{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"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":"1702.07476","title":"Renyi Differential Privacy","created":"2017-02-24","cited_by_count":650},{"id":"1805.04049","title":"Exploiting Unintended Feature Leakage in Collaborative Learning","created":"2018-05-10","cited_by_count":520},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"1804.05271","title":"Adaptive Federated Learning in Resource Constrained Edge Computing Systems","created":"2018-04-14","cited_by_count":409},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"2007.10319","title":"MCUNet: Tiny Deep Learning on IoT Devices","created":"2020-07-20","cited_by_count":273},{"id":"1903.03934","title":"Asynchronous Federated Optimization","created":"2019-03-10","cited_by_count":267},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224},{"id":"1908.10530","title":"R\\'enyi Differential Privacy of the Sampled Gaussian Mechanism","created":"2019-08-28","cited_by_count":204},{"id":"2101.11203","title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","created":"2021-01-27","cited_by_count":193},{"id":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190},{"id":"2103.00039","title":"Practical and Private (Deep) Learning without Sampling or Shuffling","created":"2021-02-26","cited_by_count":170},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160},{"id":"2008.03606","title":"Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning","created":"2020-08-08","cited_by_count":154},{"id":"1910.00643","title":"SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum","created":"2019-10-01","cited_by_count":121},{"id":"1903.07424","title":"Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation","created":"2019-03-18","cited_by_count":100},{"id":"1609.08326","title":"Asynchronous Stochastic Gradient Descent with Delay Compensation","created":"2016-09-27","cited_by_count":99},{"id":"2111.04877","title":"Papaya: Practical, Private, and Scalable Federated Learning","created":"2021-11-08","cited_by_count":90},{"id":"2102.08503","title":"Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications","created":"2021-02-16","cited_by_count":85},{"id":"2106.10874","title":"FedCM: Federated Learning with Client-level Momentum","created":"2021-06-21","cited_by_count":77},{"id":"1803.01113","title":"Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD","created":"2018-03-03","cited_by_count":68},{"id":"2305.18465","title":"Federated Learning of Gboard Language Models with Differential Privacy","created":"2023-05-29","cited_by_count":66},{"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":"2202.08312","title":"Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams","created":"2022-02-16","cited_by_count":59},{"id":"2306.08153","title":"(Amplified) Banded Matrix Factorization: A unified approach to private training","created":"2023-06-13","cited_by_count":49},{"id":"1511.05950","title":"Staleness-aware Async-SGD for Distributed Deep Learning","created":"2015-11-18","cited_by_count":43},{"id":"2106.10435","title":"STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning","created":"2021-06-19","cited_by_count":43},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32},{"id":"1605.09774","title":"Asynchrony begets Momentum, with an Application to Deep Learning","created":"2016-05-31","cited_by_count":30},{"id":"2012.09102","title":"FedADC: Accelerated Federated Learning with Drift Control","created":"2020-12-16","cited_by_count":26},{"id":"2207.08869","title":"FLAIR: Federated Learning Annotated Image Repository","created":"2022-07-18","cited_by_count":22},{"id":"2007.09208","title":"Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noise","created":"2020-07-17","cited_by_count":21},{"id":"2212.00309","title":"Differentially Private Adaptive Optimization with Delayed Preconditioners","created":"2022-12-01","cited_by_count":18},{"id":"2302.12862","title":"FLINT: A Platform for Federated Learning Integration","created":"2023-02-24","cited_by_count":17},{"id":"1706.03471","title":"YellowFin and the Art of Momentum Tuning","created":"2017-06-12","cited_by_count":16},{"id":"2207.08988","title":"Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices","created":"2022-07-18","cited_by_count":16},{"id":"2312.12670","title":"On the Role of Server Momentum in Federated Learning","created":"2023-12-19","cited_by_count":16},{"id":"1909.10802","title":"Gap Aware Mitigation of Gradient Staleness","created":"2019-09-24","cited_by_count":14},{"id":"2210.16105","title":"Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout","created":"2022-10-28","cited_by_count":12},{"id":"2003.11666","title":"Pipelined Backpropagation at Scale: Training Large Models without Batches","created":"2020-03-25","cited_by_count":11},{"id":"1907.11612","title":"Taming Momentum in a Distributed Asynchronous Environment","created":"2019-07-26","cited_by_count":9},{"id":"2307.15017","title":"Samplable Anonymous Aggregation for Private Federated Data Analysis","created":"2023-07-27","cited_by_count":6}],"next_cursor":null}