{"list":"other","total":72,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"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":"1812.01097","title":"LEAF: A Benchmark for Federated Settings","created":"2018-12-03","cited_by_count":792},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"1811.03604","title":"Federated Learning for Mobile Keyboard Prediction","created":"2018-11-08","cited_by_count":572},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"2105.10056","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","created":"2021-05-20","cited_by_count":383},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"2002.07948","title":"Personalized Federated Learning: A Meta-Learning Approach","created":"2020-02-19","cited_by_count":312},{"id":"2007.13518","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","created":"2020-07-27","cited_by_count":300},{"id":"1812.02903","title":"Applied Federated Learning: Improving Google Keyboard Query Suggestions","created":"2018-12-07","cited_by_count":204},{"id":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"2010.01243","title":"Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies","created":"2020-10-03","cited_by_count":198},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2209.10083","title":"Federated Learning from Pre-Trained Models: A Contrastive Learning Approach","created":"2022-09-21","cited_by_count":142},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136},{"id":"2012.06043","title":"Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective","created":"2020-12-08","cited_by_count":94},{"id":"2104.08815","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","created":"2021-04-18","cited_by_count":85},{"id":"2205.08514","title":"Recovering Private Text in Federated Learning of Language Models","created":"2022-05-17","cited_by_count":70},{"id":"1905.05460","title":"Cognitive Graph for Multi-Hop Reading Comprehension at Scale","created":"2019-05-14","cited_by_count":65},{"id":"2104.13417","title":"Towards Fair Federated Learning with Zero-Shot Data Augmentation","created":"2021-04-27","cited_by_count":64},{"id":"1909.12641","title":"Active Federated Learning","created":"2019-09-27","cited_by_count":63},{"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":"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":"2202.08827","title":"LAMP: Extracting Text from Gradients with Language Model Priors","created":"2022-02-17","cited_by_count":54},{"id":"2107.12603","title":"Federated Learning Meets Natural Language Processing: A Survey","created":"2021-07-27","cited_by_count":43},{"id":"2102.05218","title":"FLOP: Federated Learning on Medical Datasets using Partial Networks","created":"2021-02-10","cited_by_count":42},{"id":"2209.10526","title":"Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces","created":"2022-09-21","cited_by_count":36},{"id":"2209.15245","title":"Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction","created":"2022-09-30","cited_by_count":32},{"id":"2206.02291","title":"Pretrained Models for Multilingual Federated Learning","created":"2022-06-06","cited_by_count":30},{"id":"2105.00562","title":"Personalized Federated Learning by Structured and Unstructured Pruning under Data Heterogeneity","created":"2021-05-02","cited_by_count":27},{"id":"2003.09288","title":"FedNER: Privacy-preserving Medical Named Entity Recognition with Federated Learning","created":"2020-03-20","cited_by_count":24},{"id":"2208.09754","title":"FLIS: Clustered Federated Learning via Inference Similarity for Non-IID Data Distribution","created":"2022-08-20","cited_by_count":22},{"id":"1809.01293","title":"Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theory","created":"2018-09-05","cited_by_count":20},{"id":"2210.03277","title":"Rethinking Normalization Methods in Federated Learning","created":"2022-10-07","cited_by_count":19},{"id":"2110.01643","title":"Privacy enabled Financial Text Classification using Differential Privacy and Federated Learning","created":"2021-10-04","cited_by_count":18},{"id":"2004.03657","title":"FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning","created":"2020-04-07","cited_by_count":14},{"id":"2112.05120","title":"On Convergence of Federated Averaging Langevin Dynamics","created":"2021-12-09","cited_by_count":14},{"id":"2208.08140","title":"Differential Privacy in Natural Language Processing: The Story So Far","created":"2022-08-17","cited_by_count":12},{"id":"1811.08052","title":"Variance Reduction in Stochastic Particle-Optimization Sampling","created":"2018-11-20","cited_by_count":11},{"id":"2205.13299","title":"Federated Split BERT for Heterogeneous Text Classification","created":"2022-05-26","cited_by_count":11},{"id":"2210.06101","title":"Federated Continual Learning for Text Classification via Selective Inter-client Transfer","created":"2022-10-12","cited_by_count":9},{"id":"2212.12712","title":"When Do Curricula Work in Federated Learning?","created":"2022-12-24","cited_by_count":9},{"id":"1811.08929","title":"Self-Adversarially Learned Bayesian Sampling","created":"2018-11-21","cited_by_count":8},{"id":"2102.05561","title":"Meta Federated Learning","created":"2021-02-10","cited_by_count":8},{"id":"2205.11788","title":"Meta Policy Learning for Cold-Start Conversational Recommendation","created":"2022-05-24","cited_by_count":6},{"id":"2110.06419","title":"Federated Natural Language Generation for Personalized Dialogue System","created":"2021-10-13","cited_by_count":5},{"id":"2201.09384","title":"A Comprehensive Survey on Federated Learning: Concept and Applications","created":"2022-01-23","cited_by_count":4}],"next_cursor":null}