{"list":"other","total":73,"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":"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1811.05868","title":"Pitfalls of Graph Neural Network Evaluation","created":"2018-11-14","cited_by_count":1007},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1509.09292","title":"Convolutional Networks on Graphs for Learning Molecular Fingerprints","created":"2015-09-30","cited_by_count":754},{"id":"2007.08663","title":"TUDataset: A collection of benchmark datasets for learning with graphs","created":"2020-07-16","cited_by_count":728},{"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":"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":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"2302.11640","title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","created":"2023-02-22","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":"1605.05273","title":"Learning Convolutional Neural Networks for Graphs","created":"2016-05-17","cited_by_count":314},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"1912.09893","title":"A Fair Comparison of Graph Neural Networks for Graph Classification","created":"2019-12-20","cited_by_count":244},{"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":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"2112.14936","title":"Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks","created":"2021-12-30","cited_by_count":176},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"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":"2402.00789","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","created":"2024-02-01","cited_by_count":134},{"id":"2301.09505","title":"Rethinking the Expressive Power of GNNs via Graph Biconnectivity","created":"2023-01-23","cited_by_count":119},{"id":"2009.03294","title":"GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training","created":"2020-09-07","cited_by_count":117},{"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":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2301.09474","title":"DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion","created":"2023-01-23","cited_by_count":87},{"id":"2402.08678","title":"Graph Mamba: Towards Learning on Graphs with State Space Models","created":"2024-02-13","cited_by_count":86},{"id":"2309.00367","title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","created":"2023-09-01","cited_by_count":85},{"id":"2406.08993","title":"Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification","created":"2024-06-13","cited_by_count":85},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83},{"id":"2305.08018","title":"DRew: Dynamically Rewired Message Passing with Delay","created":"2023-05-13","cited_by_count":82},{"id":"2201.12787","title":"GRPE: Relative Positional Encoding for Graph Transformer","created":"2022-01-30","cited_by_count":70},{"id":"2011.07682","title":"A Large-Scale Database for Graph Representation Learning","created":"2020-11-16","cited_by_count":55},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55},{"id":"2103.13355","title":"Bag of Tricks for Node Classification with Graph Neural Networks","created":"2021-03-24","cited_by_count":40},{"id":"2310.01267","title":"Cooperative Graph Neural Networks","created":"2023-10-02","cited_by_count":36},{"id":"2407.09777","title":"Graph Transformers: A Survey","created":"2024-07-13","cited_by_count":32},{"id":"2210.13148","title":"Transformers over Directed Acyclic Graphs","created":"2022-10-24","cited_by_count":23},{"id":"2308.11129","title":"Enhancing Graph Transformers with Hierarchical Distance Structural Encoding","created":"2023-08-22","cited_by_count":16},{"id":"2206.02404","title":"A Simple yet Effective Method for Graph Classification","created":"2022-06-06","cited_by_count":14},{"id":"2402.02005","title":"Topology-Informed Graph Transformer","created":"2024-02-03","cited_by_count":13},{"id":"2406.05815","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","created":"2024-06-09","cited_by_count":13},{"id":"2411.12732","title":"Benchmarking Positional Encodings for GNNs and Graph Transformers","created":"2024-11-19","cited_by_count":13},{"id":"2405.16435","title":"Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning","created":"2024-05-26","cited_by_count":10},{"id":"2402.08450","title":"Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products","created":"2024-02-13","cited_by_count":8},{"id":"2410.06746","title":"Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention","created":"2024-10-09","cited_by_count":8},{"id":"2401.16176","title":"A Survey on Structure-Preserving Graph Transformers","created":"2024-01-29","cited_by_count":7},{"id":"2311.17327","title":"Improving Self-supervised Molecular Representation Learning using Persistent Homology","created":"2023-11-29","cited_by_count":6},{"id":"2304.12217","title":"Impact-Oriented Contextual Scholar Profiling using Self-Citation Graphs","created":"2023-04-24","cited_by_count":5},{"id":"2406.12059","title":"A Scalable and Effective Alternative to Graph Transformers","created":"2024-06-17","cited_by_count":4},{"id":"2405.21061","title":"Graph External Attention Enhanced Transformer","created":"2024-05-31","cited_by_count":3}],"next_cursor":null}