The Impact of Data Distribution on Fairness and Robustness in Federated Learning

被引:2
|
作者
Ozdayi, Mustafa Safa [1 ]
Kantarcioglu, Murat [1 ]
机构
[1] Univ Texas Dallas, Dept Comp Sci, Richardson, TX 75083 USA
关键词
Federated Learning; Algorithmic Fairness; Adversarial Machine Learning;
D O I
10.1109/TPSISA52974.2021.00022
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:191 / 196
页数:6
相关论文
共 50 条
  • [1] Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark
    Huang, Wenke
    Ye, Mang
    Shi, Zekun
    Wan, Guancheng
    Li, He
    Du, Bo
    Yang, Qiang
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (12) : 9387 - 9406
  • [2] Boosting Fairness and Robustness in Over-the-Air Federated Learning
    Oeksuez, Halil Yigit
    Molinari, Fabio
    Sprekeler, Henning
    Raisch, Joerg
    IEEE CONTROL SYSTEMS LETTERS, 2024, 8 : 682 - 687
  • [3] Personalized Federated Learning towards Communication Efficiency, Robustness and Fairness
    Lin, Shiyun
    Han, Yuze
    Li, Xiang
    Zhang, Zhihua
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [4] CosPer: An adaptive personalized approach for enhancing fairness and robustness of federated learning
    Ren, Pengcheng
    Qi, Kaiyue
    Li, Jialin
    Yan, Tongjiang
    Dai, Qiang
    INFORMATION SCIENCES, 2024, 675
  • [5] Analyzing the Impact of Personalization on Fairness in Federated Learning for Healthcare
    Tongnian Wang
    Kai Zhang
    Jiannan Cai
    Yanmin Gong
    Kim-Kwang Raymond Choo
    Yuanxiong Guo
    Journal of Healthcare Informatics Research, 2024, 8 : 181 - 205
  • [6] The Impact of Differential Privacy on Model Fairness in Federated Learning
    Gu, Xiuting
    Zhu, Tianqing
    Li, Jie
    Zhang, Tao
    Ren, Wei
    NETWORK AND SYSTEM SECURITY, NSS 2020, 2020, 12570 : 419 - 430
  • [7] Analyzing the Impact of Personalization on Fairness in Federated Learning for Healthcare
    Wang, Tongnian
    Zhang, Kai
    Cai, Jiannan
    Gong, Yanmin
    Choo, Kim-Kwang Raymond
    Guo, Yuanxiong
    JOURNAL OF HEALTHCARE INFORMATICS RESEARCH, 2024, 8 (02) : 181 - 205
  • [8] On the impact of non-IID data on the performance and fairness of differentially private federated learning
    Amiri, Saba
    Belloum, Adam
    Nalisnick, Eric
    Klous, Sander
    Gommans, Leon
    52ND ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS WORKSHOP VOLUME (DSN-W 2022), 2022, : 52 - 58
  • [9] Improving Fairness for Data Valuation in Horizontal Federated Learning
    Fan, Zhenan
    Fang, Huang
    Zhou, Zirui
    Pei, Jian
    Friedlander, Michael P.
    Liu, Changxin
    Zhang, Yong
    2022 IEEE 38TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2022), 2022, : 2440 - 2453
  • [10] SARS: A Personalized Federated Learning Framework Towards Fairness and Robustness against Backdoor Attacks
    Zhang, Webin
    Li, Youpeng
    An, Lingling
    Wan, Bo
    Wang, Xuyu
    PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT, 2024, 8 (04):