The field of federated learning is rapidly advancing, with a focus on addressing the challenges of privacy, security, and scalability in various applications, including air quality monitoring and medical imaging. Recent developments have led to the creation of more efficient and secure federated learning algorithms, such as those utilizing homomorphic encryption and foundation models. These advancements have the potential to improve the accuracy and reliability of air quality monitoring and medical image classification, while maintaining the privacy and security of sensitive data. Noteworthy papers in this area include 'Improving Efficiency in Federated Learning with Optimized Homomorphic Encryption', which introduces a novel algorithm to address the inefficiency problem of homomorphic encryption, and 'FAST: Federated Active Learning with Foundation Models', which substantially reduces the overhead incurred by iterative active sampling. Overall, the field of federated learning is moving towards more efficient, secure, and scalable solutions, with significant implications for various applications.
Federated Learning for Air Quality Monitoring and Medical Imaging
Sources
Enhancing Air Quality Monitoring: A Brief Review of Federated Learning Advances
Improving Efficiency in Federated Learning with Optimized Homomorphic Encryption
FAST: Federated Active Learning with Foundation Models for Communication-efficient Sampling and Training
Secure Federated XGBoost with CUDA-accelerated Homomorphic Encryption via NVIDIA FLARE
Scaling Federated Learning Solutions with Kubernetes for Synthesizing Histopathology Images
Infinitely Divisible Noise for Differential Privacy: Nearly Optimal Error in the High $\varepsilon$ Regime
Federated Learning for Medical Image Classification: A Comprehensive Benchmark
Technical Report: Full Version of Analyzing and Optimizing Perturbation of DP-SGD Geometrically
Reliability Assessment of Low-Cost PM Sensors under High Humidity and High PM Level Outdoor Conditions