Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition

• URL: http://arxiv.org/abs/2307.11333v2
• Date: Mon, 4 Mar 2024 22:56:09 GMT
• Title: Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
• Authors: Faisal Hamman, Sanghamitra Dutta
• Abstract summary: This work presents an information-theoretic perspective to group fairness trade-offs in federated learning (FL) We identify three sources of unfairness in FL, namely, $textitUnique Disparity$, $textitRedundant Disparity$, and $textitMasked Disparity$. We derive fundamental limits on the trade-off between global and local fairness, highlighting where they agree or disagree.
• Score: 7.918307236588161
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work presents an information-theoretic perspective to group fairness trade-offs in federated learning (FL) with respect to sensitive attributes, such as gender, race, etc. Existing works often focus on either $\textit{global fairness}$ (overall disparity of the model across all clients) or $\textit{local fairness}$ (disparity of the model at each client), without always considering their trade-offs. There is a lack of understanding regarding the interplay between global and local fairness in FL, particularly under data heterogeneity, and if and when one implies the other. To address this gap, we leverage a body of work in information theory called partial information decomposition (PID), which first identifies three sources of unfairness in FL, namely, $\textit{Unique Disparity}$, $\textit{Redundant Disparity}$, and $\textit{Masked Disparity}$. We demonstrate how these three disparities contribute to global and local fairness using canonical examples. This decomposition helps us derive fundamental limits on the trade-off between global and local fairness, highlighting where they agree or disagree. We introduce the $\textit{Accuracy and Global-Local Fairness Optimality Problem (AGLFOP)}$, a convex optimization that defines the theoretical limits of accuracy and fairness trade-offs, identifying the best possible performance any FL strategy can attain given a dataset and client distribution. We also present experimental results on synthetic datasets and the ADULT dataset to support our theoretical findings.

Related papers

• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• GLOCALFAIR: Jointly Improving Global and Local Group Fairness in Federated Learning [8.77650197859131]
  Federated learning (FL) has emerged as a prospective solution for collaboratively learning a shared model across clients without sacrificing their data privacy. FL tends to be biased against certain demographic groups due to the inherent FL properties, such as data heterogeneity and party selection. We propose GFAIR, a client-server codesign that can improve global and local group fairness without the need for sensitive statistics about the client's private datasets.
  arXiv  Detail & Related papers  (2024-01-07T18:10:14Z)
• Multi-dimensional Fair Federated Learning [25.07463977553212]
  Federated learning (FL) has emerged as a promising collaborative and secure paradigm for training a model from decentralized data. Group fairness and client fairness are two dimensions of fairness that are important for FL. We propose a method, called mFairFL, to achieve group fairness and client fairness simultaneously.
  arXiv  Detail & Related papers  (2023-12-09T11:37:30Z)
• Rethinking Client Drift in Federated Learning: A Logit Perspective [125.35844582366441]
  Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection. We find that the difference in logits between the local and global models increases as the model is continuously updated. We propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models.
  arXiv  Detail & Related papers  (2023-08-20T04:41:01Z)
• Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach [72.19525160912943]
  We first theoretically demonstrate the inherent connection between distribution shift, data perturbation, and model weight perturbation. We then analyze the sufficient conditions to guarantee fairness for the target dataset. Motivated by these sufficient conditions, we propose robust fairness regularization (RFR)
  arXiv  Detail & Related papers  (2023-03-06T17:19:23Z)
• FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data [31.611582207768464]
  Federated learning (FL) allows agents to jointly train a global model without sharing their local data. We propose a formal FL fairness definition, fairness via agent-awareness (FAA), which takes different contributions of heterogeneous agents into account. We also propose a fair FL training algorithm based on agent clustering (FOCUS) to achieve fairness in FL measured by FAA.
  arXiv  Detail & Related papers  (2022-07-21T02:21:03Z)
• How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts [107.72786199113183]
  We propose a novel fairness learning method termed CUrvature MAtching (CUMA) CUMA achieves robust fairness generalizable to unseen domains with unknown distributional shifts. We evaluate our method on three popular fairness datasets.
  arXiv  Detail & Related papers  (2022-07-04T02:37:50Z)
• Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning [86.59588262014456]
  Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. We propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG) Our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD.
  arXiv  Detail & Related papers  (2022-03-17T11:18:17Z)
• Proportional Fairness in Federated Learning [27.086313029073683]
  PropFair is a novel and easy-to-implement algorithm for finding proportionally fair solutions in federated learning. We demonstrate that PropFair can approximately find PF solutions, and it achieves a good balance between the average performances of all clients and of the worst 10% clients.
  arXiv  Detail & Related papers  (2022-02-03T16:28:04Z)
• Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning [61.488646649045215]
  Federated learning (FL) is a promising strategy for performing privacy-preserving, distributed learning with a network of clients (i.e., edge devices)
  arXiv  Detail & Related papers  (2021-11-28T19:03:39Z)
• Preservation of the Global Knowledge by Not-True Self Knowledge Distillation in Federated Learning [8.474470736998136]
  In Federated Learning (FL), a strong global model is collaboratively learned by aggregating the clients' locally trained models. We observe that fitting on biased local distribution shifts the feature on global distribution and results in forgetting of global knowledge. We propose a simple yet effective framework Federated Local Self-Distillation (FedLSD), which utilizes the global knowledge on locally available data.
  arXiv  Detail & Related papers  (2021-06-06T11:51:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.