{"list":"other","total":73,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"1811.05868","title":"Pitfalls of Graph Neural Network Evaluation","created":"2018-11-14","cited_by_count":1007},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"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":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"1905.11136","title":"Provably Powerful Graph Networks","created":"2019-05-27","cited_by_count":389},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"1807.02547","title":"3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data","created":"2018-07-06","cited_by_count":354},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","cited_by_count":346},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320},{"id":"1612.08498","title":"Steerable CNNs","created":"2016-12-27","cited_by_count":305},{"id":"1911.03584","title":"On the Relationship between Self-Attention and Convolutional Layers","created":"2019-11-08","cited_by_count":300},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2006.13318","title":"A Note on Over-Smoothing for Graph Neural Networks","created":"2020-06-23","cited_by_count":249},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248},{"id":"2002.04025","title":"Can Graph Neural Networks Count Substructures?","created":"2020-02-10","cited_by_count":236},{"id":"1411.4280","title":"Efficient Object Localization Using Convolutional Networks","created":"2014-11-16","cited_by_count":227},{"id":"1905.04943","title":"Universal Invariant and Equivariant Graph Neural Networks","created":"2019-05-13","cited_by_count":183},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179},{"id":"2203.00555","title":"DeepNet: Scaling Transformers to 1,000 Layers","created":"2022-03-01","cited_by_count":178},{"id":"1901.09342","title":"On the Universality of Invariant Networks","created":"2019-01-27","cited_by_count":152},{"id":"1702.08389","title":"Equivariance Through Parameter-Sharing","created":"2017-02-27","cited_by_count":141},{"id":"1710.11278","title":"Approximating Continuous Functions by ReLU Nets of Minimal Width","created":"2017-10-31","cited_by_count":122},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107},{"id":"2002.08599","title":"On Learning Sets of Symmetric Elements","created":"2020-02-20","cited_by_count":98},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96},{"id":"1610.09072","title":"Orthogonal Random Features","created":"2016-10-28","cited_by_count":91},{"id":"2002.07028","title":"Low-Rank Bottleneck in Multi-head Attention Models","created":"2020-02-17","cited_by_count":89},{"id":"2006.09286","title":"On the Computational Power of Transformers and its Implications in Sequence Modeling","created":"2020-06-16","cited_by_count":85},{"id":"2201.12787","title":"GRPE: Relative Positional Encoding for Graph Transformer","created":"2022-01-30","cited_by_count":70},{"id":"2203.04810","title":"Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets","created":"2022-03-09","cited_by_count":64},{"id":"2106.03764","title":"On the Expressive Power of Self-Attention Matrices","created":"2021-06-07","cited_by_count":47},{"id":"1703.00864","title":"The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings","created":"2017-03-02","cited_by_count":45},{"id":"1909.11855","title":"Universal Graph Transformer Self-Attention Networks","created":"2019-09-26","cited_by_count":41},{"id":"2110.14416","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","created":"2021-10-27","cited_by_count":35},{"id":"1909.00383","title":"Self-Attention with Structural Position Representations","created":"2019-09-01","cited_by_count":21},{"id":"2002.08772","title":"Set2Graph: Learning Graphs From Sets","created":"2020-02-20","cited_by_count":16},{"id":"2105.03928","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","created":"2021-05-09","cited_by_count":16},{"id":"1905.01289","title":"Convolution, attention and structure embedding","created":"2019-05-03","cited_by_count":15},{"id":"2202.10156","title":"1-WL Expressiveness Is (Almost) All You Need","created":"2022-02-21","cited_by_count":15}],"next_cursor":null}