{"list":"other","total":73,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"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":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"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":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"2006.10503","title":"SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks","created":"2020-06-18","cited_by_count":607},{"id":"2003.01332","title":"Heterogeneous Graph Transformer","created":"2020-03-03","cited_by_count":582},{"id":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"id":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"2102.03150","title":"Equivariant message passing for the prediction of tensorial properties and molecular spectra","created":"2021-02-05","cited_by_count":441},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"1905.11136","title":"Provably Powerful Graph Networks","created":"2019-05-27","cited_by_count":389},{"id":"2106.08903","title":"GemNet: Universal Directional Graph Neural Networks for Molecules","created":"2021-06-02","cited_by_count":343},{"id":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2006.09252","title":"Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting","created":"2020-06-16","cited_by_count":313},{"id":"1704.02901","title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","created":"2017-04-10","cited_by_count":310},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2206.11990","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","created":"2022-06-23","cited_by_count":264},{"id":"2106.12575","title":"Weisfeiler and Lehman Go Cellular: CW Networks","created":"2021-06-23","cited_by_count":218},{"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":"2202.02541","title":"TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials","created":"2022-02-05","cited_by_count":182},{"id":"2208.09481","title":"Graph neural networks for materials science and chemistry","created":"2022-08-05","cited_by_count":182},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179},{"id":"1905.12560","title":"On the equivalence between graph isomorphism testing and function approximation with GNNs","created":"2019-05-29","cited_by_count":172},{"id":"1905.02850","title":"Understanding Attention and Generalization in Graph Neural Networks","created":"2019-05-08","cited_by_count":169},{"id":"2210.07606","title":"Revisiting Heterophily For Graph Neural Networks","created":"2022-10-14","cited_by_count":169},{"id":"2302.02941","title":"On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology","created":"2023-02-06","cited_by_count":166},{"id":"2005.03675","title":"Machine Learning on Graphs: A Model and Comprehensive Taxonomy","created":"2020-05-07","cited_by_count":156},{"id":"2010.05731","title":"Probing Pretrained Language Models for Lexical Semantics","created":"2020-10-12","cited_by_count":156},{"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":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2010.02863","title":"Directional Graph Networks","created":"2020-10-06","cited_by_count":133},{"id":"2010.08853","title":"From Local Structures to Size Generalization in Graph Neural Networks","created":"2020-10-17","cited_by_count":124},{"id":"2112.09992","title":"Weisfeiler and Leman go Machine Learning: The Story so far","created":"2021-12-18","cited_by_count":122},{"id":"2102.11533","title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","created":"2021-02-23","cited_by_count":120},{"id":"2301.09505","title":"Rethinking the Expressive Power of GNNs via Graph Biconnectivity","created":"2023-01-23","cited_by_count":119},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107},{"id":"2203.00199","title":"Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks","created":"2022-03-01","cited_by_count":94},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2301.09308","title":"On the Expressive Power of Geometric Graph Neural Networks","created":"2023-01-23","cited_by_count":90},{"id":"2209.11807","title":"Periodic Graph Transformers for Crystal Material Property Prediction","created":"2022-09-23","cited_by_count":87},{"id":"2210.01765","title":"One Transformer Can Understand Both 2D & 3D Molecular Data","created":"2022-10-04","cited_by_count":77},{"id":"2210.02997","title":"Expander Graph Propagation","created":"2022-10-06","cited_by_count":75},{"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":"2301.11956","title":"On the Connection Between MPNN and Graph Transformer","created":"2023-01-27","cited_by_count":61},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55},{"id":"2001.10667","title":"Interpretable Rumor Detection in Microblogs by Attending to User Interactions","created":"2020-01-29","cited_by_count":44},{"id":"2302.00049","title":"Transformers Meet Directed Graphs","created":"2023-01-31","cited_by_count":40},{"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":"2205.15117","title":"OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphs","created":"2022-05-30","cited_by_count":38},{"id":"2212.02229","title":"GPS++: An Optimised Hybrid MPNN/Transformer for Molecular Property Prediction","created":"2022-11-18","cited_by_count":28},{"id":"2201.13311","title":"Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer","created":"2022-01-25","cited_by_count":13},{"id":"2102.13419","title":"Iterative SE(3)-Transformers","created":"2021-02-26","cited_by_count":10}],"next_cursor":null}