{"list":"other","total":73,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"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":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"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":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"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":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"2102.02079","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","created":"2021-02-03","cited_by_count":568},{"id":"2110.08263","title":"FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling","created":"2021-10-15","cited_by_count":540},{"id":"1908.02983","title":"Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning","created":"2019-08-08","cited_by_count":510},{"id":"1904.05046","title":"Generalizing from a Few Examples: A Survey on Few-Shot Learning","created":"2019-04-10","cited_by_count":463},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"1708.02072","title":"Measuring Catastrophic Forgetting in Neural Networks","created":"2017-08-07","cited_by_count":360},{"id":"1804.08333","title":"Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge","created":"2018-04-23","cited_by_count":352},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"1803.00942","title":"Not All Samples Are Created Equal: Deep Learning with Importance Sampling","created":"2018-03-02","cited_by_count":328},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"2006.05987","title":"Revisiting Few-sample BERT Fine-tuning","created":"2020-06-10","cited_by_count":238},{"id":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"1811.08737","title":"SpotTune: Transfer Learning through Adaptive Fine-tuning","created":"2018-11-21","cited_by_count":168},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"1902.01718","title":"End-to-End Open-Domain Question Answering with BERTserini","created":"2019-02-05","cited_by_count":152},{"id":"1801.07883","title":"Deep Learning for Sentiment Analysis : A Survey","created":"2018-01-24","cited_by_count":139},{"id":"2106.13353","title":"Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models","created":"2021-06-24","cited_by_count":139},{"id":"2105.11367","title":"FedScale: Benchmarking Model and System Performance of Federated Learning at Scale","created":"2021-05-24","cited_by_count":136},{"id":"2204.03649","title":"Unsupervised Prompt Learning for Vision-Language Models","created":"2022-04-07","cited_by_count":127},{"id":"1902.11175","title":"One-Shot Federated Learning","created":"2019-02-28","cited_by_count":125},{"id":"2006.12097","title":"Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning","created":"2020-06-22","cited_by_count":112},{"id":"2004.04314","title":"Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective","created":"2020-04-09","cited_by_count":103},{"id":"2104.08815","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","created":"2021-04-18","cited_by_count":85},{"id":"1511.06481","title":"Variance Reduction in SGD by Distributed Importance Sampling","created":"2015-11-20","cited_by_count":79},{"id":"1806.08054","title":"Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization","created":"2018-06-21","cited_by_count":76},{"id":"2003.13848","title":"Code Prediction by Feeding Trees to Transformers","created":"2020-03-30","cited_by_count":70},{"id":"1909.04925","title":"How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations","created":"2019-09-11","cited_by_count":63},{"id":"2103.06819","title":"TAG: Gradient Attack on Transformer-based Language Models","created":"2021-03-11","cited_by_count":63},{"id":"2202.08827","title":"LAMP: Extracting Text from Gradients with Language Model Priors","created":"2022-02-17","cited_by_count":54},{"id":"2201.01601","title":"FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients","created":"2022-01-05","cited_by_count":46},{"id":"2106.01432","title":"SemiFL: Semi-Supervised Federated Learning for Unlabeled Clients with Alternate Training","created":"2021-06-02","cited_by_count":45},{"id":"2101.00787","title":"Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation","created":"2021-01-04","cited_by_count":40},{"id":"2111.13440","title":"True Few-Shot Learning with Prompts -- A Real-World Perspective","created":"2021-11-26","cited_by_count":38},{"id":"2007.11622","title":"TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning","created":"2020-07-22","cited_by_count":32},{"id":"2206.07509","title":"Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading","created":"2022-06-15","cited_by_count":29},{"id":"2106.13973","title":"Benchmarking Differential Privacy and Federated Learning for BERT Models","created":"2021-06-26","cited_by_count":28},{"id":"2011.00851","title":"Semi-supervised Federated Learning for Activity Recognition","created":"2020-11-02","cited_by_count":18},{"id":"2203.08810","title":"Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling","created":"2022-03-15","cited_by_count":12},{"id":"2104.00365","title":"Federated Few-Shot Learning with Adversarial Learning","created":"2021-04-01","cited_by_count":11},{"id":"2109.03395","title":"From Cloud to Edge: A First Look at Public Edge Platforms","created":"2021-09-08","cited_by_count":9},{"id":"2201.11934","title":"A Secure and Efficient Federated Learning Framework for NLP","created":"2022-01-28","cited_by_count":9},{"id":"2212.00192","title":"Towards Practical Few-shot Federated NLP","created":"2022-12-01","cited_by_count":5},{"id":"2203.02652","title":"Unfreeze with Care: Space-Efficient Fine-Tuning of Semantic Parsing Models","created":"2022-03-05","cited_by_count":4}],"next_cursor":null}