{"list":"other","total":53,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1909.03211","title":"Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View","created":"2019-09-07","cited_by_count":545},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"1802.08773","title":"GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models","created":"2018-02-24","cited_by_count":413},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1805.07984","title":"Adversarial Attacks on Neural Networks for Graph Data","created":"2018-05-21","cited_by_count":397},{"id":"2005.10203","title":"Graph Structure Learning for Robust Graph Neural Networks","created":"2020-05-20","cited_by_count":371},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"1806.02371","title":"Adversarial Attack on Graph Structured Data","created":"2018-06-06","cited_by_count":301},{"id":"1905.11485","title":"Representation Learning for Dynamic Graphs: A Survey","created":"2019-05-27","cited_by_count":265},{"id":"1909.01315","title":"Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks","created":"2019-09-03","cited_by_count":242},{"id":"1910.00760","title":"Efficient Graph Generation with Graph Recurrent Attention Networks","created":"2019-10-02","cited_by_count":234},{"id":"1903.11960","title":"Learning Discrete Structures for Graph Neural Networks","created":"2019-03-28","cited_by_count":231},{"id":"2006.06830","title":"Data Augmentation for Graph Neural Networks","created":"2020-06-11","cited_by_count":203},{"id":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"1803.07294","title":"GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs","created":"2018-03-20","cited_by_count":165},{"id":"2005.03675","title":"Machine Learning on Graphs: A Model and Comprehensive Taxonomy","created":"2020-05-07","cited_by_count":156},{"id":"1801.03226","title":"Adaptive Graph Convolutional Neural Networks","created":"2018-01-10","cited_by_count":155},{"id":"2006.09136","title":"When Does Self-Supervision Help Graph Convolutional Networks?","created":"2020-06-16","cited_by_count":121},{"id":"2003.04078","title":"A Survey on The Expressive Power of Graph Neural Networks","created":"2020-03-09","cited_by_count":111},{"id":"1805.06334","title":"Auxiliary Tasks in Multi-task Learning","created":"2018-05-16","cited_by_count":108},{"id":"2006.10141","title":"Self-supervised Learning on Graphs: Deep Insights and New Direction","created":"2020-06-17","cited_by_count":108},{"id":"1905.13177","title":"Graph Normalizing Flows","created":"2019-05-30","cited_by_count":104},{"id":"2002.04999","title":"Differentiable Graph Module (DGM) for Graph Convolutional Networks","created":"2020-02-11","cited_by_count":86},{"id":"1905.01102","title":"Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning","created":"2019-05-03","cited_by_count":69},{"id":"1911.07123","title":"Graph-Revised Convolutional Network","created":"2019-11-17","cited_by_count":59},{"id":"1902.07987","title":"Learning representations of irregular particle-detector geometry with distance-weighted graph networks","created":"2019-02-21","cited_by_count":43},{"id":"2007.12002","title":"Grale: Designing Networks for Graph Learning","created":"2020-07-23","cited_by_count":28},{"id":"1902.00756","title":"Graph Neural Networks with Generated Parameters for Relation Extraction","created":"2019-02-02","cited_by_count":27},{"id":"2006.02380","title":"Self-supervised Training of Graph Convolutional Networks","created":"2020-06-03","cited_by_count":24},{"id":"1612.02251","title":"When is multitask learning effective? Semantic sequence prediction under varying data conditions","created":"2016-12-07","cited_by_count":21},{"id":"1912.07832","title":"Deep Iterative and Adaptive Learning for Graph Neural Networks","created":"2019-12-17","cited_by_count":18},{"id":"1912.10206","title":"How Robust Are Graph Neural Networks to Structural Noise?","created":"2019-12-21","cited_by_count":15},{"id":"1909.12385","title":"A Quest for Structure: Jointly Learning the Graph Structure and Semi-Supervised Classification","created":"2019-09-26","cited_by_count":13},{"id":"2007.04929","title":"Learning Graph Structure With A Finite-State Automaton Layer","created":"2020-07-09","cited_by_count":10}],"next_cursor":null}