{"total":88,"rows":[{"id":"2211.08413","title":"Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges","created":"2022-11-15","cited_by_count":138,"area":null},{"id":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87,"area":null},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69,"area":null},{"id":"2202.03836","title":"An Improved Analysis of Gradient Tracking for Decentralized Machine Learning","created":"2022-02-08","cited_by_count":69,"area":null},{"id":"2201.13320","title":"BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression","created":"2022-01-31","cited_by_count":41,"area":null},{"id":"2107.10996","title":"Communication Efficiency in Federated Learning: Achievements and Challenges","created":"2021-07-23","cited_by_count":40,"area":null},{"id":"2206.03665","title":"Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression","created":"2022-06-08","cited_by_count":33,"area":null},{"id":"2103.11109","title":"DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation","created":"2021-03-20","cited_by_count":31,"area":null},{"id":"2106.02743","title":"SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks","created":"2021-06-04","cited_by_count":30,"area":null},{"id":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30,"area":null},{"id":"2103.00543","title":"On the Utility of Gradient Compression in Distributed Training Systems","created":"2021-02-28","cited_by_count":26,"area":null},{"id":"2106.07976","title":"Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection","created":"2021-06-15","cited_by_count":20,"area":null},{"id":"2209.15505","title":"Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data","created":"2022-09-30","cited_by_count":20,"area":null},{"id":"2107.00961","title":"ResIST: Layer-Wise Decomposition of ResNets for Distributed Training","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2306.10015","title":"Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomness","created":"2023-06-16","cited_by_count":18,"area":null},{"id":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17,"area":null},{"id":"2104.07515","title":"FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems","created":"2021-04-15","cited_by_count":16,"area":null},{"id":"2105.07806","title":"Towards Demystifying Serverless Machine Learning Training","created":"2021-05-17","cited_by_count":16,"area":null},{"id":"2107.11304","title":"Finite-Bit Quantization For Distributed Algorithms With Linear Convergence","created":"2021-07-23","cited_by_count":15,"area":null},{"id":"2107.01499","title":"BAGUA: Scaling up Distributed Learning with System Relaxations","created":"2021-07-03","cited_by_count":13,"area":null},{"id":"2105.06697","title":"Innovation Compression for Communication-efficient Distributed Optimization with Linear Convergence","created":"2021-05-14","cited_by_count":12,"area":null},{"id":"2106.07243","title":"Compressed Gradient Tracking for Decentralized Optimization Over General Directed Networks","created":"2021-06-14","cited_by_count":12,"area":null},{"id":"2301.05872","title":"CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence","created":"2023-01-14","cited_by_count":9,"area":null},{"id":"2305.09896","title":"Convergence and Privacy of Decentralized Nonconvex Optimization with Gradient Clipping and Communication Compression","created":"2023-05-17","cited_by_count":9,"area":null},{"id":"2305.11420","title":"Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence","created":"2023-05-19","cited_by_count":9,"area":null},{"id":"2509.26337","title":"FedMuon: Federated Learning with Bias-corrected LMO-based Optimization","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2102.05715","title":"Sparse-Push: Communication- & Energy-Efficient Decentralized Distributed Learning over Directed & Time-Varying Graphs with non-IID Datasets","created":"2021-02-10","cited_by_count":7,"area":null},{"id":"2108.04448","title":"Decentralized Composite Optimization with Compression","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2209.07821","title":"Quantization for decentralized learning under subspace constraints","created":"2022-09-16","cited_by_count":7,"area":null},{"id":"2202.00255","title":"DoCoM: Compressed Decentralized Optimization with Near-Optimal Sample Complexity","created":"2022-02-01","cited_by_count":6,"area":null},{"id":"2202.11655","title":"TEE-based decentralized recommender systems: The raw data sharing redemption","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2208.07237","title":"Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation","created":"2022-08-15","cited_by_count":6,"area":null},{"id":"2303.08423","title":"Communication-Efficient Design for Quantized Decentralized Federated Learning","created":"2023-03-15","cited_by_count":6,"area":null},{"id":"2306.04377","title":"Get More for Less in Decentralized Learning Systems","created":"2023-06-07","cited_by_count":6,"area":null},{"id":"2102.07521","title":"Distributed Online Learning for Joint Regret with Communication Constraints","created":"2021-02-15","cited_by_count":5,"area":null},{"id":"2104.08100","title":"Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2312.10815","title":"DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations","created":"2023-12-17","cited_by_count":5,"area":null},{"id":"2405.20114","title":"Towards Faster Decentralized Stochastic Optimization with Communication Compression","created":"2024-05-30","cited_by_count":5,"area":null},{"id":"2406.18156","title":"FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantization","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2407.19234","title":"Ordered Momentum for Asynchronous SGD","created":"2024-07-27","cited_by_count":5,"area":null},{"id":"2110.11006","title":"Bristle: Decentralized Federated Learning in Byzantine, Non-i.i.d. Environments","created":"2021-10-21","cited_by_count":4,"area":null},{"id":"2204.03326","title":"Enabling All In-Edge Deep Learning: A Literature Review","created":"2022-04-07","cited_by_count":4,"area":null},{"id":"2204.12443","title":"A review of Federated Learning in Intrusion Detection Systems for IoT","created":"2022-04-26","cited_by_count":4,"area":null},{"id":"2304.10902","title":"Near-Optimal Decentralized Momentum Method for Nonconvex-PL Minimax Problems","created":"2023-04-21","cited_by_count":4,"area":null},{"id":"2307.07406","title":"Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noise","created":"2023-07-14","cited_by_count":4,"area":null},{"id":"2403.14716","title":"Distributed Learning based on 1-Bit Gradient Coding in the Presence of Stragglers","created":"2024-03-19","cited_by_count":4,"area":null},{"id":"2410.11998","title":"From promise to practice: realizing high-performance decentralized training","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2510.01377","title":"DeMuon: A Decentralized Muon for Matrix Optimization over Graphs","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2001.05918","title":"Elastic Consistency: A General Consistency Model for Distributed Stochastic Gradient Descent","created":"2020-01-16","cited_by_count":3,"area":"diffusion"},{"id":"2102.06280","title":"Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers","created":"2021-02-11","cited_by_count":3,"area":null},{"id":"2202.02812","title":"Lossy Gradient Compression: How Much Accuracy Can One Bit Buy?","created":"2022-02-06","cited_by_count":3,"area":null},{"id":"2212.09483","title":"Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning","created":"2022-12-19","cited_by_count":3,"area":null},{"id":"2306.06559","title":"Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates","created":"2023-06-11","cited_by_count":3,"area":null},{"id":"2406.18418","title":"Differential error feedback for communication-efficient decentralized learning","created":"2024-06-26","cited_by_count":3,"area":null},{"id":"2501.15259","title":"Scalable Decentralized Learning with Teleportation","created":"2025-01-25","cited_by_count":3,"area":null},{"id":"2205.03779","title":"Communication Compression for Decentralized Learning with Operator Splitting Methods","created":"2022-05-08","cited_by_count":2,"area":null},{"id":"2308.16671","title":"Sparse Decentralized Federated Learning","created":"2023-08-31","cited_by_count":2,"area":null},{"id":"2310.16106","title":"Decentralized Learning over Wireless Networks with Broadcast-Based Subgraph Sampling","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2401.13779","title":"Faster Convergence with Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning over Wireless Networks","created":"2024-01-24","cited_by_count":2,"area":null},{"id":"2408.04705","title":"Overlay-based Decentralized Federated Learning in Bandwidth-limited Networks","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2601.04907","title":"Distributed Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower bounds","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2111.02949","title":"Finite-Time Consensus Learning for Decentralized Optimization with Nonlinear Gossiping","created":"2021-11-04","cited_by_count":1,"area":null},{"id":"2205.14452","title":"Stochastic Gradient Methods with Compressed Communication for Decentralized Saddle Point Problems","created":"2022-05-28","cited_by_count":1,"area":null},{"id":"2301.09269","title":"M22: A Communication-Efficient Algorithm for Federated Learning Inspired by Rate-Distortion","created":"2023-01-23","cited_by_count":1,"area":null},{"id":"2401.03083","title":"Energy-efficient Decentralized Learning via Graph Sparsification","created":"2024-01-05","cited_by_count":1,"area":null},{"id":"2410.19319","title":"Fully First-Order Methods for Decentralized Bilevel Optimization","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2506.00961","title":"Enhancing Parallelism in Decentralized Stochastic Convex Optimization","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2512.13583","title":"DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2512.24069","title":"Time-varying Mixing Matrix Design for Energy-efficient Decentralized Federated Learning","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2603.01730","title":"Decentralized Federated Learning by Partial Message Exchange","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2604.09276","title":"Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.23426","title":"Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2606.09154","title":"Improved Convergence Analysis of Topology Dependence in Decentralized SGD","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2104.13818","title":"NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization","created":"2021-04-28","cited_by_count":0,"area":null},{"id":"2109.01718","title":"Communication Efficient Generalized Tensor Factorization for Decentralized Healthcare Networks","created":"2021-09-03","cited_by_count":0,"area":null},{"id":"2110.04523","title":"An Empirical Study on Compressed Decentralized Stochastic Gradient Algorithms with Overparameterized Models","created":"2021-10-09","cited_by_count":0,"area":null},{"id":"2201.11343","title":"Distributed gradient-based optimization in the presence of dependent aperiodic communication","created":"2022-01-27","cited_by_count":0,"area":null},{"id":"2207.10046","title":"Adaptive Step-Size Methods for Compressed SGD","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2311.05760","title":"Compressed and Sparse Models for Non-Convex Decentralized Learning","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2402.01070","title":"FedShift: Robust Federated Learning Aggregation Scheme in Resource Constrained Environment via Weight Shifting","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2405.13961","title":"SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2410.14115","title":"A Communication and Computation Efficient Fully First-order Method for Decentralized Bilevel Optimization","created":"2024-10-18","cited_by_count":0,"area":"deeprl"},{"id":"2511.19513","title":"Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2606.04757","title":"Near-Optimal Decentralized Stochastic Convex Optimization over Networks","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.01665","title":"Revisiting Decentralized Online Convex Optimization with Compressed Communication","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.01755","title":"Decentralized Stochastic Subgradient-type Methods with Communication Compression for Nonsmooth Nonconvex Optimization","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.12172","title":"Decentralized Gradient Descent: Bottleneck Regimes and Budget Complexity","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.26493","title":"A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraints","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":null}