Advancements in Federated Learning

The field of federated learning is moving towards addressing the challenges of non-IID data, heterogeneity, and scalability. Recent developments have focused on proposing novel frameworks and algorithms that improve the performance and efficiency of federated learning models. Notably, advancements in areas such as graph condensation, dynamic contract design, and personalized learning have shown great promise. Additionally, researchers have explored the application of federated learning in various domains, including IoT management, healthcare, and cancer histopathology.

Noteworthy papers include Stratify, which introduces a novel FL framework designed to systematically manage class and feature distributions throughout training, and FedC4, which combines graph condensation with client-client collaboration to enable efficient and private federated graph learning. Other notable works, such as OPUS-VFL, UDJ-FL, and DP2FL, have made significant contributions to the field by addressing issues like privacy-utility tradeoffs, distributive justice, and personalized learning.

Overall, the field of federated learning is rapidly advancing, with a growing focus on developing innovative solutions to real-world problems. As researchers continue to push the boundaries of what is possible with federated learning, we can expect to see significant improvements in areas like model performance, communication efficiency, and privacy preservation.

Sources

Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling

FedC4: Graph Condensation Meets Client-Client Collaboration for Efficient and Private Federated Graph Learning

Diffusion-based Dynamic Contract for Federated AI Agent Construction in Mobile Metaverses

GENE-FL: Gene-Driven Parameter-Efficient Dynamic Federated Learning

Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data

Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directions

Achieving Distributive Justice in Federated Learning via Uncertainty Quantification

OPUS-VFL: Incentivizing Optimal Privacy-Utility Tradeoffs in Vertical Federated Learning

LLMs meet Federated Learning for Scalable and Secure IoT Management

DP2FL: Dual Prompt Personalized Federated Learning in Foundation Models

Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections

Efficient Data Valuation Approximation in Federated Learning: A Sampling-based Approach

Simplified Swarm Learning Framework for Robust and Scalable Diagnostic Services in Cancer Histopathology

Communication-Efficient Personalized Distributed Learning with Data and Node Heterogeneity

TACO: Tackling Over-correction in Federated Learning with Tailored Adaptive Correction

Decentralized Time Series Classification with ROCKET Features

Federated Learning: A Survey on Privacy-Preserving Collaborative Intelligence

Silenzio: Secure Non-Interactive Outsourced MLP Training