{"list":"other","total":67,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"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":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"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":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"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":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"1705.10467","title":"Federated Multi-Task Learning","created":"2017-05-30","cited_by_count":672},{"id":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541},{"id":"1911.00222","title":"Federated Learning with Differential Privacy: Algorithms and Performance Analysis","created":"2019-11-01","cited_by_count":536},{"id":"1910.01991","title":"Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints","created":"2019-10-04","cited_by_count":503},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"id":"1903.02891","title":"Robust and Communication-Efficient Federated Learning from Non-IID Data","created":"2019-03-07","cited_by_count":419},{"id":"1804.05271","title":"Adaptive Federated Learning in Resource Constrained Edge Computing Systems","created":"2018-04-14","cited_by_count":409},{"id":"1905.10497","title":"Fair Resource Allocation in Federated Learning","created":"2019-05-25","cited_by_count":394},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"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":"1605.02065","title":"Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds","created":"2016-05-06","cited_by_count":346},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1912.13445","title":"Robust Aggregation for Federated Learning","created":"2019-12-31","cited_by_count":317},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"1909.12488","title":"Improving Federated Learning Personalization via Model Agnostic Meta Learning","created":"2019-09-27","cited_by_count":269},{"id":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1702.05373","title":"EMNIST: an extension of MNIST to handwritten letters","created":"2017-02-17","cited_by_count":213},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"id":"2010.05893","title":"Large-Scale Methods for Distributionally Robust Optimization","created":"2020-10-12","cited_by_count":179},{"id":"1506.02188","title":"Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach","created":"2015-06-06","cited_by_count":170},{"id":"1908.08729","title":"Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning","created":"2019-08-23","cited_by_count":170},{"id":"1803.06523","title":"Stochastic model-based minimization of weakly convex functions","created":"2018-03-17","cited_by_count":159},{"id":"1610.02581","title":"Variance-based regularization with convex objectives","created":"2016-10-08","cited_by_count":155},{"id":"2004.00010","title":"The Discrete Gaussian for Differential Privacy","created":"2020-03-31","cited_by_count":135},{"id":"2102.06387","title":"The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation","created":"2021-02-12","cited_by_count":128},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"id":"2006.03262","title":"UVeQFed: Universal Vector Quantization for Federated Learning","created":"2020-06-05","cited_by_count":107},{"id":"2007.01162","title":"Tilted Empirical Risk Minimization","created":"2020-07-02","cited_by_count":106},{"id":"2102.12660","title":"Distributionally Robust Federated Averaging","created":"2021-02-25","cited_by_count":104},{"id":"2006.08907","title":"Robust Federated Learning: The Case of Affine Distribution Shifts","created":"2020-06-16","cited_by_count":102},{"id":"1708.01012","title":"On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization","created":"2017-08-03","cited_by_count":92},{"id":"1901.08665","title":"Fairness risk measures","created":"2019-01-24","cited_by_count":85},{"id":"2102.08503","title":"Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications","created":"2021-02-16","cited_by_count":85},{"id":"1502.03919","title":"Policy Gradient for Coherent Risk Measures","created":"2015-02-13","cited_by_count":76},{"id":"2009.12787","title":"Over-the-Air Federated Learning from Heterogeneous Data","created":"2020-09-27","cited_by_count":73},{"id":"1903.09296","title":"Patient Clustering Improves Efficiency of Federated Machine Learning to predict mortality and hospital stay time using distributed Electronic Medical Records","created":"2019-03-22","cited_by_count":72},{"id":"1611.02189","title":"CoCoA: A General Framework for Communication-Efficient Distributed Optimization","created":"2016-11-07","cited_by_count":69},{"id":"2009.10031","title":"Training Production Language Models without Memorizing User Data","created":"2020-09-21","cited_by_count":68},{"id":"2110.04995","title":"The Skellam Mechanism for Differentially Private Federated Learning","created":"2021-10-11","cited_by_count":68},{"id":"2102.04487","title":"Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning","created":"2021-02-08","cited_by_count":63},{"id":"1605.00125","title":"Efficiency of minimizing compositions of convex functions and smooth maps","created":"2016-04-30","cited_by_count":59},{"id":"2010.05166","title":"Robust Fairness under Covariate Shift","created":"2020-10-11","cited_by_count":58},{"id":"2103.17150","title":"Federated Learning: A Signal Processing Perspective","created":"2021-03-31","cited_by_count":49},{"id":"1904.10120","title":"Semi-Cyclic Stochastic Gradient Descent","created":"2019-04-23","cited_by_count":40},{"id":"1910.12511","title":"Adaptive Sampling for Stochastic Risk-Averse Learning","created":"2019-10-28","cited_by_count":39},{"id":"1801.03749","title":"Improved asynchronous parallel optimization analysis for stochastic incremental methods","created":"2018-01-11","cited_by_count":30},{"id":"1808.04883","title":"COLA: Decentralized Linear Learning","created":"2018-08-13","cited_by_count":30},{"id":"1512.04039","title":"Distributed Optimization with Arbitrary Local Solvers","created":"2015-12-13","cited_by_count":23},{"id":"1812.10942","title":"Answering Range Queries Under Local Differential Privacy","created":"2018-12-28","cited_by_count":12},{"id":"1902.03228","title":"A Smoother Way to Train Structured Prediction Models","created":"2019-02-08","cited_by_count":9},{"id":"2009.14575","title":"First-order Optimization for Superquantile-based Supervised Learning","created":"2020-09-30","cited_by_count":4},{"id":"1512.04848","title":"Data Driven Resource Allocation for Distributed Learning","created":"2015-12-15","cited_by_count":3}],"next_cursor":null}