aiqbench analysis
This survey bridges a critical gap in Federated Learning by explicitly linking data properties, split protocols, and defense mechanisms to model convergence speed and stability. It provides actionable insights for practitioners by ranking the impact of non-IID data traits and exposing artifacts introduced by experimental splitting practices. Ultimately, the work clarifies the trade-offs between convergence robustness and security, offering a data-centric framework for designing more predictable FL systems.
From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning
arXiv:2606.10595v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as a promising solution for data hunger in centralized learning. This paradigm enables privacy with multiple clients to train a shared-task model collaboratively without exposing their local data. While being a key component in any learning system, data is also a primary source of vulnerabilities and challenges, and a major determinant of a stable and well-converged training. Existing FL reviews describe general foundations, security practices, opportunities, challenges, and applications, without delving into diverse aspects of data and considering problems from the data perspective. They rarely provide a data-lens synthesis that links concrete data properties, split protocols, and defenses to convergence speed and stability. This survey fills that gap with three advances. First, we analyze non-IID into measurable traits and rank their influence on convergence as strong, medium, or light, explaining the mechanisms behind each and reconciling evidence across images, texts, and graphs. Second, we connect experimental splitting practices to the real phenomena they emulate, expose the artifacts they introduce, and show how those artifacts affect target accuracy. Third, we analyze how data-related vulnerabilities and their proposed defenses affect convergence, reporting performance under clean and adversarial conditions to make the convergence-robustness trade-off explicit. To our knowledge, this is the first survey to provide a complete understanding of data-related challenges that govern FL. With clear takeaways distilled for each concern, our work serves as actionable guidance, helping practitioners design their system with predictable convergence and stability.
Abstract:Federated Learning (FL) has emerged as a promising solution for data hunger in centralized learning. This paradigm enables privacy with multiple clients to train a shared-task model collaboratively without exposing their local data. While being a key component in any learning system, data is also a primary source of vulnerabilities and challenges, and a major determinant of a stable and well-converged training. Existing FL reviews describe general foundations, security practices, opportunities, challenges, and applications, without delving into diverse aspects of data and considering problems from the data perspective. They rarely provide a data-lens synthesis that links concrete data properties, split protocols, and defenses to convergence speed and stability. This survey fills that gap with three advances. First, we analyze non-IID into measurable traits and rank their influence on convergence as strong, medium, or light, explaining the mechanisms behind each and reconciling evidence across images, texts, and graphs. Second, we connect experimental splitting practices to the real phenomena they emulate, expose the artifacts they introduce, and show how those artifacts affect target accuracy. Third, we analyze how data-related vulnerabilities and their proposed defenses affect convergence, reporting performance under clean and adversarial conditions to make the convergence-robustness trade-off explicit. To our knowledge, this is the first survey to provide a complete understanding of data-related challenges that govern FL. With clear takeaways distilled for each concern, our work serves as actionable guidance, helping practitioners design their system with predictable convergence and stability.
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
arXiv:2606.10595 [cs.CR]
(or arXiv:2606.10595v1 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2606.10595 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 337 words
Related coverage
Convergence Analysis of Sequential Federated Learning on Heterogeneous Data
arXiv · Sep 15, 2026
FedCSGA: Client Selection Based on Genetic Algorithm for Federated Learning
arXiv · Nov 4, 2026
Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning
arXiv · Jun 16, 2026
Gradient Heterogeneity Complements Hessian Heterogeneity in Transformer Optimization
arXiv · Aug 20, 2026