{"list":"other","total":65,"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":"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":"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":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"1806.03536","title":"Representation Learning on Graphs with Jumping Knowledge Networks","created":"2018-06-09","cited_by_count":877},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"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":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"id":"1905.05178","title":"Graph U-Nets","created":"2019-05-11","cited_by_count":492},{"id":"2004.05718","title":"Principal Neighbourhood Aggregation for Graph Nets","created":"2020-04-12","cited_by_count":478},{"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":"1904.08082","title":"Self-Attention Graph Pooling","created":"2019-04-17","cited_by_count":421},{"id":"1802.08773","title":"GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models","created":"2018-02-24","cited_by_count":413},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333},{"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":"2004.11198","title":"SIGN: Scalable Inception Graph Neural Networks","created":"2020-04-23","cited_by_count":284},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"1803.03324","title":"Learning Deep Generative Models of Graphs","created":"2018-03-08","cited_by_count":229},{"id":"2103.03212","title":"Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks","created":"2021-03-04","cited_by_count":221},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2002.03230","title":"Hierarchical Generation of Molecular Graphs using Structural Motifs","created":"2020-02-08","cited_by_count":208},{"id":"2202.03036","title":"Structure-Aware Transformer for Graph Representation Learning","created":"2022-02-07","cited_by_count":194},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"id":"1911.07979","title":"ASAP: Adaptive Structure Aware Pooling for Learning Hierarchical Graph Representations","created":"2019-11-18","cited_by_count":156},{"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":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133},{"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":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"1506.08839","title":"Inferring Networks of Substitutable and Complementary Products","created":"2015-06-29","cited_by_count":92},{"id":"2301.09474","title":"DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion","created":"2023-01-23","cited_by_count":87},{"id":"2305.08018","title":"DRew: Dynamically Rewired Message Passing with Delay","created":"2023-05-13","cited_by_count":82},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72},{"id":"2110.13094","title":"Gophormer: Ego-Graph Transformer for Node Classification","created":"2021-10-25","cited_by_count":63},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58},{"id":"2210.13148","title":"Transformers over Directed Acyclic Graphs","created":"2022-10-24","cited_by_count":23},{"id":"2009.03717","title":"Hierarchical Message-Passing Graph Neural Networks","created":"2020-09-08","cited_by_count":21},{"id":"2305.02866","title":"Hierarchical Transformer for Scalable Graph Learning","created":"2023-05-04","cited_by_count":17},{"id":"2211.14425","title":"PatchGT: Transformer over Non-trainable Clusters for Learning Graph Representations","created":"2022-11-26","cited_by_count":8},{"id":"2304.12217","title":"Impact-Oriented Contextual Scholar Profiling using Self-Citation Graphs","created":"2023-04-24","cited_by_count":5},{"id":"2305.07521","title":"AGFormer: Efficient Graph Representation with Anchor-Graph Transformer","created":"2023-05-12","cited_by_count":5},{"id":"2002.04425","title":"A Hierarchical Transitive-Aligned Graph Kernel for Un-attributed Graphs","created":"2020-02-08","cited_by_count":4}],"next_cursor":null}