{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1610.05492","title":"Federated Learning: Strategies for Improving Communication Efficiency","created":"2016-10-18","cited_by_count":1475},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1707.01083","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices","created":"2017-07-04","cited_by_count":1200},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"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":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","created":"2016-09-22","cited_by_count":426},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"2107.06917","title":"A Field Guide to Federated Optimization","created":"2021-07-14","cited_by_count":315},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"1405.3866","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","created":"2014-05-15","cited_by_count":284},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1903.05134","title":"Universally Slimmable Networks and Improved Training Techniques","created":"2019-03-12","cited_by_count":221},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"1512.06473","title":"Quantized Convolutional Neural Networks for Mobile Devices","created":"2015-12-21","cited_by_count":215},{"id":"1612.01064","title":"Trained Ternary Quantization","created":"2016-12-04","cited_by_count":208},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"2108.06098","title":"FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning","created":"2021-08-13","cited_by_count":141},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106},{"id":"2104.07705","title":"How to Train BERT with an Academic Budget","created":"2021-04-15","cited_by_count":80},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76},{"id":"2211.01452","title":"MPCFormer: fast, performant and private Transformer inference with MPC","created":"2022-11-02","cited_by_count":69},{"id":"2103.03936","title":"Pufferfish: Communication-efficient Models At No Extra Cost","created":"2021-03-05","cited_by_count":61},{"id":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58},{"id":"2202.12002","title":"Rare Gems: Finding Lottery Tickets at Initialization","created":"2022-02-24","cited_by_count":34},{"id":"2111.14655","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","created":"2021-11-29","cited_by_count":31},{"id":"1511.06744","title":"Training CNNs with Low-Rank Filters for Efficient Image Classification","created":"2015-11-20","cited_by_count":25},{"id":"2006.13347","title":"Principal Component Networks: Parameter Reduction Early in Training","created":"2020-06-23","cited_by_count":9}],"next_cursor":null}