Towards One-shot Federated Learning: Advances, Challenges, and Future Directions

2025-05-05

AI Summary

Traditional federated learning (FL) suffers from high multi-round communication overhead and poor generalization and scalability under resource-constrained, privacy-sensitive settings with non-IID data. To address these challenges, this paper proposes the first systematic one-shot FL framework. Our method introduces a client-adaptive initialization strategy tailored to heterogeneous data distributions and a robust single-round weighted/adaptively aggregated mechanism, integrating distribution modeling and bias correction. Evaluated across multiple non-IID benchmarks, our approach achieves over 85% global accuracy with only one communication round—reducing communication overhead by more than 90% compared to standard FL. It significantly improves training efficiency, model generalization, and scalability while preserving privacy. This work establishes a practical, lightweight collaborative training paradigm for edge intelligence and privacy-preserving AI.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Multiagent Systems: Multiagent Learning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

One-shot FL enables collaborative training in a single round, eliminating the need for iterative communication, making it particularly suitable for use in resource-constrained and privacy-sensitive applications. This survey offers a thorough examination of One-shot FL, highlighting its distinct operational framework compared to traditional federated approaches. One-shot FL supports resource-limited devices by enabling single-round model aggregation while maintaining data locality. The survey systematically categorizes existing methodologies, emphasizing advancements in client model initialization, aggregation techniques, and strategies for managing heterogeneous data distributions. Furthermore, we analyze the limitations of current approaches, particularly in terms of scalability and generalization in non-IID settings. By analyzing cutting-edge techniques and outlining open challenges, this survey aspires to provide a comprehensive reference for researchers and practitioners aiming to design and implement One-shot FL systems, advancing the development and adoption of One-shot FL solutions in a real-world, resource-constrained scenario.

Problem

• Enabling single-round collaborative training for resource-constrained applications
• Addressing challenges in client model initialization and data heterogeneity
• Improving scalability and generalization in non-IID federated learning settings

Innovation

• Single-round model aggregation for efficiency
• Advanced client initialization and aggregation methods
• Handling non-IID data with novel strategies