{"list":"other","total":54,"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":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1811.05868","title":"Pitfalls of Graph Neural Network Evaluation","created":"2018-11-14","cited_by_count":1007},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"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":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"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":"1908.01000","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","created":"2019-07-31","cited_by_count":441},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2101.00797","title":"Beyond Low-frequency Information in Graph Convolutional Networks","created":"2021-01-04","cited_by_count":362},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"2110.14446","title":"Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods","created":"2021-10-27","cited_by_count":311},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2106.10994","title":"BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation","created":"2021-06-21","cited_by_count":195},{"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":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"2205.11172","title":"How Powerful are Spectral Graph Neural Networks","created":"2022-05-23","cited_by_count":169},{"id":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","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":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133},{"id":"2311.06190","title":"FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective","created":"2023-11-10","cited_by_count":127},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102},{"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":"2403.01232","title":"Polynormer: Polynomial-Expressive Graph Transformer in Linear Time","created":"2024-03-02","cited_by_count":65},{"id":"2007.16002","title":"Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning","created":"2020-07-27","cited_by_count":51},{"id":"2104.12840","title":"AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter","created":"2021-04-26","cited_by_count":43},{"id":"2306.00006","title":"Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection","created":"2023-05-29","cited_by_count":43},{"id":"2406.01034","title":"Enhancing Graph Collaborative Filtering with FourierKAN Feature Transformation","created":"2024-06-03","cited_by_count":42},{"id":"2409.09957","title":"Deep Graph Anomaly Detection: A Survey and New Perspectives","created":"2024-09-16","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":"2402.11887","title":"Generative Semi-supervised Graph Anomaly Detection","created":"2024-02-19","cited_by_count":22},{"id":"2311.00049","title":"On the Kolmogorov neural networks","created":"2023-10-31","cited_by_count":19},{"id":"2201.09332","title":"How Expressive are Transformers in Spectral Domain for Graphs?","created":"2022-01-23","cited_by_count":15},{"id":"2309.12971","title":"Higher-order Graph Convolutional Network with Flower-Petals Laplacians on Simplicial Complexes","created":"2023-09-22","cited_by_count":15},{"id":"2407.14459","title":"PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer","created":"2024-07-19","cited_by_count":10},{"id":"2406.19258","title":"Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers","created":"2024-06-27","cited_by_count":9},{"id":"2310.11025","title":"SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning","created":"2023-10-17","cited_by_count":5},{"id":"2211.11761","title":"From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm","created":"2022-11-21","cited_by_count":4}],"next_cursor":null}