{"list":"other","total":165,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"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":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2002.02126","title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation","created":"2020-02-06","cited_by_count":1139},{"id":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1910.09457","title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","created":"2019-10-21","cited_by_count":913},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"2003.00982","title":"Benchmarking Graph Neural Networks","created":"2020-03-02","cited_by_count":680},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"1905.03222","title":"Conformalized Quantile Regression","created":"2019-05-08","cited_by_count":629},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"2006.04131","title":"Deep Graph Contrastive Representation Learning","created":"2020-06-07","cited_by_count":539},{"id":"1904.06019","title":"Conformal Prediction Under Covariate Shift","created":"2019-04-12","cited_by_count":519},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2011.02260","title":"Graph Neural Networks in Recommender Systems: A Survey","created":"2020-11-04","cited_by_count":494},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"2006.09963","title":"GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training","created":"2020-06-17","cited_by_count":463},{"id":"1904.01685","title":"Measuring Calibration in Deep Learning","created":"2019-04-02","cited_by_count":446},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"2006.02544","title":"Classification with Valid and Adaptive Coverage","created":"2020-06-03","cited_by_count":396},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"1802.03480","title":"GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders","created":"2018-02-09","cited_by_count":383},{"id":"2106.00170","title":"Adaptive Conformal Inference Under Distribution Shift","created":"2021-06-01","cited_by_count":375},{"id":"2009.14193","title":"Uncertainty Sets for Image Classifiers using Conformal Prediction","created":"2020-09-29","cited_by_count":366},{"id":"1910.12656","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration","created":"2019-10-28","cited_by_count":364},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"2202.13415","title":"Conformal prediction beyond exchangeability","created":"2022-02-27","cited_by_count":355},{"id":"1810.08750","title":"Learning Models with Uniform Performance via Distributionally Robust Optimization","created":"2018-10-20","cited_by_count":335},{"id":"2208.02814","title":"Conformal Risk Control","created":"2022-08-04","cited_by_count":299},{"id":"1505.05116","title":"Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations","created":"2015-05-19","cited_by_count":291},{"id":"2103.00111","title":"Graph Self-Supervised Learning: A Survey","created":"2021-02-27","cited_by_count":289},{"id":"2001.01328","title":"Scalable Gradients for Stochastic Differential Equations","created":"2020-01-05","cited_by_count":271},{"id":"2308.07134","title":"Language is All a Graph Needs","created":"2023-08-14","cited_by_count":220},{"id":"1905.02928","title":"Predictive inference with the jackknife+","created":"2019-05-08","cited_by_count":211},{"id":"1906.04214","title":"Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective","created":"2019-06-10","cited_by_count":196},{"id":"1604.02199","title":"Distributionally Robust Stochastic Optimization with Wasserstein Distance","created":"2016-04-08","cited_by_count":185},{"id":"1610.03425","title":"Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach","created":"2016-10-11","cited_by_count":183},{"id":"1908.08729","title":"Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning","created":"2019-08-23","cited_by_count":170},{"id":"2201.07766","title":"Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons","created":"2022-01-19","cited_by_count":170},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"1905.02850","title":"Understanding Attention and Generalization in Graph Neural Networks","created":"2019-05-08","cited_by_count":169},{"id":"2009.01454","title":"Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information","created":"2020-09-03","cited_by_count":168},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"id":"2102.13186","title":"Towards a Unified Framework for Fair and Stable Graph Representation Learning","created":"2021-02-25","cited_by_count":128},{"id":"2010.08853","title":"From Local Structures to Size Generalization in Graph Neural Networks","created":"2020-10-17","cited_by_count":124},{"id":"2012.07923","title":"Improving model calibration with accuracy versus uncertainty optimization","created":"2020-12-14","cited_by_count":123},{"id":"2006.09136","title":"When Does Self-Supervision Help Graph Convolutional Networks?","created":"2020-06-16","cited_by_count":121},{"id":"2106.08460","title":"Localized Conformal Prediction: A Generalized Inference Framework for Conformal Prediction","created":"2021-06-15","cited_by_count":114},{"id":"1803.10459","title":"Graphite: Iterative Generative Modeling of Graphs","created":"2018-03-28","cited_by_count":112},{"id":"2110.09192","title":"Learning Optimal Conformal Classifiers","created":"2021-10-18","cited_by_count":112},{"id":"1903.03088","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","created":"2019-03-07","cited_by_count":105},{"id":"2102.08501","title":"DEUP: Direct Epistemic Uncertainty Prediction","created":"2021-02-16","cited_by_count":104},{"id":"2110.14038","title":"Robustness of Graph Neural Networks at Scale","created":"2021-10-26","cited_by_count":100},{"id":"2004.13546","title":"Multivariate Confidence Calibration for Object Detection","created":"2020-04-28","cited_by_count":98},{"id":"2006.12800","title":"Calibration of Neural Networks using Splines","created":"2020-06-23","cited_by_count":97},{"id":"2202.07987","title":"Out-Of-Distribution Generalization on Graphs: A Survey","created":"2022-02-16","cited_by_count":97},{"id":"2010.12783","title":"Uncertainty Aware Semi-Supervised Learning on Graph Data","created":"2020-10-24","cited_by_count":95},{"id":"1810.05546","title":"Uncertainty in Neural Networks: Approximately Bayesian Ensembling","created":"2018-10-12","cited_by_count":94},{"id":"1902.08226","title":"Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure","created":"2019-02-20","cited_by_count":93},{"id":"2109.14285","title":"Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration","created":"2021-09-29","cited_by_count":92},{"id":"1811.11103","title":"Bayesian graph convolutional neural networks for semi-supervised classification","created":"2018-11-27","cited_by_count":89},{"id":"1908.09710","title":"Variational Graph Recurrent Neural Networks","created":"2019-08-26","cited_by_count":87},{"id":"2204.09308","title":"A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement","created":"2022-04-20","cited_by_count":87},{"id":"2402.02216","title":"Position: Graph Foundation Models are Already Here","created":"2024-02-03","cited_by_count":86},{"id":"2008.04267","title":"Robust Validation: Confident Predictions Even When Distributions Shift","created":"2020-08-10","cited_by_count":82},{"id":"2006.04064","title":"Bayesian Graph Neural Networks with Adaptive Connection Sampling","created":"2020-06-07","cited_by_count":81},{"id":"2110.14012","title":"Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification","created":"2021-10-26","cited_by_count":80},{"id":"2305.14535","title":"Uncertainty Quantification over Graph with Conformalized Graph Neural Networks","created":"2023-05-23","cited_by_count":79},{"id":"2008.10546","title":"SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates","created":"2020-08-24","cited_by_count":75},{"id":"1905.10943","title":"Distributionally Robust Optimization and Generalization in Kernel Methods","created":"2019-05-27","cited_by_count":73},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73},{"id":"1908.07078","title":"Semi-Implicit Graph Variational Auto-Encoders","created":"2019-08-19","cited_by_count":54},{"id":"2104.02228","title":"Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs","created":"2021-04-06","cited_by_count":50},{"id":"1707.02476","title":"Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks","created":"2017-07-08","cited_by_count":48}],"next_cursor":"100"}