{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1806.01973","title":"Graph Convolutional Neural Networks for Web-Scale Recommender Systems","created":"2018-06-06","cited_by_count":1138},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2006.05205","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":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"id":"1801.10247","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","created":"2018-01-30","cited_by_count":584},{"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":"1905.07953","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","created":"2019-05-20","cited_by_count":541},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"1911.05485","title":"Diffusion Improves Graph Learning","created":"2019-10-28","cited_by_count":414},{"id":"2005.11079","title":"Graph Random Neural Network for Semi-Supervised Learning on Graphs","created":"2020-05-22","cited_by_count":213},{"id":"2006.06830","title":"Data Augmentation for Graph Neural Networks","created":"2020-06-11","cited_by_count":203},{"id":"2201.08821","title":"Representing Long-Range Context for Graph Neural Networks with Global Attention","created":"2022-01-21","cited_by_count":195},{"id":"2202.03036","title":"Structure-Aware Transformer for Graph Representation Learning","created":"2022-02-07","cited_by_count":194},{"id":"1911.07323","title":"Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks","created":"2019-11-17","cited_by_count":177},{"id":"2007.01570","title":"Scaling Graph Neural Networks with Approximate PageRank","created":"2020-07-03","cited_by_count":174},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"2011.09643","title":"Node Similarity Preserving Graph Convolutional Networks","created":"2020-11-19","cited_by_count":112},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107},{"id":"2010.15421","title":"Scalable Graph Neural Networks via Bidirectional Propagation","created":"2020-10-29","cited_by_count":87},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72},{"id":"2008.09864","title":"Tackling Over-Smoothing for General Graph Convolutional Networks","created":"2020-08-22","cited_by_count":66},{"id":"2110.13094","title":"Gophormer: Ego-Graph Transformer for Node Classification","created":"2021-10-25","cited_by_count":63},{"id":"2010.09891","title":"Robust Optimization as Data Augmentation for Large-scale Graphs","created":"2020-10-19","cited_by_count":58},{"id":"2003.13663","title":"Revisiting Over-smoothing in Deep GCNs","created":"2020-03-30","cited_by_count":55},{"id":"2109.03856","title":"Local Augmentation for Graph Neural Networks","created":"2021-09-08","cited_by_count":53},{"id":"2010.12408","title":"On the Equivalence of Decoupled Graph Convolution Network and Label Propagation","created":"2020-10-23","cited_by_count":49},{"id":"2208.08302","title":"Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing","created":"2022-08-17","cited_by_count":31},{"id":"2203.14082","title":"Metropolis-Hastings Data Augmentation for Graph Neural Networks","created":"2022-03-26","cited_by_count":30},{"id":"2203.06389","title":"GRAND+: Scalable Graph Random Neural Networks","created":"2022-03-12","cited_by_count":25}],"next_cursor":null}