{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"2007.08663","title":"TUDataset: A collection of benchmark datasets for learning with graphs","created":"2020-07-16","cited_by_count":728},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2006.08218","title":"Self-supervised Learning: Generative or Contrastive","created":"2020-06-15","cited_by_count":694},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2006.05582","title":"Contrastive Multi-View Representation Learning on Graphs","created":"2020-06-10","cited_by_count":652},{"id":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"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":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"1804.03329","title":"Representation Tradeoffs for Hyperbolic Embeddings","created":"2018-04-10","cited_by_count":206},{"id":"2106.05819","title":"Adversarial Graph Augmentation to Improve Graph Contrastive Learning","created":"2021-06-10","cited_by_count":200},{"id":"2010.01179","title":"The Surprising Power of Graph Neural Networks with Random Node Initialization","created":"2020-10-02","cited_by_count":198},{"id":"2102.06514","title":"Large-Scale Representation Learning on Graphs via Bootstrapping","created":"2021-02-12","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":"2106.12484","title":"From Canonical Correlation Analysis to Self-supervised Graph Neural Networks","created":"2021-06-23","cited_by_count":141},{"id":"2006.10141","title":"Self-supervised Learning on Graphs: Deep Insights and New Direction","created":"2020-06-17","cited_by_count":108},{"id":"2112.02472","title":"Augmentation-Free Self-Supervised Learning on Graphs","created":"2021-12-05","cited_by_count":94},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2301.08210","title":"Everything is Connected: Graph Neural Networks","created":"2023-01-19","cited_by_count":85},{"id":"2106.03216","title":"On Memorization in Probabilistic Deep Generative Models","created":"2021-06-06","cited_by_count":60},{"id":"2307.12698","title":"MC-JEPA: A Joint-Embedding Predictive Architecture for Self-Supervised Learning of Motion and Content Features","created":"2023-07-24","cited_by_count":57},{"id":"2106.05470","title":"Automated Self-Supervised Learning for Graphs","created":"2021-06-10","cited_by_count":50},{"id":"2111.15037","title":"CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data","created":"2021-11-30","cited_by_count":28},{"id":"2204.07172","title":"Diagnosing and Fixing Manifold Overfitting in Deep Generative Models","created":"2022-04-14","cited_by_count":28},{"id":"1802.03145","title":"Relational Autoencoder for Feature Extraction","created":"2018-02-09","cited_by_count":23},{"id":"2202.08333","title":"Self-Supervised Representation Learning via Latent Graph Prediction","created":"2022-02-16","cited_by_count":22},{"id":"2302.04817","title":"The Edge of Orthogonality: A Simple View of What Makes BYOL Tick","created":"2023-02-09","cited_by_count":15},{"id":"2306.14064","title":"Modeling Graphs Beyond Hyperbolic: Graph Neural Networks in Symmetric Positive Definite Matrices","created":"2023-06-24","cited_by_count":10}],"next_cursor":null}