{"list":"other","total":97,"rows":[{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"1608.04471","title":"Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm","created":"2016-08-16","cited_by_count":507},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1709.05584","title":"Representation Learning on Graphs: Methods and Applications","created":"2017-09-17","cited_by_count":457},{"id":"1910.12933","title":"Hyperbolic Graph Convolutional Neural Networks","created":"2019-10-28","cited_by_count":402},{"id":"2003.10580","title":"Meta Pseudo Labels","created":"2020-03-23","cited_by_count":374},{"id":"1902.07208","title":"Transfusion: Understanding Transfer Learning for Medical Imaging","created":"2019-02-14","cited_by_count":368},{"id":"2007.00224","title":"Debiased Contrastive Learning","created":"2020-07-01","cited_by_count":356},{"id":"1511.02136","title":"Diffusion-Convolutional Neural Networks","created":"2015-11-06","cited_by_count":268},{"id":"1812.03372","title":"What is the Effect of Importance Weighting in Deep Learning?","created":"2018-12-08","cited_by_count":251},{"id":"1910.12892","title":"Hyperbolic Graph Neural Networks","created":"2019-10-28","cited_by_count":244},{"id":"1602.03253","title":"A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluation","created":"2016-02-10","cited_by_count":236},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"2006.07529","title":"Rethinking the Value of Labels for Improving Class-Imbalanced Learning","created":"2020-06-13","cited_by_count":216},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"1705.07664","title":"CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters","created":"2017-05-22","cited_by_count":203},{"id":"1611.01232","title":"Deep Information Propagation","created":"2016-11-04","cited_by_count":195},{"id":"1702.08892","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","created":"2017-02-28","cited_by_count":182},{"id":"1708.04202","title":"Learning to Plan Chemical Syntheses","created":"2017-08-14","cited_by_count":179},{"id":"2010.12309","title":"A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios","created":"2020-10-23","cited_by_count":171},{"id":"1612.03365","title":"Multiple Instance Learning: A Survey of Problem Characteristics and Applications","created":"2016-12-11","cited_by_count":164},{"id":"1903.10132","title":"f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning","created":"2019-03-25","cited_by_count":164},{"id":"1806.02375","title":"Understanding Batch Normalization","created":"2018-06-01","cited_by_count":159},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158},{"id":"1801.03226","title":"Adaptive Graph Convolutional Neural Networks","created":"2018-01-10","cited_by_count":155},{"id":"1805.07722","title":"Task-Agnostic Meta-Learning for Few-shot Learning","created":"2018-05-20","cited_by_count":151},{"id":"1602.02964","title":"A Kernel Test of Goodness of Fit","created":"2016-02-09","cited_by_count":143},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139},{"id":"2105.07342","title":"Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive","created":"2021-05-16","cited_by_count":136},{"id":"2010.09535","title":"Cold-start Active Learning through Self-supervised Language Modeling","created":"2020-10-19","cited_by_count":128},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126},{"id":"2011.04406","title":"A Survey of Label-noise Representation Learning: Past, Present and Future","created":"2020-11-09","cited_by_count":122},{"id":"2006.07169","title":"Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning","created":"2020-06-12","cited_by_count":116},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110},{"id":"2102.07367","title":"A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum","created":"2021-02-15","cited_by_count":106},{"id":"1910.13616","title":"Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation","created":"2019-10-30","cited_by_count":103},{"id":"2106.04319","title":"Breaking the Limits of Message Passing Graph Neural Networks","created":"2021-06-08","cited_by_count":101},{"id":"2011.11197","title":"The Emerging Trends of Multi-Label Learning","created":"2020-11-23","cited_by_count":100},{"id":"1506.03039","title":"Measuring Sample Quality with Stein's Method","created":"2015-06-09","cited_by_count":94},{"id":"1606.05233","title":"Learning feed-forward one-shot learners","created":"2016-06-16","cited_by_count":93},{"id":"2008.06043","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","created":"2020-08-13","cited_by_count":93},{"id":"1806.00194","title":"Deep Imbalanced Learning for Face Recognition and Attribute Prediction","created":"2018-06-01","cited_by_count":91},{"id":"2006.08684","title":"Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning","created":"2020-06-15","cited_by_count":86},{"id":"1507.00473","title":"The Optimal Sample Complexity of PAC Learning","created":"2015-07-02","cited_by_count":72},{"id":"2110.02027","title":"ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning","created":"2021-10-05","cited_by_count":72},{"id":"1307.5101","title":"Large-scale Multi-label Learning with Missing Labels","created":"2013-07-18","cited_by_count":58},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57},{"id":"1903.01344","title":"Hybrid Actor-Critic Reinforcement Learning in Parameterized Action Space","created":"2019-03-04","cited_by_count":54},{"id":"2003.00335","title":"Differentiating through the Fr\\'echet Mean","created":"2020-02-29","cited_by_count":53},{"id":"1903.02271","title":"High-Fidelity Image Generation With Fewer Labels","created":"2019-03-06","cited_by_count":52},{"id":"1806.07201","title":"Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation","created":"2018-06-11","cited_by_count":49},{"id":"1902.03045","title":"Partial Label Learning with Self-Guided Retraining","created":"2019-02-08","cited_by_count":47},{"id":"2111.03947","title":"Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning","created":"2021-11-06","cited_by_count":43},{"id":"1912.09033","title":"TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning","created":"2019-12-19","cited_by_count":39},{"id":"2102.07091","title":"Decentralized Riemannian Gradient Descent on the Stiefel Manifold","created":"2021-02-14","cited_by_count":33},{"id":"1904.11622","title":"Scene Graph Prediction with Limited Labels","created":"2019-04-25","cited_by_count":32},{"id":"1711.11216","title":"Riemannian Stein Variational Gradient Descent for Bayesian Inference","created":"2017-11-30","cited_by_count":24},{"id":"1910.01286","title":"Learning Temporal Action Proposals With Fewer Labels","created":"2019-10-03","cited_by_count":17},{"id":"1405.5505","title":"Kernel Mean Shrinkage Estimators","created":"2014-05-21","cited_by_count":16},{"id":"1905.04042","title":"Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph","created":"2019-05-10","cited_by_count":15},{"id":"2111.13822","title":"On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources","created":"2021-11-27","cited_by_count":15},{"id":"2202.11360","title":"Deep Graph Learning for Anomalous Citation Detection","created":"2022-02-23","cited_by_count":14},{"id":"2011.09645","title":"Finding the Homology of Decision Boundaries with Active Learning","created":"2020-11-19","cited_by_count":12},{"id":"2203.09308","title":"Few-Shot Learning on Graphs","created":"2022-03-17","cited_by_count":11},{"id":"2002.07348","title":"Adaptive Region-Based Active Learning","created":"2020-02-18","cited_by_count":10},{"id":"2206.15204","title":"Data-Efficient Learning via Minimizing Hyperspherical Energy","created":"2022-06-30","cited_by_count":4}],"next_cursor":null}