Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Redefining Contributions: Shapley-Driven Federated Learning

About

Federated learning (FL) has emerged as a pivotal approach in machine learning, enabling multiple participants to collaboratively train a global model without sharing raw data. While FL finds applications in various domains such as healthcare and finance, it is challenging to ensure global model convergence when participants do not contribute equally and/or honestly. To overcome this challenge, principled mechanisms are required to evaluate the contributions made by individual participants in the FL setting. Existing solutions for contribution assessment rely on general accuracy evaluation, often failing to capture nuanced dynamics and class-specific influences. This paper proposes a novel contribution assessment method called ShapFed for fine-grained evaluation of participant contributions in FL. Our approach uses Shapley values from cooperative game theory to provide a granular understanding of class-specific influences. Based on ShapFed, we introduce a weighted aggregation method called ShapFed-WA, which outperforms conventional federated averaging, especially in class-imbalanced scenarios. Personalizing participant updates based on their contributions further enhances collaborative fairness by delivering differentiated models commensurate with the participant contributions. Experiments on CIFAR-10, Chest X-Ray, and Fed-ISIC2019 datasets demonstrate the effectiveness of our approach in improving utility, efficiency, and fairness in FL systems. The code can be found at https://github.com/tnurbek/shapfed.

Nurbek Tastan, Samar Fares, Toluwani Aremu, Samuel Horvath, Karthik Nandakumar• 2024

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-10
Accuracy82.12
875
Image ClassificationCIFAR-100
Accuracy41.83
357
Image ClassificationCIFAR-10 IID
Accuracy81.99
185
Image ClassificationCIFAR-100 IID
Accuracy40.39
47
Image ClassificationCIFAR-100 Step-Imbalance
Accuracy41.65
29
Image ClassificationCIFAR-10 Dirichlet alpha=0.1
Global Accuracy75.72
17
Image ClassificationFedISIC (Natural split)
Balanced Accuracy62.31
10
Client Contribution Estimation CorrelationCIFAR-10 Dirichlet (α = 0.01)
Average Pearson Correlation0.94
10
Client Contribution Estimation CorrelationFEMNIST (Natural split)
Average Pearson Correlation0.41
5
Client Contribution Estimation CorrelationFedISIC (Natural split)
Average Pearson Correlation0.92
5
Showing 10 of 40 rows

Other info

Follow for update