{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"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":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"1903.02891","title":"Robust and Communication-Efficient Federated Learning from Non-IID Data","created":"2019-03-07","cited_by_count":419},{"id":"1809.07599","title":"Sparsified SGD with Memory","created":"2018-09-20","cited_by_count":376},{"id":"1804.08333","title":"Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge","created":"2018-04-23","cited_by_count":352},{"id":"1901.09847","title":"Error Feedback Fixes SignSGD and other Gradient Compression Schemes","created":"2019-01-28","cited_by_count":310},{"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":"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":"1811.11479","title":"Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data","created":"2018-11-28","cited_by_count":243},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1905.06641","title":"Client-Edge-Cloud Hierarchical Federated Learning","created":"2019-05-16","cited_by_count":202},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"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":"1910.00962","title":"Privacy-preserving Federated Brain Tumour Segmentation","created":"2019-10-02","cited_by_count":169},{"id":"1310.7063","title":"On the Convergence of Decentralized Gradient Descent","created":"2013-10-26","cited_by_count":159},{"id":"1610.02132","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","created":"2016-10-07","cited_by_count":147},{"id":"1803.07068","title":"D$^2$: Decentralized Training over Decentralized Data","created":"2018-03-19","cited_by_count":140},{"id":"1908.06287","title":"Scheduling Policies for Federated Learning in Wireless Networks","created":"2019-08-17","cited_by_count":131},{"id":"1910.00643","title":"SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum","created":"2019-10-01","cited_by_count":121},{"id":"1506.08272","title":"Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization","created":"2015-06-27","cited_by_count":116},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"id":"1808.07576","title":"Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms","created":"2018-08-22","cited_by_count":106},{"id":"1609.08326","title":"Asynchronous Stochastic Gradient Descent with Delay Compensation","created":"2016-09-27","cited_by_count":99},{"id":"1905.05957","title":"DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression","created":"2019-05-15","cited_by_count":99},{"id":"1909.02362","title":"Hierarchical Federated Learning Across Heterogeneous Cellular Networks","created":"2019-09-05","cited_by_count":98},{"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":"1812.02858","title":"Wireless Network Intelligence at the Edge","created":"2018-12-07","cited_by_count":92},{"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":"2001.10402","title":"Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edge","created":"2020-01-28","cited_by_count":71},{"id":"1706.07880","title":"Collaborative Deep Learning in Fixed Topology Networks","created":"2017-06-23","cited_by_count":60},{"id":"2007.02315","title":"Multi-Armed Bandit Based Client Scheduling for Federated Learning","created":"2020-07-05","cited_by_count":57},{"id":"1905.10936","title":"Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback","created":"2019-05-27","cited_by_count":50},{"id":"1911.00856","title":"Device Scheduling with Fast Convergence for Wireless Federated Learning","created":"2019-11-03","cited_by_count":46},{"id":"1511.05950","title":"Staleness-aware Async-SGD for Distributed Deep Learning","created":"2015-11-18","cited_by_count":43},{"id":"1608.05766","title":"On Nonconvex Decentralized Gradient Descent","created":"2016-08-20","cited_by_count":42},{"id":"1910.14648","title":"Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networks","created":"2019-10-31","cited_by_count":39},{"id":"2007.07122","title":"Energy-Efficient Resource Management for Federated Edge Learning with CPU-GPU Heterogeneous Computing","created":"2020-07-14","cited_by_count":39},{"id":"1901.04359","title":"A Distributed Synchronous SGD Algorithm with Global Top-$k$ Sparsification for Low Bandwidth Networks","created":"2019-01-14","cited_by_count":37},{"id":"2008.11141","title":"Convergence of Federated Learning over a Noisy Downlink","created":"2020-08-25","cited_by_count":29},{"id":"2009.13269","title":"Communicate to Learn at the Edge","created":"2020-09-28","cited_by_count":28},{"id":"2005.10761","title":"rTop-k: A Statistical Estimation Approach to Distributed SGD","created":"2020-05-21","cited_by_count":27},{"id":"2003.04216","title":"Decentralized SGD with Over-the-Air Computation","created":"2020-03-06","cited_by_count":16},{"id":"2009.09271","title":"Sparse Communication for Training Deep Networks","created":"2020-09-19","cited_by_count":10},{"id":"2011.06495","title":"Distributed Sparse SGD with Majority Voting","created":"2020-11-12","cited_by_count":2}],"next_cursor":null}