{"total":36,"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":"2206.07638","title":"Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays","created":"2022-06-15","cited_by_count":63,"area":null},{"id":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38,"area":null},{"id":"2201.07598","title":"Near-Optimal Sparse Allreduce for Distributed Deep Learning","created":"2022-01-19","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":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2410.15526","title":"SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training","created":"2024-10-20","cited_by_count":14,"area":null},{"id":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13,"area":null},{"id":"2206.03588","title":"Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation","created":"2022-06-07","cited_by_count":11,"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":"2206.10032","title":"Communication-Efficient Federated Learning With Data and Client Heterogeneity","created":"2022-06-20","cited_by_count":9,"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":"2312.07060","title":"Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learning","created":"2023-12-12","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":"2411.17461","title":"SoK: Blockchain-Based Decentralized AI (DeAI)","created":"2024-11-26","cited_by_count":6,"area":null},{"id":"2310.14423","title":"A Quadratic Synchronization Rule for Distributed Deep Learning","created":"2023-10-22","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":"2205.11048","title":"GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Model","created":"2022-05-23","cited_by_count":4,"area":null},{"id":"2304.13545","title":"Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning","created":"2023-04-26","cited_by_count":4,"area":null},{"id":"2308.00890","title":"Tango: rethinking quantization for graph neural network training on GPUs","created":"2023-08-02","cited_by_count":4,"area":null},{"id":"2106.03585","title":"Asynchronous speedup in decentralized optimization","created":"2021-06-07","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":"2404.08079","title":"DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models","created":"2024-04-11","cited_by_count":3,"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":"2307.11617","title":"Robust Fully-Asynchronous Methods for Distributed Training over General Architecture","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2507.06931","title":"DICE: Data Influence Cascade in Decentralized Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2411.00365","title":"ROSS: RObust decentralized Stochastic learning based on Shapley values","created":"2024-11-01","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":"2311.05760","title":"Compressed and Sparse Models for Non-Convex Decentralized Learning","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2403.11163","title":"A Selective Review on Statistical Methods for Massive Data Computation: Distributed Computing, Subsampling, and Minibatch Techniques","created":"2024-03-17","cited_by_count":0,"area":null},{"id":"2410.18774","title":"A Stochastic Approximation Approach for Efficient Decentralized Optimization on Random Networks","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2503.16123","title":"Distributed Learning over Arbitrary Topology: Linear Speed-Up with Polynomial Transient Time","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2504.09792","title":"A Tale of Two Learning Algorithms: Multiple Stream Random Walk and Asynchronous Gossip","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2505.05486","title":"FedAvgen: Metadata for Model Aggregation In Communication Systems","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2509.03709","title":"From Federated Learning to X-Learning: Breaking the Barriers of Decentrality Through Random Walks","created":"2025-09-03","cited_by_count":0,"area":null}],"next_cursor":null}