{"list":"other","total":53,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"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":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"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":"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":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"2010.01264","title":"HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients","created":"2020-10-03","cited_by_count":337},{"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":"1605.00459","title":"Multi30K: Multilingual English-German Image Descriptions","created":"2016-05-02","cited_by_count":250},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"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":"2102.13451","title":"FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout","created":"2021-02-26","cited_by_count":192},{"id":"1711.08393","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","created":"2017-11-22","cited_by_count":189},{"id":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184},{"id":"1812.07210","title":"Expanding the Reach of Federated Learning by Reducing Client Resource Requirements","created":"2018-12-18","cited_by_count":163},{"id":"2206.15472","title":"On-Device Training Under 256KB Memory","created":"2022-06-30","cited_by_count":160},{"id":"1712.06559","title":"The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning","created":"2017-12-18","cited_by_count":150},{"id":"1611.00429","title":"Distributed Mean Estimation with Limited Communication","created":"2016-11-02","cited_by_count":136},{"id":"1611.05128","title":"Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning","created":"2016-11-16","cited_by_count":134},{"id":"1511.06422","title":"All you need is a good init","created":"2015-11-19","cited_by_count":124},{"id":"2212.01548","title":"FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction","created":"2022-12-03","cited_by_count":102},{"id":"1402.0915","title":"Learning Ordered Representations with Nested Dropout","created":"2014-02-05","cited_by_count":84},{"id":"2106.05022","title":"Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions","created":"2021-06-09","cited_by_count":75},{"id":"2107.07467","title":"Only Train Once: A One-Shot Neural Network Training And Pruning Framework","created":"2021-07-15","cited_by_count":70},{"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":"1308.6370","title":"Fast Convergence of Stochastic Gradient Descent under a Strong Growth Condition","created":"2013-08-29","cited_by_count":54},{"id":"2106.14289","title":"Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization","created":"2021-06-27","cited_by_count":45},{"id":"2210.03044","title":"Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?","created":"2022-10-06","cited_by_count":38},{"id":"2202.12002","title":"Rare Gems: Finding Lottery Tickets at Initialization","created":"2022-02-24","cited_by_count":34},{"id":"2109.13963","title":"Smart at what cost? Characterising Mobile Deep Neural Networks in the wild","created":"2021-09-28","cited_by_count":25},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25},{"id":"2102.12810","title":"Hyperparameter Transfer Learning with Adaptive Complexity","created":"2021-02-25","cited_by_count":17},{"id":"2110.03450","title":"Efficient and Private Federated Learning with Partially Trainable Networks","created":"2021-10-06","cited_by_count":13},{"id":"2210.10514","title":"The Future of Consumer Edge-AI Computing","created":"2022-10-19","cited_by_count":12},{"id":"1907.03540","title":"ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning","created":"2019-07-08","cited_by_count":7},{"id":"2212.04084","title":"Federated Learning for Inference at Anytime and Anywhere","created":"2022-12-08","cited_by_count":6}],"next_cursor":null}