{"list":"other","total":58,"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":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"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":"1909.06335","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","created":"2019-09-13","cited_by_count":851},{"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":"1610.02527","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","created":"2016-10-08","cited_by_count":564},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"1912.00818","title":"Federated Learning with Personalization Layers","created":"2019-12-02","cited_by_count":541},{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464},{"id":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"id":"1905.12022","title":"Bayesian Nonparametric Federated Learning of Neural Networks","created":"2019-05-28","cited_by_count":387},{"id":"1707.09835","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","created":"2017-07-31","cited_by_count":379},{"id":"2003.13461","title":"Adaptive Personalized Federated Learning","created":"2020-03-30","cited_by_count":358},{"id":"1909.13014","title":"FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization","created":"2019-09-28","cited_by_count":356},{"id":"2001.01523","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","created":"2020-01-06","cited_by_count":325},{"id":"2002.10619","title":"Three Approaches for Personalization with Applications to Federated Learning","created":"2020-02-25","cited_by_count":325},{"id":"2002.07948","title":"Personalized Federated Learning: A Meta-Learning Approach","created":"2020-02-19","cited_by_count":312},{"id":"2007.03797","title":"Personalized Cross-Silo Federated Learning on Non-IID Data","created":"2020-07-07","cited_by_count":283},{"id":"1909.12488","title":"Improving Federated Learning Personalization via Model Agnostic Meta Learning","created":"2019-09-27","cited_by_count":269},{"id":"1411.2005","title":"Scalable Variational Gaussian Process Classification","created":"2014-11-07","cited_by_count":228},{"id":"2103.04628","title":"Personalized Federated Learning using Hypernetworks","created":"2021-03-08","cited_by_count":212},{"id":"2002.05516","title":"Federated Learning of a Mixture of Global and Local Models","created":"2020-02-10","cited_by_count":210},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"2012.08565","title":"Personalized Federated Learning with First Order Model Optimization","created":"2020-12-15","cited_by_count":201},{"id":"1805.10559","title":"cpSGD: Communication-efficient and differentially-private distributed SGD","created":"2018-05-27","cited_by_count":158},{"id":"1910.14425","title":"On the Convergence of Local Descent Methods in Federated Learning","created":"2019-10-31","cited_by_count":153},{"id":"2003.08673","title":"Survey of Personalization Techniques for Federated Learning","created":"2020-03-19","cited_by_count":145},{"id":"1908.10400","title":"On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms","created":"2019-08-27","cited_by_count":132},{"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":"1611.00336","title":"Stochastic Variational Deep Kernel Learning","created":"2016-11-01","cited_by_count":93},{"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":"2102.12108","title":"The Promises and Pitfalls of Deep Kernel Learning","created":"2021-02-24","cited_by_count":81},{"id":"1402.5876","title":"Manifold Gaussian Processes for Regression","created":"2014-02-24","cited_by_count":80},{"id":"2010.10154","title":"Federated Bayesian Optimization via Thompson Sampling","created":"2020-10-20","cited_by_count":77},{"id":"1906.06268","title":"Variational Federated Multi-Task Learning","created":"2019-06-14","cited_by_count":69},{"id":"2009.06419","title":"Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descent","created":"2020-09-11","cited_by_count":35},{"id":"1902.08534","title":"Federated Heavy Hitters Discovery with Differential Privacy","created":"2019-02-22","cited_by_count":32},{"id":"2007.10417","title":"Bayesian Few-Shot Classification with One-vs-Each P\\'olya-Gamma Augmented Gaussian Processes","created":"2020-07-20","cited_by_count":32},{"id":"2103.01439","title":"Fast Adaptation with Linearized Neural Networks","created":"2021-03-02","cited_by_count":32},{"id":"1811.11206","title":"Partitioned Variational Inference: A unified framework encompassing federated and continual learning","created":"2018-11-27","cited_by_count":29},{"id":"1506.05843","title":"Dependent Multinomial Models Made Easy: Stick Breaking with the P\\'olya-Gamma Augmentation","created":"2015-06-18","cited_by_count":26},{"id":"2102.07868","title":"GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning","created":"2021-02-15","cited_by_count":26},{"id":"1905.07435","title":"Alpha MAML: Adaptive Model-Agnostic Meta-Learning","created":"2019-05-17","cited_by_count":25},{"id":"1810.12263","title":"Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Bounds","created":"2018-10-29","cited_by_count":24},{"id":"1911.04655","title":"Hyper-Sphere Quantization: Communication-Efficient SGD for Federated Learning","created":"2019-11-12","cited_by_count":18},{"id":"1802.06383","title":"Efficient Gaussian Process Classification Using Polya-Gamma Data Augmentation","created":"2018-02-18","cited_by_count":17},{"id":"1905.09670","title":"Multi-Class Gaussian Process Classification Made Conjugate: Efficient Inference via Data Augmentation","created":"2019-05-23","cited_by_count":16},{"id":"2103.01901","title":"Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?","created":"2021-03-02","cited_by_count":15},{"id":"2001.10523","title":"Multi-class Gaussian Process Classification with Noisy Inputs","created":"2020-01-28","cited_by_count":10},{"id":"2002.11451","title":"Automated Augmented Conjugate Inference for Non-conjugate Gaussian Process Models","created":"2020-02-26","cited_by_count":2}],"next_cursor":null}