# Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation

arXiv: https://arxiv.org/abs/2605.18020 · HTML: https://mlsanity.com/paper/2605.18020/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs](https://mlsanity.com/paper/1802.10026/) (2018)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [Federated Learning with Buffered Asynchronous Aggregation](https://mlsanity.com/paper/2106.06639/) (2021)
- [A Rewriting System for Convex Optimization Problems](https://mlsanity.com/paper/1709.04494/) (2017)
- [A Principled Approach to Data Valuation for Federated Learning](https://mlsanity.com/paper/2009.06192/) (2020)
- [FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning](https://mlsanity.com/paper/2207.14130/) (2022)
- [Motivating Workers in Federated Learning: A Stackelberg Game Perspective](https://mlsanity.com/paper/1908.03092/) (2019)
- [Mechanisms that Incentivize Data Sharing in Federated Learning](https://mlsanity.com/paper/2207.04557/) (2022)
- [A Comprehensive Survey of Incentive Mechanism for Federated Learning](https://mlsanity.com/paper/2106.15406/) (2021)
- [Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation](https://mlsanity.com/paper/2304.07981/) (2023)
- [Incentivizing Federated Learning](https://mlsanity.com/paper/2205.10951/) (2022)
- [Pursuing Overall Welfare in Federated Learning through Sequential Decision Making](https://mlsanity.com/paper/2405.20821/) (2024)
- [DaringFed: A Dynamic Bayesian Persuasion Pricing for Online Federated Learning under Two-sided Incomplete Information](https://mlsanity.com/paper/2505.05842/) (2025)

## Abstract (arXiv)

Federated Learning (FL) algorithms implicitly assume that clients passively comply with server-side orchestration by sharing local model updates upon server request. However, this overlooks an important aspect in real-world cross-silo environments: clients are often rational agents who may prioritize their utilities such as local model performance over that of the global model. In settings with significant statistical heterogeneity, rational clients may opt out of the federation if the perceived benefits of collaboration fail to meet their local utility thresholds. Such attrition degrades the global model performance and can lead to the collapse of the federated training process. In this work, we introduce FedUCA, (Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation), a framework that formalizes the server's role as an optimizer seeking to maximize global model performance by sustaining client participation. We substantiate our framework through extensive experiments on standard datasets demonstrating that by prioritizing participation feasibility, FedUCA achieves significantly higher client retention and, consequently, a superior global model performance.