This survey aims to provide a structured perspective on the relationship between non-IID mitigation and fairness and support the development of more balanced and scalable FL systems under non-IID conditions.
Abstract
Federated learning (FL) is a promising approach for training distributed machine learning models while preserving clients’ data privacy. However, in real-world FL systems, data are often not independent and identically distributed (non-IID). This heterogeneity can slow convergence, degrade model performance, and increase client drift. To address these challenges, numerous methods have been proposed to mitigate non-IID data effects by optimizing client selection, local training, and model aggregation strategies. Despite their effectiveness in improving performance and efficiency, these methods rarely consider fairness across clients. Improving global accuracy does not guarantee balanced participation, influence, or outcomes, which may lead to biased model behavior across clients. In this survey, we review existing non-IID mitigation methods in FL from a fairness perspective and provide a systematic analysis of their implicit impact on client participation and influence. Unlike prior surveys that treat fairness as a separate research direction, this work analyzes how these methods designed for non-IID mitigation implicitly shape fairness outcomes across clients. Our taxonomy classifies existing methods into three categories—fairness-aware, semi-fairness-aware, and fairness-unaware—based on their design strategies for client selection and model aggregation. Using this taxonomy, we analyze the advantages, trade-offs, and limitations of each category and highlight that mitigating non-IID data does not guarantee fairness across clients. Finally, we identify open challenges and outline future directions, including system-level FL design that jointly considers non-IID mitigation and fairness and the development of standardized fairness evaluation metrics. Overall, this survey aims to provide a structured perspective on the relationship between non-IID mitigation and fairness and support the development of more balanced and scalable FL systems under non-IID conditions.
This study experimentally measures the impact of non-IID data, noisy data, and fairness in client selection on model accuracy and convergence, and proposes a privacy-preserving scoring method to assess each client's contribution in FL.
The results show that ML data selection can hurt model fairness in a non-negligible number of cases, and compromise model utility in more than half of the cases, and provide interesting research directions for utility- and fairness-aware ML data selection.
Nawel Benarba, Zeyang Kong, Sara Bouchenak· IEEE Access· 1 citation
FedFairLAB is introduced, a FL method that enforces group, intersectional, and multiclass fairness simultaneously at both the local and global levels and a tunable performance budget allows practitioners to control how much predictive performance can be sacrificed to improve fairness.
Michele Fontana, Francesca Naretto, A. Monreale· Data mining and knowledge di...· 0 citations
Participation in federated learning (FL) comes at a cost. Clients trade off privacy, communication, and compute costs for potentially greater gains in model efficacy. This paper explores this tradeoff under the aegis of individual rationality (IR) versus autarky, the basic game-theoretic requirement that the federation provide utility no worse than local training. Using the above as the design target, we examine pathwise performance of FL, as a per-round bound on cumulative surplus, not just as an asymptotic equilibrium guarantee under different models of client data distribution heterogeneity. Along this path, clients can remain below their local-training baseline for hundreds of rounds. The natural remedy is to cap each client's per-round contribution so that this shortfall stays bounded, and we prove that it backfires, collapsing learning even at low-to-modest heterogeneity. We then propose a novel design that combines short-term participation guarantees with personalized model evaluation, while maintaining fair incentives. We provide a theoretical basis for this new approach and empirically demonstrate that clients can avoid short-term losses without harming overall performance, even under moderate data distribution heterogeneity; under severe heterogeneity, the design shows promising outcomes for clients compared to their local baseline at some cost in accuracy.
Amin Meghrazi, Srinivasan Parthasarathy, A. Perrault· 0 citations
Accurate client contribution evaluation is critical for sustainable federated learning and incentive design, yet existing methods face a trade-off between trust, complexity, and robustness. We show that validation-free, similarity-based metrics can suffer from a federated noise coupling effect, where historical low-quality updates become entangled with the global trajectory, causing evaluation noise to accumulate and manifest as systematic bias across rounds. We propose D3em, a dual-layer dynamic debiasing mechanism built on a parallel local–federated dual-model training framework. D3em extracts a noise-decoupled independent value from the local branch and a collaborative value from the federated branch, and fuses them via a phase-aware weighting schedule to stabilize contribution scores throughout training. Experiments on CIFAR-10, Fashion-MNIST, and SST-5 under diverse heterogeneous partitions show that D3em improves global accuracy by 6.15 percentage points on average over representative baselines, and achieves an average fairness of 97.08% when coupled with incentive schemes. Meanwhile, D3em achieves comparable or even better end-to-end overhead in terms of total communication and total latency. The code is available at https://anonymous.4open.science/r/D_3AM-8A70
Federated Learning (FL) client selection faces significant challenges in real-world deployments due to label noise, Non-Independent and Identically Distributed (Non-IID) data, long-tailed class distributions, unreliable client participation, and fairness constraints. These challenges become even more pronounced in Web of Things networks, wherein highly dynamic, resource-constrained clients operate under variable data quality and generate noisy, imbalanced, and non-IID data. In such settings, reliability-based client selection may inadvertently discard valuable knowledge associated with underrepresented tail-classes when informative clients are treated as unreliable. Accordingly, we introduce ConTaFL, a contrastive and tail-aware FL client selection framework, that systematically addresses the aforementioned key challenges through coordinated mechanisms. ConTaFL employs (a) contrastive representation divergence to address long-tailed class distributions, (b) an uncertainty-guided reliability-based weighting to dynamically identify and select reliable clients, (c) adaptive noise-resilient distillation to mitigate the impact of noisy updates, and (d) client rehabilitation to enable previously excluded clients to rejoin training once they surpass the predefined reliability threshold, thereby promoting fair participation across clients. Extensive experiments on CIFAR-10, CIFAR-100, MNIST, and TON-IoT datasets demonstrate that ConTaFL consistently outperforms state-of-the-art FL frameworks across diverse noisy and non-IID settings while improving global model robustness and tail-class representation.
Fahmida Islam, Adnan Mahmood, Ying-Xun Wang et al.· IEEE Open Journal of the Com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
