically impossible. This has led to a fast-growing area in machine learning, i.e., federated learning. However, it was discovered that the federated learning in its original form, where a server iteratively aggregates local gradients received from the distributed users, may suffer from privacy leakage as an attacker can infer sensitive information from the local gradients. Since then, many improvements have been presented to mitigate this privacy leakage, but they often achieve better privacy with the compromise of other critical properties such as the accuracy and communication complexity. In this paper, we propose a novel solution that is based on a fully decentralised distributed learning. Our solution enables the optimisation over, and achieve a balance between, multiple properties, including privacy preservation, accuracy, communication complexity, efficiency, and tolerance to user failures. Our solution proceeds by first synthesising a communication topology between users according to the required properties and then applying a fully decentralised distributed learning where the server is not involved in the computation. In the decentralised learning, the aggregation of local gradients is reduced to a distributed consensus between users. Finally, the agreed value of the users is sent to the server after added a differential privacy noise. We are conducting experiments on both use cases in the US/UK privacy enhancing technologies challenge to validate our solution.
机器学习应用程序的训练数据可以从地理上不同的地方收集,但将分布式数据传输到中央服务器进行训练在法律上或实际上是不可能的。这导致了机器学习中一个快速增长的领域,即,联邦学习然而,人们发现,在其原始形式的联合学习中,服务器迭代地聚合从分布式用户接收的局部梯度,可能会遭受隐私泄露,因为攻击者可以从局部梯度中推断敏感信息。从那时起,已经提出了许多改进来减轻这种隐私泄漏,但它们通常在其他关键属性(如准确性和通信复杂性)的妥协下实现更好的隐私。在本文中,我们提出了一种基于完全分散的分布式学习的新解决方案。我们的解决方案能够优化多个属性,并在多个属性之间实现平衡,包括隐私保护,准确性,通信复杂性,效率和对用户故障的容忍度。我们的解决方案首先根据所需属性合成用户之间的通信拓扑,然后应用完全分散的分布式学习,其中服务器不参与计算。在分散式学习中,局部梯度的聚合被简化为用户之间的分布式共识。最后,用户的同意值被发送到服务器后,添加一个差分隐私噪声。我们正在对美国/英国隐私增强技术挑战中的两个用例进行实验,以验证我们的解决方案。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
其他文献
吉治仁志 他: "トランスジェニックマウスによるTIMP-1の線維化促進機序"最新医学. 55. 1781-1787 (2000)
Hitoshi Yoshiji 等:“转基因小鼠中 TIMP-1 的促纤维化机制”现代医学 55. 1781-1787 (2000)。
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
LiDAR Implementations for Autonomous Vehicle Applications
- DOI:
- 发表时间:
2021 - 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
吉治仁志 他: "イラスト医学&サイエンスシリーズ血管の分子医学"羊土社(渋谷正史編). 125 (2000)
Hitoshi Yoshiji 等人:“血管医学与科学系列分子医学图解”Yodosha(涉谷正志编辑)125(2000)。
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
Effect of manidipine hydrochloride,a calcium antagonist,on isoproterenol-induced left ventricular hypertrophy: "Yoshiyama,M.,Takeuchi,K.,Kim,S.,Hanatani,A.,Omura,T.,Toda,I.,Akioka,K.,Teragaki,M.,Iwao,H.and Yoshikawa,J." Jpn Circ J. 62(1). 47-52 (1998)
钙拮抗剂盐酸马尼地平对异丙肾上腺素引起的左心室肥厚的影响:“Yoshiyama,M.,Takeuchi,K.,Kim,S.,Hanatani,A.,Omura,T.,Toda,I.,Akioka,
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('', 18)}}的其他基金
An implantable biosensor microsystem for real-time measurement of circulating biomarkers
用于实时测量循环生物标志物的植入式生物传感器微系统
- 批准号:
2901954 - 财政年份:2028
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Exploiting the polysaccharide breakdown capacity of the human gut microbiome to develop environmentally sustainable dishwashing solutions
利用人类肠道微生物群的多糖分解能力来开发环境可持续的洗碗解决方案
- 批准号:
2896097 - 财政年份:2027
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
A Robot that Swims Through Granular Materials
可以在颗粒材料中游动的机器人
- 批准号:
2780268 - 财政年份:2027
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Likelihood and impact of severe space weather events on the resilience of nuclear power and safeguards monitoring.
严重空间天气事件对核电和保障监督的恢复力的可能性和影响。
- 批准号:
2908918 - 财政年份:2027
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Proton, alpha and gamma irradiation assisted stress corrosion cracking: understanding the fuel-stainless steel interface
质子、α 和 γ 辐照辅助应力腐蚀开裂:了解燃料-不锈钢界面
- 批准号:
2908693 - 财政年份:2027
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Field Assisted Sintering of Nuclear Fuel Simulants
核燃料模拟物的现场辅助烧结
- 批准号:
2908917 - 财政年份:2027
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Assessment of new fatigue capable titanium alloys for aerospace applications
评估用于航空航天应用的新型抗疲劳钛合金
- 批准号:
2879438 - 财政年份:2027
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Developing a 3D printed skin model using a Dextran - Collagen hydrogel to analyse the cellular and epigenetic effects of interleukin-17 inhibitors in
使用右旋糖酐-胶原蛋白水凝胶开发 3D 打印皮肤模型,以分析白细胞介素 17 抑制剂的细胞和表观遗传效应
- 批准号:
2890513 - 财政年份:2027
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
CDT year 1 so TBC in Oct 2024
CDT 第 1 年,预计 2024 年 10 月
- 批准号:
2879865 - 财政年份:2027
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Understanding the interplay between the gut microbiome, behavior and urbanisation in wild birds
了解野生鸟类肠道微生物组、行为和城市化之间的相互作用
- 批准号:
2876993 - 财政年份:2027
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
相似海外基金
Collaborative Research: SHF: Small: Efficient and Scalable Privacy-Preserving Neural Network Inference based on Ciphertext-Ciphertext Fully Homomorphic Encryption
合作研究:SHF:小型:基于密文-密文全同态加密的高效、可扩展的隐私保护神经网络推理
- 批准号:
2412357 - 财政年份:2024
- 资助金额:
$ 7.14万 - 项目类别:
Standard Grant
Development of a fully humanised model for understanding platelet function
开发了解血小板功能的完全人源化模型
- 批准号:
NC/Y000870/1 - 财政年份:2024
- 资助金额:
$ 7.14万 - 项目类别:
Research Grant
AerialHitches: Forming and Controlling Hitches for Fully Autonomous Transportation Using Aerial Robots with Cables
空中挂钩:使用带有电缆的空中机器人形成和控制全自动运输的挂钩
- 批准号:
2322840 - 财政年份:2024
- 资助金额:
$ 7.14万 - 项目类别:
Standard Grant
Fully general-relativistic magneto-hydrodynamic simulations beyond Relativity with GPUs
使用 GPU 进行超越相对论的完全广义相对论磁流体动力学模拟
- 批准号:
ST/Z000424/1 - 财政年份:2024
- 资助金额:
$ 7.14万 - 项目类别:
Research Grant
Extremely efficient fully three-dimensional hydrodynamic simulations of supernova remnants for the new age of microcalorimetric X-ray astronomy
针对微量热 X 射线天文学新时代的超新星遗迹进行极其高效的全三维流体动力学模拟
- 批准号:
24K07092 - 财政年份:2024
- 资助金额:
$ 7.14万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Calon-Cardio's Fully Implantable ventricular assist device
Calon-Cardio 的完全植入式心室辅助装置
- 批准号:
10037229 - 财政年份:2023
- 资助金额:
$ 7.14万 - 项目类别:
Collaborative R&D
Sustainable Chemical Innovations Enabling Net Carbon Emissions (SCIENCE): Fully funded PhD studentship, School of Chemistry, University of Nottingham
实现净碳排放的可持续化学创新(科学):诺丁汉大学化学学院全额资助博士生奖学金
- 批准号:
2884925 - 财政年份:2023
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Fully Bayesian 3D PET-MR Neuroimaging Reconstruction
完全贝叶斯 3D PET-MR 神经影像重建
- 批准号:
2886403 - 财政年份:2023
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Fast, Cost-Effective and Fully Automated Structure Verification through Synergistic Use of Infrared and NMR Spectra
通过红外和核磁共振光谱的协同使用进行快速、经济高效的全自动结构验证
- 批准号:
2894203 - 财政年份:2023
- 资助金额:
$ 7.14万 - 项目类别:
Studentship
Exploiting fully coupled fluid-structure interaction: optimal wing heterogeneity and efficient flow state estimation in flapping flight
利用完全耦合的流固相互作用:扑翼飞行中的最佳机翼异质性和有效的流动状态估计
- 批准号:
2320875 - 财政年份:2023
- 资助金额:
$ 7.14万 - 项目类别:
Standard Grant