Federated Learning: Strategies for Improving Communication Efficiency

2016/10/18 by Jakub Konečný, H. Brendan McMahan, Konečný, Jakub +9 · 1 voice · 319 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques #cs.LG

paper · pdf · doi:10.48550/arxiv.1610.05492

openalex publication_date 2016/10/18 · arxiv published 2016/10/18 · arxiv created 2017/10/30 · arxiv updated 2017/11/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Federated Learning is a machine learning setting where the goal is to train a high-quality centralized model while training data remains distributed over a large number of clients each with unreliable and relatively slow network connections. We consider learning algorithms for this setting where on each round, each client independently computes an update to the current model based on its local data, and communicates this update to a central server, where the client-side updates are aggregated to compute a new global model. The typical clients in this setting are mobile phones, and communication efficiency is of the utmost importance. In this paper, we propose two ways to reduce the uplink communication costs: structured updates, where we directly learn an update from a restricted space parametrized using a smaller number of variables, e.g. either low-rank or a random mask; and sketched updates, where we learn a full model update and then compress it using a combination of quantization, random rotations, and subsampling before sending it to the server. Experiments on both convolutional and recurrent networks show that the proposed methods can reduce the communication cost by two orders of magnitude.

Citations

• On Randomized Distributed Coordinate Descent with Quantized Updates
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Learning Multiple Layers of Features from Tiny Images

Cited by

• On Signal Peak Power Constraint of Over-the-Air Federated Learning
• QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation
• First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
• Learned Digital Codes for Over-the-Air Computation in Federated Edge Learning
• Multi-user Pufferfish Privacy
• Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
• Optimal Key Rates for Decentralized Secure Aggregation with Arbitrary Collusion and Heterogeneous Security Constraints
• Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning
• DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning
• Non-Convex Federated Optimization under Cost-Aware Client Selection
• Dual Smoothing for Decentralized Optimization
• University Building Recognition Dataset in Thailand for the mission-oriented IoT sensor system
• Efficient Asynchronous Federated Evaluation with Strategy Similarity Awareness for Intent-Based Networking in Industrial Internet of Things
• On hierarchical secure aggregation against relay and user collusion
• Harnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimization
• Distributed Agent Reasoning Across Independent Systems With Strict Data Locality
• The Capacity of Collusion-Resilient Decentralized Secure Aggregation with Groupwise Keys
• Federated Cyber Defense: Privacy-Preserving Ransomware Detection Across Distributed Systems
• A Unified Convergence Analysis for Semi-Decentralized Learning: Sampled-to-Sampled vs. Sampled-to-All Communication
• SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data
• Experiences Building Enterprise-Level Privacy-Preserving Federated Learning to Power AI for Science
• Implicit Federated In-context Learning For Task-Specific LLM Fine-Tuning
• Towards Personalized Quantum Federated Learning for Anomaly Detection
• TT-Prune: Joint Model Pruning and Resource Allocation for Communication-efficient Time-triggered Federated Learning
• Federated Quantum Kernel Learning for Anomaly Detection in Multivariate IoT Time-Series
• Communication-Constrained Private Decentralized Online Personalized Mean Estimation
• An All-Reduce Compatible Top-K Compressor for Communication-Efficient Distributed Learning
• PowerScale: Energy-Efficient Geo-Distributed Model Training with Federated Datacenter Power
• MuonBP: Faster Muon via Block-Periodic Orthogonalization
• PassREfinder-FL: Privacy-Preserving Credential Stuffing Risk Prediction via Graph-Based Federated Learning for Representing Password Reuse between Websites
• Scalable Asynchronous Federated Modeling for Spatial Data
• Scaling Unsupervised Multi-Source Federated Domain Adaptation through Group-Wise Discrepancy Minimization
• FedLAM: Low-latency Wireless Federated Learning via Layer-wise Adaptive Modulation
• SketchGuard: Scaling Byzantine-Robust Decentralized Federated Learning via Sketch-Based Screening
• High-Probability Convergence Guarantees of Decentralized SGD
• FedSRD: Sparsify-Reconstruct-Decompose for Communication-Efficient Federated Large Language Models Fine-Tuning
• OptiFLIDS: Optimized Federated Learning for Energy-Efficient Intrusion Detection in IoT
• TAP: Two-Stage Adaptive Personalization of Multi-task and Multi-Modal Foundation Models in Federated Learning
• H+: An Efficient Similarity-Aware Aggregation for Byzantine Resilient Federated Learning
• Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning
• Adversarial Versus Federated: An Adversarial Learning based Multi-Modality Cross-Domain Federated Medical Segmentation
• CoSIFL: Collaborative Secure and Incentivized Federated Learning with Differential Privacy
• Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity
• Federated Learning of Quantile Inference under Local Differential Privacy
• Federated Flow Matching
• Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy
• Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
• Optimizing Split Federated Learning with Unstable Client Participation
• A non-smooth regularization framework for learning over multitask graphs
• Learned Digital Over-the-Air Computing for Federated Edge Learning
• Who to Trust? Aggregating Client Predictions in Federated Distillation
• Enhancing Smart Farming Through Federated Learning: A Secure, Scalable, and Efficient Approach for AI-Driven Agriculture
• From PowerSGD to PowerSGD+: Low-Rank Gradient Compression for Distributed Optimization with Convergence Guarantees
• Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration
• Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise
• Green Federated Learning via Carbon-Aware Client and Time Slot Scheduling
• DSFL: A Dual-Server Byzantine-Resilient Federated Learning Framework via Group-Based Secure Aggregation
• An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data
• From Federated Learning to X-Learning: Breaking the Barriers of Decentrality Through Random Walks
• Stochastic versus Deterministic in Stochastic Gradient Descent
• Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats
• SmartFLow: A Communication-Efficient SDN Framework for Cross-Silo Federated Learning
• Heterogeneous Self-Supervised Acoustic Pre-Training with Local Constraints
• From Research to Reality: Feasibility of Gradient Inversion Attacks in Federated Learning
• Enhancing Model Privacy in Federated Learning with Random Masking and Quantization
• Federated Learning based on Self-Evolving Gaussian Clustering
• Federated Nonlinear System Identification
• DOPA: Stealthy and Generalizable Backdoor Attacks from a Single Client under Challenging Federated Constraints
• Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learning
• FedSODA: Federated Fine-tuning of LLMs via Similarity Group Pruning and Orchestrated Distillation Alignment
• Decentralized Rank Scheduling for Energy-Constrained Multi-Task Federated Fine-Tuning in Edge-Assisted IoV Networks
• Benchmarking Federated Learning for Throughput Prediction in 5G Live Streaming Applications
• Communication-Efficient Zero-Order and First-Order Federated Learning Methods over Wireless Networks
• EFU: Enforcing Federated Unlearning via Functional Encryption
• Towards Useful and Private Synthetic Omics: Community Benchmarking of Generative Models for Transcriptomics Data
• HeteRo-Select: Informativeness as the Participation Driver in Heterogeneous Federated Learning
• Convergence Analysis of Aggregation-Broadcast in LoRA-enabled Distributed Fine-Tuning
• Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resilience
• Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRF
• Power-Constrained Policy Gradient Methods for LQR
• Federated Learning on Riemannian Manifolds: A Gradient-Free Projection-Based Approach
• Optimal Batch-Size Control for Low-Latency Federated Learning with Device Heterogeneity
• Scaling Decentralized Learning with FLock
• Federated Learning in Active STARS-Aided Uplink Networks
• PowerTrip: Exploiting Federated Heterogeneous Datacenter Power for Distributed ML Training
• Federated Learning for Large-Scale Cloud Robotic Manipulation: Opportunities and Challenges
• A Privacy-Centric Approach: Scalable and Secure Federated Learning Enabled by Hybrid Homomorphic Encryption
• Hierarchical Secure Aggregation with Heterogeneous Security Constraints and Arbitrary User Collusion
• FedStrategist: A Meta-Learning Framework for Adaptive and Robust Aggregation in Federated Learning
• Byzantine-resilient federated online learning for Gaussian process regression
• Decentralized Federated Learning of Probabilistic Generative Classifiers
• Federated Learning for Commercial Image Sources
• Self-Adaptive and Robust Federated Spectrum Sensing without Benign Majority for Cellular Networks
• Federated Neural Architecture Search
• Accelerating DNN Training in Wireless Federated Edge Learning Systems
• Learning Structured Distributions From Untrusted Batches: Faster and Simpler
• Mechanism Design for Multi-Party Machine Learning
• ReFRS: Resource-efficient Federated Recommender System for Dynamic and Diversified User Preferences
• Federated Learning of N-gram Language Models
• Slashing Communication Traffic in Federated Learning by Transmitting Clustered Model Updates
• Federated Edge Learning with Misaligned Over-The-Air Computation
• Distributed Machine Learning through Heterogeneous Edge Systems
• Deep Learning Framework for Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems
• Privacy-preserving Learning via Deep Net Pruning
• Distantly Supervised Relation Extraction in Federated Settings
• On Addressing Heterogeneity in Federated Learning for Autonomous Vehicles Connected to a Drone Orchestrator
• Asynchronous Federated Learning for Sensor Data with Concept Drift
• Privacy Preservation in Federated Learning: An insightful survey from the GDPR Perspective
• Communication trade-offs for synchronized distributed SGD with large step size
• The Tradeoff Between Privacy and Accuracy in Anomaly Detection Using Federated XGBoost
• D3FL: Data Distribution and Detrending for Robust Federated Learning in Non-linear Time-series Data
• Multi-resource allocation for federated settings: A non-homogeneous Markov chain model
• Quantized Rank Reduction: A Communications-Efficient Federated Learning Scheme for Network-Critical Applications
• Convergence of Agnostic Federated Averaging
• Learn distributed GAN with Temporary Discriminators
• MTF-Grasp: A Multi-tier Federated Learning Approach for Robotic Grasping
• HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systems
• Federated Classification using Parsimonious Functions in Reproducing Kernel Hilbert Spaces
• Greedy Low-Rank Gradient Compression for Distributed Learning with Convergence Guarantees
• Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift
• FlexOlmo: Open Language Models for Flexible Data Use
• Adaptive collaboration for online personalized distributed learning with heterogeneous clients
• Cost-Effective Federated Learning Design
• New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design
• Ampere: Communication-Efficient and High-Accuracy Split Federated Learning
• Communication-Efficient Module-Wise Federated Learning for Grasp Pose Detection in Cluttered Environments
• Byzantine-Robust Variance-Reduced Federated Learning over Distributed Non-i.i.d. Data
• Kalman Filter Aided Federated Koopman Learning
• BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning
• TiFL: A Tier-based Federated Learning System
• Loss Tolerant Federated Learning
• A Hybrid Machine Learning Framework for Optimizing Crop Selection via Agronomic and Economic Forecasting
• One-Bit Model Aggregation for Differentially Private and Byzantine-Robust Personalized Federated Learning
• Density-Aware Federated Imitation Learning for Connected and Automated Vehicles with Unsignalized Intersection
• Practical Defences Against Model Inversion Attacks for Split Neural Networks
• Local SGD: Unified Theory and New Efficient Methods
• Meta Clustering for Collaborative Learning
• A Comprehensive Overview on 5G-and-Beyond Networks with UAVs: From Communications to Sensing and Intelligence
• CLUES: Collaborative High-Quality Data Selection for LLMs via Training Dynamics
• Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
• ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training
• How to Securely Shuffle? A survey about Secure Shufflers for privacy-preserving computations
• Federated Learning of a Mixture of Global and Local Models
• Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning
• Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning
• Splitfed learning without client-side synchronization: Analyzing client-side split network portion size to overall performance
• Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection
• PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstruction
• Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction
• FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization
• Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission
• Federated Noisy Client Learning
• Federated Learning With Quantized Global Model Updates
• Robust Coreset Construction for Distributed Machine Learning
• GFL: A Decentralized Federated Learning Framework Based On Blockchain
• CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings
• Practical Privacy Preserving POI Recommendation
• Federated Item Response Theory Models
• From Local SGD to Local Fixed-Point Methods for Federated Learning
• Robust Federated Learning with Noisy Communication
• Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?
• Pufferfish: Communication-efficient Models At No Extra Cost
• Federated machine learning with Anonymous Random Hybridization (FeARH) on medical records
• ASCII: ASsisted Classification with Ignorance Interchange
• Federated Multi-Task Learning
• BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning
• PNCS:Power-Norm Cosine Similarity for Diverse Client Selection in Federated Learning
• Multi-Timescale Primal Dual Hybrid Gradient with Application to Distributed Optimization
• A Federated Random Forest Solution for Secure Distributed Machine Learning
• Don't Use Large Mini-Batches, Use Local SGD
• A Survey on World Models Grounded in Acoustic Physical Information
• NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets
• A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression
• Local SGD With a Communication Overhead Depending Only on the Number of Workers
• Federated pretraining and fine tuning of BERT using clinical notes from multiple silos
• BAFFLE : Blockchain Based Aggregator Free Federated Learning
• Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation
• HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learning
• SLSGD: Secure and Efficient Distributed On-device Machine Learning
• Sharing Models or Coresets: A Study based on Membership Inference Attack
• Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data
• A Quantitative Metric for Privacy Leakage in Federated Learning
• Wireless Data Acquisition for Edge Learning: Data-Importance Aware Retransmission
• Eavesdrop the Composition Proportion of Training Labels in Federated Learning
• Communication-Efficient Federated Learning with Compensated Overlap-FedAvg
• Spatio-Temporal Federated Learning for Massive Wireless Edge Networks
• Federated Multi-Armed Bandits
• Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
• Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
• Assisted Learning: A Framework for Multi-Organization Learning
• Federated Learning in Adversarial Settings
• Resource Rationing for Wireless Federated Learning: Concept, Benefits, and Challenges
• Real-Time Decentralized knowledge Transfer at the Edge
• FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning
• FedLoc: Federated Learning Framework for Data-Driven Cooperative Localization and Location Data Processing
• CovidSens: A Vision on Reliable Social Sensing for COVID-19
• Variance Reduced Local SGD with Lower Communication Complexity
• Pronto: Federated Task Scheduling
• VFL: A Verifiable Federated Learning with Privacy-Preserving for Big Data in Industrial IoT
• On the Benefits of Multiple Gossip Steps in Communication-Constrained\n Decentralized Optimization
• Memory-Efficient Distributed Unlearning
• Towards More Efficient Federated Learning with Better Optimization Objects
• Decentralized Bayesian Learning over Graphs
• Active Learning Solution on Distributed Edge Computing
• FORLA: Federated Object-centric Representation Learning with Slot Attention
• MAB-based Client Selection for Federated Learning with Uncertain Resources in Mobile Networks
• R-GAP: Recursive Gradient Attack on Privacy
• Secure Byzantine-Robust Distributed Learning via Clustering
• Shredder: Learning Noise Distributions to Protect Inference Privacy
• Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning
• ByGARS: Byzantine SGD with Arbitrary Number of Attackers
• FLRA: A Reference Architecture for Federated Learning Systems
• Combining Federated and Active Learning for Communication-efficient Distributed Failure Prediction in Aeronautics
• Network-Aware Optimization of Distributed Learning for Fog Computing
• Multiple Kernel-Based Online Federated Learning
• The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning
• Voting-based Approaches For Differentially Private Federated Learning
• Improving Fairness via Federated Learning
• Federated Learning With Highly Imbalanced Audio Data
• Fed-EINI: An Efficient and Interpretable Inference Framework for Decision Tree Ensembles in Federated Learning
• When Machine Learning Meets Privacy: A Survey and Outlook
• Fairness in Federated Learning: Fairness for Whom?
• A Federated Learning Approach for Mobile Packet Classification
• Generalized and Personalized Federated Learning with Black-Box Foundation Models via Orthogonal Transformations
• SEMFED: Semantic-Aware Resource-Efficient Federated Learning for Heterogeneous NLP Tasks
• Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels
• C³DRec: Cloud-Client Cooperative Deep Learning for Temporal Recommendation in the Post-GDPR Era
• Federated Traffic Synthesizing and Classification Using Generative Adversarial Networks
• FedJAX: Federated learning simulation with JAX
• Federated Unlearning
• Gain without Pain: Offsetting DP-injected Nosies Stealthily in Cross-device Federated Learning
• OL4EL: Online Learning for Edge-cloud Collaborative Learning on Heterogeneous Edges with Resource Constraints
• LocalKMeans: Convergence of Lloyd's Algorithm with Distributed Local Iterations
• Privacy-preserving Decentralized Aggregation for Federated Learning
• ATR-Bench: A Federated Learning Benchmark for Adaptation, Trust, and Reasoning
• From Local Patterns to Global Understanding: Cross-Stock Trend Integration for Enhanced Predictive Modeling
• Navigating the Edge-Cloud Continuum: A State-of-Practice Survey
• Federated Learning for Healthcare Informatics
• Secure Aggregation with Heterogeneous Quantization in Federated Learning
• Distributionally Robust Federated Learning with Client Drift Minimization
• DEAL: Decremental Energy-Aware Learning in a Federated System
• DPD-InfoGAN: Differentially Private Distributed InfoGAN
• EcoLoRA: Communication-Efficient Federated Fine-Tuning of Large Language Models
• PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN
• MC²-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation
• Shuffle-Exchange Brings Faster: Reduce the Idle Time During Communication for Decentralized Neural Network Training
• FlexFed: Mitigating Catastrophic Forgetting in Heterogeneous Federated Learning in Pervasive Computing Environments
• FLTG: Byzantine-Robust Federated Learning via Angle-Based Defense and Non-IID-Aware Weighting
• RIFLES: Resource-effIcient Federated LEarning via Scheduling
• The Stochastic Multi-Proximal Method for Nonsmooth Optimization
• Cluster-Aware Over-the-Air Federated Learning with Energy-Harvesting Devices: From Global Training to Model Personalization
• Robust Federated Learning: The Case of Affine Distribution Shifts
• Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners
• Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systems
• FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients
• FedDuA: Doubly Adaptive Federated Learning
• Deep learning for tomographic image reconstruction
• Exploiting Heterogeneity in Robust Federated Best-Arm Identification
• Decentralized Learning of Generative Adversarial Networks from Non-iid Data
• Management of Resource at the Network Edge for Federated Learning
• Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning
• Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information
• Federated Learning for Ranking Browser History Suggestions
• Vertical federated learning based on DFP and BFGS
• Machine Learning on Volatile Instances
• Federated Learning with Additional Mechanisms on Clients to Reduce Communication Costs
• Federated f-Differential Privacy
• Federated Learning for Cyber Physical Systems: A Comprehensive Survey
• Real-time Federated Evolutionary Neural Architecture Search
• Is Network the Bottleneck of Distributed Training?
• Proximal and Federated Random Reshuffling
• Federated Acoustic Modeling For Automatic Speech Recognition
• Secure Federated Submodel Learning
• Data-Free Evaluation of User Contributions in Federated Learning
• Large-Scale Generative Data-Free Distillation
• Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters
• Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks
• Communication-Censored Distributed Stochastic Gradient Descent
• A Generalized Meta Federated Learning Framework with Theoretical Convergence Guarantees
• Financial Data Analysis with Robust Federated Logistic Regression
• Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation
• UnifyFL: Enabling Decentralized Cross-Silo Federated Learning
• User Interaction Aware Reinforcement Learning for Power and Thermal Efficiency of CPU-GPU Mobile MPSoCs
• More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence
• Federated Learning: Opportunities and Challenges
• Genuinely distributed Byzantine machine learning
• Fed-ComBat: A Generalized Federated Framework for Batch Effect Harmonization in Collaborative Studies
• Differential Privacy Meets Federated Learning under Communication Constraints
• Federated Extra-Trees with Privacy Preserving
• Federated Forest
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization
• Local Differential Privacy in Decentralized Optimization
• Towards Communication-Efficient and Attack-Resistant Federated Edge Learning for Industrial Internet of Things
• CaPC Learning: Confidential and Private Collaborative Learning
• Exact Support Recovery in Federated Regression with One-shot Communication
• CatFedAvg: Optimising Communication-efficiency and Classification Accuracy in Federated Learning
• Federated Heavy Hitters Discovery with Differential Privacy
• Distributed Deep Learning with Event-Triggered Communication
• Two-stage Federated Phenotyping and Patient Representation Learning
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
• UVeQFed: Universal Vector Quantization for Federated Learning
• FlexPD: A Flexible Framework Of First-Order Primal-Dual Algorithms for Distributed Optimization
• Efficient Split Federated Learning for Large Language Models over Communication Networks
• Scalable and Communication-efficient Decentralized Federated Edge Learning with Multi-blockchain Framework
• Distributed Proximal Splitting Algorithms with Rates and Acceleration
• Tighter Theory for Local SGD on Identical and Heterogeneous Data
• Federated Learning without Revealing the Decision Boundaries
• Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation
• Trends and Advancements in Deep Neural Network Communication
• Joint Coreset Construction and Quantization for Distributed Machine Learning
• Learning, Computing, and Trustworthiness in Intelligent IoT Environments: Performance-Energy Tradeoffs
• FedEPA: Enhancing Personalization and Modality Alignment in Multimodal Federated Learning
• DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting
• Beyond Weights and Gradients: A Taxonomy of Federated Learning Messages
• Accelerating Differentially Private Federated Learning via Adaptive Extrapolation
• Query-based Knowledge Transfer for Heterogeneous Learning Environments
• Boosting multi-demographic federated learning for chest radiograph analysis using general-purpose self-supervised representations
• OCTOPUS: Overcoming Performance and Privatization Bottlenecks in Distributed Learning

Discussions

• Federated Learning: Strategies for Improving Communication Efficiency [hn, 2 points, 0 comments]

Related

• Federated Learning With Quantized Global Model Updates
• FedNet2Net: Saving Communication and Computations in Federated Learning with Model Growing
• Adaptive Federated Dropout: Improving Communication Efficiency and Generalization for Federated Learning
• Federated Learning via Synthetic Data
• RingFed: Reducing Communication Costs in Federated Learning on Non-IID Data