{"list":"other","total":52,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"2012.04221","title":"Ditto: Fair and Robust Federated Learning Through Personalization","created":"2020-12-08","cited_by_count":672},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"2006.04088","title":"An Efficient Framework for Clustered Federated Learning","created":"2020-06-07","cited_by_count":511},{"id":"1407.0202","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","created":"2014-07-01","cited_by_count":402},{"id":"1905.10497","title":"Fair Resource Allocation in Federated Learning","created":"2019-05-25","cited_by_count":394},{"id":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"1803.00942","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling","created":"2018-03-02","cited_by_count":328},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"2010.01243","title":"Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies","created":"2020-10-03","cited_by_count":198},{"id":"2009.13012","title":"Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges","created":"2020-09-28","cited_by_count":139},{"id":"1310.5715","title":"Stochastic Gradient Descent, Weighted Sampling, and the Randomized Kaczmarz algorithm","created":"2013-10-21","cited_by_count":133},{"id":"2010.13723","title":"Optimal Client Sampling for Federated Learning","created":"2020-10-26","cited_by_count":124},{"id":"2007.01162","title":"Tilted Empirical Risk Minimization","created":"2020-07-02","cited_by_count":106},{"id":"2105.05883","title":"Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning","created":"2021-05-12","cited_by_count":93},{"id":"1401.2753","title":"Stochastic Optimization with Importance Sampling","created":"2014-01-13","cited_by_count":91},{"id":"2106.04159","title":"Fast Federated Learning in the Presence of Arbitrary Device Unavailability","created":"2021-06-08","cited_by_count":72},{"id":"2207.14130","title":"FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning","created":"2022-07-28","cited_by_count":64},{"id":"2107.11621","title":"FedLab: A Flexible Federated Learning Framework","created":"2021-07-24","cited_by_count":55},{"id":"2011.11266","title":"Federated learning with class imbalance reduction","created":"2020-11-23","cited_by_count":52},{"id":"2207.04338","title":"Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning","created":"2022-07-09","cited_by_count":33},{"id":"2202.06187","title":"On the Convergence of Clustered Federated Learning","created":"2022-02-13","cited_by_count":31},{"id":"2302.03109","title":"On the Convergence of Federated Averaging with Cyclic Client Participation","created":"2023-02-06","cited_by_count":31},{"id":"1706.04957","title":"Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications","created":"2017-06-15","cited_by_count":29},{"id":"2012.08009","title":"Bandit-based Communication-Efficient Client Selection Strategies for Federated Learning","created":"2020-12-14","cited_by_count":29},{"id":"2307.09619","title":"Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning","created":"2023-07-18","cited_by_count":29},{"id":"2205.13925","title":"DELTA: Diverse Client Sampling for Fasting Federated Learning","created":"2022-05-27","cited_by_count":24},{"id":"2306.05706","title":"Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization","created":"2023-06-09","cited_by_count":21},{"id":"1310.3438","title":"On Optimal Probabilities in Stochastic Coordinate Descent Methods","created":"2013-10-13","cited_by_count":14},{"id":"1412.8060","title":"Coordinate Descent with Arbitrary Sampling I: Algorithms and Complexity","created":"2014-12-27","cited_by_count":14},{"id":"1809.04146","title":"Nonconvex Variance Reduced Optimization with Arbitrary Sampling","created":"2018-09-11","cited_by_count":14},{"id":"2302.03662","title":"Federated Learning with Regularized Client Participation","created":"2023-02-07","cited_by_count":14},{"id":"1802.04715","title":"Online Variance Reduction for Stochastic Optimization","created":"2018-02-13","cited_by_count":11},{"id":"2103.12243","title":"Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes","created":"2021-03-23","cited_by_count":10},{"id":"1708.02544","title":"Stochastic Optimization with Bandit Sampling","created":"2017-08-08","cited_by_count":9},{"id":"1903.12416","title":"Online Variance Reduction with Mixtures","created":"2019-03-29","cited_by_count":8},{"id":"2208.05135","title":"Fast Heterogeneous Federated Learning with Hybrid Client Selection","created":"2022-08-10","cited_by_count":8},{"id":"2012.03270","title":"Accurate and Fast Federated Learning via Combinatorial Multi-Armed Bandits","created":"2020-12-06","cited_by_count":7},{"id":"2112.14332","title":"Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback","created":"2021-12-28","cited_by_count":7},{"id":"2204.08134","title":"A Practical Cross-Device Federated Learning Framework over 5G Networks","created":"2022-04-18","cited_by_count":7},{"id":"2310.00198","title":"Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning","created":"2023-09-30","cited_by_count":2}],"next_cursor":null}