{"list":"other","total":53,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"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":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"1710.01878","title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","created":"2017-10-05","cited_by_count":603},{"id":"2007.14390","title":"Flower: A Friendly Federated Learning Research Framework","created":"2020-07-28","cited_by_count":455},{"id":"2005.07683","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","created":"2020-05-15","cited_by_count":403},{"id":"1907.09693","title":"A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection","created":"2019-07-23","cited_by_count":374},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"1909.13014","title":"FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization","created":"2019-09-28","cited_by_count":356},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"id":"2007.13518","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","created":"2020-07-27","cited_by_count":300},{"id":"2104.07914","title":"Federated Learning for Internet of Things: A Comprehensive Survey","created":"2021-04-16","cited_by_count":252},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"2102.13451","title":"FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout","created":"2021-02-26","cited_by_count":192},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149},{"id":"1911.02054","title":"Federated Adversarial Domain Adaptation","created":"2019-11-05","cited_by_count":140},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131},{"id":"2102.07053","title":"Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients","created":"2021-02-14","cited_by_count":123},{"id":"1901.09269","title":"Distributed Learning with Compressed Gradient Differences","created":"2019-01-26","cited_by_count":112},{"id":"2308.06522","title":"SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models","created":"2023-08-12","cited_by_count":93},{"id":"2208.12268","title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","created":"2022-08-25","cited_by_count":91},{"id":"2210.13291","title":"NVIDIA FLARE: Federated Learning from Simulation to Real-World","created":"2022-10-24","cited_by_count":80},{"id":"2302.13485","title":"FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning","created":"2023-02-27","cited_by_count":70},{"id":"2103.02885","title":"Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework","created":"2021-03-04","cited_by_count":69},{"id":"1712.01048","title":"Adaptive Quantization for Deep Neural Network","created":"2017-12-04","cited_by_count":67},{"id":"2104.14362","title":"From Distributed Machine Learning to Federated Learning: A Survey","created":"2021-04-29","cited_by_count":66},{"id":"2305.18465","title":"Federated Learning of Gboard Language Models with Differential Privacy","created":"2023-05-29","cited_by_count":66},{"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":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59},{"id":"2105.06413","title":"OpenFL: An open-source framework for Federated Learning","created":"2021-05-13","cited_by_count":58},{"id":"2007.10987","title":"IBM Federated Learning: an Enterprise Framework White Paper V0.1","created":"2020-07-22","cited_by_count":57},{"id":"2312.06353","title":"Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes","created":"2023-12-11","cited_by_count":55},{"id":"2204.05011","title":"FederatedScope: A Flexible Federated Learning Platform for Heterogeneity","created":"2022-04-11","cited_by_count":53},{"id":"2305.11414","title":"Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models","created":"2023-05-19","cited_by_count":50},{"id":"2206.09888","title":"SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression","created":"2022-06-20","cited_by_count":34},{"id":"2209.15328","title":"Sparse Random Networks for Communication-Efficient Federated Learning","created":"2022-09-30","cited_by_count":32},{"id":"1703.02952","title":"A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics","created":"2017-03-08","cited_by_count":30},{"id":"2208.05174","title":"FedOBD: Opportunistic Block Dropout for Efficiently Training Large-scale Neural Networks through Federated Learning","created":"2022-08-10","cited_by_count":17},{"id":"2302.12862","title":"FLINT: A Platform for Federated Learning Integration","created":"2023-02-24","cited_by_count":17},{"id":"2310.03150","title":"Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly","created":"2023-10-04","cited_by_count":17},{"id":"1910.11567","title":"Substra: a framework for privacy-preserving, traceable and collaborative Machine Learning","created":"2019-10-25","cited_by_count":14},{"id":"2106.00275","title":"H-FL: A Hierarchical Communication-Efficient and Privacy-Protected Architecture for Federated Learning","created":"2021-06-01","cited_by_count":14},{"id":"2212.01977","title":"Distributed Pruning Towards Tiny Neural Networks in Federated Learning","created":"2022-12-05","cited_by_count":11},{"id":"1904.07933","title":"Audio-Visual Model Distillation Using Acoustic Images","created":"2019-04-16","cited_by_count":8},{"id":"2109.11105","title":"Distiller: A Systematic Study of Model Distillation Methods in Natural Language Processing","created":"2021-09-23","cited_by_count":7},{"id":"2306.03163","title":"How Can We Train Deep Learning Models Across Clouds and Continents? An Experimental Study","created":"2023-06-05","cited_by_count":4}],"next_cursor":null}