Network EM Algorithms for Gaussian Mixture Models in Decentralized Federated Learning: Addressing Heterogeneity and Poor Separation
This research paper introduces novel network Expectation-Maximization (EM) algorithms to address the challenges of fitting Gaussian Mixture Models (GMMs) in decentralized federated learning, particularly focusing on handling heterogeneous data and poorly-separated Gaussian components.
OledFL: Enhancing Decentralized Federated Learning Performance Through Opposite Lookahead Enhancement
OledFL, a novel approach using an opposite lookahead enhancement technique, significantly improves the convergence speed and generalization performance of decentralized federated learning (DFL) by addressing client inconsistency.
Decentralized Federated Learning using Game Theory in Dynamic Networks: The pFedGame Algorithm
pFedGame, a novel decentralized federated learning algorithm, leverages game theory to achieve efficient model aggregation in dynamic network environments, addressing challenges like data heterogeneity and the absence of a central server.
Decentralized Federated Learning: A Comprehensive Survey and Perspective
Decentralized federated learning (DFL) is an emerging framework that eliminates the need for a central server, enabling direct communication and knowledge sharing among clients to improve privacy, efficiency, and resource utilization.
Optimizing Decentralized Federated Learning in Energy and Latency Constrained Wireless Networks
The core message of this paper is to propose an adaptive decentralized federated learning (DFL) framework that optimizes the number of local training rounds across diverse devices with varying resource budgets, in order to enhance the model performance while considering energy and latency constraints.
OCD-FL: A Novel Communication-Efficient Peer Selection-based Decentralized Federated Learning
分散フェデレーテッドラーニングにおける効率的な通信を重視した新しいピア選択ベースのOCD-FLの提案とその効果的な実装。
Decentralized Federated Learning with Blockchain for Secure Model Verification
The author argues that Blockchain-based Decentralized Federated Learning (BDFL) enhances model verification and trustworthiness in decentralized machine learning systems by leveraging a blockchain infrastructure.
OCD-FL: Opportunistic Communication-Efficient Decentralized Federated Learning
The author proposes OCD-FL as a novel scheme for decentralized federated learning, focusing on communication efficiency and energy consumption reduction.
© 2024 by Linnk AI