{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"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":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"2102.02079","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","created":"2021-02-03","cited_by_count":568},{"id":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"1909.13014","title":"FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization","created":"2019-09-28","cited_by_count":356},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"id":"2007.03797","title":"Personalized Cross-Silo Federated Learning on Non-IID Data","created":"2020-07-07","cited_by_count":283},{"id":"1704.05021","title":"Sparse Communication for Distributed Gradient Descent","created":"2017-04-17","cited_by_count":249},{"id":"1905.13727","title":"PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization","created":"2019-05-31","cited_by_count":238},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"1812.11750","title":"Federated Learning via Over-the-Air Computation","created":"2018-12-31","cited_by_count":219},{"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":"1907.09769","title":"Federated Learning over Wireless Fading Channels","created":"2019-07-23","cited_by_count":183},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"1905.03817","title":"On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization","created":"2019-05-09","cited_by_count":180},{"id":"1808.02941","title":"On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization","created":"2018-08-08","cited_by_count":174},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"2002.12410","title":"On Biased Compression for Distributed Learning","created":"2020-02-27","cited_by_count":140},{"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":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133},{"id":"1908.06287","title":"Scheduling Policies for Federated Learning in Wireless Networks","created":"2019-08-17","cited_by_count":131},{"id":"1908.06847","title":"Federated Learning for Wireless Communications: Motivation, Opportunities and Challenges","created":"2019-07-30","cited_by_count":129},{"id":"2001.06202","title":"FedVision: An Online Visual Object Detection Platform Powered by Federated Learning","created":"2020-01-17","cited_by_count":124},{"id":"2102.07053","title":"Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients","created":"2021-02-14","cited_by_count":123},{"id":"1506.08272","title":"Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization","created":"2015-06-27","cited_by_count":116},{"id":"1808.05671","title":"On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization","created":"2018-08-16","cited_by_count":91},{"id":"1903.04488","title":"Communication-efficient distributed SGD with Sketching","created":"2019-03-12","cited_by_count":81},{"id":"2102.07845","title":"MARINA: Faster Non-Convex Distributed Learning with Compression","created":"2021-02-15","cited_by_count":78},{"id":"1806.08054","title":"Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization","created":"2018-06-21","cited_by_count":76},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"1511.04561","title":"8-Bit Approximations for Parallelism in Deep Learning","created":"2015-11-14","cited_by_count":56},{"id":"1905.10936","title":"Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback","created":"2019-05-27","cited_by_count":50},{"id":"2010.12229","title":"Throughput-Optimal Topology Design for Cross-Silo Federated Learning","created":"2020-10-23","cited_by_count":39},{"id":"1910.07561","title":"A Double Residual Compression Algorithm for Efficient Distributed Learning","created":"2019-10-16","cited_by_count":31},{"id":"2102.01593","title":"FEDZIP: A Compression Framework for Communication-Efficient Federated Learning","created":"2021-02-02","cited_by_count":27},{"id":"2109.05109","title":"Toward Communication Efficient Adaptive Gradient Method","created":"2021-09-10","cited_by_count":25},{"id":"2111.10586","title":"Satellite Based Computing Networks with Federated Learning","created":"2021-11-20","cited_by_count":25},{"id":"1811.03617","title":"GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training","created":"2018-11-08","cited_by_count":21},{"id":"2008.04975","title":"FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching","created":"2020-08-11","cited_by_count":20},{"id":"2205.05632","title":"On Distributed Adaptive Optimization with Gradient Compression","created":"2022-05-11","cited_by_count":19},{"id":"2109.03194","title":"On the Convergence of Decentralized Adaptive Gradient Methods","created":"2021-09-07","cited_by_count":17},{"id":"1911.09721","title":"Communication-Efficient and Byzantine-Robust Distributed Learning with Error Feedback","created":"2019-11-21","cited_by_count":15},{"id":"1805.09969","title":"Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication","created":"2018-05-25","cited_by_count":13},{"id":"2201.05500","title":"Communication-Efficient TeraByte-Scale Model Training Framework for Online Advertising","created":"2022-01-05","cited_by_count":5}],"next_cursor":null}