# Price of Stability in Quality-Aware Federated Learning

arXiv: https://arxiv.org/abs/2310.08790 · HTML: https://mlsanity.com/paper/2310.08790/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 13 Oct 2023.

## Builds on (most cited first, 7 of 7)

- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [FedCorr: Multi-Stage Federated Learning for Label Noise Correction](https://mlsanity.com/paper/2204.04677/) (2022)
- [Optimality and Stability in Federated Learning: A Game-theoretic Approach](https://mlsanity.com/paper/2106.09580/) (2021)
- [Enabling Long-Term Cooperation in Cross-Silo Federated Learning: A Repeated Game Perspective](https://mlsanity.com/paper/2106.11814/) (2021)
- [An Instance-Dependent Simulation Framework for Learning with Label Noise](https://mlsanity.com/paper/2107.11413/) (2021)
- [Quantifying the Impact of Label Noise on Federated Learning](https://mlsanity.com/paper/2211.07816/) (2022)

## Abstract (arXiv)

Federated Learning (FL) is a distributed machine learning scheme that enables clients to train a shared global model without exchanging local data. The presence of label noise can severely degrade the FL performance, and some existing studies have focused on algorithm design for label denoising. However, they ignored the important issue that clients may not apply costly label denoising strategies due to them being self-interested and having heterogeneous valuations on the FL performance. To fill this gap, we model the clients' interactions as a novel label denoising game and characterize its equilibrium. We also analyze the price of stability, which quantifies the difference in the system performance (e.g., global model accuracy, social welfare) between the equilibrium outcome and the socially optimal solution. We prove that the equilibrium outcome always leads to a lower global model accuracy than the socially optimal solution does. We further design an efficient algorithm to compute the socially optimal solution. Numerical experiments on MNIST dataset show that the price of stability increases as the clients' data become noisier, calling for an effective incentive mechanism.