{"list":"other","total":62,"rows":[{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2102.09844","title":"E(n) Equivariant Graph Neural Networks","created":"2021-02-19","cited_by_count":965},{"id":"2002.09405","title":"Learning to Simulate Complex Physics with Graph Networks","created":"2020-02-21","cited_by_count":880},{"id":"2010.03409","title":"Learning Mesh-Based Simulation with Graph Networks","created":"2020-10-07","cited_by_count":868},{"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":"2203.17003","title":"Equivariant Diffusion for Molecule Generation in 3D","created":"2022-03-31","cited_by_count":677},{"id":"1704.04760","title":"In-Datacenter Performance Analysis of a Tensor Processing Unit","created":"2017-04-16","cited_by_count":618},{"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":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2003.03123","title":"Directional Message Passing for Molecular Graphs","created":"2020-03-06","cited_by_count":561},{"id":"1909.03211","title":"Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View","created":"2019-09-07","cited_by_count":545},{"id":"2203.02923","title":"GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation","created":"2022-03-06","cited_by_count":516},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"1908.01000","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","created":"2019-07-31","cited_by_count":441},{"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":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"1909.12223","title":"PairNorm: Tackling Oversmoothing in GNNs","created":"2019-09-26","cited_by_count":297},{"id":"2103.00111","title":"Graph Self-Supervised Learning: A Survey","created":"2021-02-27","cited_by_count":289},{"id":"1906.04015","title":"Cormorant: Covariant Molecular Neural Networks","created":"2019-06-06","cited_by_count":263},{"id":"2011.14115","title":"Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules","created":"2020-11-28","cited_by_count":255},{"id":"2006.13318","title":"A Note on Over-Smoothing for Graph Neural Networks","created":"2020-06-23","cited_by_count":249},{"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":"2110.07728","title":"Pre-training Molecular Graph Representation with 3D Geometry","created":"2021-10-07","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":"1806.01242","title":"Graph networks as learnable physics engines for inference and control","created":"2018-06-04","cited_by_count":244},{"id":"2110.02905","title":"Geometric and Physical Quantities Improve E(3) Equivariant Message Passing","created":"2021-10-06","cited_by_count":228},{"id":"1511.01432","title":"Semi-supervised Sequence Learning","created":"2015-11-04","cited_by_count":198},{"id":"2002.03155","title":"Random Features Strengthen Graph Neural Networks","created":"2020-02-08","cited_by_count":186},{"id":"2102.10757","title":"Self-Supervised Learning of Graph Neural Networks: A Unified Review","created":"2021-02-22","cited_by_count":184},{"id":"2202.02541","title":"TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials","created":"2022-02-05","cited_by_count":182},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"id":"2102.05013","title":"Spherical Message Passing for 3D Graph Networks","created":"2021-02-09","cited_by_count":168},{"id":"2105.03902","title":"Learning Gradient Fields for Molecular Conformation Generation","created":"2021-05-09","cited_by_count":163},{"id":"1702.08591","title":"The Shattered Gradients Problem: If resnets are the answer, then what is the question?","created":"2017-02-28","cited_by_count":157},{"id":"2012.10885","title":"LieTransformer: Equivariant self-attention for Lie Groups","created":"2020-12-20","cited_by_count":100},{"id":"1806.09206","title":"N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules","created":"2018-06-24","cited_by_count":93},{"id":"2003.13663","title":"Revisiting Over-smoothing in Deep GCNs","created":"2020-03-30","cited_by_count":55},{"id":"1801.02144","title":"Covariant Compositional Networks For Learning Graphs","created":"2018-01-07","cited_by_count":54},{"id":"2106.09575","title":"Rotation Invariant Graph Neural Networks using Spin Convolutions","created":"2021-06-17","cited_by_count":52},{"id":"2110.01765","title":"Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping","created":"2021-10-05","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":"2203.08120","title":"Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers","created":"2022-03-15","cited_by_count":28},{"id":"2203.09697","title":"Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations","created":"2022-03-18","cited_by_count":25},{"id":"2008.12578","title":"Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization","created":"2020-08-28","cited_by_count":15},{"id":"2112.02958","title":"Automap: Towards Ergonomic Automated Parallelism for ML Models","created":"2021-12-06","cited_by_count":12}],"next_cursor":null}