【论文分享】《资源受限边缘计算系统中的自适应联邦学习》| JSAC（CCF A）

发布人

paper:《Adaptive Federated Learning in Resource Constrained Edge Computing Systems》
Abstract: Emerging technologies and applications including Internet of Things, social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable the detection, classification, and prediction of future events. Due to bandwidth, storage, and privacy concerns, it is often impractical to send all the data to a centralized location. In this paper, we consider the problem of learning model parameters from data distributed across multiple edge nodes, without sending raw data to a centralized place. Our focus is on a generic class of machine learning models that are trained using gradient-descent-based approaches. We analyze the convergence bound of distributed gradient descent from a theoretical point of view, based on which we propose a control algorithm that determines the best tradeoff between local update and global parameter aggregation to minimize the loss function under a given resource budget. The performance of the proposed algorithm is evaluated via extensive experiments with real datasets, both on a networked prototype system and in a larger-scale simulated environment. The experimentation results show that our proposed approach performs near to the optimum with various machine learning models and different data distributions.
在通信资源（本地迭代+与中心交互）的限制下，最优化本地自适应迭代次数的，即自适应联邦聚合次数

打开封面下载高清视频观看高清视频视频下载器

【论文分享】《资源受限边缘计算系统中的自适应联邦学习》| JSAC（CCF A）

[Flower+PyTorch] 1分钟开始联邦学习！如何快速用 Pytorch 和 Flower 搭建一个简单场景？

【论文分享】《用于个性化联邦学习的分层模型聚合》 | CPVR 2022

【论文分享】DASFFA 2019 | FedSel: 基于Top-k维度选择的本地差分隐私联邦学习算法

【组会分享】自适应差分隐私深度学习-《An Adaptive and Fast Convergent Approach to DP DL 》

【学习分享】《本地化差分隐私综述》—LDP

【论文分享】特邀中科院博士蒋雪枫最新论文《基于局部自正则化的抗噪声标签联合学习》CIKM 2022！

【论文分享】差分隐私~《deep learning with differential privacy》~Moments Accoutant的关键思想

【论文分享】特邀西安电子科技大学博士分享《Local and Central DP for Robustness and Privacy in FL》

【论文分享】《基于DPSGD的图节点分类任务》| ICLR 2023 （欢迎有做图神经/图联邦结合DP的同僚与我联系交流）

【论文汇报】特邀浙江大学博士冯浩哲（知乎大V“捡到一束光”）分享《KD3A: 一种满足隐私保护要求的去中心化无监督域适应范式》[ICML2021]

自适应打包机，这次好像真的完美了

【论文分享】湖南大学江政良分享论文《通过LWE难题实现高效且满足差分隐私的联邦学习安全聚合》| usenix security'22

【论文分享】基于K-means 聚类的差分隐私（指数机制）协同过滤推荐算法

【组会论文记录】《User-Level Privacy-Preserving Federated Learning: Analysis and Perform》

【论文讨论】《Learning Differenitally Private Languange Model》~Client Level FL-DP

【论文分享】USENIX 2023 | 利用社区信息进行差分隐私图数据发布

【论文分享】中科院博士刘博超论文分享《DPGEN：用于自然图像合成的差分隐私生成能量引导网络》

【录制搬运】浙江大学特聘研究员陈超超 《隐私保护机器学习》

【论文分享】《renyi differential privacy》-瑞丽差分隐私

【论文分享】VLDB 2024 | 基于选择性更新和释放的差分隐私梯度下降算法

【论文分享】《Locally Differentially Private Protocols for Frequency Estimation》

【组会分享】《Comprehensive Privacy Analysis of Deep Learning》集中式与联邦场景下的消极与积极的成员推理攻击

【论文分享】《基于本地差分隐私的多维数据收集和分析》 | ICDE 2019

【转载】Three Flavors of Differentially Private Federated Learning | Dr. Yang Cao

【论文分享】《一种分布估计场景下的实用性本地差分隐私机制》| USENIX 2019

【教材分享】梯度下降在强凸/凸/非凸下的收敛速率证明

【录制搬运】埃默里大学 Li Xiong 教授《Federated Learning: Privacy, Efficiency, and Robustness》

【学术论文写作】英文学术会议论文写作经验分享-Jeff

本地部署开源模型使用反思的思想优化RAG 效果

简单自适应打包机

【组会分享】《Gaussian Differential Privacy》

【教材分享】拉普拉斯机制？高斯机制？严格差分隐私？松弛差分隐私？

【转载】Privacy is Not an Afterthought | Dr. Xi He

【论文讨论】《Towards Security Threats of Deep Learning Systems: A Survey》

【转载】Differential Privacy: Potential and Limitations | Prof. Ninghui Li

【ASTAPLE DP Group】CSF 2017 | Renyi Differential Privacy (瑞丽差分隐私) - Jianping Cai

【录制搬运】奥本大学教授 Yang Zhou 《可信机器学习：安全，隐私和公平》

【组会汇报】差分隐私-《PATESEMI-SUPERVISED KNOWLEDGE TRANSFER FOR DEEP LEARNING》（PATE）

【ASTAPLE DP Group】SIGMO 2022 | LDP-IDS：无限数据流的本地差分隐私保护 - Rong Du

【ASTAPLE DP Group】Advanced Composition in Differential Privacy - Xun Ran

【录制搬运】浙江大学特聘研究员陈超超《隐私保护机器学习》