{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"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":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"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":"1804.03209","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","created":"2018-04-09","cited_by_count":752},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"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":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1903.02891","title":"Robust and Communication-Efficient Federated Learning from Non-IID Data","created":"2019-03-07","cited_by_count":419},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"1704.08847","title":"Parseval Networks: Improving Robustness to Adversarial Examples","created":"2017-04-28","cited_by_count":293},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"id":"2010.01243","title":"Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies","created":"2020-10-03","cited_by_count":198},{"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":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174},{"id":"1511.06297","title":"Conditional Computation in Neural Networks for faster models","created":"2015-11-19","cited_by_count":167},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125},{"id":"1906.04329","title":"Federated Learning for Emoji Prediction in a Mobile Keyboard","created":"2019-06-11","cited_by_count":118},{"id":"1705.08665","title":"Bayesian Compression for Deep Learning","created":"2017-05-24","cited_by_count":116},{"id":"2111.04877","title":"Papaya: Practical, Private, and Scalable Federated Learning","created":"2021-11-08","cited_by_count":90},{"id":"2204.10836","title":"Federated Learning Enables Big Data for Rare Cancer Boundary Detection","created":"2022-04-22","cited_by_count":84},{"id":"1909.05122","title":"Implicit Regularization for Optimal Sparse Recovery","created":"2019-09-11","cited_by_count":80},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74},{"id":"1811.07457","title":"Generalizable Adversarial Training via Spectral Normalization","created":"2018-11-19","cited_by_count":68},{"id":"2005.06870","title":"Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers","created":"2020-05-14","cited_by_count":68},{"id":"2106.04502","title":"Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing","created":"2021-06-08","cited_by_count":58},{"id":"2112.09824","title":"Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better","created":"2021-12-18","cited_by_count":55},{"id":"2110.00296","title":"Powerpropagation: A sparsity inducing weight reparameterisation","created":"2021-10-01","cited_by_count":49},{"id":"2001.01969","title":"Sparse Weight Activation Training","created":"2020-01-07","cited_by_count":45},{"id":"2208.02507","title":"ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity","created":"2022-08-04","cited_by_count":45},{"id":"1610.04574","title":"Generalization Error of Invariant Classifiers","created":"2016-10-14","cited_by_count":42},{"id":"1904.10120","title":"Semi-Cyclic Stochastic Gradient Descent","created":"2019-04-23","cited_by_count":40},{"id":"2201.11380","title":"Achieving Personalized Federated Learning with Sparse Local Models","created":"2022-01-27","cited_by_count":31},{"id":"2102.01593","title":"FEDZIP: A Compression Framework for Communication-Efficient Federated Learning","created":"2021-02-02","cited_by_count":27},{"id":"1903.09367","title":"High-Dimensional Linear Regression via Implicit Regularization","created":"2019-03-22","cited_by_count":25},{"id":"2010.01791","title":"Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior","created":"2020-10-05","cited_by_count":23},{"id":"2302.12862","title":"FLINT: A Platform for Federated Learning Integration","created":"2023-02-24","cited_by_count":17},{"id":"2208.13141","title":"Federated Learning of Large Models at the Edge via Principal Sub-Model Training","created":"2022-08-28","cited_by_count":13},{"id":"2208.13092","title":"Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edge","created":"2022-08-27","cited_by_count":12},{"id":"2403.07953","title":"Enabling Unstructured Sparse Acceleration on Structured Sparse Accelerators","created":"2024-03-12","cited_by_count":8},{"id":"2309.03237","title":"Federated Learning Over Images: Vertical Decompositions and Pre-Trained Backbones Are Difficult to Beat","created":"2023-09-06","cited_by_count":4}],"next_cursor":null}