{"list":"other","total":66,"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":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"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":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"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":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"1912.00818","title":"Federated Learning with Personalization Layers","created":"2019-12-02","cited_by_count":541},{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541},{"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":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2003.13461","title":"Adaptive Personalized Federated Learning","created":"2020-03-30","cited_by_count":358},{"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":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"2001.01523","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","created":"2020-01-06","cited_by_count":325},{"id":"2002.07948","title":"Personalized Federated Learning: A Meta-Learning Approach","created":"2020-02-19","cited_by_count":312},{"id":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"id":"1909.12488","title":"Improving Federated Learning Personalization via Model Agnostic Meta Learning","created":"2019-09-27","cited_by_count":269},{"id":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"2104.07914","title":"Federated Learning for Internet of Things: A Comprehensive Survey","created":"2021-04-16","cited_by_count":252},{"id":"1807.01647","title":"Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences","created":"2018-07-04","cited_by_count":242},{"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":"2012.08565","title":"Personalized Federated Learning with First Order Model Optimization","created":"2020-12-15","cited_by_count":201},{"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":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"2009.01974","title":"FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning","created":"2020-09-04","cited_by_count":176},{"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":"1610.02132","title":"QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding","created":"2016-10-07","cited_by_count":147},{"id":"2009.13012","title":"Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges","created":"2020-09-28","cited_by_count":139},{"id":"1906.04688","title":"An Improved Analysis of Training Over-parameterized Deep Neural Networks","created":"2019-06-11","cited_by_count":121},{"id":"2104.11375","title":"Decentralized Federated Averaging","created":"2021-04-23","cited_by_count":114},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"2105.05883","title":"Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning","created":"2021-05-12","cited_by_count":93},{"id":"1901.11173","title":"Peer-to-peer Federated Learning on Graphs","created":"2019-01-31","cited_by_count":85},{"id":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","cited_by_count":85},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"1903.04488","title":"Communication-efficient distributed SGD with Sketching","created":"2019-03-12","cited_by_count":81},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69},{"id":"1706.07880","title":"Collaborative Deep Learning in Fixed Topology Networks","created":"2017-06-23","cited_by_count":60},{"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":"2112.09824","title":"Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better","created":"2021-12-18","cited_by_count":55},{"id":"2012.10931","title":"Recent advances in deep learning theory","created":"2020-12-20","cited_by_count":41},{"id":"2011.08756","title":"Stochastic Client Selection for Federated Learning with Volatile Clients","created":"2020-11-17","cited_by_count":39},{"id":"1611.09726","title":"Gossip training for deep learning","created":"2016-11-29","cited_by_count":35},{"id":"2203.09747","title":"Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization","created":"2022-03-18","cited_by_count":35},{"id":"2102.09743","title":"Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques","created":"2021-02-19","cited_by_count":34},{"id":"2201.11380","title":"Achieving Personalized Federated Learning with Sparse Local Models","created":"2022-01-27","cited_by_count":31},{"id":"2004.14180","title":"Quantized Adam with Error Feedback","created":"2020-04-29","cited_by_count":27},{"id":"2105.00562","title":"Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity","created":"2021-05-02","cited_by_count":27},{"id":"1802.07389","title":"3LC: Lightweight and Effective Traffic Compression for Distributed Machine Learning","created":"2018-02-21","cited_by_count":16},{"id":"2107.00778","title":"On Bridging Generic and Personalized Federated Learning for Image Classification","created":"2021-07-02","cited_by_count":15},{"id":"2007.09371","title":"Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms","created":"2020-07-18","cited_by_count":14},{"id":"2205.14473","title":"Efficient-Adam: Communication-Efficient Distributed Adam","created":"2022-05-28","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},{"id":"2203.02770","title":"Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance","created":"2022-03-05","cited_by_count":7}],"next_cursor":null}