{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"2003.00982","title":"Benchmarking Graph Neural Networks","created":"2020-03-02","cited_by_count":680},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"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":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","cited_by_count":346},{"id":"2006.09252","title":"Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting","created":"2020-06-16","cited_by_count":313},{"id":"2104.00272","title":"Mesh Graphormer","created":"2021-04-01","cited_by_count":265},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"2006.13318","title":"A Note on Over-Smoothing for Graph Neural Networks","created":"2020-06-23","cited_by_count":249},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247},{"id":"1901.06032","title":"A Survey of the Recent Architectures of Deep Convolutional Neural Networks","created":"2019-01-17","cited_by_count":213},{"id":"2010.01179","title":"The Surprising Power of Graph Neural Networks with Random Node Initialization","created":"2020-10-02","cited_by_count":198},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2002.03155","title":"Random Features Strengthen Graph Neural Networks","created":"2020-02-08","cited_by_count":186},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179},{"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":"2110.03753","title":"From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness","created":"2021-10-07","cited_by_count":155},{"id":"2110.02910","title":"Equivariant Subgraph Aggregation Networks","created":"2021-10-06","cited_by_count":154},{"id":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153},{"id":"1903.02541","title":"Relational Pooling for Graph Representations","created":"2019-03-06","cited_by_count":150},{"id":"2112.09992","title":"Weisfeiler and Leman go Machine Learning: The Story so far","created":"2021-12-18","cited_by_count":122},{"id":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112},{"id":"2004.11154","title":"Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond","created":"2020-04-23","cited_by_count":109},{"id":"2006.15646","title":"Expressive Power of Invariant and Equivariant Graph Neural Networks","created":"2020-06-28","cited_by_count":100},{"id":"2107.02392","title":"Dirichlet Energy Constrained Learning for Deep Graph Neural Networks","created":"2021-07-06","cited_by_count":97},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2006.04064","title":"Bayesian Graph Neural Networks with Adaptive Connection Sampling","created":"2020-06-07","cited_by_count":81},{"id":"1907.05008","title":"Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology","created":"2019-07-11","cited_by_count":52},{"id":"1912.06058","title":"Coloring graph neural networks for node disambiguation","created":"2019-12-12","cited_by_count":52},{"id":"1703.00864","title":"The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings","created":"2017-03-02","cited_by_count":45},{"id":"2106.08443","title":"Reproducing Kernel Hilbert Space, Mercer's Theorem, Eigenfunctions, Nystr\\\"om Method, and Use of Kernels in Machine Learning: Tutorial and Survey","created":"2021-06-15","cited_by_count":37},{"id":"2110.14416","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","created":"2021-10-27","cited_by_count":35},{"id":"2310.02579","title":"On the Stability of Expressive Positional Encodings for Graphs","created":"2023-10-04","cited_by_count":33},{"id":"2407.09777","title":"Graph Transformers: A Survey","created":"2024-07-13","cited_by_count":32},{"id":"2502.01122","title":"Learning Efficient Positional Encodings with Graph Neural Networks","created":"2025-02-03","cited_by_count":24},{"id":"2310.18716","title":"Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding","created":"2023-10-28","cited_by_count":21},{"id":"2305.00156","title":"Taming graph kernels with random features","created":"2023-04-29","cited_by_count":17},{"id":"2402.08595","title":"Homomorphism Counts for Graph Neural Networks: All About That Basis","created":"2024-02-13","cited_by_count":16},{"id":"2410.18676","title":"Homomorphism Counts as Structural Encodings for Graph Learning","created":"2024-10-24","cited_by_count":7}],"next_cursor":null}