{"list":"other","total":51,"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"1910.04732","title":"Structured Pruning of Large Language Models","created":"2019-10-10","cited_by_count":203},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"1707.01213","title":"Data-Driven Sparse Structure Selection for Deep Neural Networks","created":"2017-07-05","cited_by_count":181},{"id":"1810.11809","title":"Discrimination-aware Channel Pruning for Deep Neural Networks","created":"2018-10-28","cited_by_count":171},{"id":"1308.6594","title":"Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization","created":"2013-08-29","cited_by_count":143},{"id":"1906.05497","title":"Deep Network Approximation Characterized by Number of Neurons","created":"2019-06-13","cited_by_count":122},{"id":"1909.08174","title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","created":"2019-09-18","cited_by_count":118},{"id":"2010.10732","title":"SCOP: Scientific Control for Reliable Neural Network Pruning","created":"2020-10-21","cited_by_count":93},{"id":"2001.08565","title":"Channel Pruning via Automatic Structure Search","created":"2020-01-23","cited_by_count":85},{"id":"2007.03938","title":"Operation-Aware Soft Channel Pruning using Differentiable Masks","created":"2020-07-08","cited_by_count":74},{"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":"2003.01794","title":"Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection","created":"2020-03-03","cited_by_count":70},{"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":"2003.13683","title":"DHP: Differentiable Meta Pruning via HyperNetworks","created":"2020-03-30","cited_by_count":57},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50},{"id":"2105.11228","title":"Towards Compact CNNs via Collaborative Compression","created":"2021-05-24","cited_by_count":36},{"id":"2212.00974","title":"Faster Adaptive Federated Learning","created":"2022-12-02","cited_by_count":35},{"id":"2303.06862","title":"OTOV2: Automatic, Generic, User-Friendly","created":"2023-03-13","cited_by_count":32},{"id":"2102.03214","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","created":"2021-02-05","cited_by_count":30},{"id":"2006.16433","title":"Fast OSCAR and OWL Regression via Safe Screening Rules","created":"2020-06-29","cited_by_count":25},{"id":"2310.08670","title":"Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction","created":"2023-10-12","cited_by_count":24},{"id":"2208.06058","title":"An Accelerated Doubly Stochastic Gradient Method with Faster Explicit Model Identification","created":"2022-08-11","cited_by_count":14},{"id":"2107.04217","title":"Joint Models for Answer Verification in Question Answering Systems","created":"2021-07-09","cited_by_count":13},{"id":"2307.08483","title":"Differentiable Transportation Pruning","created":"2023-07-17","cited_by_count":10},{"id":"2310.03613","title":"Solving a Class of Non-Convex Minimax Optimization in Federated Learning","created":"2023-10-05","cited_by_count":10},{"id":"2305.11315","title":"Improving Toponym Resolution with Better Candidate Generation, Transformer-based Reranking, and Two-Stage Resolution","created":"2023-05-18","cited_by_count":7},{"id":"1904.10921","title":"Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks","created":"2019-04-24","cited_by_count":6},{"id":"1911.10436","title":"ScienceExamCER: A High-Density Fine-Grained Science-Domain Corpus for Common Entity Recognition","created":"2019-11-24","cited_by_count":6},{"id":"2311.08479","title":"Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning","created":"2023-11-14","cited_by_count":5},{"id":"2401.14544","title":"Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal Data","created":"2024-01-25","cited_by_count":5},{"id":"2201.05981","title":"Double Retrieval and Ranking for Accurate Question Answering","created":"2022-01-16","cited_by_count":4},{"id":"2201.05984","title":"In Situ Answer Sentence Selection at Web-scale","created":"2022-01-16","cited_by_count":2}],"next_cursor":null}