Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges

Abstract

In recent years, Federated Learning (FL) has gained relevance in training collaborative models without sharing sensitive data. Since its birth, Centralized FL (CFL) has been the most common approach in the literature, where a central entity creates a global model. However, a centralized approach leads to increased latency due to bottlenecks, heightened vulnerability to system failures, and trustworthiness concerns affecting the entity responsible for the global model creation. Decentralized Federated Learning (DFL) emerged to address these concerns by promoting decentralized model aggregation and minimizing reliance on centralized architectures. However, despite the work done in DFL, the literature has not (i) studied the main aspects differentiating DFL and CFL; (ii) analyzed DFL frameworks to create and evaluate new solutions; and (iii) reviewed application scenarios using DFL. Thus, this article identifies and analyzes the main fundamentals of DFL in terms of federation architectures, topologies, communication mechanisms, security approaches, and key performance indicators. Additionally, the paper at hand explores existing mechanisms to optimize critical DFL fundamentals. Then, the most relevant features of the current DFL frameworks are reviewed and compared. After that, it analyzes the most used DFL application scenarios, identifying solutions based on the fundamentals and frameworks previously defined. Finally, the evolution of existing DFL solutions is studied to provide a list of trends, lessons learned, and open challenges.

References in corpus (39)

• Distilling the Knowledge in a Neural Network
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Federated Learning for Internet of Things: A Comprehensive Survey
• FedKD: Communication Efficient Federated Learning via Knowledge Distillation
• EMNIST: an extension of MNIST to handwritten letters
• Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
• BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning
• Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
• Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems
• Decentralized Federated Learning through Proxy Model Sharing
• FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measure
• A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guarantee
• Decentralized Federated Learning via Mutual Knowledge Transfer
• Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey
• Asynchronous Decentralized Federated Learning for Collaborative Fault Diagnosis of PV Stations
• Throughput-Optimal Topology Design for Cross-Silo Federated Learning
• DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training
• Confederated Learning: Federated Learning with Decentralized Edge Servers
• Federated Knowledge Distillation
• PEPPER: Empowering User-Centric Recommender Systems over Gossip Learning
• A Systematic Literature Review on Blockchain Enabled Federated Learning Framework for Internet of Vehicles
• Wireless Ad Hoc Federated Learning: A Fully Distributed Cooperative Machine Learning
• DACFL: Dynamic Average Consensus Based Federated Learning in Decentralized Topology
• Beyond spectral gap: The role of the topology in decentralized learning
• Improving the Model Consistency of Decentralized Federated Learning
• Decentralized Quantum Federated Learning for Metaverse: Analysis, Design and Implementation
• Decentralized Zero-Trust Framework for Digital Twin-based 6G
• P4L: Privacy Preserving Peer-to-Peer Learning for Infrastructureless Setups
• Jointly Learning from Decentralized (Federated) and Centralized Data to Mitigate Distribution Shift
• FederatedTrust: A Solution for Trustworthy Federated Learning
• Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario
• Decentralized Model Dissemination Empowered Federated Learning in mmWave Aerial-Terrestrial Integrated Networks
• Scatterbrained: A flexible and expandable pattern for decentralized machine learning
• Towards Decentralized Predictive Quality of Service in Next-Generation Vehicular Networks
• Towards More Suitable Personalization in Federated Learning via Decentralized Partial Model Training
• Efficient Fully Distributed Federated Learning with Adaptive Local Links
• TemporalFED: Detecting Cyberattacks in Industrial Time-Series Data Using Decentralized Federated Learning
• Mitigating Communications Threats in Decentralized Federated Learning through Moving Target Defense
• DeFL: Decentralized Weight Aggregation for Cross-silo Federated Learning

Cited by in corpus (27)

• Fedstellar: A Platform for Decentralized Federated Learning
• Privacy-Preserving in Blockchain-based Federated Learning Systems
• Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning
• Federated learning in food research
• Energy Efficiency in Network Slicing: Survey and Taxonomy
• Combining Federated Learning and Control: A Survey
• Enhancing Scalability and Reliability in Semi-Decentralized Federated Learning With Blockchain: Trust Penalization and Asynchronous Functionality
• Scalability and Performance Evaluation of Federated Learning Frameworks: A Comparative Analysis
• DeRelayL: Sustainable Decentralized Relay Learning
• Noiseless Privacy-Preserving Decentralized Learning
• Centralized vs Decentralized Federated Learning: A trade-off performance analysis
• TDML -- A Trustworthy Distributed Machine Learning Framework
• Unified Analysis of Decentralized Gradient Descent: a Contraction Mapping Framework
• Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulator
• Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning
• Boosting Asynchronous Decentralized Learning with Model Fragmentation
• Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimization
• Integrating Identity-Based Identification against Adaptive Adversaries in Federated Learning
• Federated Clustering: An Unsupervised Cluster-Wise Training for Decentralized Data Distributions
• De-DSI: Decentralised Differentiable Search Index
• Fair Decentralized Learning
• FedA2L: Adaptive layer-wise learning rate adjustment in decentralized federated learning
• On Asynchronous Multiparty Session Types for Federated Learning
• CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection
• FedDPG: An Adaptive Yet Efficient Prompt-tuning Approach in Federated Learning Settings
• Evaluation Framework for Centralized and Decentralized Aggregation Algorithm in Federated Systems
• Trust-Based Incentive Mechanisms in Semi-Decentralized Federated Learning Systems