{"list":"other","total":56,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2102.00554","title":"Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks","created":"2021-01-31","cited_by_count":527},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"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":"1610.05755","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","created":"2016-10-18","cited_by_count":348},{"id":"1905.12101","title":"Differential Privacy Has Disparate Impact on Model Accuracy","created":"2019-05-28","cited_by_count":316},{"id":"1910.06188","title":"Q8BERT: Quantized 8Bit BERT","created":"2019-10-14","cited_by_count":300},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"1802.08908","title":"Scalable Private Learning with PATE","created":"2018-02-24","cited_by_count":269},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"2011.11660","title":"Differentially Private Learning Needs Better Features (or Much More Data)","created":"2020-11-23","cited_by_count":235},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224},{"id":"2106.02848","title":"Numerical Composition of Differential Privacy","created":"2021-06-05","cited_by_count":180},{"id":"2106.08962","title":"Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better","created":"2021-06-16","cited_by_count":154},{"id":"1903.12136","title":"Distilling Task-Specific Knowledge from BERT into Simple Neural Networks","created":"2019-03-28","cited_by_count":153},{"id":"2004.07320","title":"Training with Quantization Noise for Extreme Model Compression","created":"2020-04-15","cited_by_count":145},{"id":"1908.08962","title":"Well-Read Students Learn Better: On the Importance of Pre-training Compact Models","created":"2019-08-23","cited_by_count":120},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118},{"id":"2002.11985","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","created":"2020-02-27","cited_by_count":96},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86},{"id":"2004.12254","title":"Privacy in Deep Learning: A Survey","created":"2020-04-25","cited_by_count":71},{"id":"2011.14203","title":"EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference","created":"2020-11-28","cited_by_count":70},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56},{"id":"2004.04124","title":"LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression","created":"2020-04-08","cited_by_count":45},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41},{"id":"2009.05537","title":"Federated Model Distillation with Noise-Free Differential Privacy","created":"2020-09-11","cited_by_count":40},{"id":"2009.08065","title":"Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning","created":"2020-09-17","cited_by_count":39},{"id":"2004.05686","title":"XtremeDistil: Multi-stage Distillation for Massive Multilingual Models","created":"2020-04-12","cited_by_count":38},{"id":"1811.05072","title":"Private Model Compression via Knowledge Distillation","created":"2018-11-13","cited_by_count":37},{"id":"2205.13621","title":"Differentially Private Decoding in Large Language Models","created":"2022-05-26","cited_by_count":34},{"id":"2106.12576","title":"DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?","created":"2021-06-22","cited_by_count":33},{"id":"2107.13686","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","created":"2021-07-29","cited_by_count":31},{"id":"2201.00971","title":"Submix: Practical Private Prediction for Large-Scale Language Models","created":"2022-01-04","cited_by_count":31},{"id":"1909.12486","title":"Reweighted Proximal Pruning for Large-Scale Language Representation","created":"2019-09-27","cited_by_count":29},{"id":"2005.00697","title":"DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering","created":"2020-05-02","cited_by_count":29},{"id":"1911.03588","title":"MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models","created":"2019-11-09","cited_by_count":8},{"id":"2005.03848","title":"Distilling Knowledge from Pre-trained Language Models via Text Smoothing","created":"2020-05-08","cited_by_count":2}],"next_cursor":null}