{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1812.06127","title":"Federated Optimization in Heterogeneous Networks","created":"2018-12-14","cited_by_count":2987},{"id":"1806.00582","title":"Federated Learning with Non-IID Data","created":"2018-06-02","cited_by_count":1108},{"id":"2003.00295","title":"Adaptive Federated Optimization","created":"2020-02-29","cited_by_count":1046},{"id":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"2103.16257","title":"Model-Contrastive Federated Learning","created":"2021-03-30","cited_by_count":766},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"2111.04263","title":"Federated Learning Based on Dynamic Regularization","created":"2021-11-08","cited_by_count":562},{"id":"1911.00222","title":"Federated Learning with Differential Privacy: Algorithms and Performance Analysis","created":"2019-11-01","cited_by_count":536},{"id":"2106.06843","title":"Federated Learning on Non-IID Data: A Survey","created":"2021-06-12","cited_by_count":346},{"id":"2007.05084","title":"Attack of the Tails: Yes, You Really Can Backdoor Federated Learning","created":"2020-07-09","cited_by_count":309},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"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":"1312.7853","title":"Communication Efficient Distributed Optimization using an Approximate Newton-type Method","created":"2013-12-30","cited_by_count":132},{"id":"2006.03637","title":"LDP-Fed: Federated Learning with Local Differential Privacy","created":"2020-06-05","cited_by_count":132},{"id":"1910.07796","title":"Overcoming Forgetting in Federated Learning on Non-IID Data","created":"2019-10-17","cited_by_count":120},{"id":"1901.09269","title":"Distributed Learning with Compressed Gradient Differences","created":"2019-01-26","cited_by_count":112},{"id":"2311.06750","title":"Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark","created":"2023-11-12","cited_by_count":99},{"id":"2002.11364","title":"Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization","created":"2020-02-26","cited_by_count":90},{"id":"2011.02828","title":"Local SGD: Unified Theory and New Efficient Methods","created":"2020-11-03","cited_by_count":88},{"id":"2006.08950","title":"Federated Accelerated Stochastic Gradient Descent","created":"2020-06-16","cited_by_count":85},{"id":"2001.01920","title":"FedDANE: A Federated Newton-Type Method","created":"2020-01-07","cited_by_count":76},{"id":"2106.04159","title":"Fast Federated Learning in the Presence of Arbitrary Device Unavailability","created":"2021-06-08","cited_by_count":72},{"id":"2301.09604","title":"FedExP: Speeding Up Federated Averaging via Extrapolation","created":"2023-01-23","cited_by_count":69},{"id":"2207.14130","title":"FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learning","created":"2022-07-28","cited_by_count":64},{"id":"2104.14937","title":"Federated Learning with Fair Averaging","created":"2021-04-30","cited_by_count":61},{"id":"1911.10071","title":"Federated Learning with Bayesian Differential Privacy","created":"2019-11-22","cited_by_count":60},{"id":"1506.02186","title":"A Universal Catalyst for First-Order Optimization","created":"2015-06-06","cited_by_count":54},{"id":"2106.02969","title":"FedNL: Making Newton-Type Methods Applicable to Federated Learning","created":"2021-06-05","cited_by_count":52},{"id":"1709.03528","title":"GIANT: Globally Improved Approximate Newton Method for Distributed Optimization","created":"2017-09-11","cited_by_count":44},{"id":"1608.06879","title":"AIDE: Fast and Communication Efficient Distributed Optimization","created":"2016-08-24","cited_by_count":43},{"id":"2106.13897","title":"Implicit Gradient Alignment in Distributed and Federated Learning","created":"2021-06-25","cited_by_count":29},{"id":"2102.07158","title":"Distributed Second Order Methods with Fast Rates and Compressed Communication","created":"2021-02-14","cited_by_count":25},{"id":"1512.04039","title":"Distributed Optimization with Arbitrary Local Solvers","created":"2015-12-13","cited_by_count":23},{"id":"2206.08829","title":"FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning","created":"2022-06-17","cited_by_count":23},{"id":"2306.05706","title":"Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization","created":"2023-06-09","cited_by_count":21},{"id":"1901.05134","title":"DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization","created":"2019-01-16","cited_by_count":20},{"id":"1905.11546","title":"Distributed estimation of the inverse Hessian by determinantal averaging","created":"2019-05-28","cited_by_count":16},{"id":"2101.12240","title":"Differential Privacy Meets Federated Learning under Communication Constraints","created":"2021-01-28","cited_by_count":16},{"id":"2105.07320","title":"LocalNewton: Reducing Communication Bottleneck for Distributed Learning","created":"2021-05-16","cited_by_count":15},{"id":"2111.01847","title":"Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning","created":"2021-11-02","cited_by_count":15},{"id":"2206.05891","title":"Anchor Sampling for Federated Learning with Partial Client Participation","created":"2022-06-13","cited_by_count":14},{"id":"2202.05800","title":"SHED: A Newton-type algorithm for federated learning based on incremental Hessian eigenvector sharing","created":"2022-02-11","cited_by_count":11},{"id":"2203.15488","title":"Over-the-Air Federated Learning via Second-Order Optimization","created":"2022-03-29","cited_by_count":11},{"id":"2109.02388","title":"On Second-order Optimization Methods for Federated Learning","created":"2021-09-06","cited_by_count":9},{"id":"2012.05625","title":"DONE: Distributed Approximate Newton-type Method for Federated Edge Learning","created":"2020-12-10","cited_by_count":8},{"id":"2310.06227","title":"Exploring adversarial attacks in federated learning for medical imaging","created":"2023-10-10","cited_by_count":8},{"id":"1509.03475","title":"Hessian-free Optimization for Learning Deep Multidimensional Recurrent Neural Networks","created":"2015-09-11","cited_by_count":5},{"id":"2406.06655","title":"Fed-Sophia: A Communication-Efficient Second-Order Federated Learning Algorithm","created":"2024-06-10","cited_by_count":5},{"id":"2501.10877","title":"Distributed Quasi-Newton Method for Fair and Fast Federated Learning","created":"2025-01-18","cited_by_count":5},{"id":"2110.08577","title":"Nys-Newton: Nystr\\\"om-Approximated Curvature for Stochastic Optimization","created":"2021-10-16","cited_by_count":4},{"id":"2206.09576","title":"FedSSO: A Federated Server-Side Second-Order Optimization Algorithm","created":"2022-06-20","cited_by_count":3},{"id":"2211.15596","title":"A survey of deep learning optimizers -- first and second order methods","created":"2022-11-28","cited_by_count":3},{"id":"2401.02734","title":"FedNS: A Fast Sketching Newton-Type Algorithm for Federated Learning","created":"2024-01-05","cited_by_count":3},{"id":"2403.11041","title":"FAGH: Accelerating Federated Learning with Approximated Global Hessian","created":"2024-03-16","cited_by_count":2}],"next_cursor":null}