{"list":"other","total":59,"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":"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":"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"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":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"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":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"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":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"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":"2006.07242","title":"Ensemble Distillation for Robust Model Fusion in Federated Learning","created":"2020-06-12","cited_by_count":682},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1610.02527","title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence","created":"2016-10-08","cited_by_count":564},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"1905.10497","title":"Fair Resource Allocation in Federated Learning","created":"2019-05-25","cited_by_count":394},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269},{"id":"1807.01647","title":"Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergences","created":"2018-07-04","cited_by_count":242},{"id":"1909.08478","title":"Simple, Scalable Adaptation for Neural Machine Translation","created":"2019-09-18","cited_by_count":242},{"id":"2106.05001","title":"No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data","created":"2021-06-09","cited_by_count":241},{"id":"1808.00087","title":"Subsampled R\\'enyi Differential Privacy and Analytical Moments Accountant","created":"2018-07-31","cited_by_count":236},{"id":"2210.07558","title":"DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","created":"2022-10-14","cited_by_count":233},{"id":"1908.10530","title":"R\\'enyi Differential Privacy of the Sampled Gaussian Mechanism","created":"2019-08-28","cited_by_count":204},{"id":"1505.00855","title":"Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature","created":"2015-05-05","cited_by_count":182},{"id":"2403.12313","title":"Improving LoRA in Privacy-preserving Federated Learning","created":"2024-03-18","cited_by_count":161},{"id":"2110.01900","title":"DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT","created":"2021-10-05","cited_by_count":144},{"id":"1702.05800","title":"Revisiting Distributed Synchronous SGD","created":"2017-02-19","cited_by_count":142},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141},{"id":"2102.06387","title":"The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation","created":"2021-02-12","cited_by_count":128},{"id":"2208.12268","title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","created":"2022-08-25","cited_by_count":91},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88},{"id":"1905.09982","title":"Hypothesis Testing Interpretations and Renyi Differential Privacy","created":"2019-05-24","cited_by_count":85},{"id":"1311.3158","title":"Fingerprinting Codes and the Price of Approximate Differential Privacy","created":"2013-11-13","cited_by_count":82},{"id":"1811.07971","title":"Private Selection from Private Candidates","created":"2018-11-19","cited_by_count":75},{"id":"2111.09278","title":"Differentially Private Federated Learning on Heterogeneous Data","created":"2021-11-17","cited_by_count":74},{"id":"2305.18465","title":"Federated Learning of Gboard Language Models with Differential Privacy","created":"2023-05-29","cited_by_count":66},{"id":"2008.07665","title":"Inverse Distance Aggregation for Federated Learning with Non-IID Data","created":"2020-08-17","cited_by_count":44},{"id":"2111.00465","title":"DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning","created":"2021-10-31","cited_by_count":41},{"id":"2211.08025","title":"FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers","created":"2022-11-15","cited_by_count":33},{"id":"2305.15212","title":"Towards Adaptive Prefix Tuning for Parameter-Efficient Language Model Fine-tuning","created":"2023-05-24","cited_by_count":29},{"id":"2204.09715","title":"Scaling Language Model Size in Cross-Device Federated Learning","created":"2022-03-31","cited_by_count":25},{"id":"2207.08869","title":"FLAIR: Federated Learning Annotated Image Repository","created":"2022-07-18","cited_by_count":22},{"id":"2207.08988","title":"Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices","created":"2022-07-18","cited_by_count":16},{"id":"2211.13579","title":"Knowledge-Aware Federated Active Learning with Non-IID Data","created":"2022-11-24","cited_by_count":16},{"id":"2207.10635","title":"Widespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix It","created":"2022-07-21","cited_by_count":8}],"next_cursor":null}