{"list":"other","total":66,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"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":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"2003.08119","title":"The Future of Digital Health with Federated Learning","created":"2020-03-18","cited_by_count":633},{"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":"1910.03581","title":"FedMD: Heterogenous Federated Learning via Model Distillation","created":"2019-10-08","cited_by_count":459},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1812.00564","title":"Split learning for health: Distributed deep learning without sharing raw patient data","created":"2018-12-03","cited_by_count":395},{"id":"1804.08333","title":"Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge","created":"2018-04-23","cited_by_count":352},{"id":"2106.06843","title":"Federated Learning on Non-IID Data: A Survey","created":"2021-06-12","cited_by_count":346},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"2004.12088","title":"SplitFed: When Federated Learning Meets Split Learning","created":"2020-04-25","cited_by_count":310},{"id":"1710.09282","title":"A Survey of Model Compression and Acceleration for Deep Neural Networks","created":"2017-10-23","cited_by_count":301},{"id":"2007.13518","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","created":"2020-07-27","cited_by_count":300},{"id":"1810.06060","title":"Distributed learning of deep neural network over multiple agents","created":"2018-10-14","cited_by_count":279},{"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":"1811.02084","title":"Mesh-TensorFlow: Deep Learning for Supercomputers","created":"2018-11-05","cited_by_count":169},{"id":"1802.09941","title":"Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis","created":"2018-02-26","cited_by_count":156},{"id":"1702.05800","title":"Revisiting Distributed Synchronous SGD","created":"2017-02-19","cited_by_count":142},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"1806.03377","title":"PipeDream: Fast and Efficient Pipeline Parallel DNN Training","created":"2018-06-08","cited_by_count":117},{"id":"2012.02670","title":"Unleashing the Tiger: Inference Attacks on Split Learning","created":"2020-12-04","cited_by_count":105},{"id":"1903.04476","title":"Continual Learning via Neural Pruning","created":"2019-03-11","cited_by_count":101},{"id":"2104.14380","title":"PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments","created":"2021-04-29","cited_by_count":93},{"id":"1905.11786","title":"Putting An End to End-to-End: Gradient-Isolated Learning of Representations","created":"2019-05-28","cited_by_count":86},{"id":"1901.08164","title":"Decoupled Greedy Learning of CNNs","created":"2019-01-23","cited_by_count":78},{"id":"1909.09145","title":"Detailed comparison of communication efficiency of split learning and federated learning","created":"2019-09-18","cited_by_count":77},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"1912.12115","title":"Split Learning for collaborative deep learning in healthcare","created":"2019-12-27","cited_by_count":73},{"id":"2008.09161","title":"NoPeek: Information leakage reduction to share activations in distributed deep learning","created":"2020-08-20","cited_by_count":66},{"id":"2003.13376","title":"End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things","created":"2020-03-30","cited_by_count":64},{"id":"2008.02608","title":"Communication-Efficient and Distributed Learning Over Wireless Networks: Principles and Applications","created":"2020-08-06","cited_by_count":62},{"id":"2006.01412","title":"Federated Learning in Vehicular Networks","created":"2020-06-02","cited_by_count":53},{"id":"1904.05514","title":"Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach","created":"2019-04-11","cited_by_count":48},{"id":"2010.15965","title":"Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework","created":"2020-10-29","cited_by_count":46},{"id":"2011.14818","title":"Advancements of federated learning towards privacy preservation: from federated learning to split learning","created":"2020-11-25","cited_by_count":34},{"id":"1703.02952","title":"A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics","created":"2017-03-08","cited_by_count":30},{"id":"1812.03288","title":"No Peek: A Survey of private distributed deep learning","created":"2018-12-08","cited_by_count":30},{"id":"2012.08009","title":"Bandit-based Communication-Efficient Client Selection Strategies for Federated Learning","created":"2020-12-14","cited_by_count":29},{"id":"2102.01593","title":"FEDZIP: A Compression Framework for Communication-Efficient Federated Learning","created":"2021-02-02","cited_by_count":27},{"id":"2011.03180","title":"FedSL: Federated Split Learning on Distributed Sequential Data in Recurrent Neural Networks","created":"2020-11-06","cited_by_count":23},{"id":"2012.11025","title":"DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks","created":"2020-12-20","cited_by_count":23},{"id":"2012.03837","title":"Parallel Training of Deep Networks with Local Updates","created":"2020-12-07","cited_by_count":19},{"id":"2003.00645","title":"Communication-Efficient Multimodal Split Learning for mmWave Received Power Prediction","created":"2020-03-02","cited_by_count":18},{"id":"2010.04116","title":"Interlocking Backpropagation: Improving depthwise model-parallelism","created":"2020-10-08","cited_by_count":17},{"id":"1512.01891","title":"Sparsifying Neural Network Connections for Face Recognition","created":"2015-12-07","cited_by_count":15},{"id":"2012.12591","title":"Comparison of Privacy-Preserving Distributed Deep Learning Methods in Healthcare","created":"2020-12-23","cited_by_count":14},{"id":"1901.09546","title":"Interpretable Complex-Valued Neural Networks for Privacy Protection","created":"2019-01-28","cited_by_count":10},{"id":"2011.04232","title":"SplitEasy: A Practical Approach for Training ML models on Mobile Devices","created":"2020-11-09","cited_by_count":10},{"id":"1602.06709","title":"Distributed Deep Learning Using Synchronous Stochastic Gradient Descent","created":"2016-02-22","cited_by_count":8},{"id":"1905.11814","title":"Shredder: Learning Noise Distributions to Protect Inference Privacy","created":"2019-05-26","cited_by_count":5},{"id":"2106.02685","title":"Massively Parallel and Dynamic Algorithms for Minimum Size Clustering","created":"2021-06-04","cited_by_count":4},{"id":"2106.14126","title":"AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning","created":"2021-06-27","cited_by_count":4},{"id":"1910.03731","title":"ExpertMatcher: Automating ML Model Selection for Clients using Hidden Representations","created":"2019-10-09","cited_by_count":3},{"id":"1910.02312","title":"ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries","created":"2019-10-05","cited_by_count":2},{"id":"2103.14291","title":"Vulnerability Due to Training Order in Split Learning","created":"2021-03-26","cited_by_count":2},{"id":"2007.08208","title":"Distributed Heteromodal Split Learning for Vision Aided mmWave Received Power Prediction","created":"2020-07-16","cited_by_count":1}],"next_cursor":null}