{"list":"other","total":54,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2003.08119","title":"The Future of Digital Health with Federated Learning","created":"2020-03-18","cited_by_count":633},{"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":"1909.11875","title":"Federated Learning in Mobile Edge Networks: A Comprehensive Survey","created":"2019-09-26","cited_by_count":408},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"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":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"1807.06629","title":"Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning","created":"2018-07-17","cited_by_count":278},{"id":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1905.13727","title":"PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization","created":"2019-05-31","cited_by_count":238},{"id":"2002.05516","title":"Federated Learning of a Mixture of Global and Local Models","created":"2020-02-10","cited_by_count":210},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"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":"2101.11203","title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","created":"2021-01-27","cited_by_count":193},{"id":"2102.13451","title":"FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout","created":"2021-02-26","cited_by_count":192},{"id":"1910.06378","title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","created":"2019-10-14","cited_by_count":175},{"id":"1610.02132","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","created":"2016-10-07","cited_by_count":147},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"1812.00984","title":"Protection Against Reconstruction and Its Applications in Private Federated Learning","created":"2018-12-03","cited_by_count":130},{"id":"2010.13723","title":"Optimal Client Sampling for Federated Learning","created":"2020-10-26","cited_by_count":124},{"id":"2006.05988","title":"Random Reshuffling: Simple Analysis with Vast Improvements","created":"2020-06-10","cited_by_count":115},{"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":"1905.10988","title":"Natural Compression for Distributed Deep Learning","created":"2019-05-27","cited_by_count":90},{"id":"2008.00051","title":"On the Convergence of SGD with Biased Gradients","created":"2020-07-31","cited_by_count":83},{"id":"1510.08560","title":"Why Random Reshuffling Beats Stochastic Gradient Descent","created":"2015-10-29","cited_by_count":79},{"id":"2004.01442","title":"From Local SGD to Local Fixed-Point Methods for Federated Learning","created":"2020-04-03","cited_by_count":74},{"id":"2106.04159","title":"Fast Federated Learning in the Presence of Arbitrary Device Unavailability","created":"2021-06-08","cited_by_count":72},{"id":"2112.11256","title":"Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling","created":"2021-12-21","cited_by_count":66},{"id":"2006.06954","title":"Towards Flexible Device Participation in Federated Learning","created":"2020-06-12","cited_by_count":65},{"id":"2007.13137","title":"Fast-Convergent Federated Learning","created":"2020-07-26","cited_by_count":61},{"id":"1506.01900","title":"Communication Complexity of Distributed Convex Learning and Optimization","created":"2015-06-05","cited_by_count":60},{"id":"2006.06946","title":"SGD with shuffling: optimal rates without component convexity and large epoch requirements","created":"2020-06-12","cited_by_count":58},{"id":"2205.13648","title":"A Unified Analysis of Federated Learning with Arbitrary Client Participation","created":"2022-05-26","cited_by_count":45},{"id":"2006.11077","title":"A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning","created":"2020-06-19","cited_by_count":43},{"id":"2108.09875","title":"Anarchic Federated Learning","created":"2021-08-23","cited_by_count":42},{"id":"1611.07555","title":"Randomized Distributed Mean Estimation: Accuracy vs Communication","created":"2016-11-22","cited_by_count":39},{"id":"2007.15197","title":"Communication-Efficient Federated Learning via Optimal Client Sampling","created":"2020-07-30","cited_by_count":39},{"id":"2110.10342","title":"Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond","created":"2021-10-20","cited_by_count":36},{"id":"2102.06704","title":"Proximal and Federated Random Reshuffling","created":"2021-02-12","cited_by_count":33},{"id":"2207.04338","title":"Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning","created":"2022-07-09","cited_by_count":33},{"id":"2201.11066","title":"Server-Side Stepsizes and Sampling Without Replacement Provably Help in Federated Optimization","created":"2022-01-26","cited_by_count":23},{"id":"2212.14370","title":"Can 5th Generation Local Training Methods Support Client Sampling? Yes!","created":"2022-12-29","cited_by_count":22},{"id":"2204.13169","title":"FedShuffle: Recipes for Better Use of Local Work in Federated Learning","created":"2022-04-27","cited_by_count":21},{"id":"2002.07399","title":"Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability","created":"2020-02-18","cited_by_count":20},{"id":"2104.09342","title":"Random Reshuffling with Variance Reduction: New Analysis and Better Rates","created":"2021-04-19","cited_by_count":19},{"id":"2206.07021","title":"Federated Optimization Algorithms with Random Reshuffling and Gradient Compression","created":"2022-06-14","cited_by_count":18},{"id":"2205.03914","title":"Federated Random Reshuffling with Compression and Variance Reduction","created":"2022-05-08","cited_by_count":12},{"id":"2202.03099","title":"FL_PyTorch: optimization research simulator for federated learning","created":"2022-02-07","cited_by_count":10},{"id":"2111.13322","title":"Random-reshuffled SARAH does not need a full gradient computations","created":"2021-11-26","cited_by_count":7},{"id":"2004.08657","title":"On Tight Convergence Rates of Without-replacement SGD","created":"2020-04-18","cited_by_count":3},{"id":"1901.09437","title":"99% of Distributed Optimization is a Waste of Time: The Issue and How to Fix it","created":"2019-01-27","cited_by_count":1}],"next_cursor":null}