{"list":"other","total":67,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"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":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"1705.10467","title":"Federated Multi-Task Learning","created":"2017-05-30","cited_by_count":672},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1912.00818","title":"Federated Learning with Personalization Layers","created":"2019-12-02","cited_by_count":541},{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"2003.13461","title":"Adaptive Personalized Federated Learning","created":"2020-03-30","cited_by_count":358},{"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":"2007.13518","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","created":"2020-07-27","cited_by_count":300},{"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":"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":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"2103.04628","title":"Personalized Federated Learning using Hypernetworks","created":"2021-03-08","cited_by_count":212},{"id":"2002.05516","title":"Federated Learning of a Mixture of Global and Local Models","created":"2020-02-10","cited_by_count":210},{"id":"1901.09401","title":"SGD: General Analysis and Improved Rates","created":"2019-01-27","cited_by_count":207},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"2012.08565","title":"Personalized Federated Learning with First Order Model Optimization","created":"2020-12-15","cited_by_count":201},{"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":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"2003.08673","title":"Survey of Personalization Techniques for Federated Learning","created":"2020-03-19","cited_by_count":145},{"id":"2002.12410","title":"On Biased Compression for Distributed Learning","created":"2020-02-27","cited_by_count":140},{"id":"1611.00429","title":"Distributed Mean Estimation with Limited Communication","created":"2016-11-02","cited_by_count":136},{"id":"1806.04090","title":"ATOMO: Communication-efficient Learning via Atomic Sparsification","created":"2018-06-11","cited_by_count":136},{"id":"1312.7853","title":"Communication Efficient Distributed Optimization using an Approximate Newton-type Method","created":"2013-12-30","cited_by_count":132},{"id":"2006.05988","title":"Random Reshuffling: Simple Analysis with Vast Improvements","created":"2020-06-10","cited_by_count":115},{"id":"2204.03809","title":"Federated Learning with Partial Model Personalization","created":"2022-04-08","cited_by_count":114},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"id":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"id":"1805.09965","title":"LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning","created":"2018-05-25","cited_by_count":96},{"id":"2205.03993","title":"Layer-wised Model Aggregation for Personalized Federated Learning","created":"2022-05-09","cited_by_count":96},{"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":"1412.6651","title":"Deep learning with Elastic Averaging SGD","created":"2014-12-20","cited_by_count":90},{"id":"1905.10988","title":"Natural Compression for Distributed Deep Learning","created":"2019-05-27","cited_by_count":90},{"id":"2011.02828","title":"Local SGD: Unified Theory and New Efficient Methods","created":"2020-11-03","cited_by_count":88},{"id":"1909.04715","title":"First Analysis of Local GD on Heterogeneous Data","created":"2019-09-10","cited_by_count":81},{"id":"1810.00736","title":"Benchmark Analysis of Representative Deep Neural Network Architectures","created":"2018-10-01","cited_by_count":77},{"id":"1810.08313","title":"Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD","created":"2018-10-19","cited_by_count":77},{"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":"1808.04752","title":"A Survey on Methods and Theories of Quantized Neural Networks","created":"2018-08-13","cited_by_count":75},{"id":"2206.00187","title":"DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training","created":"2022-06-01","cited_by_count":74},{"id":"1904.05115","title":"Stochastic Distributed Learning with Gradient Quantization and Variance Reduction","created":"2019-04-10","cited_by_count":65},{"id":"2010.12292","title":"Linearly Converging Error Compensated SGD","created":"2020-10-23","cited_by_count":61},{"id":"1806.06573","title":"Distributed learning with compressed gradients","created":"2018-06-18","cited_by_count":55},{"id":"2006.10672","title":"Federated Learning With Quantized Global Model Updates","created":"2020-06-18","cited_by_count":55},{"id":"2002.08958","title":"Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor","created":"2020-02-20","cited_by_count":45},{"id":"2108.00951","title":"Rethinking gradient sparsification as total error minimization","created":"2021-08-02","cited_by_count":41},{"id":"1611.07555","title":"Randomized Distributed Mean Estimation: Accuracy vs Communication","created":"2016-11-22","cited_by_count":39},{"id":"2204.03880","title":"CD$^2$-pFed: Cyclic Distillation-guided Channel Decoupling for Model Personalization in Federated Learning","created":"2022-04-08","cited_by_count":34},{"id":"1911.08250","title":"On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep Learning","created":"2019-11-19","cited_by_count":32},{"id":"1409.1458","title":"Communication-Efficient Distributed Dual Coordinate Ascent","created":"2014-09-04","cited_by_count":31},{"id":"1811.03619","title":"Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training","created":"2018-11-08","cited_by_count":28},{"id":"1912.09925","title":"Distributed Fixed Point Methods with Compressed Iterates","created":"2019-12-20","cited_by_count":11},{"id":"1901.08924","title":"Exploring Fast and Communication-Efficient Algorithms in Large-scale Distributed Networks","created":"2019-01-25","cited_by_count":8}],"next_cursor":null}