The Impact of Data Distribution on Fairness and Robustness in Federated Learning
The Impact of Data Distribution on Fairness and Robustness in Federated Learning
复制标题
DOI：
10.1109/tpsisa52974.2021.00022
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Mustafa Safa Ozdayi;Murat Kantarcioglu
中科院分区：
文献类型：
--
作者：
Mustafa Safa Ozdayi;Murat Kantarcioglu
联邦学习(FL)是一种分布式机器学习协议，允许一组代理在不共享数据集的情况下协作训练模型。这使得FL特别适合需要数据隐私的设置。然而，已经观察到FL的性能与代理的局部数据分布的相似性密切相关。特别是，当代理的数据分布不同时，训练的模型的精度会下降。在这项工作中，我们研究了局部数据分布的变化如何影响训练模型的公平性和稳健性，以及准确性。我们的实验结果表明，训练后的模型表现出更高的偏差，并且随着局部数据分布的不同而变得更容易受到攻击。重要的是，公平性和稳健性的降级可能比准确性严重得多。因此，我们发现，如果训练的模型要部署在公平/安全关键的环境中，那么对精度影响很小的小变化仍然可能是重要的。
Federated Learning (FL) is a distributed machine learning protocol that allows a set of agents to collaboratively train a model without sharing their datasets. This makes FL particularly suitable for settings where data privacy is desired. However, it has been observed that the performance of FL is closely related to the similarity of the local data distributions of agents. Particularly, as the data distributions of agents differ, the accuracy of the trained models drop. In this work, we look at how variations in local data distributions affect the fairness and the robustness properties of the trained models in addition to the accuracy. Our experimental results indicate that, the trained models exhibit higher bias, and become more susceptible to attacks as local data distributions differ. Importantly, the degradation in the fairness, and robustness can be much more severe than the accuracy. Therefore, we reveal that small variations that have little impact on the accuracy could still be important if the trained model is to be deployed in a fairness/security critical context.