The field of federated learning is moving towards addressing the challenges of data heterogeneity, privacy, and communication efficiency. Researchers are exploring innovative solutions such as federated distillation, subspace algorithms, and differential privacy to improve the performance and scalability of federated learning models. Notably, the development of frameworks like FLEET and PracMHBench is enabling more comprehensive evaluation and testing of federated learning algorithms. Furthermore, the application of federated learning to real-world problems like object detection in connected autonomous vehicles and human activity recognition is demonstrating its potential for practical impact. Some papers, such as 'Curriculum Guided Personalized Subgraph Federated Learning' and 'Sketched Gaussian Mechanism for Private Federated Learning', are particularly noteworthy for their innovative approaches to mitigating data heterogeneity and improving privacy guarantees.
Advances in Federated Learning
Sources
Centralized vs. Federated Learning for Educational Data Mining: A Comparative Study on Student Performance Prediction with SAEB Microdata
Curriculum Guided Personalized Subgraph Federated Learning
SmartFLow: A Communication-Efficient SDN Framework for Cross-Silo Federated Learning
FLEET: A Federated Learning Emulation and Evaluation Testbed for Holistic Research
Federated Survival Analysis with Node-Level Differential Privacy: Private Kaplan-Meier Curves
Fairness in Federated Learning: Trends, Challenges, and Opportunities
One-Shot Clustering for Federated Learning Under Clustering-Agnostic Assumption
Communication-Aware Knowledge Distillation for Federated LLM Fine-Tuning over Wireless Networks
Optimal Parallel Scheduling under Concave Speedup Functions
Enabling Federated Object Detection for Connected Autonomous Vehicles: A Deployment-Oriented Evaluation
Federated learning over physical channels: adaptive algorithms with near-optimal guarantees
Fair Resource Allocation for Fleet Intelligence
Warming Up for Zeroth-Order Federated Pre-Training with Low Resource Clients
FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity
Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights
An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data
GraMFedDHAR: Graph Based Multimodal Differentially Private Federated HAR
Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces
Optimization Methods and Software for Federated Learning
Sketched Gaussian Mechanism for Private Federated Learning
Strategies for Improving Communication Efficiency in Distributed and Federated Learning: Compression, Local Training, and Personalization
Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models
PracMHBench: Re-evaluating Model-Heterogeneous Federated Learning Based on Practical Edge Device Constraints