Federated Learning: Recent Advances and Future Directions
Lakshmi Indrani, Deepika Gadiraju, Vishnu Vardhan Baligodugula · 2025
This review examines federated learning as an innovative approach enabling distributed machine learning while preserving data privacy. We explore recent developments addressing four core challenges: data heterogeneity across participants, optimizing communication between devices, strengthening privacy protections, and accommodating diverse system capabilities. Our analysis identifies substantial algorithmic progress while highlighting persistent gaps in practical implementations across varied devices, balancing privacy with model performance, and expanding applications in vertical federated learning contexts. The survey concludes with strategic recommendations for overcoming these limitations and accelerating real-world adoption of federated learning techniques, particularly focusing on scalability across heterogeneous environments, enhanced privacy-utility balance, and improved cross-organizational implementations that could substantially expand federated learning's practical impact.