The field of federated learning and edge computing is rapidly advancing, with a focus on improving efficiency, privacy, and scalability. Recent developments have led to the creation of novel frameworks and algorithms that enable more effective collaboration between edge devices and centralized servers. One of the key trends is the integration of federated learning with other techniques, such as contrastive learning and domain generalization, to enhance model performance and robustness. Additionally, there is a growing interest in decentralized and peer-to-peer approaches, which aim to reduce the reliance on centralized servers and improve the overall resilience of the system. Noteworthy papers in this area include 'Learning Like Humans: Resource-Efficient Federated Fine-Tuning through Cognitive Developmental Stages', which introduces a novel approach to federated fine-tuning inspired by human learning, and 'HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation', which proposes a hierarchical framework for federated domain generalization. Overall, the field is moving towards more efficient, private, and scalable solutions that can be applied to a wide range of applications, from recommendation systems to intelligent transportation systems.
Advancements in Federated Learning and Edge Computing
Sources
Learning Like Humans: Resource-Efficient Federated Fine-Tuning through Cognitive Developmental Stages
Privacy-Preserving Driver Drowsiness Detection with Spatial Self-Attention and Federated Learning
Integrated user scheduling and beam steering in over-the-air federated learning for mobile IoT
Joint Association and Phase Shifts Design for UAV-mounted Stacked Intelligent Metasurfaces-assisted Communications
Low-Communication Resilient Distributed Estimation Algorithm Based on Memory Mechanism
Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment
On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach
Energy-efficient Federated Learning for UAV Communications
FedPromo: Federated Lightweight Proxy Models at the Edge Bring New Domains to Foundation Models
Decoupled Contrastive Learning for Federated Learning
FeDaL: Federated Dataset Learning for Time Series Foundation Models
FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutions
Channel-Independent Federated Traffic Prediction
Edge-assisted Parallel Uncertain Skyline Processing for Low-latency IoE Analysis
Edge-Assisted Collaborative Fine-Tuning for Multi-User Personalized Artificial Intelligence Generated Content (AIGC)
HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation
pFedDSH: Enabling Knowledge Transfer in Personalized Federated Learning through Data-free Sub-Hypernetwork
Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learning
Federated Multi-Objective Learning with Controlled Pareto Frontiers
X-VFL: A New Vertical Federated Learning Framework with Cross Completion and Decision Subspace Alignment