赞
踩
熬过了一个比赛,也开始第二篇论文推荐的内容。huuuu
目录
Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms
Adaptive Federated Optimization
Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity
FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
Sageflow: Robust Federated Learning against Both Stragglers and Adversaries
STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating
Federated Composite Optimization
本部分主要关注如何在分布式学习环境中保持算法的公平性,以及如何识别和减少可能存在于训练数据中的偏见。
性能公平性
论文: "Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning"内容复分析:该论文提出了一种方法来解决算法在不同设备或数据集上性能不一致的问题,通过调整模型更新或选择策略来提高整体性能。公平性意识的联邦学习
论文: "Fairness-aware Agnostic Federated Learning"内容复分析:论文探讨了在缺乏对局部数据分布了解的情况下,如何设计联邦学习算法以确保公平性。资源分配公平性
论文: "Fair Resource Allocation in Federated Learning"内容复分析:该论文讨论了如何在资源有限的情况下,公平地在参与者之间分配计算资源或数据。未知数据分布的联邦学习
论文: "Agnostic Federated Learning"内容复分析:论文提出了一种策略来处理数据分布未知的情况,确保模型训练的鲁棒性和公平性。减少偏见
论文: "Mitigating Bias in Federated Learning"内容复分析:论文研究了如何识别和减少联邦学习中的数据偏见,以提高模型的公正性。个性化的公平和鲁棒联邦学习
论文: "Ditto: Fair and Robust Federated Learning Through Personalization"内容复分析:该论文提出了一种个性化的方法来提高联邦学习的公平性和鲁棒性,通过定制模型以适应不同的用户数据。客户端选择效率提升
论文: "An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee"内容复分析:论文提出了一种客户端选择方案,旨在提高联邦学习的训练效率,同时保证选择过程的公平性。贡献公平性
论文: "Profit Allocation for Federated Learning"内容复分析:该论文探讨了如何根据参与者的贡献公平地分配利润或其他形式的回报。这些论文涵盖了联邦学习中公平性的不同方面,包括性能一致性、资源分配、客户端选择、个性化以及利润分配等。
联邦学习作为一种分布式机器学习方法,已经在多个领域显示出其强大的应用潜力。
Computer Vision(计算机视觉)
Nature Language Processing(自然语言处理)
Automatic Speech Recognition(自动语音识别)
Healthcare(医疗保健)
Blockchain(区块链)
Data-Free Knowledge Distillation for Heterogeneous Federated Learning
Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity
Exploiting Shared Representations for Personalized Federated Learning
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
Personalized Federated Learning with Moreau Envelopes
Federated Learning of a Mixture of Global and Local Models
Salvaging Federated Learning by Local Adaptation
Sageflow: Robust Federated Learning against Both Stragglers and Adversaries
Towards Flexible Device Participation in Federated Learning
Supplementary
在联邦学习中,客户端选择(Client Selection)是一个关键问题,它直接影响到学习过程的效率、模型的质量和系统的鲁棒性。
Diverse Client Selection for Federated Learning via Submodular Maximization
TiFL: A Tier-based Federated Learning System
HACCS: Heterogeneity-Aware Clustered Client Selection for Accelerated Federated Learning
Communication-Efficient Federated Learning via Optimal Client Sampling
Oort: Efficient Federated Learning via Guided Participant Selection
Optimizing federated learning on non-iid data with reinforcement learning
Reference
1.Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., ... & Zhao, S. (2021). Advances and open problems in federated learning. Foundations and trends® in machine learning, 14(1–2), 1-210.
2. GitHub - innovation-cat/Awesome-Federated-Machine-Learning: Everything about federated learning, including research papers, books, codes, tutorials, videos and beyond
————————————————
版权声明:本文为博主原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。
原文链接:https://blog.csdn.net/weixin_74181752/article/details/139419927
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。