{"total":153,"rows":[{"id":"2108.10252","title":"Federated Multi-Task Learning under a Mixture of Distributions","created":"2021-08-23","cited_by_count":192,"area":null},{"id":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190,"area":null},{"id":"2104.11375","title":"Decentralized Federated Averaging","created":"2021-04-23","cited_by_count":114,"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":"2306.01603","title":"Decentralized Federated Learning: A Survey and Perspective","created":"2023-06-02","cited_by_count":86,"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":"2107.06925","title":"Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines","created":"2021-07-14","cited_by_count":68,"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":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2108.09875","title":"Anarchic Federated Learning","created":"2021-08-23","cited_by_count":42,"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":"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":"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":"2206.10870","title":"Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks","created":"2022-06-22","cited_by_count":32,"area":null},{"id":"2301.01313","title":"Decentralized Gradient Tracking with Local Steps","created":"2023-01-03","cited_by_count":32,"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":"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":"2112.07221","title":"HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework","created":"2021-12-14","cited_by_count":28,"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":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26,"area":null},{"id":"2105.09080","title":"Accelerating Gossip SGD with Periodic Global Averaging","created":"2021-05-19","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":"2210.14026","title":"SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication","created":"2022-10-25","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":"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":"2205.13797","title":"AsyncFedED: Asynchronous Federated Learning with Euclidean Distance based Adaptive Weight Aggregation","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2101.03705","title":"FedAR: Activity and Resource-Aware Federated Learning Model for Distributed Mobile Robots","created":"2021-01-11","cited_by_count":18,"area":null},{"id":"2501.16168","title":"Ringmaster ASGD: The First Asynchronous SGD with Optimal Time Complexity","created":"2025-01-27","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":"2111.05897","title":"Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters","created":"2021-11-10","cited_by_count":17,"area":null},{"id":"2206.10189","title":"A General Theory for Federated Optimization with Asynchronous and Heterogeneous Clients Updates","created":"2022-06-21","cited_by_count":17,"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":"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":"2107.01499","title":"BAGUA: Scaling up Distributed Learning with System Relaxations","created":"2021-07-03","cited_by_count":13,"area":null},{"id":"2104.07365","title":"D-Cliques: Compensating for Data Heterogeneity with Topology in Decentralized Federated Learning","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2203.10736","title":"The activity-weight duality in feed forward neural networks: The geometric determinants of generalization","created":"2022-03-21","cited_by_count":12,"area":null},{"id":"2209.10931","title":"Robust Collaborative Learning with Linear Gradient Overhead","created":"2022-09-22","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":"2312.02515","title":"mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2311.00465","title":"Asynchronous SGD on Graphs: a Unified Framework for Asynchronous Decentralized and Federated Optimization","created":"2023-11-01","cited_by_count":11,"area":null},{"id":"2405.15362","title":"Pipeline Parallelism with Controllable Memory","created":"2024-05-24","cited_by_count":11,"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":"2508.14318","title":"Power Stabilization for AI Training Datacenters","created":"2025-08-20","cited_by_count":9,"area":null},{"id":"2112.13381","title":"FRuDA: Framework for Distributed Adversarial Domain Adaptation","created":"2021-12-26","cited_by_count":8,"area":null},{"id":"2410.23131","title":"Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis","created":"2024-10-30","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":"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":"2106.06401","title":"Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning","created":"2021-06-11","cited_by_count":6,"area":null},{"id":"2305.13041","title":"Distributed Learning over Networks with Graph-Attention-Based Personalization","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2305.15371","title":"Stochastic Unrolled Federated Learning","created":"2023-05-24","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":"2312.04504","title":"Coordination-free Decentralised Federated Learning on Complex Networks: Overcoming Heterogeneity","created":"2023-12-07","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":"2103.13026","title":"The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication","created":"2021-03-24","cited_by_count":5,"area":null},{"id":"2205.08364","title":"Network Gradient Descent Algorithm for Decentralized Federated Learning","created":"2022-05-06","cited_by_count":5,"area":null},{"id":"2307.10492","title":"Blockchain-Based Federated Learning: Incentivizing Data Sharing and Penalizing Dishonest Behavior","created":"2023-07-19","cited_by_count":5,"area":null},{"id":"2309.04980","title":"Linear Speedup of Incremental Aggregated Gradient Methods on Streaming Data","created":"2023-09-10","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":"2407.19234","title":"Ordered Momentum for Asynchronous SGD","created":"2024-07-27","cited_by_count":5,"area":null},{"id":"2410.03529","title":"No Need to Talk: Asynchronous Mixture of Language Models","created":"2024-10-04","cited_by_count":5,"area":null},{"id":"2503.17469","title":"OmniLearn: A Framework for Distributed Deep Learning over Heterogeneous Clusters","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2104.05588","title":"Accelerating Neural Network Training with Distributed Asynchronous and Selective Optimization (DASO)","created":"2021-04-12","cited_by_count":4,"area":null},{"id":"2109.07704","title":"Federated Submodel Optimization for Hot and Cold Data Features","created":"2021-09-16","cited_by_count":4,"area":null},{"id":"2112.04737","title":"Asynchronous Semi-Decentralized Federated Edge Learning for Heterogeneous Clients","created":"2021-12-09","cited_by_count":4,"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":"2306.07159","title":"On the Computation-Communication Trade-Off with A Flexible Gradient Tracking Approach","created":"2023-06-12","cited_by_count":4,"area":null},{"id":"2403.11795","title":"Low-Cost Privacy-Preserving Decentralized Learning","created":"2024-03-18","cited_by_count":4,"area":null},{"id":"2404.11754","title":"Differentiated Aggregation to Improve Generalization in Federated Learning","created":"2024-04-17","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":"2407.07966","title":"A Comprehensive Survey on the Security of Smart Grid: Challenges, Mitigations, and Future Research Opportunities","created":"2024-07-10","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":"2102.06280","title":"Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers","created":"2021-02-11","cited_by_count":3,"area":null},{"id":"2104.13092","title":"Towards On-Device Federated Learning: A Direct Acyclic Graph-based Blockchain Approach","created":"2021-04-27","cited_by_count":3,"area":null},{"id":"2106.03585","title":"Asynchronous speedup in decentralized optimization","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2112.01433","title":"Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2210.10311","title":"Latency Aware Semi-synchronous Client Selection and Model Aggregation for Wireless Federated Learning","created":"2022-10-19","cited_by_count":3,"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":"2305.13503","title":"Asynchronous Multi-Model Dynamic Federated Learning over Wireless Networks: Theory, Modeling, and Optimization","created":"2023-05-22","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":"2308.08072","title":"Decentralized Graph Neural Network for Privacy-Preserving Recommendation","created":"2023-08-15","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":"2412.07890","title":"Protocol Learning, Decentralized Frontier Risk and the No-Off Problem","created":"2024-12-10","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":"2105.13348","title":"Optimization in Open Networks via Dual Averaging","created":"2021-05-27","cited_by_count":2,"area":null},{"id":"2110.07029","title":"Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2110.11199","title":"Asynchronous Decentralized Distributed Training of Acoustic Models","created":"2021-10-21","cited_by_count":2,"area":null},{"id":"2111.14837","title":"p2pGNN: A Decentralized Graph Neural Network for Node Classification in Peer-to-Peer Networks","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2112.07938","title":"Analysis and Evaluation of Synchronous and Asynchronous FLchain","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2201.12718","title":"Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning","created":"2022-01-30","cited_by_count":2,"area":null},{"id":"2208.13154","title":"Asynchronous Training Schemes in Distributed Learning with Time Delay","created":"2022-08-28","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":"2211.00889","title":"Accelerating Parallel Stochastic Gradient Descent via Non-blocking Mini-batches","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2211.10280","title":"TensAIR: Real-Time Training of Neural Networks from Data-streams","created":"2022-11-18","cited_by_count":2,"area":null},{"id":"2303.04676","title":"Considerations on the Theory of Training Models with Differential Privacy","created":"2023-03-08","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":"2308.13157","title":"Federated Learning in IoT: a Survey from a Resource-Constrained Perspective","created":"2023-08-25","cited_by_count":2,"area":null}],"next_cursor":"100"}