{"total":149,"rows":[{"id":"2306.01603","title":"Decentralized Federated Learning: A Survey and Perspective","created":"2023-06-02","cited_by_count":86,"area":null},{"id":"2206.08307","title":"Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning","created":"2022-06-16","cited_by_count":79,"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":"2107.06925","title":"Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines","created":"2021-07-14","cited_by_count":68,"area":null},{"id":"2104.14362","title":"From Distributed Machine Learning to Federated Learning: A Survey","created":"2021-04-29","cited_by_count":66,"area":null},{"id":"2206.07638","title":"Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays","created":"2022-06-15","cited_by_count":63,"area":null},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58,"area":null},{"id":"2111.11343","title":"Decentralized Federated Learning through Proxy Model Sharing","created":"2021-11-22","cited_by_count":57,"area":null},{"id":"2110.13363","title":"Exponential Graph is Provably Efficient for Decentralized Deep Training","created":"2021-10-26","cited_by_count":56,"area":null},{"id":"2205.13692","title":"FedAvg with Fine Tuning: Local Updates Lead to Representation Learning","created":"2022-05-27","cited_by_count":56,"area":null},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2107.00052","title":"Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity","created":"2021-06-30","cited_by_count":43,"area":null},{"id":"2104.11981","title":"DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training","created":"2021-04-24","cited_by_count":40,"area":null},{"id":"2110.04175","title":"RelaySum for Decentralized Deep Learning on Heterogeneous Data","created":"2021-10-08","cited_by_count":39,"area":null},{"id":"2206.04723","title":"On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data","created":"2022-06-09","cited_by_count":38,"area":null},{"id":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38,"area":null},{"id":"2103.03239","title":"Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices","created":"2021-03-04","cited_by_count":36,"area":null},{"id":"2102.07091","title":"Decentralized Riemannian Gradient Descent on the Stiefel Manifold","created":"2021-02-14","cited_by_count":33,"area":null},{"id":"2103.02051","title":"Cross-Gradient Aggregation for Decentralized Learning from Non-IID data","created":"2021-03-02","cited_by_count":33,"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":"2204.04452","title":"Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data","created":"2022-04-09","cited_by_count":32,"area":null},{"id":"2202.01545","title":"Byzantine-Robust Decentralized Learning via ClippedGossip","created":"2022-02-03","cited_by_count":31,"area":null},{"id":"2105.08023","title":"Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD","created":"2021-05-17","cited_by_count":29,"area":null},{"id":"2206.03093","title":"Beyond spectral gap: The role of the topology in decentralized learning","created":"2022-06-07","cited_by_count":27,"area":null},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","cited_by_count":25,"area":null},{"id":"2106.08315","title":"Decentralized Local Stochastic Extra-Gradient for Variational Inequalities","created":"2021-06-15","cited_by_count":25,"area":null},{"id":"2107.08517","title":"Decentralized federated learning of deep neural networks on non-iid data","created":"2021-07-18","cited_by_count":25,"area":null},{"id":"2210.07881","title":"Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate","created":"2022-10-14","cited_by_count":25,"area":null},{"id":"2210.07863","title":"Revisiting Optimal Convergence Rate for Smooth and Non-convex Stochastic Decentralized Optimization","created":"2022-10-14","cited_by_count":23,"area":null},{"id":"2102.06752","title":"A Hybrid Variance-Reduced Method for Decentralized Stochastic Non-Convex Optimization","created":"2021-02-12","cited_by_count":21,"area":null},{"id":"2310.01972","title":"Epidemic Learning: Boosting Decentralized Learning with Randomized Communication","created":"2023-10-03","cited_by_count":21,"area":null},{"id":"2405.11525","title":"Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors","created":"2024-05-19","cited_by_count":21,"area":null},{"id":"2110.08133","title":"Trade-offs of Local SGD at Scale: An Empirical Study","created":"2021-10-15","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":"2104.05245","title":"Distributed Learning Systems with First-order Methods","created":"2021-04-12","cited_by_count":17,"area":null},{"id":"2109.03194","title":"On the Convergence of Decentralized Adaptive Gradient Methods","created":"2021-09-07","cited_by_count":17,"area":null},{"id":"2401.16265","title":"CO2: Efficient Distributed Training with Full Communication-Computation Overlap","created":"2024-01-29","cited_by_count":17,"area":null},{"id":"2110.01165","title":"DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization","created":"2021-10-04","cited_by_count":16,"area":null},{"id":"2111.04287","title":"BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning","created":"2021-11-08","cited_by_count":16,"area":null},{"id":"2205.10998","title":"Semi-Decentralized Federated Learning with Collaborative Relaying","created":"2022-05-23","cited_by_count":16,"area":null},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2312.10935","title":"AEDFL: Efficient Asynchronous Decentralized Federated Learning with Heterogeneous Devices","created":"2023-12-18","cited_by_count":15,"area":null},{"id":"2105.04851","title":"Improving the Transient Times for Distributed Stochastic Gradient Methods","created":"2021-05-11","cited_by_count":13,"area":null},{"id":"2406.04142","title":"Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2106.11257","title":"Secure Distributed Training at Scale","created":"2021-06-21","cited_by_count":12,"area":null},{"id":"2204.06477","title":"Data-heterogeneity-aware Mixing for Decentralized Learning","created":"2022-04-13","cited_by_count":12,"area":null},{"id":"2305.04792","title":"Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data","created":"2023-05-08","cited_by_count":12,"area":null},{"id":"2307.07652","title":"DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updates","created":"2023-07-14","cited_by_count":12,"area":null},{"id":"2207.03730","title":"Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology","created":"2022-07-08","cited_by_count":10,"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":"2306.04984","title":"G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2404.09536","title":"Noiseless Privacy-Preserving Decentralized Learning","created":"2024-04-15","cited_by_count":9,"area":null},{"id":"2405.17876","title":"Decentralized Directed Collaboration for Personalized Federated Learning","created":"2024-05-28","cited_by_count":9,"area":null},{"id":"2209.07116","title":"On Generalization of Decentralized Learning with Separable Data","created":"2022-09-15","cited_by_count":8,"area":null},{"id":"2305.18497","title":"Collaborative Learning via Prediction Consensus","created":"2023-05-29","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":"2112.15287","title":"Distributed Random Reshuffling over Networks","created":"2021-12-31","cited_by_count":7,"area":null},{"id":"2306.08289","title":"$\\textbf{A}^2\\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2502.19717","title":"Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning","created":"2025-02-27","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":"2306.00256","title":"DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm","created":"2023-06-01","cited_by_count":6,"area":null},{"id":"2406.02613","title":"ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2410.12918","title":"Boosting Asynchronous Decentralized Learning with Model Fragmentation","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2503.20117","title":"Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2202.11850","title":"Robust Federated Learning with Connectivity Failures: A Semi-Decentralized Framework with Collaborative Relaying","created":"2022-02-24","cited_by_count":5,"area":null},{"id":"2209.14390","title":"Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data Distributions","created":"2022-09-28","cited_by_count":5,"area":null},{"id":"2310.05093","title":"Asymmetrically Decentralized Federated Learning","created":"2023-10-08","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":"2406.13533","title":"DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networks","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2410.18862","title":"FedSPD: A Soft-clustering Approach for Personalized Decentralized Federated Learning","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2211.00533","title":"Optimal Complexity in Non-Convex Decentralized Learning over Time-Varying Networks","created":"2022-11-01","cited_by_count":4,"area":null},{"id":"2306.05100","title":"Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates","created":"2023-06-08","cited_by_count":4,"area":null},{"id":"2306.10598","title":"DropCompute: simple and more robust distributed synchronous training via compute variance reduction","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2405.02638","title":"PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds","created":"2024-05-04","cited_by_count":4,"area":null},{"id":"2405.03782","title":"Interpretable Data Fusion for Distributed Learning: A Representative Approach via Gradient Matching","created":"2024-05-06","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":"2502.07750","title":"PFedDST: Personalized Federated Learning with Decentralized Selection Training","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2301.02151","title":"Beyond spectral gap (extended): The role of the topology in decentralized learning","created":"2023-01-05","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":"2310.03461","title":"Towards Understanding Generalization and Stability Gaps between Centralized and Decentralized Federated Learning","created":"2023-10-05","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":"2508.08278","title":"Towards Heterogeneity-Aware and Energy-Efficient Topology Optimization for Decentralized Federated Learning in Edge Environment","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2111.09389","title":"Low Precision Decentralized Distributed Training over IID and non-IID Data","created":"2021-11-17","cited_by_count":2,"area":null},{"id":"2112.09341","title":"Personalized On-Device E-health Analytics with Decentralized Block Coordinate Descent","created":"2021-12-17","cited_by_count":2,"area":null},{"id":"2202.03346","title":"Variance reduced stochastic optimization over directed graphs with row and column stochastic weights","created":"2022-02-07","cited_by_count":2,"area":null},{"id":"2203.06798","title":"The Role of Local Steps in Local SGD","created":"2022-03-14","cited_by_count":2,"area":null},{"id":"2210.07703","title":"Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2303.15378","title":"CoDeC: Communication-Efficient Decentralized Continual Learning","created":"2023-03-27","cited_by_count":2,"area":null},{"id":"2307.11617","title":"Robust Fully-Asynchronous Methods for Distributed Training over General Architecture","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2308.05292","title":"Byzantine-Robust Decentralized Stochastic Optimization with Stochastic Gradient Noise-Independent Learning Error","created":"2023-08-10","cited_by_count":2,"area":null},{"id":"2309.03754","title":"Convergence Analysis of Decentralized ASGD","created":"2023-09-07","cited_by_count":2,"area":null},{"id":"2508.04950","title":"Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2602.03383","title":"Dynamic Topology Optimization for Non-IID Data in Decentralized Learning","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2102.09631","title":"Peering Beyond the Gradient Veil with Distributed Auto Differentiation","created":"2021-02-18","cited_by_count":1,"area":null},{"id":"2112.10389","title":"Decentralized Stochastic Proximal Gradient Descent with Variance Reduction over Time-varying Networks","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2203.06638","title":"Scaling the Wild: Decentralizing Hogwild!-style Shared-memory SGD","created":"2022-03-13","cited_by_count":1,"area":null},{"id":"2203.13085","title":"Locally Asynchronous Stochastic Gradient Descent for Decentralised Deep Learning","created":"2022-03-24","cited_by_count":1,"area":null},{"id":"2204.08160","title":"On Arbitrary Compression for Decentralized Consensus and Stochastic Optimization over Directed Networks","created":"2022-04-18","cited_by_count":1,"area":null}],"next_cursor":"100"}