{"total":25,"rows":[{"id":"2103.04628","title":"Personalized Federated Learning using Hypernetworks","created":"2021-03-08","cited_by_count":212,"area":null},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121,"area":null},{"id":"2106.10874","title":"FedCM: Federated Learning with Client-level Momentum","created":"2021-06-21","cited_by_count":77,"area":null},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2401.09135","title":"Asynchronous Local-SGD Training for Language Modeling","created":"2024-01-17","cited_by_count":26,"area":null},{"id":"2109.08119","title":"Personalized Federated Learning for Heterogeneous Clients with Clustered Knowledge Transfer","created":"2021-09-16","cited_by_count":23,"area":null},{"id":"2502.12996","title":"Eager Updates For Overlapped Communication and Computation in DiLoCo","created":"2025-02-18","cited_by_count":11,"area":null},{"id":"2102.03970","title":"Coordinating Momenta for Cross-silo Federated Learning","created":"2021-02-08","cited_by_count":9,"area":null},{"id":"2201.01954","title":"Federated Optimization of Smooth Loss Functions","created":"2022-01-06","cited_by_count":6,"area":null},{"id":"2210.14560","title":"Hierarchical Federated Learning with Momentum Acceleration in Multi-Tier Networks","created":"2022-10-26","cited_by_count":6,"area":null},{"id":"2302.06599","title":"FilFL: Client Filtering for Optimized Client Participation in Federated Learning","created":"2023-02-13","cited_by_count":5,"area":null},{"id":"2405.14446","title":"Worldwide Federated Training of Language Models","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2412.01630","title":"Review of Mathematical Optimization in Federated Learning","created":"2024-12-02","cited_by_count":3,"area":null},{"id":"2108.05974","title":"An Operator Splitting View of Federated Learning","created":"2021-08-12","cited_by_count":2,"area":null},{"id":"2204.03174","title":"FedCos: A Scene-adaptive Federated Optimization Enhancement for Performance Improvement","created":"2022-04-07","cited_by_count":2,"area":null},{"id":"2404.15834","title":"FEDSTR: Money-In AI-Out | A Decentralized Marketplace for Federated Learning and LLM Training on the NOSTR Protocol","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2510.05361","title":"MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2406.16193","title":"Semi-Variance Reduction for Fair Federated Learning","created":"2024-06-23","cited_by_count":1,"area":null},{"id":"2509.19396","title":"OmniFed: A Modular Framework for Configurable Federated Learning from Edge to HPC","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2202.08402","title":"Federated Stochastic Gradient Descent Begets Self-Induced Momentum","created":"2022-02-17","cited_by_count":0,"area":null},{"id":"2301.03720","title":"Federated Learning for Energy Constrained IoT devices: A systematic mapping study","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2411.02908","title":"Photon: Federated LLM Pre-Training","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2608.22945","title":"A Momentum-Based Variance-Reduced Algorithm for Federated Multiobjective Optimization","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.20359","title":"Accelerating Sharded Data Parallelism at Scale with Federated Learning","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}