前言:
隐语awesome-PETs(PETs即Privacy-Enhancing Technologies ,隐私增强技术)精选业内优秀论文,按技术类型进行整理分类,旨在为隐私计算领域的学习研究者提供一个高质量的学习交流社区。awesome-pets包含:安全多方计算(MPC)、零知识证明(ZKP)、联邦学习(FL)、差分隐私(DP)、可信执行环境(TEE)、隐私求交(PSI)等系列主题论文!
继上期[《多方安全计算》系列论文推荐活动小伙伴们参与热烈,社区收到了不少Paper留言。
本期继续带来联邦学习 (FL)系列论文推荐,更多主题Paper持续更新中ing~欢迎收藏项目。https://github.com/secretflow/secretflow/blob/main/docs/awesome-pets/awesome-pets.md
联邦学习系列论文
1、Survey
General
-
Federated machine learning: Concept and applications
-
Federated Learning in Mobile Edge Networks: A Comprehensive Survey
-
Advances and Open Problems in Federated Learning
-
Federated Learning: Challenges, Methods, and Future Directions
Security
-
A survey on security and privacy of federated learning
-
Threats to Federated Learning: A Survey
-
Vulnerabilities in Federated Learning
由于篇幅原因,还有更多论文未能一一列举,请访问github收藏!https://github.com/secretflow/secretflow/blob/main/docs/awesome-pets/papers/applications/ppml/fl/fl.md
2、Datasets
-
LEAF: A Benchmark for Federated Settings HomePage
-
UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones HomePage
-
The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
-
Evaluation Framework For Large-scale Federated Learning
-
(*) PrivacyFL: A simulator for privacy-preserving and secure federated learning. MIT CSAIL.
-
Revocable Federated Learning: A Benchmark of Federated Forest
3、Efficiency
Quantization
-
Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients
-
Lazily Aggregated Quantized Gradient Innovation for Communication-Efficient Federated Learning
-
Communication Efficient Federated Learning with Adaptive Quantization
-
QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
-
DEED: A General Quantization Scheme for Communication Efficiency in Bits
4、Effectiveness
Model Aggregation
-
FedAvg: Communication-Efficient Learning of Deep Networks from Decentralized Data
-
LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning
-
Federated Learning with Matched Averaging
-
Federated Learning of a Mixture of Global and Local Models
-
Faster On-Device Training Using New Federated Momentum Algorithm
-
FedDANE: A Federated Newton-Type Method
-
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
5、Incentive
Contribution Evaluation
-
Data Shapley: Equitable Valuation of Data for Machine Learning
-
A principled approach to data valuation for federated learning
-
Measure contribution of participants in federated learning
-
GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning
-
Profit allocation for federated learning
-
Fedcoin: A peer-to-peer payment system for federated learning
Profit Allocation
-
Hierarchical Incentive Mechanism Design for Federated Machine Learning in Mobile networks
-
FAIR: Quality-Aware Federated Learning with Precise User Incentive and Model Aggregation
-
Incentive Mechanism for Horizontal Federated Learning Based on Reputation and Reverse Auction
6、Vertical FL
-
SecureBoost: A Lossless Federated Learning Framework
-
Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator
-
Entity Resolution and Federated Learning get a Federated Resolution.
-
Multi-Participant Multi-Class Vertical Federated Learning
-
A Communication-Efficient Collaborative Learning Framework for Distributed Features
-
Asymmetrical Vertical Federated Learning
7、Boosting
-
Practical Federated Gradient Boosting Decision Trees
-
Secureboost: A lossless federated learning framework
-
Large-scale Secure XGB for Vertical Federated Learning
8、Application
Natural language Processing
-
Federated pretraining and fine tuning of BERT using clinical notes from multiple silos
-
Federated Learning for Mobile Keyboard Prediction
-
Federated Learning for Keyword Spotting
-
generative sequence models (e.g., language models)
-
Federated User Representation Learning
-
Two-stage Federated Phenotyping and Patient Representation Learning
由于篇幅原因,还有更多论文未能一一列举,请访问github收藏!
https://github.com/secretflow/secretflow/blob/main/docs/awesome-pets/papers/applications/ppml/fl/fl.md