{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"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":"1808.09781","title":"Self-Attentive Sequential Recommendation","created":"2018-08-20","cited_by_count":1184},{"id":"1708.05031","title":"Neural Collaborative Filtering","created":"2017-08-16","cited_by_count":1111},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1811.05868","title":"Pitfalls of Graph Neural Network Evaluation","created":"2018-11-14","cited_by_count":1007},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"1904.06690","title":"BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer","created":"2019-04-14","cited_by_count":964},{"id":"1610.02415","title":"Automatic chemical design using a data-driven continuous representation of molecules","created":"2016-10-07","cited_by_count":765},{"id":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"2003.00982","title":"Benchmarking Graph Neural Networks","created":"2020-03-02","cited_by_count":680},{"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":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"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":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"2006.09963","title":"GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training","created":"2020-06-17","cited_by_count":463},{"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":"1707.03815","title":"Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking","created":"2017-07-12","cited_by_count":335},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320},{"id":"1909.12223","title":"PairNorm: Tackling Oversmoothing in GNNs","created":"2019-09-26","cited_by_count":297},{"id":"2007.02901","title":"Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks","created":"2020-07-06","cited_by_count":260},{"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":"2007.11498","title":"CrossTransformers: spatially-aware few-shot transfer","created":"2020-07-22","cited_by_count":174},{"id":"2002.08264","title":"Molecule Attention Transformer","created":"2020-02-19","cited_by_count":92},{"id":"2108.06625","title":"Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer","created":"2021-08-14","cited_by_count":69},{"id":"2110.13094","title":"Gophormer: Ego-Graph Transformer for Node Classification","created":"2021-10-25","cited_by_count":63},{"id":"2006.07107","title":"Understanding and Resolving Performance Degradation in Graph Convolutional Networks","created":"2020-06-12","cited_by_count":53},{"id":"2105.08908","title":"Where are we in embedding spaces? A Comprehensive Analysis on Network Embedding Approaches for Recommender Systems","created":"2021-05-19","cited_by_count":24},{"id":"1910.12241","title":"Pre-train and Learn: Preserve Global Information for Graph Neural Networks","created":"2019-10-27","cited_by_count":8},{"id":"2006.03814","title":"The Impact of Global Structural Information in Graph Neural Networks Applications","created":"2020-06-06","cited_by_count":4}],"next_cursor":null}