Distribution-Free Fair Federated Learning with Small Samples
- URL: http://arxiv.org/abs/2402.16158v1
- Date: Sun, 25 Feb 2024 17:37:53 GMT
- Title: Distribution-Free Fair Federated Learning with Small Samples
- Authors: Qichuan Yin, Junzhou Huang, Huaxiu Yao, Linjun Zhang
- Abstract summary: FedFaiREE is a post-processing algorithm developed specifically for distribution-free fair learning in decentralized settings with small samples.
We provide rigorous theoretical guarantees for both fairness and accuracy, and our experimental results further provide robust empirical validation for our proposed method.
- Score: 64.03051465062269
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: As federated learning gains increasing importance in real-world applications
due to its capacity for decentralized data training, addressing fairness
concerns across demographic groups becomes critically important. However, most
existing machine learning algorithms for ensuring fairness are designed for
centralized data environments and generally require large-sample and
distributional assumptions, underscoring the urgent need for fairness
techniques adapted for decentralized and heterogeneous systems with
finite-sample and distribution-free guarantees. To address this issue, this
paper introduces FedFaiREE, a post-processing algorithm developed specifically
for distribution-free fair learning in decentralized settings with small
samples. Our approach accounts for unique challenges in decentralized
environments, such as client heterogeneity, communication costs, and small
sample sizes. We provide rigorous theoretical guarantees for both fairness and
accuracy, and our experimental results further provide robust empirical
validation for our proposed method.
Related papers
- Certification of Distributional Individual Fairness [41.65399122566472]
We provide certificates for individual fairness (IF) of neural networks.
We show that our method allows us to certify neural networks that are several dozen larger than those considered by prior works.
arXiv Detail & Related papers (2023-11-20T16:41:54Z) - Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk
Minimization Framework [12.734559823650887]
In the presence of distribution shifts, fair machine learning models may behave unfairly on test data.
Existing algorithms require full access to data and cannot be used when small batches are used.
This paper proposes the first distributionally robust fairness framework with convergence guarantees that do not require knowledge of the causal graph.
arXiv Detail & Related papers (2023-09-20T23:25:28Z) - Mitigating Group Bias in Federated Learning: Beyond Local Fairness [0.6882042556551609]
We study the relationship between global model fairness and local model fairness.
We propose a globally fair training algorithm that directly minimizes the penalized empirical loss.
arXiv Detail & Related papers (2023-05-17T03:28:19Z) - 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) - Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated
Learning via Class-Imbalance Reduction [76.26710990597498]
We show that the class-imbalance of the grouped data from randomly selected clients can lead to significant performance degradation.
Based on our key observation, we design an efficient client sampling mechanism, i.e., Federated Class-balanced Sampling (Fed-CBS)
In particular, we propose a measure of class-imbalance and then employ homomorphic encryption to derive this measure in a privacy-preserving way.
arXiv Detail & Related papers (2022-09-30T05:42:56Z) - 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) - Certifying Some Distributional Fairness with Subpopulation Decomposition [20.009388617013986]
We first formulate the certified fairness of an ML model trained on a given data distribution as an optimization problem.
We then propose a general fairness certification framework and instantiate it for both sensitive shifting and general shifting scenarios.
Our framework is flexible to integrate additional non-skewness constraints and we show that it provides even tighter certification under different real-world scenarios.
arXiv Detail & Related papers (2022-05-31T01:17:50Z) - FairFed: Enabling Group Fairness in Federated Learning [22.913999279079878]
Federated learning has been viewed as a promising solution for learning machine learning models among multiple parties.
We propose FairFed, a novel algorithm to enhance group fairness via a fairness-aware aggregation method.
Our proposed method outperforms the state-of-the-art fair federated learning frameworks under a high heterogeneous sensitive attribute distribution.
arXiv Detail & Related papers (2021-10-02T17:55:20Z) - Decentralized Local Stochastic Extra-Gradient for Variational
Inequalities [125.62877849447729]
We consider distributed variational inequalities (VIs) on domains with the problem data that is heterogeneous (non-IID) and distributed across many devices.
We make a very general assumption on the computational network that covers the settings of fully decentralized calculations.
We theoretically analyze its convergence rate in the strongly-monotone, monotone, and non-monotone settings.
arXiv Detail & Related papers (2021-06-15T17:45:51Z) - Fair Densities via Boosting the Sufficient Statistics of Exponential
Families [72.34223801798422]
We introduce a boosting algorithm to pre-process data for fairness.
Our approach shifts towards better data fitting while still ensuring a minimal fairness guarantee.
Empirical results are present to display the quality of result on real-world data.
arXiv Detail & Related papers (2020-12-01T00:49:17Z)
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.