# Fairness in Federated Learning via Core-Stability

arXiv: https://arxiv.org/abs/2211.02091 · HTML: https://mlsanity.com/paper/2211.02091/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 3 Nov 2022.

## Builds on (most cited first, 16 of 16)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Fair Resource Allocation in Federated Learning](https://mlsanity.com/paper/1905.10497/) (2019)
- [Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment](https://mlsanity.com/paper/1610.08452/) (2016)
- [Fairness-aware Agnostic Federated Learning](https://mlsanity.com/paper/2010.05057/) (2020)
- [An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee](https://mlsanity.com/paper/2011.01783/) (2020)
- [Federated learning with class imbalance reduction](https://mlsanity.com/paper/2011.11266/) (2020)
- [Optimality and Stability in Federated Learning: A Game-theoretic Approach](https://mlsanity.com/paper/2106.09580/) (2021)
- [Improving Fairness via Federated Learning](https://mlsanity.com/paper/2110.15545/) (2021)
- [Almost Envy-Freeness with General Valuations](https://mlsanity.com/paper/1707.04769/) (2017)
- [Fair Allocation of Indivisible Public Goods](https://mlsanity.com/paper/1805.03164/) (2018)
- [Unified Group Fairness on Federated Learning](https://mlsanity.com/paper/2111.04986/) (2021)
- [Federating for Learning Group Fair Models](https://mlsanity.com/paper/2110.01999/) (2021)
- [Justifications of Welfare Guarantees under Normalized Utilities](https://mlsanity.com/paper/1905.10774/) (2019)

## Built on by (most cited first, 23 of 23)

- [Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity](https://mlsanity.com/paper/2405.16585/) (2024)
- [COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits](https://mlsanity.com/paper/2403.11348/) (2024)
- [Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning](https://mlsanity.com/paper/2410.19321/) (2024)
- [S2FGL: Spatial Spectral Federated Graph Learning](https://mlsanity.com/paper/2507.02409/) (2025)
- [Proportional Fairness in Non-Centroid Clustering](https://mlsanity.com/paper/2410.23273/) (2024)
- [FedFair^3: Unlocking Threefold Fairness in Federated Learning](https://mlsanity.com/paper/2401.16350/) (2024)
- [Entropy-driven Fair and Effective Federated Learning](https://mlsanity.com/paper/2301.12407/) (2023)
- [FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants](https://mlsanity.com/paper/2312.11391/) (2023)
- [Achieving Distributive Justice in Federated Learning via Uncertainty Quantification](https://mlsanity.com/paper/2504.15924/) (2025)
- [Efficient Core-selecting Incentive Mechanism for Data Sharing in Federated Learning](https://mlsanity.com/paper/2309.11722/) (2023)
- [A Note on Bias to Complete](https://mlsanity.com/paper/2402.11710/) (2024)
- [Prediction-sharing During Training and Inference](https://mlsanity.com/paper/2403.17515/) (2024)
- [Harm Ratio: A Novel and Versatile Fairness Criterion](https://mlsanity.com/paper/2410.02977/) (2024)
- [Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners](https://mlsanity.com/paper/2505.12010/) (2025)
- [Cooperative Game-Theoretic Credit Assignment for Multi-Agent Policy Gradients via the Core](https://mlsanity.com/paper/2506.04265/) (2025)
- [Fair Transit Stop Placement: A Clustering Perspective and Beyond](https://mlsanity.com/paper/2602.06776/) (2026)
- [Data Quality in Edge Machine Learning: A State-of-the-Art Survey](https://mlsanity.com/paper/2406.02600/) (2024)
- [Local K-Similarity Constraint for Federated Learning with Label Noise](https://mlsanity.com/paper/2511.06169/) (2025)
- [Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning](https://mlsanity.com/paper/2512.24959/) (2025)
- [Cumulative Utility Parity for Fair Federated Learning under Intermittent Client Participation](https://mlsanity.com/paper/2602.13651/) (2026)
- [Stable and Budget-Feasible Coalition Formation for Clustered Federated Learning: A Hedonic Potential-Game Approach](https://mlsanity.com/paper/2607.26788/) (2026)
- [Federated Agent Optimization](https://mlsanity.com/paper/2610.01195/) (2026)
- [FUSE: Fairness-aware Update Screening against Byzantine Exploitation in q-Fair Federated Learning](https://mlsanity.com/paper/2610.20264/) (2026)

## Abstract (arXiv)

Federated learning provides an effective paradigm to jointly optimize a model benefited from rich distributed data while protecting data privacy. Nonetheless, the heterogeneity nature of distributed data makes it challenging to define and ensure fairness among local agents. For instance, it is intuitively "unfair" for agents with data of high quality to sacrifice their performance due to other agents with low quality data. Currently popular egalitarian and weighted equity-based fairness measures suffer from the aforementioned pitfall. In this work, we aim to formally represent this problem and address these fairness issues using concepts from co-operative game theory and social choice theory. We model the task of learning a shared predictor in the federated setting as a fair public decision making problem, and then define the notion of core-stable fairness: Given N agents, there is no subset of agents S that can benefit significantly by forming a coalition among themselves based on their utilities UN and US (i.e., frac|S|N US ≥ UN). Core-stable predictors are robust to low quality local data from some agents, and additionally they satisfy Proportionality and Pareto-optimality, two well sought-after fairness and efficiency notions within social choice. We then propose an efficient federated learning protocol CoreFed to optimize a core stable predictor. CoreFed determines a core-stable predictor when the loss functions of the agents are convex. CoreFed also determines approximate core-stable predictors when the loss functions are not convex, like smooth neural networks. We further show the existence of core-stable predictors in more general settings using Kakutani's fixed point theorem. Finally, we empirically validate our analysis on two real-world datasets, and we show that CoreFed achieves higher core-stability fairness than FedAvg while having similar accuracy.