{"list":"other","total":53,"rows":[{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"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":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"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":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"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":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"1705.10467","title":"Federated Multi-Task Learning","created":"2017-05-30","cited_by_count":672},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"id":"2102.02079","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","created":"2021-02-03","cited_by_count":568},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"2004.02984","title":"MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices","created":"2020-04-06","cited_by_count":482},{"id":"1712.07557","title":"Differentially Private Federated Learning: A Client Level Perspective","created":"2017-12-20","cited_by_count":459},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"id":"1909.11875","title":"Federated Learning in Mobile Edge Networks: A Comprehensive Survey","created":"2019-09-26","cited_by_count":408},{"id":"1905.10497","title":"Fair Resource Allocation in Federated Learning","created":"2019-05-25","cited_by_count":394},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"2104.07857","title":"ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning","created":"2021-04-16","cited_by_count":256},{"id":"2106.05001","title":"No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data","created":"2021-06-09","cited_by_count":241},{"id":"1911.02549","title":"MLPerf Inference Benchmark","created":"2019-11-06","cited_by_count":199},{"id":"1910.01500","title":"MLPerf Training Benchmark","created":"2019-10-02","cited_by_count":115},{"id":"1509.09308","title":"Fast Algorithms for Convolutional Neural Networks","created":"2015-09-30","cited_by_count":102},{"id":"1910.13067","title":"Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation","created":"2019-10-29","cited_by_count":94},{"id":"1312.5851","title":"Fast Training of Convolutional Networks through FFTs","created":"2013-12-20","cited_by_count":89},{"id":"1801.08618","title":"JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services","created":"2018-01-25","cited_by_count":80},{"id":"2008.03371","title":"LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets","created":"2020-08-07","cited_by_count":60},{"id":"2011.11266","title":"Federated learning with class imbalance reduction","created":"2020-11-23","cited_by_count":52},{"id":"2011.05497","title":"Understanding Training Efficiency of Deep Learning Recommendation Models at Scale","created":"2020-11-11","cited_by_count":43},{"id":"2003.09518","title":"Deep Learning Training in Facebook Data Centers: Design of Scale-up and Scale-out Systems","created":"2020-03-20","cited_by_count":38},{"id":"2009.02010","title":"ConfuciuX: Autonomous Hardware Resource Assignment for DNN Accelerators using Reinforcement Learning","created":"2020-09-04","cited_by_count":35},{"id":"1710.05420","title":"NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks","created":"2017-10-15","cited_by_count":30},{"id":"2103.15332","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","created":"2021-03-29","cited_by_count":23},{"id":"2007.09208","title":"Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise","created":"2020-07-17","cited_by_count":21},{"id":"2005.12326","title":"Towards Efficient Scheduling of Federated Mobile Devices under Computational and Statistical Heterogeneity","created":"2020-05-25","cited_by_count":20},{"id":"1908.11450","title":"Neural Network Inference on Mobile SoCs","created":"2019-08-24","cited_by_count":17},{"id":"1805.08899","title":"Echo: Compiler-based GPU Memory Footprint Reduction for LSTM RNN Training","created":"2018-05-22","cited_by_count":10},{"id":"1908.04705","title":"Exploiting Parallelism Opportunities with Deep Learning Frameworks","created":"2019-08-13","cited_by_count":10},{"id":"1811.04383","title":"Adapting multi-armed bandits policies to contextual bandits scenarios","created":"2018-11-11","cited_by_count":8},{"id":"2004.09817","title":"Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learning","created":"2020-04-21","cited_by_count":5},{"id":"1804.00706","title":"Synergy: A HW/SW Framework for High Throughput CNNs on Embedded Heterogeneous SoC","created":"2018-03-28","cited_by_count":4},{"id":"2003.09526","title":"An Energy-Aware Online Learning Framework for Resource Management in Heterogeneous Platforms","created":"2020-03-20","cited_by_count":3},{"id":"2008.05687","title":"WAFFLe: Weight Anonymized Factorization for Federated Learning","created":"2020-08-13","cited_by_count":3}],"next_cursor":null}