{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1806.03536","title":"Representation Learning on Graphs with Jumping Knowledge Networks","created":"2018-06-09","cited_by_count":877},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1509.09292","title":"Convolutional Networks on Graphs for Learning Molecular Fingerprints","created":"2015-09-30","cited_by_count":754},{"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":"1802.04364","title":"Junction Tree Variational Autoencoder for Molecular Graph Generation","created":"2018-02-12","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":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"2006.09252","title":"Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting","created":"2020-06-16","cited_by_count":313},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"1909.12223","title":"PairNorm: Tackling Oversmoothing in GNNs","created":"2019-09-26","cited_by_count":297},{"id":"2007.09296","title":"Towards Deeper Graph Neural Networks","created":"2020-07-18","cited_by_count":296},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"1905.09550","title":"Revisiting Graph Neural Networks: All We Have is Low-Pass Filters","created":"2019-05-23","cited_by_count":261},{"id":"1602.04485","title":"Benefits of depth in neural networks","created":"2016-02-14","cited_by_count":250},{"id":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"id":"2002.04025","title":"Can Graph Neural Networks Count Substructures?","created":"2020-02-10","cited_by_count":236},{"id":"2106.12575","title":"Weisfeiler and Lehman Go Cellular: CW Networks","created":"2021-06-23","cited_by_count":218},{"id":"1904.11491","title":"Local Relation Networks for Image Recognition","created":"2019-04-25","cited_by_count":210},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"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":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2203.00555","title":"DeepNet: Scaling Transformers to 1,000 Layers","created":"2022-03-01","cited_by_count":178},{"id":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"1806.05393","title":"Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks","created":"2018-06-14","cited_by_count":176},{"id":"2201.12987","title":"Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism","created":"2022-01-31","cited_by_count":171},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169},{"id":"2110.03753","title":"From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness","created":"2021-10-07","cited_by_count":155},{"id":"1903.02541","title":"Relational Pooling for Graph Representations","created":"2019-03-06","cited_by_count":150},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147},{"id":"2110.13197","title":"Nested Graph Neural Networks","created":"2021-10-25","cited_by_count":137},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"2002.08264","title":"Molecule Attention Transformer","created":"2020-02-19","cited_by_count":92},{"id":"2202.08625","title":"Revisiting Over-smoothing in BERT from the Perspective of Graph","created":"2022-02-17","cited_by_count":72},{"id":"2201.12787","title":"GRPE: Relative Positional Encoding for Graph Transformer","created":"2022-01-30","cited_by_count":70},{"id":"1908.11365","title":"Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention","created":"2019-08-29","cited_by_count":59},{"id":"2107.07999","title":"From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers","created":"2021-07-16","cited_by_count":38},{"id":"2202.10581","title":"Unleashing the Power of Transformer for Graphs","created":"2022-02-18","cited_by_count":6}],"next_cursor":null}