{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"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":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2003.03033","title":"What is the State of Neural Network Pruning?","created":"2020-03-06","cited_by_count":583},{"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":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2110.14430","title":"Adversarial Neuron Pruning Purifies Backdoored Deep Models","created":"2021-10-27","cited_by_count":235},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1306.0543","title":"Predicting Parameters in Deep Learning","created":"2013-06-03","cited_by_count":224},{"id":"1803.06373","title":"Adversarial Logit Pairing","created":"2018-03-16","cited_by_count":224},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"2002.08307","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","created":"2020-02-19","cited_by_count":185},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"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":"2002.02925","title":"BERT-of-Theseus: Compressing BERT by Progressive Module Replacing","created":"2020-02-07","cited_by_count":113},{"id":"1905.05934","title":"EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis","created":"2019-05-15","cited_by_count":98},{"id":"1911.07412","title":"Provable Filter Pruning for Efficient Neural Networks","created":"2019-11-18","cited_by_count":98},{"id":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"1506.02515","title":"Fast ConvNets Using Group-wise Brain Damage","created":"2015-06-08","cited_by_count":82},{"id":"2110.13981","title":"CHIP: CHannel Independence-based Pruning for Compact Neural Networks","created":"2021-10-26","cited_by_count":78},{"id":"2003.08935","title":"Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression","created":"2020-03-19","cited_by_count":72},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62},{"id":"2007.01429","title":"The Global Landscape of Neural Networks: An Overview","created":"2020-07-02","cited_by_count":57},{"id":"1906.03728","title":"The Generalization-Stability Tradeoff In Neural Network Pruning","created":"2019-06-09","cited_by_count":54},{"id":"1811.00731","title":"The age of secrecy and unfairness in recidivism prediction","created":"2018-11-02","cited_by_count":53},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47},{"id":"2205.13574","title":"Pruning has a disparate impact on model accuracy","created":"2022-05-26","cited_by_count":44},{"id":"1804.05345","title":"Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds","created":"2018-04-15","cited_by_count":43},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41},{"id":"2109.03228","title":"Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression","created":"2021-09-07","cited_by_count":38},{"id":"2001.00218","title":"Lossless Compression of Deep Neural Networks","created":"2020-01-01","cited_by_count":34},{"id":"2007.08243","title":"Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning","created":"2020-07-16","cited_by_count":23},{"id":"2108.04890","title":"On the Effect of Pruning on Adversarial Robustness","created":"2021-08-10","cited_by_count":23},{"id":"2009.09936","title":"Prune Responsibly","created":"2020-09-10","cited_by_count":20},{"id":"2102.07804","title":"Scaling Up Exact Neural Network Compression by ReLU Stability","created":"2021-02-15","cited_by_count":19},{"id":"2012.01604","title":"Going Beyond Classification Accuracy Metrics in Model Compression","created":"2020-12-03","cited_by_count":15},{"id":"2106.07849","title":"Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation","created":"2021-06-15","cited_by_count":15},{"id":"1607.04683","title":"On the efficient representation and execution of deep acoustic models","created":"2016-07-15","cited_by_count":13},{"id":"2201.01709","title":"The Effect of Model Compression on Fairness in Facial Expression Recognition","created":"2022-01-05","cited_by_count":13},{"id":"2007.06567","title":"Lossless Compression of Structured Convolutional Models via Lifting","created":"2020-07-13","cited_by_count":11},{"id":"2201.12795","title":"Training Thinner and Deeper Neural Networks: Jumpstart Regularization","created":"2022-01-30","cited_by_count":3}],"next_cursor":null}