{"list":"other","total":67,"rows":[{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"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":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2007.07481","title":"Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization","created":"2020-07-15","cited_by_count":906},{"id":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"2103.16257","title":"Model-Contrastive Federated Learning","created":"2021-03-30","cited_by_count":766},{"id":"2110.14795","title":"MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification","created":"2021-10-27","cited_by_count":690},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"2012.04221","title":"Ditto: Fair and Robust Federated Learning Through Personalization","created":"2020-12-08","cited_by_count":672},{"id":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"id":"2102.07623","title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","created":"2021-02-15","cited_by_count":571},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"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":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"id":"1804.08333","title":"Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge","created":"2018-04-23","cited_by_count":352},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"2001.01523","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","created":"2020-01-06","cited_by_count":325},{"id":"2002.10619","title":"Three Approaches for Personalization with Applications to Federated Learning","created":"2020-02-25","cited_by_count":325},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"1904.04971","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","created":"2019-04-10","cited_by_count":273},{"id":"1909.12488","title":"Improving Federated Learning Personalization via Model Agnostic Meta Learning","created":"2019-09-27","cited_by_count":269},{"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":"2004.11791","title":"Federated learning with hierarchical clustering of local updates to improve training on non-IID data","created":"2020-04-24","cited_by_count":223},{"id":"1903.05134","title":"Universally Slimmable Networks and Improved Training Techniques","created":"2019-03-12","cited_by_count":221},{"id":"2103.04628","title":"Personalized Federated Learning using Hypernetworks","created":"2021-03-08","cited_by_count":212},{"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":"2112.00059","title":"Evaluating Gradient Inversion Attacks and Defenses in Federated Learning","created":"2021-11-30","cited_by_count":196},{"id":"2102.13451","title":"FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout","created":"2021-02-26","cited_by_count":192},{"id":"1711.08393","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","created":"2017-11-22","cited_by_count":189},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"2108.13323","title":"FedKD: Communication Efficient Federated Learning via Knowledge Distillation","created":"2021-08-30","cited_by_count":187},{"id":"2106.06042","title":"FedBABU: Towards Enhanced Representation for Federated Image Classification","created":"2021-06-04","cited_by_count":182},{"id":"1910.06378","title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","created":"2019-10-14","cited_by_count":175},{"id":"2203.09249","title":"Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning","created":"2022-03-17","cited_by_count":172},{"id":"1910.10252","title":"Federated Evaluation of On-device Personalization","created":"2019-10-22","cited_by_count":147},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141},{"id":"2006.08950","title":"Federated Accelerated Stochastic Gradient Descent","created":"2020-06-16","cited_by_count":85},{"id":"2102.11628","title":"FINE Samples for Learning with Noisy Labels","created":"2021-02-23","cited_by_count":82},{"id":"2001.04756","title":"Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach","created":"2020-01-14","cited_by_count":81},{"id":"2011.09011","title":"AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling","created":"2020-11-18","cited_by_count":66},{"id":"1701.00299","title":"Dynamic Deep Neural Networks: Optimizing Accuracy-Efficiency Trade-offs by Selective Execution","created":"2017-01-02","cited_by_count":59},{"id":"2106.04502","title":"Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing","created":"2021-06-08","cited_by_count":58},{"id":"2004.10342","title":"Federated Learning with Only Positive Labels","created":"2020-04-21","cited_by_count":55},{"id":"2003.14058","title":"MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning","created":"2020-03-31","cited_by_count":50},{"id":"2011.04050","title":"Adaptive Federated Dropout: Improving Communication Efficiency and Generalization for Federated Learning","created":"2020-11-08","cited_by_count":38},{"id":"2102.07954","title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","created":"2021-02-16","cited_by_count":36},{"id":"2110.15210","title":"Towards Model Agnostic Federated Learning Using Knowledge Distillation","created":"2021-10-28","cited_by_count":31},{"id":"1906.05226","title":"Continual and Multi-Task Architecture Search","created":"2019-06-12","cited_by_count":22},{"id":"2106.11890","title":"Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization","created":"2021-06-22","cited_by_count":15},{"id":"2112.13939","title":"SPIDER: Searching Personalized Neural Architecture for Federated Learning","created":"2021-12-27","cited_by_count":13},{"id":"1801.09335","title":"Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks","created":"2018-01-29","cited_by_count":7}],"next_cursor":null}