{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"2002.09405","title":"Learning to Simulate Complex Physics with Graph Networks","created":"2020-02-21","cited_by_count":880},{"id":"1806.03536","title":"Representation Learning on Graphs with Jumping Knowledge Networks","created":"2018-06-09","cited_by_count":877},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"id":"1905.07953","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","created":"2019-05-20","cited_by_count":541},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"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":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320},{"id":"2004.11198","title":"SIGN: Scalable Inception Graph Neural Networks","created":"2020-04-23","cited_by_count":284},{"id":"2206.11990","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","created":"2022-06-23","cited_by_count":264},{"id":"2010.09990","title":"The Open Catalyst 2020 (OC20) Dataset and Community Challenges","created":"2020-10-20","cited_by_count":246},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2009.13566","title":"Graph Neural Networks with Heterophily","created":"2020-09-28","cited_by_count":202},{"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":"2205.07308","title":"Finding Global Homophily in Graph Neural Networks When Meeting Heterophily","created":"2022-05-15","cited_by_count":179},{"id":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"2202.02466","title":"Handling Distribution Shifts on Graphs: An Invariance Perspective","created":"2022-02-05","cited_by_count":164},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147},{"id":"1601.02513","title":"How to learn a graph from smooth signals","created":"2016-01-11","cited_by_count":146},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2005.07959","title":"Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models","created":"2020-05-16","cited_by_count":116},{"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":"1506.08839","title":"Inferring Networks of Substitutable and Complementary Products","created":"2015-06-29","cited_by_count":92},{"id":"2106.05609","title":"GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings","created":"2021-06-10","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":"2104.01404","title":"New Benchmarks for Learning on Non-Homophilous Graphs","created":"2021-04-03","cited_by_count":81},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72},{"id":"2302.02914","title":"Energy-based Out-of-Distribution Detection for Graph Neural Networks","created":"2023-02-06","cited_by_count":68},{"id":"2110.13094","title":"Gophormer: Ego-Graph Transformer for Node Classification","created":"2021-10-25","cited_by_count":63},{"id":"2111.00234","title":"On Joint Learning for Solving Placement and Routing in Chip Design","created":"2021-10-30","cited_by_count":44},{"id":"2212.09034","title":"Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs","created":"2022-12-18","cited_by_count":42},{"id":"1903.10433","title":"Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems","created":"2019-03-25","cited_by_count":41},{"id":"2111.07337","title":"$p$-Laplacian Based Graph Neural Networks","created":"2021-11-14","cited_by_count":39},{"id":"2210.00102","title":"MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization","created":"2022-09-30","cited_by_count":31},{"id":"2210.13014","title":"Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks","created":"2022-10-24","cited_by_count":22},{"id":"2201.09332","title":"How Expressive are Transformers in Spectral Domain for Graphs?","created":"2022-01-23","cited_by_count":15},{"id":"2302.02104","title":"HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline","created":"2023-02-04","cited_by_count":12}],"next_cursor":null}