{"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":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"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":"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":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1903.07293","title":"Heterogeneous Graph Attention Network","created":"2019-03-18","cited_by_count":734},{"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":"2003.01332","title":"Heterogeneous Graph Transformer","created":"2020-03-03","cited_by_count":582},{"id":"1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","created":"2017-06-26","cited_by_count":571},{"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":"2004.05718","title":"Principal Neighbourhood Aggregation for Graph Nets","created":"2020-04-12","cited_by_count":478},{"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":"1811.00855","title":"Session-based Recommendation with Graph Neural Networks","created":"2018-11-01","cited_by_count":312},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"2103.00111","title":"Graph Self-Supervised Learning: A Survey","created":"2021-02-27","cited_by_count":289},{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287},{"id":"2110.07728","title":"Pre-training Molecular Graph Representation with 3D Geometry","created":"2021-10-07","cited_by_count":248},{"id":"2002.01169","title":"Graph Representation Learning via Graphical Mutual Information Maximization","created":"2020-02-04","cited_by_count":217},{"id":"2106.06130","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","created":"2021-06-11","cited_by_count":204},{"id":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"2202.03104","title":"SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation","created":"2022-02-07","cited_by_count":171},{"id":"2110.00987","title":"Motif-based Graph Self-Supervised Learning for Molecular Property Prediction","created":"2021-10-03","cited_by_count":159},{"id":"2106.12484","title":"From Canonical Correlation Analysis to Self-supervised Graph Neural Networks","created":"2021-06-23","cited_by_count":141},{"id":"2105.09111","title":"Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning","created":"2021-05-19","cited_by_count":130},{"id":"2106.04113","title":"Self-supervised Graph-level Representation Learning with Local and Global Structure","created":"2021-06-08","cited_by_count":125},{"id":"2109.01116","title":"An Empirical Study of Graph Contrastive Learning","created":"2021-09-02","cited_by_count":113},{"id":"2101.06448","title":"Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation","created":"2021-01-16","cited_by_count":101},{"id":"1508.00200","title":"PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks","created":"2015-08-02","cited_by_count":96},{"id":"1806.09206","title":"N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules","created":"2018-06-24","cited_by_count":93},{"id":"2010.11418","title":"Rethinking pooling in graph neural networks","created":"2020-10-22","cited_by_count":73},{"id":"2105.05682","title":"Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning","created":"2021-05-12","cited_by_count":70},{"id":"1908.05620","title":"Visualizing and Understanding the Effectiveness of BERT","created":"2019-08-15","cited_by_count":67},{"id":"1908.07078","title":"Semi-Implicit Graph Variational Auto-Encoders","created":"2019-08-19","cited_by_count":54},{"id":"2112.00544","title":"Molecular Contrastive Learning with Chemical Element Knowledge Graph","created":"2021-12-01","cited_by_count":50},{"id":"2012.07064","title":"Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation","created":"2020-12-13","cited_by_count":42},{"id":"2107.08765","title":"Adaptive Transfer Learning on Graph Neural Networks","created":"2021-07-19","cited_by_count":31},{"id":"2007.00216","title":"An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph","created":"2020-07-01","cited_by_count":29},{"id":"2201.01702","title":"Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations","created":"2022-01-04","cited_by_count":28},{"id":"2106.10234","title":"Dual-view Molecule Pre-training","created":"2021-06-17","cited_by_count":27},{"id":"2002.12620","title":"TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing","created":"2020-02-28","cited_by_count":26},{"id":"1905.13728","title":"Pre-Training Graph Neural Networks for Generic Structural Feature Extraction","created":"2019-05-31","cited_by_count":24},{"id":"1606.08928","title":"subgraph2vec: Learning Distributed Representations of Rooted Sub-graphs from Large Graphs","created":"2016-06-29","cited_by_count":19},{"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":"2106.06722","title":"Curriculum Pre-Training Heterogeneous Subgraph Transformer for Top-$N$ Recommendation","created":"2021-06-12","cited_by_count":8}],"next_cursor":null}