{"list":"other","total":64,"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"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":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"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":"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":"2012.04221","title":"Ditto: Fair and Robust Federated Learning Through Personalization","created":"2020-12-08","cited_by_count":672},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"2102.07623","title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","created":"2021-02-15","cited_by_count":571},{"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":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"2111.12797","title":"ReAct: Out-of-distribution Detection With Rectified Activations","created":"2021-11-24","cited_by_count":486},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"id":"1805.11604","title":"How Does Batch Normalization Help Optimization?","created":"2018-05-29","cited_by_count":357},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"2002.10619","title":"Three Approaches for Personalization with Applications to Federated Learning","created":"2020-02-25","cited_by_count":325},{"id":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"id":"1603.04779","title":"Revisiting Batch Normalization For Practical Domain Adaptation","created":"2016-03-15","cited_by_count":288},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"1901.09321","title":"Fixup Initialization: Residual Learning Without Normalization","created":"2019-01-27","cited_by_count":198},{"id":"2009.01974","title":"FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning","created":"2020-09-04","cited_by_count":176},{"id":"1806.02375","title":"Understanding Batch Normalization","created":"2018-06-01","cited_by_count":159},{"id":"2008.03606","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","created":"2020-08-08","cited_by_count":154},{"id":"1910.14425","title":"On the Convergence of Local Descent Methods in Federated Learning","created":"2019-10-31","cited_by_count":153},{"id":"2002.04758","title":"Salvaging Federated Learning by Local Adaptation","created":"2020-02-12","cited_by_count":142},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141},{"id":"2009.07999","title":"Distilled One-Shot Federated Learning","created":"2020-09-17","cited_by_count":109},{"id":"1708.01012","title":"On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization","created":"2017-08-03","cited_by_count":92},{"id":"2006.08950","title":"Federated Accelerated Stochastic Gradient Descent","created":"2020-06-16","cited_by_count":85},{"id":"1912.12844","title":"Variance Reduced Local SGD with Lower Communication Complexity","created":"2019-12-30","cited_by_count":80},{"id":"2001.01920","title":"FedDANE: A Federated Newton-Type Method","created":"2020-01-07","cited_by_count":76},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"2206.11488","title":"On the Importance and Applicability of Pre-Training for Federated Learning","created":"2022-06-23","cited_by_count":71},{"id":"2010.05958","title":"FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers","created":"2020-10-12","cited_by_count":64},{"id":"2110.14216","title":"What Do We Mean by Generalization in Federated Learning?","created":"2021-10-27","cited_by_count":62},{"id":"2008.07424","title":"Siloed Federated Learning for Multi-Centric Histopathology Datasets","created":"2020-08-17","cited_by_count":61},{"id":"1902.08129","title":"A Mean Field Theory of Batch Normalization","created":"2019-02-21","cited_by_count":58},{"id":"2106.04502","title":"Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing","created":"2021-06-08","cited_by_count":58},{"id":"1809.00846","title":"Towards Understanding Regularization in Batch Normalization","created":"2018-09-04","cited_by_count":56},{"id":"2012.04057","title":"Design and Analysis of Uplink and Downlink Communications for Federated Learning","created":"2020-12-07","cited_by_count":48},{"id":"2111.14248","title":"Fed2: Feature-Aligned Federated Learning","created":"2021-11-28","cited_by_count":42},{"id":"2106.09397","title":"Quantized Federated Learning under Transmission Delay and Outage Constraints","created":"2021-06-17","cited_by_count":37},{"id":"2301.02982","title":"Why Batch Normalization Damage Federated Learning on Non-IID Data?","created":"2023-01-08","cited_by_count":29},{"id":"2112.00734","title":"Personalized Federated Learning with Adaptive Batchnorm for Healthcare","created":"2021-12-01","cited_by_count":26},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25},{"id":"2207.07223","title":"Accelerated Federated Learning with Decoupled Adaptive Optimization","created":"2022-07-14","cited_by_count":23},{"id":"2201.11986","title":"Gradient Masked Averaging for Federated Learning","created":"2022-01-28","cited_by_count":22},{"id":"2210.03277","title":"Rethinking Normalization Methods in Federated Learning","created":"2022-10-07","cited_by_count":19},{"id":"2205.11096","title":"FedNorm: Modality-Based Normalization in Federated Learning for Multi-Modal Liver Segmentation","created":"2022-05-23","cited_by_count":12},{"id":"2104.08776","title":"Federated Learning of User Verification Models Without Sharing Embeddings","created":"2021-04-18","cited_by_count":11},{"id":"2207.03075","title":"Towards the Practical Utility of Federated Learning in the Medical Domain","created":"2022-07-07","cited_by_count":9},{"id":"2208.11512","title":"FedOS: using open-set learning to stabilize training in federated learning","created":"2022-08-22","cited_by_count":1}],"next_cursor":null}