{"list":"other","total":77,"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":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"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":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"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":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"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":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"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":"2006.08848","title":"Personalized Federated Learning with Moreau Envelopes","created":"2020-06-16","cited_by_count":618},{"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":"1610.02527","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","created":"2016-10-08","cited_by_count":564},{"id":"1509.00519","title":"Importance Weighted Autoencoders","created":"2015-09-01","cited_by_count":456},{"id":"1902.00146","title":"Agnostic Federated Learning","created":"2019-02-01","cited_by_count":456},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"1905.10497","title":"Fair Resource Allocation in Federated Learning","created":"2019-05-25","cited_by_count":394},{"id":"2003.10422","title":"A Unified Theory of Decentralized SGD with Changing Topology and Local Updates","created":"2020-03-23","cited_by_count":367},{"id":"2003.13461","title":"Adaptive Personalized Federated Learning","created":"2020-03-30","cited_by_count":358},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"2001.01523","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","created":"2020-01-06","cited_by_count":325},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"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":"1909.04746","title":"Tighter Theory for Local SGD on Identical and Heterogeneous Data","created":"2019-09-10","cited_by_count":266},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"1702.05373","title":"EMNIST: an extension of MNIST to handwritten letters","created":"2017-02-17","cited_by_count":213},{"id":"2002.05516","title":"Federated Learning of a Mixture of Global and Local Models","created":"2020-02-10","cited_by_count":210},{"id":"1906.02717","title":"Adaptive Gradient-Based Meta-Learning Methods","created":"2019-06-06","cited_by_count":183},{"id":"1906.02367","title":"Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification, and Local Computations","created":"2019-06-06","cited_by_count":181},{"id":"1905.03817","title":"On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization","created":"2019-05-09","cited_by_count":180},{"id":"2009.01974","title":"FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning","created":"2020-09-04","cited_by_count":176},{"id":"1802.07876","title":"Federated Meta-Learning with Fast Convergence and Efficient Communication","created":"2018-02-22","cited_by_count":155},{"id":"1910.10252","title":"Federated Evaluation of On-device Personalization","created":"2019-10-22","cited_by_count":147},{"id":"2006.04735","title":"Minibatch vs Local SGD for Heterogeneous Distributed Learning","created":"2020-06-08","cited_by_count":147},{"id":"2005.11418","title":"FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data","created":"2020-05-22","cited_by_count":144},{"id":"2002.04758","title":"Salvaging Federated Learning by Local Adaptation","created":"2020-02-12","cited_by_count":142},{"id":"2006.15429","title":"Understanding Gradient Clipping in Private SGD: A Geometric Perspective","created":"2020-06-27","cited_by_count":142},{"id":"2002.12410","title":"On Biased Compression for Distributed Learning","created":"2020-02-27","cited_by_count":140},{"id":"2009.06192","title":"A Principled Approach to Data Valuation for Federated Learning","created":"2020-09-14","cited_by_count":127},{"id":"2010.02372","title":"Lower Bounds and Optimal Algorithms for Personalized Federated Learning","created":"2020-10-05","cited_by_count":123},{"id":"1910.00643","title":"SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum","created":"2019-10-01","cited_by_count":121},{"id":"2005.05238","title":"FedSplit: An algorithmic framework for fast federated optimization","created":"2020-05-11","cited_by_count":108},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"id":"1808.07576","title":"Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms","created":"2018-08-22","cited_by_count":106},{"id":"2012.06421","title":"When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?","created":"2020-12-11","cited_by_count":104},{"id":"2006.08907","title":"Robust Federated Learning: The Case of Affine Distribution Shifts","created":"2020-06-16","cited_by_count":102},{"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":"2102.03448","title":"Federated Reconstruction: Partially Local Federated Learning","created":"2021-02-05","cited_by_count":79},{"id":"2010.05273","title":"Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms","created":"2020-10-11","cited_by_count":78},{"id":"1902.10644","title":"Provable Guarantees for Gradient-Based Meta-Learning","created":"2019-02-27","cited_by_count":67},{"id":"2010.12292","title":"Linearly Converging Error Compensated SGD","created":"2020-10-23","cited_by_count":61},{"id":"2011.08474","title":"Federated Composite Optimization","created":"2020-11-17","cited_by_count":49},{"id":"2010.12460","title":"Adaptive Gradient Quantization for Data-Parallel SGD","created":"2020-10-23","cited_by_count":45},{"id":"2006.11077","title":"A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning","created":"2020-06-19","cited_by_count":43},{"id":"2007.06605","title":"Privacy Amplification via Random Check-Ins","created":"2020-07-13","cited_by_count":39},{"id":"2010.03246","title":"Optimal Gradient Compression for Distributed and Federated Learning","created":"2020-10-07","cited_by_count":39},{"id":"2007.00878","title":"On the Outsized Importance of Learning Rates in Local Update Methods","created":"2020-07-02","cited_by_count":36},{"id":"1902.08534","title":"Federated Heavy Hitters Discovery with Differential Privacy","created":"2019-02-22","cited_by_count":32},{"id":"2102.07158","title":"Distributed Second Order Methods with Fast Rates and Compressed Communication","created":"2021-02-14","cited_by_count":25},{"id":"2003.12880","title":"Federated Residual Learning","created":"2020-03-28","cited_by_count":23},{"id":"2005.02503","title":"Information-Theoretic Bounds on the Generalization Error and Privacy Leakage in Federated Learning","created":"2020-05-05","cited_by_count":21},{"id":"2011.01963","title":"A Scalable Approach for Privacy-Preserving Collaborative Machine Learning","created":"2020-11-03","cited_by_count":21},{"id":"1910.06093","title":"Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks","created":"2019-10-14","cited_by_count":20},{"id":"1905.04346","title":"On the Computation and Communication Complexity of Parallel SGD with Dynamic Batch Sizes for Stochastic Non-Convex Optimization","created":"2019-05-10","cited_by_count":15},{"id":"2008.05687","title":"WAFFLe: Weight Anonymized Factorization for Federated Learning","created":"2020-08-13","cited_by_count":3}],"next_cursor":null}