{"list":"other","total":65,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"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":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"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":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"2103.16257","title":"Model-Contrastive Federated Learning","created":"2021-03-30","cited_by_count":766},{"id":"1807.00459","title":"How To Backdoor Federated Learning","created":"2018-07-02","cited_by_count":765},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"2102.02079","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","created":"2021-02-03","cited_by_count":568},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541},{"id":"1911.11815","title":"Local Model Poisoning Attacks to Byzantine-Robust Federated Learning","created":"2019-11-26","cited_by_count":493},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"id":"1804.05271","title":"Adaptive Federated Learning in Resource Constrained Edge Computing Systems","created":"2018-04-14","cited_by_count":409},{"id":"1407.0202","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","created":"2014-07-01","cited_by_count":402},{"id":"1905.10497","title":"Fair Resource Allocation in Federated Learning","created":"2019-05-25","cited_by_count":394},{"id":"2003.13461","title":"Adaptive Personalized Federated Learning","created":"2020-03-30","cited_by_count":358},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"2002.07948","title":"Personalized Federated Learning: A Meta-Learning Approach","created":"2020-02-19","cited_by_count":312},{"id":"2007.05084","title":"Attack of the Tails: Yes, You Really Can Backdoor Federated Learning","created":"2020-07-09","cited_by_count":309},{"id":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"id":"1911.07963","title":"Can You Really Backdoor Federated Learning?","created":"2019-11-18","cited_by_count":255},{"id":"1910.05653","title":"Model Fusion via Optimal Transport","created":"2019-10-12","cited_by_count":219},{"id":"2010.15110","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","created":"2020-10-28","cited_by_count":187},{"id":"2003.02133","title":"Threats to Federated Learning: A Survey","created":"2020-03-04","cited_by_count":178},{"id":"1808.04866","title":"Mitigating Sybils in Federated Learning Poisoning","created":"2018-08-14","cited_by_count":161},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"2008.03606","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","created":"2020-08-08","cited_by_count":154},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"2003.08673","title":"Survey of Personalization Techniques for Federated Learning","created":"2020-03-19","cited_by_count":145},{"id":"2006.07322","title":"Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks","created":"2020-06-12","cited_by_count":138},{"id":"1611.00429","title":"Distributed Mean Estimation with Limited Communication","created":"2016-11-02","cited_by_count":136},{"id":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"2006.09365","title":"Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing","created":"2020-06-16","cited_by_count":128},{"id":"1910.00643","title":"SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum","created":"2019-10-01","cited_by_count":121},{"id":"2007.11115","title":"Byzantine-Resilient Secure Federated Learning","created":"2020-07-21","cited_by_count":93},{"id":"2203.06176","title":"More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize","created":"2022-03-11","cited_by_count":91},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69},{"id":"2009.10031","title":"Training Production Language Models without Memorizing User Data","created":"2020-09-21","cited_by_count":68},{"id":"2002.10671","title":"Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework","created":"2020-02-25","cited_by_count":59},{"id":"2111.14248","title":"Fed2: Feature-Aligned Federated Learning","created":"2021-11-28","cited_by_count":42},{"id":"2206.04723","title":"On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data","created":"2022-06-09","cited_by_count":38},{"id":"2107.13892","title":"QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning","created":"2021-07-29","cited_by_count":32},{"id":"2110.15210","title":"Towards Model Agnostic Federated Learning Using Knowledge Distillation","created":"2021-10-28","cited_by_count":31},{"id":"2004.05529","title":"Gradients as Features for Deep Representation Learning","created":"2020-04-12","cited_by_count":30},{"id":"2105.10585","title":"Properties of the After Kernel","created":"2021-05-21","cited_by_count":27},{"id":"1511.00175","title":"FireCaffe: near-linear acceleration of deep neural network training on compute clusters","created":"2015-10-31","cited_by_count":25},{"id":"2012.11140","title":"LQF: Linear Quadratic Fine-Tuning","created":"2020-12-21","cited_by_count":25},{"id":"2008.12478","title":"Predicting Training Time Without Training","created":"2020-08-28","cited_by_count":22},{"id":"1910.00359","title":"Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory","created":"2019-10-01","cited_by_count":21},{"id":"1611.03225","title":"Sharper Bounds for Regularized Data Fitting","created":"2016-11-10","cited_by_count":19},{"id":"2110.03681","title":"Neural Tangent Kernel Empowered Federated Learning","created":"2021-10-07","cited_by_count":15},{"id":"2206.00395","title":"Optimization with Access to Auxiliary Information","created":"2022-06-01","cited_by_count":13}],"next_cursor":null}