{"list":"other","total":54,"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1712.01887","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","created":"2017-12-05","cited_by_count":478},{"id":"1903.02891","title":"Robust and Communication-Efficient Federated Learning from Non-IID Data","created":"2019-03-07","cited_by_count":419},{"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":"1705.07878","title":"TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning","created":"2017-05-22","cited_by_count":256},{"id":"1704.05021","title":"Sparse Communication for Distributed Gradient Descent","created":"2017-04-17","cited_by_count":249},{"id":"1807.01647","title":"Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences","created":"2018-07-04","cited_by_count":242},{"id":"1905.13727","title":"PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization","created":"2019-05-31","cited_by_count":238},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"id":"1808.00087","title":"Subsampled R\\'enyi Differential Privacy and Analytical Moments Accountant","created":"2018-07-31","cited_by_count":236},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"1905.03871","title":"Differentially Private Learning with Adaptive Clipping","created":"2019-05-09","cited_by_count":220},{"id":"1905.01067","title":"Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask","created":"2019-05-03","cited_by_count":207},{"id":"2007.07682","title":"FetchSGD: Communication-Efficient Federated Learning with Sketching","created":"2020-07-15","cited_by_count":179},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"1811.12469","title":"Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity","created":"2018-11-29","cited_by_count":164},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"1611.00429","title":"Distributed Mean Estimation with Limited Communication","created":"2016-11-02","cited_by_count":136},{"id":"1806.04090","title":"ATOMO: Communication-efficient Learning via Atomic Sparsification","created":"2018-06-11","cited_by_count":136},{"id":"2012.12803","title":"Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling","created":"2020-12-23","cited_by_count":96},{"id":"2006.07990","title":"Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient","created":"2020-06-14","cited_by_count":81},{"id":"2206.00187","title":"DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training","created":"2022-06-01","cited_by_count":74},{"id":"2110.04995","title":"The Skellam Mechanism for Differentially Private Federated Learning","created":"2021-10-11","cited_by_count":68},{"id":"2008.03371","title":"LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets","created":"2020-08-07","cited_by_count":60},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55},{"id":"2108.08842","title":"EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning","created":"2021-08-19","cited_by_count":55},{"id":"2112.09824","title":"Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better","created":"2021-12-18","cited_by_count":55},{"id":"2105.08339","title":"DRIVE: One-bit Distributed Mean Estimation","created":"2021-05-18","cited_by_count":52},{"id":"2007.06605","title":"Privacy Amplification via Random Check-Ins","created":"2020-07-13","cited_by_count":39},{"id":"1609.00222","title":"Ternary Neural Networks for Resource-Efficient AI Applications","created":"2016-09-01","cited_by_count":33},{"id":"2005.10761","title":"rTop-k: A Statistical Estimation Approach to Distributed SGD","created":"2020-05-21","cited_by_count":27},{"id":"2101.08837","title":"Time-Correlated Sparsification for Communication-Efficient Federated Learning","created":"2021-01-21","cited_by_count":26},{"id":"2102.08329","title":"An Information-Theoretic Justification for Model Pruning","created":"2021-02-16","cited_by_count":25},{"id":"2008.04975","title":"FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching","created":"2020-08-11","cited_by_count":20},{"id":"2003.09603","title":"Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning","created":"2020-03-21","cited_by_count":16},{"id":"2106.08895","title":"Masked Training of Neural Networks with Partial Gradients","created":"2021-06-16","cited_by_count":16},{"id":"2201.02664","title":"Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion Theory","created":"2022-01-07","cited_by_count":14},{"id":"2110.14205","title":"FedPrune: Towards Inclusive Federated Learning","created":"2021-10-27","cited_by_count":12},{"id":"2104.12501","title":"Communication-Efficient and Personalized Federated Lottery Ticket Learning","created":"2021-04-26","cited_by_count":10},{"id":"2110.04350","title":"FRL: Federated Rank Learning","created":"2021-10-08","cited_by_count":8},{"id":"2205.13341","title":"QUIC-FL: Quick Unbiased Compression for Federated Learning","created":"2022-05-26","cited_by_count":7},{"id":"2206.04385","title":"HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask","created":"2022-06-09","cited_by_count":6},{"id":"2101.06475","title":"Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks","created":"2021-01-16","cited_by_count":5},{"id":"2105.10594","title":"Privacy Amplification Via Bernoulli Sampling","created":"2021-05-21","cited_by_count":4},{"id":"2009.01867","title":"ESMFL: Efficient and Secure Models for Federated Learning","created":"2020-09-03","cited_by_count":3},{"id":"2205.01556","title":"Privacy Amplification via Random Participation in Federated Learning","created":"2022-05-03","cited_by_count":2}],"next_cursor":null}