{"list":"other","total":100,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"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":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"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":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"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":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"2003.02389","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2020-03-05","cited_by_count":240},{"id":"1911.13299","title":"What's Hidden in a Randomly Weighted Neural Network?","created":"2019-11-29","cited_by_count":237},{"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":"1905.01067","title":"Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask","created":"2019-05-03","cited_by_count":207},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"1804.03294","title":"A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers","created":"2018-04-10","cited_by_count":120},{"id":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118},{"id":"2005.00561","title":"When BERT Plays the Lottery, All Tickets Are Winning","created":"2020-05-01","cited_by_count":114},{"id":"1906.02773","title":"One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers","created":"2019-06-06","cited_by_count":102},{"id":"1912.04427","title":"Winning the Lottery with Continuous Sparsification","created":"2019-12-10","cited_by_count":100},{"id":"2012.06908","title":"The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models","created":"2020-12-12","cited_by_count":91},{"id":"2006.07990","title":"Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient","created":"2020-06-14","cited_by_count":81},{"id":"2101.00063","title":"EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets","created":"2020-12-31","cited_by_count":79},{"id":"2110.14032","title":"MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge","created":"2021-10-26","cited_by_count":79},{"id":"2010.03533","title":"Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win","created":"2020-10-07","cited_by_count":77},{"id":"1906.02768","title":"Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP","created":"2019-06-06","cited_by_count":73},{"id":"2006.12156","title":"Logarithmic Pruning is All You Need","created":"2020-06-22","cited_by_count":71},{"id":"2009.11094","title":"Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot","created":"2020-09-22","cited_by_count":66},{"id":"2008.03371","title":"LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets","created":"2020-08-07","cited_by_count":60},{"id":"2105.12002","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","created":"2021-05-25","cited_by_count":56},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55},{"id":"2107.00166","title":"Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?","created":"2021-07-01","cited_by_count":52},{"id":"2111.13445","title":"How Well Do Sparse Imagenet Models Transfer?","created":"2021-11-26","cited_by_count":50},{"id":"2001.01969","title":"Sparse Weight Activation Training","created":"2020-01-07","cited_by_count":45},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45},{"id":"2106.03225","title":"Efficient Lottery Ticket Finding: Less Data is More","created":"2021-06-06","cited_by_count":44},{"id":"2205.13571","title":"Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations","created":"2022-05-26","cited_by_count":43},{"id":"1812.11677","title":"ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers","created":"2018-12-31","cited_by_count":42},{"id":"2110.12007","title":"When to Prune? A Policy towards Early Structural Pruning","created":"2021-10-22","cited_by_count":38},{"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":"1903.01611","title":"Stabilizing the Lottery Ticket Hypothesis","created":"2019-03-05","cited_by_count":37},{"id":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36},{"id":"2012.04643","title":"The Lottery Ticket Hypothesis for Object Recognition","created":"2020-12-08","cited_by_count":34},{"id":"2202.08132","title":"Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients","created":"2022-02-16","cited_by_count":34},{"id":"2106.00134","title":"GANs Can Play Lottery Tickets Too","created":"2021-05-31","cited_by_count":32},{"id":"1911.05034","title":"Learning Sparse Sharing Architectures for Multiple Tasks","created":"2019-11-12","cited_by_count":31},{"id":"2110.11395","title":"SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning","created":"2021-10-19","cited_by_count":30},{"id":"2111.11146","title":"On the Existence of Universal Lottery Tickets","created":"2021-11-22","cited_by_count":30},{"id":"1905.07785","title":"Sparse Transfer Learning via Winning Lottery Tickets","created":"2019-05-19","cited_by_count":27},{"id":"2103.00794","title":"Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets","created":"2021-03-01","cited_by_count":27},{"id":"2202.04736","title":"Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets","created":"2022-02-09","cited_by_count":27},{"id":"2203.04248","title":"Dual Lottery Ticket Hypothesis","created":"2022-03-08","cited_by_count":27},{"id":"2106.09857","title":"Effective Model Sparsification by Scheduled Grow-and-Prune Methods","created":"2021-06-18","cited_by_count":26},{"id":"2207.01382","title":"Exploring Lottery Ticket Hypothesis in Spiking Neural Networks","created":"2022-07-04","cited_by_count":26},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26},{"id":"2010.02350","title":"Winning Lottery Tickets in Deep Generative Models","created":"2020-10-05","cited_by_count":25},{"id":"2103.00397","title":"Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective","created":"2021-02-28","cited_by_count":25},{"id":"2105.01648","title":"On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning","created":"2021-05-04","cited_by_count":24},{"id":"1910.12708","title":"Evaluating Lottery Tickets Under Distributional Shifts","created":"2019-10-28","cited_by_count":23},{"id":"2005.03454","title":"Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture","created":"2020-05-04","cited_by_count":23},{"id":"2103.16547","title":"The Elastic Lottery Ticket Hypothesis","created":"2021-03-30","cited_by_count":23},{"id":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","cited_by_count":23},{"id":"2305.02190","title":"Rethinking Graph Lottery Tickets: Graph Sparsity Matters","created":"2023-05-03","cited_by_count":23},{"id":"2102.11068","title":"Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?","created":"2021-02-19","cited_by_count":22},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21},{"id":"2206.10451","title":"Winning the Lottery Ahead of Time: Efficient Early Network Pruning","created":"2022-06-21","cited_by_count":21},{"id":"2306.10460","title":"Instant Soup: Cheap Pruning Ensembles in A Single Pass Can Draw Lottery Tickets from Large Models","created":"2023-06-18","cited_by_count":20},{"id":"2308.06619","title":"Can Unstructured Pruning Reduce the Depth in Deep Neural Networks?","created":"2023-08-12","cited_by_count":20},{"id":"2206.04270","title":"A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis","created":"2022-06-09","cited_by_count":19},{"id":"2111.00162","title":"You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership","created":"2021-10-30","cited_by_count":18},{"id":"2205.02343","title":"Convolutional and Residual Networks Provably Contain Lottery Tickets","created":"2022-05-04","cited_by_count":16},{"id":"2211.03013","title":"Robust Lottery Tickets for Pre-trained Language Models","created":"2022-11-06","cited_by_count":16},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","cited_by_count":15},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14},{"id":"2207.03677","title":"SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning","created":"2022-07-08","cited_by_count":12},{"id":"2010.15969","title":"Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough","created":"2020-10-29","cited_by_count":11},{"id":"2208.10842","title":"Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost","created":"2022-08-23","cited_by_count":11},{"id":"2310.18823","title":"Successfully Applying Lottery Ticket Hypothesis to Diffusion Model","created":"2023-10-28","cited_by_count":11},{"id":"2104.12501","title":"Communication-Efficient and Personalized Federated Lottery Ticket Learning","created":"2021-04-26","cited_by_count":10},{"id":"2204.11218","title":"Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training","created":"2022-04-24","cited_by_count":10},{"id":"2301.05345","title":"GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer","created":"2023-01-13","cited_by_count":10},{"id":"2205.07320","title":"Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective","created":"2022-05-15","cited_by_count":9},{"id":"2207.07858","title":"The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network","created":"2022-07-16","cited_by_count":7},{"id":"2211.01484","title":"Data Level Lottery Ticket Hypothesis for Vision Transformers","created":"2022-11-02","cited_by_count":7},{"id":"2004.09817","title":"Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learning","created":"2020-04-21","cited_by_count":5},{"id":"2107.06825","title":"A Generalized Lottery Ticket Hypothesis","created":"2021-07-03","cited_by_count":5},{"id":"2202.01341","title":"Robust Binary Models by Pruning Randomly-initialized Networks","created":"2022-02-03","cited_by_count":5},{"id":"2206.04762","title":"Data-Efficient Double-Win Lottery Tickets from Robust Pre-training","created":"2022-06-09","cited_by_count":5},{"id":"2211.07263","title":"Efficient Adversarial Training with Robust Early-Bird Tickets","created":"2022-11-14","cited_by_count":5},{"id":"2305.01387","title":"Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing","created":"2023-05-02","cited_by_count":5},{"id":"2212.08311","title":"Can We Find Strong Lottery Tickets in Generative Models?","created":"2022-12-16","cited_by_count":4},{"id":"2109.09670","title":"Reproducibility Study: Comparing Rewinding and Fine-tuning in Neural Network Pruning","created":"2021-09-20","cited_by_count":1},{"id":"2201.12712","title":"Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning","created":"2022-01-30","cited_by_count":1}],"next_cursor":null}