Federated Learning: Challenges, Methods, and Future Directions

Abstract

Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.

References in corpus (2)

• Federated Learning: Strategies for Improving Communication Efficiency
• Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge

Cited by in corpus (250)

• The Future of Digital Health with Federated Learning
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Towards Personalized Federated Learning
• Robust Aggregation for Federated Learning
• Edge Learning for B5G Networks with Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing
• Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges
• From Distributed Machine Learning to Federated Learning: A Survey
• A Secure Federated Learning Framework for 5G Networks
• UVeQFed: Universal Vector Quantization for Federated Learning
• Wind Power Forecasting Considering Data Privacy Protection: A Federated Deep Reinforcement Learning Approach
• Machine Learning for Microcontroller-Class Hardware: A Review
• Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach
• Over-the-Air Federated Learning from Heterogeneous Data
• Federated Neural Collaborative Filtering
• Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges
• Five Facets of 6G: Research Challenges and Opportunities
• FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data
• Clinical Concept Extraction: a Methodology Review
• The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining
• Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
• Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging
• Federated Learning: A Signal Processing Perspective
• Decentralized Federated Learning: A Survey on Security and Privacy
• A Systematic Literature Review on Federated Machine Learning: From A Software Engineering Perspective
• Blockchain-based Federated Learning with Secure Aggregation in Trusted Execution Environment for Internet-of-Things
• Analysis and Optimal Edge Assignment For Hierarchical Federated Learning on Non-IID Data
• Towards Fairness-Aware Federated Learning
• Privacy-preserving Federated Learning for Residential Short Term Load Forecasting
• FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measure
• Decentralized Federated Learning via Mutual Knowledge Transfer
• Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation
• Fusion of Probability Density Functions
• Flexible Clustered Federated Learning for Client-Level Data Distribution Shift
• Federated Learning for Computationally-Constrained Heterogeneous Devices: A Survey
• Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey
• Trustworthy Graph Neural Networks: Aspects, Methods and Trends
• FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumonia
• Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning
• Federated learning: Applications, challenges and future directions
• FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
• Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
• AI Ethics Principles in Practice: Perspectives of Designers and Developers
• Soft-Label Dataset Distillation and Text Dataset Distillation
• Performance Optimization for Federated Person Re-identification via Benchmark Analysis
• 6G: The Intelligent Network of Everything
• An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning
• Federated Learning with Spiking Neural Networks
• A Survey on Reinforcement Learning for Recommender Systems
• Concept drift detection and adaptation for federated and continual learning
• Enabling hand gesture customization on wrist-worn devices
• AI Security for Geoscience and Remote Sensing: Challenges and Future Trends
• Joint Optimization of Communications and Federated Learning Over the Air
• Privacy-Preserving in Blockchain-based Federated Learning Systems
• A review of federated learning in renewable energy applications: Potential, challenges, and future directions
• Active Learning in Robotics: A Review of Control Principles
• Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions
• Federated Learning over Energy Harvesting Wireless Networks
• Study of the performance and scalability of federated learning for medical imaging with intermittent clients
• FedStack: Personalized activity monitoring using stacked federated learning
• FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems
• Joint Privacy Enhancement and Quantization in Federated Learning
• 5G Multi-access Edge Computing: a Survey on Security, Dependability, and Performance
• Towards Federated Learning against Noisy Labels via Local Self-Regularization
• The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning
• GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression
• FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence
• FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling
• The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
• BlindFL: Vertical Federated Machine Learning without Peeking into Your Data
• Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Intervention
• CSAFL: A Clustered Semi-Asynchronous Federated Learning Framework
• Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching
• Enhanced Security and Privacy via Fragmented Federated Learning
• Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach
• Balancing Accuracy and Integrity for Reconfigurable Intelligent Surface-aided Over-the-Air Federated Learning
• Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontiers
• Towards Communication-efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things
• FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers
• Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing
• FedLGA: Towards System-Heterogeneity of Federated Learning via Local Gradient Approximation
• Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification
• Semi-Synchronous Federated Learning for Energy-Efficient Training and Accelerated Convergence in Cross-Silo Settings
• Federated and distributed learning applications for electronic health records and structured medical data: A scoping review
• Terahertz-Band Channel and Beam Split Estimation via Array Perturbation Model
• A Systematic Literature Review on Client Selection in Federated Learning
• Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application
• Time-sensitive Learning for Heterogeneous Federated Edge Intelligence
• An Efficient Federated Learning Framework for Training Semantic Communication System
• Combating Interference for Over-the-Air Federated Learning: A Statistical Approach via RIS
• Federated Domain Generalization: A Survey
• Gradient Compression and Correlation Driven Federated Learning for Wireless Traffic Prediction
• Quantization for decentralized learning under subspace constraints
• Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
• Towards Communication-efficient Vertical Federated Learning Training via Cache-enabled Local Updates
• FedHe: Heterogeneous Models and Communication-Efficient Federated Learning
• Secure Shapley Value for Cross-Silo Federated Learning (Technical Report)
• FedHybrid: A Hybrid Primal-Dual Algorithm Framework for Federated Optimization
• Graph Federated Learning for CIoT Devices in Smart Home Applications
• Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations
• DEFER: Distributed Edge Inference for Deep Neural Networks
• ISFL: Federated Learning for Non-i.i.d. Data with Local Importance Sampling
• Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis
• Client Selection for Federated Bayesian Learning
• Federated learning-outcome prediction with multi-layer privacy protection
• Tackling Noisy Clients in Federated Learning with End-to-end Label Correction
• FLrce: Resource-Efficient Federated Learning with Early-Stopping Strategy
• Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects
• Privacy Sensitive Speech Analysis Using Federated Learning to Assess Depression
• FedGiA: An Efficient Hybrid Algorithm for Federated Learning
• Attention on Personalized Clinical Decision Support System: Federated Learning Approach
• Towards Efficient Communication and Secure Federated Recommendation System via Low-rank Training
• A Payload Optimization Method for Federated Recommender Systems
• Split Two-Tower Model for Efficient and Privacy-Preserving Cross-device Federated Recommendation
• Improving Performance of Federated Learning based Medical Image Analysis in Non-IID Settings using Image Augmentation
• Novel Modelling Strategies for High-frequency Stock Trading Data
• Edge-cloud Collaborative Learning with Federated and Centralized Features
• IoT-based Analysis for Smart Energy Management
• An Experimental Study of Class Imbalance in Federated Learning
• Speeding up Heterogeneous Federated Learning with Sequentially Trained Superclients
• Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluation
• Efficient, high-performance pancreatic segmentation using multi-scale feature extraction
• Federated Data Analytics: A Study on Linear Models
• Diachronic and synchronic variation in the performance of adaptive machine learning systems: The ethical challenges
• Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing
• Privacy attacks for automatic speech recognition acoustic models in a federated learning framework
• Contrastive encoder pre-training-based clustered federated learning for heterogeneous data
• Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
• Scaling-up Distributed Processing of Data Streams for Machine Learning
• Financial technologies (FinTech) for mental health: The potential of objective financial data to better understand the relationships between financial behavior and mental health
• Federated Learning for Clinical Structured Data: A Benchmark Comparison of Engineering and Statistical Approaches
• ARFED: Attack-Resistant Federated averaging based on outlier elimination
• A Safe Deep Reinforcement Learning Approach for Energy Efficient Federated Learning in Wireless Communication Networks
• Adaptive Differentially Quantized Subspace Perturbation (ADQSP): A Unified Framework for Privacy-Preserving Distributed Average Consensus
• Federated Survival Forests
• Scaling Survival Analysis in Healthcare with Federated Survival Forests: A Comparative Study on Heart Failure and Breast Cancer Genomics
• Federated Over-Air Subspace Tracking from Incomplete and Corrupted Data
• Federated Learning with Superquantile Aggregation for Heterogeneous Data
• Device Heterogeneity in Federated Learning: A Superquantile Approach
• Privacy-Preserving Individual-Level COVID-19 Infection Prediction via Federated Graph Learning
• OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
• Ensemble learning using individual neonatal data for seizure detection
• FedCSD: A Federated Learning Based Approach for Code-Smell Detection
• Federated Learning for Energy Constrained IoT devices: A systematic mapping study
• Privacy-Preserving Distributed Learning for Residential Short-Term Load Forecasting
• Toward efficient resource utilization at edge nodes in federated learning
• Personalized Graph Federated Learning with Differential Privacy
• A Federated Learning Benchmark for Drug-Target Interaction
• Federated Gaussian Process: Convergence, Automatic Personalization and Multi-fidelity Modeling
• Ternary Compression for Communication-Efficient Federated Learning
• Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability
• Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training
• Free-Rider Games for Federated Learning with Selfish Clients in NextG Wireless Networks
• FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training
• FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneity
• Federated Uncertainty-Aware Aggregation for Fundus Diabetic Retinopathy Staging
• Asynchronous Online Federated Learning with Reduced Communication Requirements
• Massive Twinning to Enhance Emergent Intelligence
• Distributed Learning over Networks with Graph-Attention-Based Personalization
• Federated Learning for Commercial Image Sources
• Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning
• Federated Learning over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis
• Federated learning in food research
• A Review on Building Blocks of Decentralized Artificial Intelligence
• Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor
• Channel-driven Decentralized Bayesian Federated Learning for Trustworthy Decision Making in D2D Networks
• Exploring privacy-enhancing technologies in the automotive value chain
• FedSAUC: A Similarity-Aware Update Control for Communication-Efficient Federated Learning in Edge Computing
• Combining Federated Learning and Control: A Survey
• Federated Learning -- Methods, Applications and beyond
• Sample-based and Feature-based Federated Learning for Unconstrained and Constrained Nonconvex Optimization via Mini-batch SSCA
• Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing
• Fed-EC: Bandwidth-Efficient Clustering-Based Federated Learning For Autonomous Visual Robot Navigation
• Federated Learning on Non-iid Data via Local and Global Distillation
• Personalized Federated Learning with Multi-branch Architecture
• Federated Learning with Intermediate Representation Regularization
• Analysis of regularized federated learning
• A Federated Learning Benchmark on Tabular Data: Comparing Tree-Based Models and Neural Networks
• Federated Learning Using Three-Operator ADMM
• A Fair Federated Learning Framework for Collaborative Network Traffic Prediction and Resource Allocation
• BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning
• Compressed Regression over Adaptive Networks
• Distributed Computation for Marginal Likelihood based Model Choice
• Balancing Accuracy and Training Time in Federated Learning for Violence Detection in Surveillance Videos: A Study of Neural Network Architectures
• OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning
• Accelerating Distributed ML Training via Selective Synchronization
• Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy
• FedST: Secure Federated Shapelet Transformation for Time Series Classification
• Federated Hierarchical Clustering with Automatic Selection of Optimal Cluster Numbers
• Privacy Assessment of Federated Learning using Private Personalized Layers
• A New Perspective to Boost Performance Fairness for Medical Federated Learning
• Modular Federated Learning
• Communication Efficiency Optimization of Federated Learning for Computing and Network Convergence of 6G Networks
• Dr.Aid: Supporting Data-governance Rule Compliance for Decentralized Collaboration in an Automated Way
• 2SFGL: A Simple And Robust Protocol For Graph-Based Fraud Detection
• Causal Influence in Federated Edge Inference
• Centralized vs Decentralized Federated Learning: A trade-off performance analysis
• Realistic Urban Traffic Generator using Decentralized Federated Learning for the SUMO simulator
• Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning
• Gradients as an Action: Towards Communication-Efficient Federated Recommender Systems via Adaptive Action Sharing
• Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning
• Data-Aware Gradient Compression for FL in Communication-Constrained Mobile Computing
• LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation
• Federated Loss Exploration for Improved Convergence on Non-IID Data
• On the Convergence of Nested Decentralized Gradient Methods with Multiple Consensus and Gradient Steps
• Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Data
• A Stochastic Operator Framework for Optimization and Learning with Sub-Weibull Errors
• Federated Modality-specific Encoders and Partially Personalized Fusion Decoder for Multimodal Brain Tumor Segmentation
• A Federated Random Forest Solution for Secure Distributed Machine Learning
• A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations
• Robust and Communication-Efficient Federated Domain Adaptation via Random Features
• Online Distributed Learning with Quantized Finite-Time Coordination
• A Hybrid Federated Learning Based Ensemble Approach for Lung Disease Diagnosis Leveraging Fusion of SWIN Transformer and CNN
• Benchmarking Federated Learning in Edge Computing Environments: A Systematic Review and Performance Evaluation
• FedSC: Federated Learning with Semantic-Aware Collaboration
• TreeCSS: An Efficient Framework for Vertical Federated Learning
• A Ring-Based Distributed Algorithm for Learning High-Dimensional Bayesian Networks
• Federated Multi-Armed Bandits Under Byzantine Attacks
• Linear mixed modelling of federated data when only the mean, covariance, and sample size are available
• EasyFL: A Low-code Federated Learning Platform For Dummies
• From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0
• Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems
• A Novel Privacy-Preserved Recommender System Framework based on Federated Learning
• FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks
• Can Fair Federated Learning reduce the need for Personalisation?
• Noise-Robust and Resource-Efficient ADMM-based Federated Learning
• Regularized Top-$k$: A Bayesian Framework for Gradient Sparsification
• FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning
• Gradual Federated Learning with Simulated Annealing
• PPFL: A Personalized Federated Learning Framework for Heterogeneous Population
• On the Energy and Communication Efficiency Tradeoffs in Federated and Multi-Task Learning
• Private Hierarchical Clustering and Efficient Approximation
• Learn More by Using Less: Distributed Learning with Energy-Constrained Devices
• Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
• Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors
• Autonomous Cyber Resilience via a Co-Evolutionary Arms Race within a Fortified Digital Twin Sandbox
• Exploring Potential Prompt Injection Attacks in Federated Military LLMs and Their Mitigation
• Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift
• CHRONOS: A Hardware-Assisted Phase-Decoupled Framework for Secure Federated Learning in IoT
• PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstruction
• Evaluation and Analysis of Different Aggregation and Hyperparameter Selection Methods for Federated Brain Tumor Segmentation
• Lightweight Strategy for XOR PUFs as Security Primitives for Resource-constrained IoT device
• Federated Channel Learning for Intelligent Reflecting Surfaces With Fewer Pilot Signals
• Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Models
• Supervised Machine Learning with Plausible Deniability
• Federated mixed effects logistic regression based on one-time shared summary statistics
• Designing Short-Stage CDC-XPUFs: Balancing Reliability, Cost, and Security in IoT Devices
• Asynchronous Distributed Learning with Quantized Finite-Time Coordination
• Multi-Agent Optimization and Learning: A Non-Expansive Operators Perspective
• MyMigrationBot: A Cloud-based Facebook Social Chatbot for Migrant Populations
• Evaluation Framework for Centralized and Decentralized Aggregation Algorithm in Federated Systems