{"list":"other","total":52,"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":"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":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"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":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"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":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"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":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","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":"2008.13535","title":"DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems","created":"2020-08-19","cited_by_count":327},{"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":"2007.02901","title":"Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks","created":"2020-07-06","cited_by_count":260},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2202.03036","title":"Structure-Aware Transformer for Graph Representation Learning","created":"2022-02-07","cited_by_count":194},{"id":"2102.06462","title":"Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks","created":"2021-02-12","cited_by_count":182},{"id":"2205.07308","title":"Finding Global Homophily in Graph Neural Networks When Meeting Heterophily","created":"2022-05-15","cited_by_count":179},{"id":"2007.01570","title":"Scaling Graph Neural Networks with Approximate PageRank","created":"2020-07-03","cited_by_count":174},{"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":"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":"2102.11533","title":"Accurate Learning of Graph Representations with Graph Multiset Pooling","created":"2021-02-23","cited_by_count":120},{"id":"2003.04078","title":"A Survey on The Expressive Power of Graph Neural Networks","created":"2020-03-09","cited_by_count":111},{"id":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102},{"id":"2006.15646","title":"Expressive Power of Invariant and Equivariant Graph Neural Networks","created":"2020-06-28","cited_by_count":100},{"id":"2305.10498","title":"Edge Directionality Improves Learning on Heterophilic Graphs","created":"2023-05-17","cited_by_count":90},{"id":"2301.09474","title":"DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion","created":"2023-01-23","cited_by_count":87},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72},{"id":"2302.01524","title":"Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing","created":"2023-02-03","cited_by_count":67},{"id":"2111.06748","title":"Simplifying approach to Node Classification in Graph Neural Networks","created":"2021-11-12","cited_by_count":56},{"id":"2306.03589","title":"How does over-squashing affect the power of GNNs?","created":"2023-06-06","cited_by_count":53},{"id":"2210.00513","title":"Gradient Gating for Deep Multi-Rate Learning on Graphs","created":"2022-10-02","cited_by_count":49},{"id":"2003.03828","title":"$\\Pi-$nets: Deep Polynomial Neural Networks","created":"2020-03-08","cited_by_count":39},{"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":"2302.11556","title":"Equivariant Polynomials for Graph Neural Networks","created":"2023-02-22","cited_by_count":38},{"id":"2205.11691","title":"High-Order Pooling for Graph Neural Networks with Tensor Decomposition","created":"2022-05-24","cited_by_count":24},{"id":"2104.07916","title":"Augmenting Deep Classifiers with Polynomial Neural Networks","created":"2021-04-16","cited_by_count":21},{"id":"2308.13490","title":"TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs","created":"2023-08-25","cited_by_count":16},{"id":"2303.00579","title":"Are More Layers Beneficial to Graph Transformers?","created":"2023-03-01","cited_by_count":15}],"next_cursor":null}