{"list":"other","total":66,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"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":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"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":"2004.05718","title":"Principal Neighbourhood Aggregation for Graph Nets","created":"2020-04-12","cited_by_count":478},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"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":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","cited_by_count":346},{"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":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202},{"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":"2204.00408","title":"Structured Pruning Learns Compact and Accurate Models","created":"2022-04-01","cited_by_count":170},{"id":"1903.09291","title":"Towards Optimal Structured CNN Pruning via Generative Adversarial Learning","created":"2019-03-22","cited_by_count":146},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","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":"2002.11448","title":"Predicting Neural Network Accuracy from Weights","created":"2020-02-26","cited_by_count":110},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107},{"id":"1905.05934","title":"EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis","created":"2019-05-15","cited_by_count":98},{"id":"2012.09243","title":"Neural Pruning via Growing Regularization","created":"2020-12-16","cited_by_count":97},{"id":"1711.06798","title":"MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks","created":"2017-11-18","cited_by_count":94},{"id":"2001.08565","title":"Channel Pruning via Automatic Structure Search","created":"2020-01-23","cited_by_count":85},{"id":"2007.03260","title":"ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting","created":"2020-07-07","cited_by_count":85},{"id":"1312.6082","title":"Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks","created":"2013-12-20","cited_by_count":84},{"id":"1904.03837","title":"Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structure","created":"2019-04-08","cited_by_count":76},{"id":"2007.03938","title":"Operation-Aware Soft Channel Pruning using Differentiable Masks","created":"2020-07-08","cited_by_count":74},{"id":"2003.01794","title":"Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection","created":"2020-03-03","cited_by_count":70},{"id":"2302.14040","title":"Permutation Equivariant Neural Functionals","created":"2023-02-27","cited_by_count":70},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64},{"id":"2403.12143","title":"Graph Neural Networks for Learning Equivariant Representations of Neural Networks","created":"2024-03-18","cited_by_count":59},{"id":"2003.13683","title":"DHP: Differentiable Meta Pruning via HyperNetworks","created":"2020-03-30","cited_by_count":57},{"id":"2312.04501","title":"Graph Metanetworks for Processing Diverse Neural Architectures","created":"2023-12-07","cited_by_count":57},{"id":"2305.13546","title":"Neural Functional Transformers","created":"2023-05-22","cited_by_count":52},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41},{"id":"2203.04570","title":"CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction","created":"2022-03-09","cited_by_count":39},{"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":"2402.05232","title":"Universal Neural Functionals","created":"2024-02-07","cited_by_count":26},{"id":"2406.10685","title":"Scale Equivariant Graph Metanetworks","created":"2024-06-15","cited_by_count":24},{"id":"2410.04209","title":"Equivariant Neural Functional Networks for Transformers","created":"2024-10-05","cited_by_count":22},{"id":"2403.14729","title":"Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch","created":"2024-03-21","cited_by_count":20},{"id":"2409.11697","title":"Monomial Matrix Group Equivariant Neural Functional Networks","created":"2024-09-18","cited_by_count":17},{"id":"2307.08483","title":"Differentiable Transportation Pruning","created":"2023-07-17","cited_by_count":10}],"next_cursor":null}