{"list":"other","total":68,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2001.08210","title":"Multilingual Denoising Pre-training for Neural Machine Translation","created":"2020-01-22","cited_by_count":1035},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"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":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"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":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"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":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"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":"1904.01561","title":"Analyzing Learned Molecular Representations for Property Prediction","created":"2019-04-02","cited_by_count":375},{"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":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"1909.11764","title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding","created":"2019-09-25","cited_by_count":264},{"id":"1906.04015","title":"Cormorant: Covariant Molecular Neural Networks","created":"2019-06-06","cited_by_count":263},{"id":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"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":"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":"2106.06130","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","created":"2021-06-11","cited_by_count":204},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2202.02541","title":"TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials","created":"2022-02-05","cited_by_count":182},{"id":"2102.05013","title":"Spherical Message Passing for 3D Graph Networks","created":"2021-02-09","cited_by_count":168},{"id":"2110.04126","title":"3D Infomax improves GNNs for Molecular Property Prediction","created":"2021-10-08","cited_by_count":146},{"id":"2206.00133","title":"Pre-training via Denoising for Molecular Property Prediction","created":"2022-05-31","cited_by_count":124},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"2012.10885","title":"LieTransformer: Equivariant self-attention for Lie Groups","created":"2020-12-20","cited_by_count":100},{"id":"2002.08264","title":"Molecule Attention Transformer","created":"2020-02-19","cited_by_count":92},{"id":"2201.12787","title":"GRPE: Relative Positional Encoding for Graph Transformer","created":"2022-01-30","cited_by_count":70},{"id":"2206.08515","title":"ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs","created":"2022-06-17","cited_by_count":69},{"id":"2203.04810","title":"Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets","created":"2022-03-09","cited_by_count":64},{"id":"2107.10670","title":"Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity","created":"2021-07-21","cited_by_count":60},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55},{"id":"1712.07042","title":"Development and evaluation of a deep learning model for protein-ligand binding affinity prediction","created":"2017-12-19","cited_by_count":51},{"id":"2207.08806","title":"Unified 2D and 3D Pre-Training of Molecular Representations","created":"2022-07-14","cited_by_count":45},{"id":"2106.07971","title":"Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond","created":"2021-06-15","cited_by_count":44},{"id":"2003.02944","title":"Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network","created":"2020-02-19","cited_by_count":37},{"id":"2011.15069","title":"Graph convolutions that can finally model local structure","created":"2020-11-30","cited_by_count":31}],"next_cursor":null}