{"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":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"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":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1606.04838","title":"Optimization Methods for Large-Scale Machine Learning","created":"2016-06-15","cited_by_count":1150},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"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":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"2012.04221","title":"Ditto: Fair and Robust Federated Learning Through Personalization","created":"2020-12-08","cited_by_count":672},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1912.00818","title":"Federated Learning with Personalization Layers","created":"2019-12-02","cited_by_count":541},{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541},{"id":"2006.04088","title":"An Efficient Framework for Clustered Federated Learning","created":"2020-06-07","cited_by_count":511},{"id":"1910.01991","title":"Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints","created":"2019-10-04","cited_by_count":503},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464},{"id":"1910.03581","title":"FedMD: Heterogenous Federated Learning via Model Distillation","created":"2019-10-08","cited_by_count":459},{"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":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"2007.03797","title":"Personalized Cross-Silo Federated Learning on Non-IID Data","created":"2020-07-07","cited_by_count":283},{"id":"1902.00340","title":"Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication","created":"2019-02-01","cited_by_count":221},{"id":"2012.08565","title":"Personalized Federated Learning with First Order Model Optimization","created":"2020-12-15","cited_by_count":201},{"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":"2106.06042","title":"FedBABU: Towards Enhanced Representation for Federated Image Classification","created":"2021-06-04","cited_by_count":182},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144},{"id":"2211.08413","title":"Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challenges","created":"2022-11-15","cited_by_count":138},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122},{"id":"1910.07796","title":"Overcoming Forgetting in Federated Learning on Non-IID Data","created":"2019-10-17","cited_by_count":120},{"id":"1905.06731","title":"BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning","created":"2019-05-16","cited_by_count":117},{"id":"2104.11375","title":"Decentralized Federated Averaging","created":"2021-04-23","cited_by_count":114},{"id":"2204.03809","title":"Federated Learning with Partial Model Personalization","created":"2022-04-08","cited_by_count":114},{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98},{"id":"2206.00187","title":"DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training","created":"2022-06-01","cited_by_count":74},{"id":"2210.05177","title":"Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach","created":"2022-10-11","cited_by_count":70},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69},{"id":"2206.03996","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","created":"2022-06-08","cited_by_count":58},{"id":"2101.06905","title":"Blockchain Assisted Decentralized Federated Learning (BLADE-FL): Performance Analysis and Resource Allocation","created":"2021-01-18","cited_by_count":56},{"id":"2302.10429","title":"FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy","created":"2023-02-21","cited_by_count":49},{"id":"2302.04083","title":"Improving the Model Consistency of Decentralized Federated Learning","created":"2023-02-08","cited_by_count":45},{"id":"2210.05497","title":"Improving Sharpness-Aware Minimization with Fisher Mask for Better Generalization on Language Models","created":"2022-10-11","cited_by_count":42},{"id":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38},{"id":"1611.09726","title":"Gossip training for deep learning","created":"2016-11-29","cited_by_count":35},{"id":"2303.11242","title":"Make Landscape Flatter in Differentially Private Federated Learning","created":"2023-03-20","cited_by_count":33},{"id":"2201.11380","title":"Achieving Personalized Federated Learning with Sparse Local Models","created":"2022-01-27","cited_by_count":31},{"id":"2302.12156","title":"Personalized Decentralized Federated Learning with Knowledge Distillation","created":"2023-02-23","cited_by_count":21},{"id":"2303.00565","title":"AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks","created":"2023-03-01","cited_by_count":21},{"id":"2102.03990","title":"DeEPCA: Decentralized Exact PCA with Linear Convergence Rate","created":"2021-02-08","cited_by_count":18},{"id":"2206.07384","title":"Blockchain-based Federated Learning for Industrial Metaverses: Incentive Scheme with Optimal AoI","created":"2022-06-15","cited_by_count":16},{"id":"2107.07190","title":"Decentralized Personalized Federated Learning: Lower Bounds and Optimal Algorithm for All Personalization Modes","created":"2021-07-15","cited_by_count":13},{"id":"2305.00873","title":"Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy","created":"2023-05-01","cited_by_count":5}],"next_cursor":null}