{"list":"other","total":61,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"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":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"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":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1912.05671","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","created":"2019-12-11","cited_by_count":637},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"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":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1703.10146","title":"Community Detection and Stochastic Block Models","created":"2017-03-29","cited_by_count":319},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2002.00585","title":"Proving the Lottery Ticket Hypothesis: Pruning is All You Need","created":"2020-02-03","cited_by_count":201},{"id":"1905.13192","title":"Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels","created":"2019-05-30","cited_by_count":161},{"id":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"2006.03548","title":"Graphon Neural Networks and the Transferability of Graph Neural Networks","created":"2020-06-05","cited_by_count":118},{"id":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"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":"2106.10404","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","created":"2021-06-19","cited_by_count":84},{"id":"2006.07990","title":"Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient","created":"2020-06-14","cited_by_count":81},{"id":"2010.03533","title":"Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win","created":"2020-10-07","cited_by_count":77},{"id":"2006.09081","title":"Progressive Skeletonization: Trimming more fat from a network at initialization","created":"2020-06-16","cited_by_count":64},{"id":"2105.03703","title":"Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics","created":"2021-05-08","cited_by_count":57},{"id":"2109.10096","title":"Transferability of Graph Neural Networks: an Extended Graphon Approach","created":"2021-09-21","cited_by_count":53},{"id":"1901.08572","title":"Width Provably Matters in Optimization for Deep Linear Neural Networks","created":"2019-01-24","cited_by_count":52},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41},{"id":"1311.1731","title":"Stochastic blockmodel approximation of a graphon: Theory and consistent estimation","created":"2013-11-07","cited_by_count":39},{"id":"1402.1888","title":"A Consistent Histogram Estimator for Exchangeable Graph Models","created":"2014-02-08","cited_by_count":37},{"id":"2012.05644","title":"Learning Graphons via Structured Gromov-Wasserstein Barycenters","created":"2020-12-10","cited_by_count":37},{"id":"2009.11839","title":"A Gradient Flow Framework For Analyzing Network Pruning","created":"2020-09-24","cited_by_count":36},{"id":"2202.08132","title":"Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients","created":"2022-02-16","cited_by_count":34},{"id":"2304.02840","title":"NTK-SAP: Improving neural network pruning by aligning training dynamics","created":"2023-04-06","cited_by_count":30},{"id":"2006.08228","title":"Finding trainable sparse networks through Neural Tangent Transfer","created":"2020-06-15","cited_by_count":28},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21},{"id":"2211.03329","title":"Implicit Graphon Neural Representation","created":"2022-11-07","cited_by_count":19},{"id":"2010.11354","title":"PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data","created":"2020-10-22","cited_by_count":17},{"id":"2205.02343","title":"Convolutional and Residual Networks Provably Contain Lottery Tickets","created":"2022-05-04","cited_by_count":16},{"id":"2301.10808","title":"Graph Neural Tangent Kernel: Convergence on Large Graphs","created":"2023-01-25","cited_by_count":16},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","cited_by_count":15},{"id":"2101.10552","title":"A Unified Paths Perspective for Pruning at Initialization","created":"2021-01-26","cited_by_count":14},{"id":"2408.09966","title":"Mask in the Mirror: Implicit Sparsification","created":"2024-08-19","cited_by_count":14},{"id":"2203.14328","title":"On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks","created":"2022-03-27","cited_by_count":9},{"id":"2110.02722","title":"Graphon based Clustering and Testing of Networks: Algorithms and Theory","created":"2021-10-06","cited_by_count":7},{"id":"2503.14338","title":"Higher-Order Graphon Neural Networks: Approximation and Cut Distance","created":"2025-03-18","cited_by_count":7},{"id":"2504.12801","title":"Sign-In to the Lottery: Reparameterizing Sparse Training From Scratch","created":"2025-04-17","cited_by_count":6},{"id":"2402.01261","title":"TEDDY: Trimming Edges with Degree-based Discrimination strategY","created":"2024-02-02","cited_by_count":4},{"id":"1809.00420","title":"Network estimation via graphon with node features","created":"2018-09-03","cited_by_count":3},{"id":"2307.13206","title":"Transferability of Graph Neural Networks using Graphon and Sampling Theories","created":"2023-07-25","cited_by_count":3},{"id":"2006.13486","title":"Ramanujan Bipartite Graph Products for Efficient Block Sparse Neural Networks","created":"2020-06-24","cited_by_count":2},{"id":"2406.02773","title":"Cyclic Sparse Training: Is it Enough?","created":"2024-06-04","cited_by_count":1}],"next_cursor":null}