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
  • [31] Towards Fairness-Aware Federated Learning
    Shi, Yuxin
    Yu, Han
    Leung, Cyril
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (09) : 11922 - 11938
  • [32] FairFed: Enabling Group Fairness in Federated Learning
    Ezzeldin, Yahya H.
    Yan, Shen
    He, Chaoyang
    Ferrara, Emilio
    Avestimehr, Salman
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 6, 2023, : 7494 - 7502
  • [33] Federated Learning with Data-Agnostic Distribution Fusion
    Duan, Jian-hui
    Li, Wenzhong
    Lou, Derun
    Li, Ruichen
    Lu, Sanglu
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 8074 - 8083
  • [34] Fairness and privacy preserving in federated learning: A survey
    Rafi, Taki Hasan
    Noor, Faiza Anan
    Hussain, Tahmid
    Chae, Dong-Kyu
    INFORMATION FUSION, 2024, 105
  • [35] Privacy and Fairness in Federated Learning: On the Perspective of Tradeoff
    Chen, Huiqiang
    Zhu, Tianqing
    Zhang, Tao
    Zhou, Wanlei
    Yu, Philip S.
    ACM COMPUTING SURVEYS, 2024, 56 (02)
  • [36] DFFL: A dual fairness framework for federated learning
    Qi, Kaiyue
    Yan, Tongjiang
    Ren, Pengcheng
    Yang, Jianye
    Li, Jialin
    COMPUTER COMMUNICATIONS, 2025, 235
  • [37] Fairness in Federated Learning: Trends, Challenges, and Opportunities
    Mukhtiar, Noorain
    Mahmood, Adnan
    Sheng, Quan Z.
    ADVANCED INTELLIGENT SYSTEMS, 2025,
  • [38] The Current State and Challenges of Fairness in Federated Learning
    Vucinich, Sean
    Zhu, Qiang
    IEEE ACCESS, 2023, 11 : 80903 - 80914
  • [39] Enhancing Federated Learning Robustness Using Data-Agnostic Model Pruning
    Meng, Mark Huasong
    Teo, Sin G.
    Bai, Guangdong
    Wang, Kailong
    Dong, Jin Song
    ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2023, PT II, 2023, 13936 : 441 - 453
  • [40] Evaluating and Enhancing the Robustness of Federated Learning System against Realistic Data Corruption
    Yang, Chen
    Li, Yuanchun
    Lu, Hao
    Yuan, Jinliang
    Sun, Qibo
    Wang, Shangguang
    Xu, Mengwei
    2023 IEEE 34TH INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING, ISSRE, 2023, : 462 - 473