Data-Free Evaluation of User Contributions in Federated Learning

被引:0
作者
Lv, Hongtao [1 ]
Zheng, Zhenzhe [1 ]
Luo, Tie [2 ]
Wu, Fan [1 ]
Tang, Shaojie [3 ]
Hua, Lifeng [4 ]
Jie, Rongfei [4 ]
Lv, Chengfei [4 ]
机构
[1] Shanghai Jiao Tong Univ, Shanghai, Peoples R China
[2] Missouri Univ Sci & Technol, Rolla, MO 65409 USA
[3] Univ Texas Dallas, Dallas, TX USA
[4] Alibaba Grp, Hangzhou, Peoples R China
来源
2021 19TH INTERNATIONAL SYMPOSIUM ON MODELING AND OPTIMIZATION IN MOBILE, AD HOC, AND WIRELESS NETWORKS (WIOPT) | 2021年
基金
美国国家科学基金会;
关键词
Peer prediction; correlated agreement;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Federated learning (FL) trains a machine learning model on mobile devices in a distributed manner using each device's private data and computing resources. A critical issues is to evaluate individual users' contributions so that (1) users' effort in model training can be compensated with proper incentives and (2) malicious and low-quality users can be detected and removed. The state-of-the-art solutions require a representative test dataset for the evaluation purpose, but such a dataset is often unavailable and hard to synthesize. In this paper, we propose a method called Pairwise Correlated Agreement (PCA) based on the idea of peer prediction to evaluate user contribution in FL without a test dataset. PCA achieves this using the statistical correlation of the model parameters uploaded by users. We then apply PCA to designing (1) a new federated learning algorithm called Fed-PCA, and (2) a new incentive mechanism that guarantees truthfulness. We evaluate the performance of PCA and Fed-PCA using the MNIST dataset and a large industrial product recommendation dataset. The results demonstrate that our Fed-PCA outperforms the canonical FedAvg algorithm and other baseline methods in accuracy, and at the same time, PCA effectively incentivizes users to behave truthfully.
引用
收藏
页数:8
相关论文
empty
未找到相关数据