shiping998/federated-learning

Everything about Federated Learning (papers, tutorials, etc.) -- 联邦学习

联邦学习 Federated Learning

Everything about federated learning. Your contribution is highly valued!

关于联邦学习的资料，包括：介绍、综述文章、最新文章、代表工作及其代码、数据集、论文等等。 欢迎一起贡献！

---

• 目录
  • 1. 教程 Tutorial
  • 2. 相关论文 Related Papers
  • 3. 项目 Project
  • 4. 相关学者 Related Scholars

---

1. 教程 Tutorial

• 文字

  • 杨强：联邦学习
  • Google - Federated Learning: Collaborative Machine Learning without Centralized Training Data
  • 联邦学习的研究及应用
  • 杨强：GDPR对AI的挑战和基于联邦迁移学习的对策

• PPT

  • 联邦学习的研究与应用
  • Federated Learning and Transfer Learning for Privacy, Security and Confidentiality (AAAI-19)
  • GDPR, Data Shortage and AI (AAAI-19)

• 视频

  • GDPR, Data Shortage and AI (AAAI-19 Invited Talk)

• 新闻

  • 2019/02/09 谷歌发布全球首个产品级移动端分布式机器学习系统，数千万手机同步训练

---

2. 相关论文 Related Papers

• 综述与介绍 Survey And Introduction

  • arXiv 201912 - Advances and Open Problems in Federated Learning 58位学者联名综述
  • TIST 201902 - Federated Machine Learning: Concept and Applications
  • arXiv 201909 - Federated Learning in Mobile Edge Networks: A Comprehensive Survey

• 应用 Application

  • 2019 - Federated Learning for Mobile Keyboard Prediction - Google将联邦学习用于自家输入法
  • 2019 - Towards Federated Learning at Scale: System Design - Google千万设备级联邦学习系统设计

• 联邦学习的提出

  • 2015 - Federated Optimization:Distributed Optimization Beyond the Datacenter
  • 2016 - Practical Secure Aggregation for Federated Learning on User-Held Data
  • 2016 - Federated Optimization: Distributed Machine Learning for On-Device Intelligence
  • 2017 - Federated Learning: Strategies for Improving Communication Efficiency
  • 2017 - Communication-Efficient Learning of Deep Networks from Decentralized Data 联邦平均算法 the FederatedAveraging algorithm

• 联邦学习安全性

  • NIPS 2016 - Practical Secure Aggregation for Federated Learning on User-Held Data 增强联邦学习的隐私保护能力
  • 2017 - Differentially Private Federated Learning: A Client Level Perspective 使用差分隐私避免泄露用户的贡献度
  • 2018 - How to Backdoor Federated Leraning Model Poisoning攻击
  • 2019 - Can You Really Backdoor Federated Learning 如何避免联邦学习被后门攻击
  • ICML 2019 - Analyzing Federated Learning through an Adversarial Lens Model Poisoning攻击
  • ICLR 2020 - DBA: Distributed Backdoor Attacks against Federated Learning Model Poisoning攻击，在两个最新鲁棒FL框架上验证
  • AAAI 2020 - Robust Federated Training via Collaborative Machine Teaching using Trusted Instances 鲁棒FL方法，诊断训练集中的Bugs和调整label.

• 联邦学习扩展(FL+)

  • NIPS 2017 - Federated Multi-Task Learning 联邦多任务学习
  • arXiv 201901 - Federated Reinforcement Learning 联邦学习 + 强化学习 (Federated Learning + Reinforcement Learning)
  • arXiv 201901 - SecureBoost: A Lossless Federated Learning Framework 纵向联邦学习 (Vertical Federated Learning) 使用分布式决策树
  • arXiv 201810 - Secure Federated Transfer Learning 联邦迁移学习
  • ICML 2019 - Bayesian Nonparametric Federated Learning of Neural Networks 贝叶斯联邦学习
  • ICLR 2020 - Federated Adversarial Domain Adaptation 联邦对抗域适应
  • ICLR 2021 - [TOWARDS CAUSAL FEDERATED LEARNING FOR ENHANCED ROBUSTNESS AND PRIVACY] (https://arxiv.org/pdf/2104.06557.pdf) (Federated Learning + Causal Learning)
  • CyberC 2019 - Record and Reward Federated Learning Contributions with Blockchain (Federated Learning + Blockchain)

• 高效联邦学习

  • 2018 - Expanding the Reach of Federated Leraning by Reducing Client Resource Requirements 提出两个策略来提高通信效率
  • 2019 - Robust and Communication-Efficient Federated Learning from Non-IID Data 提出压缩框架STC，可以减少训练时间和通信代价

---

3. 项目 Project

• FATE - 微众银行
• TensorFlow Federated
• Federated-Learning : An implement of google's paper.

---

4. 相关学者 Related Scholars

• 杨强 Yang Qiang
• H. Brendan McMahan
• jakub konečný

---

Contributors

Thanks goes to these wonderful people:

王智勇(Wang Zhiyong)	刘一璟(Liu Yijing)

欢迎参与贡献