{"list":"other","total":77,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"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":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"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":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"2006.05582","title":"Contrastive Multi-View Representation Learning on Graphs","created":"2020-06-10","cited_by_count":652},{"id":"1503.03578","title":"LINE: Large-scale Information Network Embedding","created":"2015-03-12","cited_by_count":582},{"id":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"2006.04131","title":"Deep Graph Contrastive Representation Learning","created":"2020-06-07","cited_by_count":539},{"id":"2010.14945","title":"Graph Contrastive Learning with Adaptive Augmentation","created":"2020-10-27","cited_by_count":519},{"id":"2006.09963","title":"GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training","created":"2020-06-17","cited_by_count":463},{"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":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","cited_by_count":389},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287},{"id":"1707.05005","title":"graph2vec: Learning Distributed Representations of Graphs","created":"2017-07-17","cited_by_count":230},{"id":"1704.03165","title":"struc2vec: Learning Node Representations from Structural Identity","created":"2017-04-11","cited_by_count":215},{"id":"1806.06193","title":"Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning","created":"2018-06-16","cited_by_count":174},{"id":"2110.00987","title":"Motif-based Graph Self-Supervised Learning for Molecular Property Prediction","created":"2021-10-03","cited_by_count":159},{"id":"2202.07179","title":"G-Mixup: Graph Data Augmentation for Graph Classification","created":"2022-02-15","cited_by_count":146},{"id":"1511.06343","title":"Online Batch Selection for Faster Training of Neural Networks","created":"2015-11-19","cited_by_count":122},{"id":"2006.09136","title":"When Does Self-Supervision Help Graph Convolutional Networks?","created":"2020-06-16","cited_by_count":121},{"id":"2112.10740","title":"Are Large-scale Datasets Necessary for Self-Supervised Pre-training?","created":"2021-12-20","cited_by_count":117},{"id":"2109.01116","title":"An Empirical Study of Graph Contrastive Learning","created":"2021-09-02","cited_by_count":113},{"id":"2110.15438","title":"InfoGCL: Information-Aware Graph Contrastive Learning","created":"2021-10-28","cited_by_count":105},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104},{"id":"1710.10321","title":"Learning Structural Node Embeddings Via Diffusion Wavelets","created":"2017-10-27","cited_by_count":97},{"id":"2112.02472","title":"Augmentation-Free Self-Supervised Learning on Graphs","created":"2021-12-05","cited_by_count":94},{"id":"2007.01594","title":"Adaptive Graph Encoder for Attributed Graph Embedding","created":"2020-07-03","cited_by_count":89},{"id":"1410.3314","title":"Propagation Kernels","created":"2014-10-13","cited_by_count":88},{"id":"2009.05923","title":"Contrastive Self-supervised Learning for Graph Classification","created":"2020-09-13","cited_by_count":68},{"id":"2106.04509","title":"MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph","created":"2021-06-05","cited_by_count":65},{"id":"2206.07869","title":"Let Invariant Rationale Discovery Inspire Graph Contrastive Learning","created":"2022-06-16","cited_by_count":57},{"id":"1705.05085","title":"Active Learning for Graph Embedding","created":"2017-05-15","cited_by_count":54},{"id":"2301.04819","title":"Data-centric AI: Perspectives and Challenges","created":"2023-01-12","cited_by_count":43},{"id":"2008.03639","title":"Random Walks: A Review of Algorithms and Applications","created":"2020-08-09","cited_by_count":38},{"id":"1908.07235","title":"Density estimation in representation space to predict model uncertainty","created":"2019-08-20","cited_by_count":27},{"id":"2001.02799","title":"Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data","created":"2020-01-09","cited_by_count":27},{"id":"2007.08025","title":"GraphCL: Contrastive Self-Supervised Learning of Graph Representations","created":"2020-07-15","cited_by_count":26},{"id":"2106.02866","title":"Conditional Contrastive Learning for Improving Fairness in Self-Supervised Learning","created":"2021-06-05","cited_by_count":25},{"id":"1905.13728","title":"Pre-Training Graph Neural Networks for Generic Structural Feature Extraction","created":"2019-05-31","cited_by_count":24},{"id":"2310.04987","title":"Data-centric Graph Learning: A Survey","created":"2023-10-08","cited_by_count":22},{"id":"2303.10108","title":"Data-Centric Learning from Unlabeled Graphs with Diffusion Model","created":"2023-03-17","cited_by_count":19},{"id":"2005.10473","title":"Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation","created":"2020-05-21","cited_by_count":17},{"id":"2012.02486","title":"Unsupervised Adversarially-Robust Representation Learning on Graphs","created":"2020-12-04","cited_by_count":17},{"id":"2010.01150","title":"Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media","created":"2020-10-02","cited_by_count":16},{"id":"2010.02038","title":"A Simple Framework for Uncertainty in Contrastive Learning","created":"2020-10-05","cited_by_count":16},{"id":"1610.08904","title":"Local Similarity-Aware Deep Feature Embedding","created":"2016-10-27","cited_by_count":15},{"id":"1904.00585","title":"Using Similarity Measures to Select Pretraining Data for NER","created":"2019-04-01","cited_by_count":15},{"id":"2011.10231","title":"Efficient Conditional Pre-training for Transfer Learning","created":"2020-11-20","cited_by_count":11},{"id":"2110.13567","title":"Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks","created":"2021-10-26","cited_by_count":10},{"id":"1412.6537","title":"Fracking Deep Convolutional Image Descriptors","created":"2014-12-19","cited_by_count":7},{"id":"2208.02810","title":"Analyzing Data-Centric Properties for Graph Contrastive Learning","created":"2022-08-04","cited_by_count":7},{"id":"1906.00926","title":"Human information processing in complex networks","created":"2019-06-03","cited_by_count":2}],"next_cursor":null}