{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2102.09844","title":"E(n) Equivariant Graph Neural Networks","created":"2021-02-19","cited_by_count":965},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"2002.09405","title":"Learning to Simulate Complex Physics with Graph Networks","created":"2020-02-21","cited_by_count":880},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"id":"2101.03164","title":"E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials","created":"2021-01-08","cited_by_count":708},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2006.10503","title":"SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks","created":"2020-06-18","cited_by_count":607},{"id":"1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","created":"2017-06-26","cited_by_count":571},{"id":"2003.03123","title":"Directional Message Passing for Molecular Graphs","created":"2020-03-06","cited_by_count":561},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"2102.03150","title":"Equivariant message passing for the prediction of tensorial properties and molecular spectra","created":"2021-02-05","cited_by_count":441},{"id":"1807.02547","title":"3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data","created":"2018-07-06","cited_by_count":354},{"id":"2106.08903","title":"GemNet: Universal Directional Graph Neural Networks for Molecules","created":"2021-06-02","cited_by_count":343},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320},{"id":"2009.01411","title":"Learning from Protein Structure with Geometric Vector Perceptrons","created":"2020-09-03","cited_by_count":313},{"id":"1612.04642","title":"Harmonic Networks: Deep Translation and Rotation Equivariance","created":"2016-12-14","cited_by_count":295},{"id":"1906.04015","title":"Cormorant: Covariant Molecular Neural Networks","created":"2019-06-06","cited_by_count":263},{"id":"2204.05249","title":"Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics","created":"2022-04-11","cited_by_count":256},{"id":"2011.14115","title":"Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules","created":"2020-11-28","cited_by_count":255},{"id":"2002.12880","title":"Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data","created":"2020-02-25","cited_by_count":248},{"id":"2010.09990","title":"The Open Catalyst 2020 (OC20) Dataset and Community Challenges","created":"2020-10-20","cited_by_count":246},{"id":"2110.02905","title":"Geometric and Physical Quantities Improve E(3) Equivariant Message Passing","created":"2021-10-06","cited_by_count":228},{"id":"1707.09571","title":"Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics","created":"2017-07-30","cited_by_count":214},{"id":"2202.02541","title":"TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials","created":"2022-02-05","cited_by_count":182},{"id":"1806.09231","title":"Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network","created":"2018-06-24","cited_by_count":171},{"id":"2102.05013","title":"Spherical Message Passing for 3D Graph Networks","created":"2021-02-09","cited_by_count":168},{"id":"1803.07294","title":"GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs","created":"2018-03-20","cited_by_count":165},{"id":"1807.07814","title":"Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis","created":"2018-07-20","cited_by_count":110},{"id":"2204.04879","title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","created":"2022-04-11","cited_by_count":102},{"id":"1904.05811","title":"Relational Graph Attention Networks","created":"2019-04-11","cited_by_count":82},{"id":"2012.04035","title":"ATOM3D: Tasks On Molecules in Three Dimensions","created":"2020-12-07","cited_by_count":74},{"id":"2106.02347","title":"SE(3)-equivariant prediction of molecular wavefunctions and electronic densities","created":"2021-06-04","cited_by_count":67},{"id":"2007.08026","title":"OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features","created":"2020-07-15","cited_by_count":64},{"id":"2203.04810","title":"Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets","created":"2022-03-09","cited_by_count":64},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53},{"id":"2106.09575","title":"Rotation Invariant Graph Neural Networks using Spin Convolutions","created":"2021-06-17","cited_by_count":52},{"id":"2008.08461","title":"Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties","created":"2020-08-19","cited_by_count":51},{"id":"2106.07971","title":"Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond","created":"2021-06-15","cited_by_count":44},{"id":"2007.02005","title":"Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks","created":"2020-07-04","cited_by_count":30},{"id":"2203.09697","title":"Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations","created":"2022-03-18","cited_by_count":25},{"id":"2202.09891","title":"Equivariant Graph Attention Networks for Molecular Property Prediction","created":"2022-02-20","cited_by_count":20},{"id":"1907.04652","title":"Graph Representation Learning via Hard and Channel-Wise Attention Networks","created":"2019-07-05","cited_by_count":18},{"id":"2004.11658","title":"86 PFLOPS Deep Potential Molecular Dynamics simulation of 100 million atoms with ab initio accuracy","created":"2020-04-24","cited_by_count":15},{"id":"2006.14163","title":"Geometric Prediction: Moving Beyond Scalars","created":"2020-06-25","cited_by_count":10},{"id":"2109.00642","title":"Searching for Efficient Multi-Stage Vision Transformers","created":"2021-09-01","cited_by_count":9}],"next_cursor":null}