The field of federated learning is rapidly advancing, with a focus on developing innovative solutions for real-world applications. Recent research has explored the use of federated learning in various domains, including medicine, surveillance, and education. A key direction in this field is the development of robust and efficient federated learning algorithms that can handle non-IID data distributions, mitigate the effects of Byzantine attacks, and ensure privacy preservation. Noteworthy papers in this regard include FedERL, which proposes a novel data-agnostic robust training method for federated learning, and FLAegis, which introduces a two-stage defensive framework to identify Byzantine clients and improve the robustness of federated learning systems. Additionally, researchers are investigating the use of federated learning in emerging areas such as smart eyewear and open-set facial recognition. Overall, the field of federated learning is moving towards developing more practical and scalable solutions for real-world applications, with a focus on robustness, privacy, and efficiency.
Advances in Federated Learning for Real-World Applications
Sources
Straggler-Resilient Federated Learning over A Hybrid Conventional and Pinching Antenna Network
Machine Learning for Medicine Must Be Interpretable, Shareable, Reproducible and Accountable by Design
FedERL: Federated Efficient and Robust Learning for Common Corruptions
FedKLPR: Personalized Federated Learning for Person Re-Identification with Adaptive Pruning
Federated Reinforcement Learning for Runtime Optimization of AI Applications in Smart Eyewears
Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
Rethinking Federated Learning Over the Air: The Blessing of Scaling Up
FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning
Evaluating Federated Learning for At-Risk Student Prediction: A Comparative Analysis of Model Complexity and Data Balancing
Privacy-Preserving Federated Learning Framework for Risk-Based Adaptive Authentication
FLAegis: A Two-Layer Defense Framework for Federated Learning Against Poisoning Attacks
Enhancing Model Privacy in Federated Learning with Random Masking and Quantization
Tackling Federated Unlearning as a Parameter Estimation Problem
Sistema de Reconocimiento Facial Federado en Conjuntos Abiertos basado en OpenMax
WEBEYETRACK: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization
Federated Learning for Large Models in Medical Imaging: A Comprehensive Review