{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2103.16257","title":"Model-Contrastive Federated Learning","created":"2021-03-30","cited_by_count":766},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"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":"1610.02527","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","created":"2016-10-08","cited_by_count":564},{"id":"1910.03581","title":"FedMD: Heterogenous Federated Learning via Model Distillation","created":"2019-10-08","cited_by_count":459},{"id":"2105.00243","title":"FedProto: Federated Prototype Learning across Heterogeneous Clients","created":"2021-05-01","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":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"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":"2203.11751","title":"FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction","created":"2022-03-22","cited_by_count":181},{"id":"2307.10616","title":"Heterogeneous Federated Learning: State-of-the-art and Research Challenges","created":"2023-07-20","cited_by_count":161},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"id":"2005.04763","title":"Private Stochastic Convex Optimization: Optimal Rates in Linear Time","created":"2020-05-10","cited_by_count":153},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"1802.05251","title":"Differentially Private Empirical Risk Minimization Revisited: Faster and More General","created":"2018-02-14","cited_by_count":128},{"id":"1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","created":"2019-07-09","cited_by_count":117},{"id":"2111.14213","title":"Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning","created":"2021-11-28","cited_by_count":114},{"id":"2212.01548","title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","created":"2022-12-03","cited_by_count":102},{"id":"2004.08856","title":"Local Differential Privacy based Federated Learning for Internet of Things","created":"2020-04-19","cited_by_count":75},{"id":"1806.10188","title":"A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates","created":"2018-06-26","cited_by_count":47},{"id":"2210.04505","title":"A Survey on Heterogeneous Federated Learning","created":"2022-10-10","cited_by_count":42},{"id":"2206.09888","title":"SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression","created":"2022-06-20","cited_by_count":34},{"id":"2207.04338","title":"Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning","created":"2022-07-09","cited_by_count":33},{"id":"2110.03300","title":"Permutation Compressors for Provably Faster Distributed Nonconvex Optimization","created":"2021-10-07","cited_by_count":32},{"id":"1409.1458","title":"Communication-Efficient Distributed Dual Coordinate Ascent","created":"2014-09-04","cited_by_count":31},{"id":"2004.08546","title":"Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search","created":"2020-04-18","cited_by_count":30},{"id":"2203.06735","title":"Private Non-Convex Federated Learning Without a Trusted Server","created":"2022-03-13","cited_by_count":26},{"id":"2102.07245","title":"Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization","created":"2021-02-14","cited_by_count":21},{"id":"1910.02120","title":"Distributed Learning of Deep Neural Networks using Independent Subnet Training","created":"2019-10-04","cited_by_count":20},{"id":"1502.03508","title":"Adding vs. Averaging in Distributed Primal-Dual Optimization","created":"2015-02-12","cited_by_count":19},{"id":"2001.03836","title":"Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approach","created":"2020-01-12","cited_by_count":18},{"id":"2107.00961","title":"ResIST: Layer-Wise Decomposition of ResNets for Distributed Training","created":"2021-07-02","cited_by_count":18},{"id":"2205.11787","title":"Quadratic models for understanding catapult dynamics of neural networks","created":"2022-05-24","cited_by_count":17},{"id":"2106.09687","title":"Super-Acceleration with Cyclical Step-sizes","created":"2021-06-17","cited_by_count":14},{"id":"2003.01876","title":"Privacy-preserving Learning via Deep Net Pruning","created":"2020-03-04","cited_by_count":12},{"id":"2210.16105","title":"Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout","created":"2022-10-28","cited_by_count":12},{"id":"2112.02668","title":"On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons","created":"2021-12-05","cited_by_count":11},{"id":"2102.10424","title":"GIST: Distributed Training for Large-Scale Graph Convolutional Networks","created":"2021-02-20","cited_by_count":10},{"id":"2106.03524","title":"Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques","created":"2021-06-07","cited_by_count":9},{"id":"2206.09901","title":"Only Tails Matter: Average-Case Universality and Robustness in the Convex Regime","created":"2022-06-20","cited_by_count":7},{"id":"2306.16484","title":"Towards a Better Theoretical Understanding of Independent Subnetwork Training","created":"2023-06-28","cited_by_count":6},{"id":"2208.10025","title":"Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization","created":"2022-08-22","cited_by_count":5},{"id":"2305.13170","title":"Explicit Personalization and Local Training: Double Communication Acceleration in Federated Learning","created":"2023-05-22","cited_by_count":5}],"next_cursor":null}