{"list":"other","total":59,"rows":[{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"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":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"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":"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":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"1805.09767","title":"Local SGD Converges Fast and Communicates Little","created":"2018-05-24","cited_by_count":605},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"1805.04049","title":"Exploiting Unintended Feature Leakage in Collaborative Learning","created":"2018-05-10","cited_by_count":520},{"id":"1711.00489","title":"Don't Decay the Learning Rate, Increase the Batch Size","created":"2017-11-01","cited_by_count":320},{"id":"1910.00189","title":"The Non-IID Data Quagmire of Decentralized Machine Learning","created":"2019-10-01","cited_by_count":305},{"id":"1807.06629","title":"Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning","created":"2018-07-17","cited_by_count":278},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"1903.03934","title":"Asynchronous Federated Optimization","created":"2019-03-10","cited_by_count":267},{"id":"1806.00187","title":"Scaling Neural Machine Translation","created":"2018-06-01","cited_by_count":204},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1811.03600","title":"Measuring the Effects of Data Parallelism on Neural Network Training","created":"2018-11-08","cited_by_count":193},{"id":"1905.03817","title":"On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization","created":"2019-05-09","cited_by_count":180},{"id":"1611.04482","title":"Practical Secure Aggregation for Federated Learning on User-Held Data","created":"2016-11-14","cited_by_count":178},{"id":"2103.00039","title":"Practical and Private (Deep) Learning without Sampling or Shuffling","created":"2021-02-26","cited_by_count":170},{"id":"1710.06952","title":"Asynchronous Decentralized Parallel Stochastic Gradient Descent","created":"2017-10-18","cited_by_count":159},{"id":"1910.14425","title":"On the Convergence of Local Descent Methods in Federated Learning","created":"2019-10-31","cited_by_count":153},{"id":"2002.07839","title":"Is Local SGD Better than Minibatch SGD?","created":"2020-02-18","cited_by_count":151},{"id":"1702.05800","title":"Revisiting Distributed Synchronous SGD","created":"2017-02-19","cited_by_count":142},{"id":"1506.08272","title":"Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization","created":"2015-06-27","cited_by_count":116},{"id":"1910.13598","title":"Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization","created":"2019-10-30","cited_by_count":107},{"id":"1609.08326","title":"Asynchronous Stochastic Gradient Descent with Delay Compensation","created":"2016-09-27","cited_by_count":99},{"id":"2104.14380","title":"PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments","created":"2021-04-29","cited_by_count":93},{"id":"1910.01355","title":"SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overhead","created":"2019-10-03","cited_by_count":82},{"id":"2002.04156","title":"Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning","created":"2020-02-11","cited_by_count":78},{"id":"1512.02673","title":"Speeding Up Distributed Machine Learning Using Codes","created":"2015-12-08","cited_by_count":76},{"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":"1507.06970","title":"Perturbed Iterate Analysis for Asynchronous Stochastic Optimization","created":"2015-07-24","cited_by_count":67},{"id":"1806.00939","title":"Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy","created":"2018-06-04","cited_by_count":66},{"id":"2012.14453","title":"Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity","created":"2020-12-28","cited_by_count":56},{"id":"1710.00901","title":"Prochlo: Strong Privacy for Analytics in the Crowd","created":"2017-10-02","cited_by_count":51},{"id":"2106.06089","title":"Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix","created":"2021-06-10","cited_by_count":43},{"id":"2006.13838","title":"Advances in Asynchronous Parallel and Distributed Optimization","created":"2020-06-24","cited_by_count":40},{"id":"2001.03618","title":"Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation","created":"2020-01-10","cited_by_count":39},{"id":"1910.09126","title":"Communication-Efficient Local Decentralized SGD Methods","created":"2019-10-21","cited_by_count":23},{"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":"1508.00882","title":"Asynchronous stochastic convex optimization","created":"2015-08-04","cited_by_count":19},{"id":"1506.06840","title":"On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants","created":"2015-06-23","cited_by_count":18},{"id":"1606.04809","title":"ASAGA: Asynchronous Parallel SAGA","created":"2016-06-15","cited_by_count":18},{"id":"2102.06329","title":"Stragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients","created":"2021-02-12","cited_by_count":13},{"id":"1706.05699","title":"Gradient Diversity: a Key Ingredient for Scalable Distributed Learning","created":"2017-06-18","cited_by_count":3},{"id":"2003.10579","title":"Slow and Stale Gradients Can Win the Race","created":"2020-03-23","cited_by_count":3},{"id":"1801.07487","title":"Straggler Mitigation in Distributed Matrix Multiplication: Fundamental Limits and Optimal Coding","created":"2018-01-23","cited_by_count":1}],"next_cursor":null}