Comprehensive and Extensible Federated Learning Framework: Advances in APPFL
APPFL is a comprehensive and extensible federated learning framework that offers solutions to key challenges in federated learning, including heterogeneity and security, and provides user-friendly interfaces for integrating new algorithms and adapting to diverse applications.
FLEX: A Flexible Federated Learning Framework for Customizable Experiments and Novel Technique Development
FLEX is a flexible federated learning framework that empowers researchers to customize data distribution, privacy parameters, and communication strategies, enabling the development of novel federated learning techniques.
FedSN: A Novel Federated Learning Framework over LEO Satellite Networks
FedSN proposes a novel federated learning framework to address challenges in training models over LEO satellite networks.
ASYN2F: An Asynchronous Federated Learning Framework with Bidirectional Model Aggregation
ASYN2F is an effective asynchronous federated learning framework with bidirectional model aggregation, achieving higher performance compared to existing techniques.
Federated Learning via Lattice Joint Source-Channel Coding: A Comprehensive Study
새로운 합동 소스-채널 코딩 방식을 사용하여 무선 통신을 통한 연산을 가능케 하는 보편적인 연합 학습 프레임워크를 소개합니다.
FL-GUARD: A Holistic Framework for Run-Time Detection and Recovery of Negative Federated Learning
FL-GUARD introduces a dynamic solution for detecting and recovering from Negative Federated Learning in real-time, outperforming previous approaches.
ASYN2F: An Asynchronous Federated Learning Framework with Bidirectional Model Aggregation
ASYN2F is an effective asynchronous federated learning framework that outperforms existing techniques in terms of performance and convergence speed.
FAX: Scalable and Differentiable Federated Primitives in JAX
FAX introduces a JAX-based library for large-scale distributed and federated computations, leveraging sharding mechanisms and automatic differentiation to simplify the expression of federated computations. The main thesis of the author is to provide a performant and scalable framework for federated computations in the data center by embedding building blocks as primitives in JAX.
FEDLOGE: Joint Local and Generic Federated Learning under Long-Tailed Data
The author introduces FedLoGe, a framework that enhances both local and generic model performance in the context of Federated Long-Tailed Learning by integrating representation learning and classifier alignment within a neural collapse framework.
FL-GUARD: A Holistic Framework for Run-Time Detection and Recovery of Negative Federated Learning
The author introduces FL-GUARD, a dynamic solution for tackling Negative Federated Learning in run-time, ensuring recovery only when necessary. The framework outperforms previous approaches by detecting NFL quickly and efficiently.
© 2024 by Linnk AI