{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"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":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"2304.12620","title":"Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation","created":"2023-04-25","cited_by_count":490},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"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":"1307.5336","title":"Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts","created":"2013-07-19","cited_by_count":310},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1903.03934","title":"Asynchronous Federated Optimization","created":"2019-03-10","cited_by_count":267},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"1905.01067","title":"Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask","created":"2019-05-03","cited_by_count":207},{"id":"2106.06639","title":"Federated Learning with Buffered Asynchronous Aggregation","created":"2021-06-11","cited_by_count":190},{"id":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174},{"id":"2007.01154","title":"Federated Learning with Compression: Unified Analysis and Sharp Guarantees","created":"2020-07-02","cited_by_count":160},{"id":"1810.04304","title":"Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation","created":"2018-10-10","cited_by_count":149},{"id":"2212.01548","title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","created":"2022-12-03","cited_by_count":102},{"id":"2306.11867","title":"Personalized Federated Learning with Feature Alignment and Classifier Collaboration","created":"2023-06-20","cited_by_count":97},{"id":"2109.04269","title":"Asynchronous Federated Learning on Heterogeneous Devices: A Survey","created":"2021-09-09","cited_by_count":93},{"id":"2210.13291","title":"NVIDIA FLARE: Federated Learning from Simulation to Real-World","created":"2022-10-24","cited_by_count":80},{"id":"2206.12562","title":"PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance","created":"2022-06-25","cited_by_count":79},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70},{"id":"2010.05958","title":"FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers","created":"2020-10-12","cited_by_count":64},{"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":"2206.05187","title":"On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyond","created":"2022-06-10","cited_by_count":38},{"id":"2305.02776","title":"Efficient Personalized Federated Learning via Sparse Model-Adaptation","created":"2023-05-04","cited_by_count":38},{"id":"2201.07703","title":"Q-ViT: Fully Differentiable Quantization for Vision Transformer","created":"2022-01-19","cited_by_count":37},{"id":"2107.13892","title":"QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning","created":"2021-07-29","cited_by_count":32},{"id":"2209.15328","title":"Sparse Random Networks for Communication-Efficient Federated Learning","created":"2022-09-30","cited_by_count":32},{"id":"2312.05770","title":"FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-aware Model Update","created":"2023-12-10","cited_by_count":32},{"id":"1910.07561","title":"A Double Residual Compression Algorithm for Efficient Distributed Learning","created":"2019-10-16","cited_by_count":31},{"id":"2302.03109","title":"On the Convergence of Federated Averaging with Cyclic Client Participation","created":"2023-02-06","cited_by_count":31},{"id":"2304.06947","title":"TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Training","created":"2023-04-14","cited_by_count":27},{"id":"2310.08670","title":"Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction","created":"2023-10-12","cited_by_count":24},{"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":"2402.05926","title":"On the Convergence of Zeroth-Order Federated Tuning for Large Language Models","created":"2024-02-08","cited_by_count":19},{"id":"2109.12519","title":"AsySQN: Faster Vertical Federated Learning Algorithms with Better Computation Resource Utilization","created":"2021-09-26","cited_by_count":16},{"id":"2208.13141","title":"Federated Learning of Large Models at the Edge via Principal Sub-Model Training","created":"2022-08-28","cited_by_count":13},{"id":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13},{"id":"2403.01387","title":"A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applications","created":"2024-03-03","cited_by_count":8},{"id":"2405.15551","title":"Thinking Forward: Memory-Efficient Federated Finetuning of Language Models","created":"2024-05-24","cited_by_count":7},{"id":"2312.14478","title":"Federated Learning via Input-Output Collaborative Distillation","created":"2023-12-22","cited_by_count":6},{"id":"2301.12677","title":"Distributed Stochastic Optimization under a General Variance Condition","created":"2023-01-30","cited_by_count":4},{"id":"2405.13746","title":"CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models","created":"2024-05-22","cited_by_count":4},{"id":"2212.09483","title":"Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning","created":"2022-12-19","cited_by_count":3},{"id":"2307.11617","title":"Robust Fully-Asynchronous Methods for Distributed Training over General Architecture","created":"2023-07-21","cited_by_count":2}],"next_cursor":null}