The recent advancements in federated learning (FL) have significantly enhanced the field's ability to handle privacy-preserving, decentralized machine learning tasks. A notable trend is the integration of advanced techniques such as prompt learning, evidential deep learning, and optimal transport to address data heterogeneity and improve model generalization across diverse clients. These innovations are particularly impactful in healthcare and smart grid applications, where personalized models are crucial. Additionally, the robustness of FL frameworks against Byzantine attacks and backdoor threats has been substantially improved, ensuring secure model training in adversarial environments. Noteworthy papers include 'Evidential Federated Learning for Skin Lesion Image Classification,' which introduces a novel approach to privacy-preserving knowledge sharing, and 'DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning,' which offers a scalable solution to protect against sophisticated backdoor threats.
Enhancing Privacy and Security in Decentralized Machine Learning
Sources
A Survey of Machine Learning-based Physical-Layer Authentication in Wireless Communications
Federated Domain Generalization via Prompt Learning and Aggregation
Evidential Federated Learning for Skin Lesion Image Classification
Embedding Byzantine Fault Tolerance into Federated Learning via Virtual Data-Driven Consistency Scoring Plugin
Framework for Co-distillation Driven Federated Learning to Address Class Imbalance in Healthcare
FedAli: Personalized Federated Learning with Aligned Prototypes through Optimal Transport
Electrical Load Forecasting in Smart Grid: A Personalized Federated Learning Approach
How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution
Toward Personalized Federated Node Classification in One-shot Communication
FedCoLLM: A Parameter-Efficient Federated Co-tuning Framework for Large and Small Language Models
Freezing of Gait Detection Using Gramian Angular Fields and Federated Learning from Wearable Sensors
F$^3$OCUS -- Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics
Non-IID data in Federated Learning: A Systematic Review with Taxonomy, Metrics, Methods, Frameworks and Future Directions
Hyper-parameter Optimization for Federated Learning with Step-wise Adaptive Mechanism
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning
Attribute Inference Attacks for Federated Regression Tasks
FedRAV: Hierarchically Federated Region-Learning for Traffic Object Classification of Autonomous Vehicles
REFOL: Resource-Efficient Federated Online Learning for Traffic Flow Forecasting
Towards Adaptive Asynchronous Federated Learning for Human Activity Recognition