{"list":"other","total":96,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"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":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"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":"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":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"1812.09902","title":"Invariant and Equivariant Graph Networks","created":"2018-12-24","cited_by_count":346},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2006.09252","title":"Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting","created":"2020-06-16","cited_by_count":313},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"id":"1806.01242","title":"Graph networks as learnable physics engines for inference and control","created":"2018-06-04","cited_by_count":244},{"id":"2103.03212","title":"Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks","created":"2021-03-04","cited_by_count":221},{"id":"2106.12575","title":"Weisfeiler and Lehman Go Cellular: CW Networks","created":"2021-06-23","cited_by_count":218},{"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":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2006.04710","title":"The Lipschitz Constant of Self-Attention","created":"2020-06-08","cited_by_count":174},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"id":"1707.00683","title":"Modulating early visual processing by language","created":"2017-07-02","cited_by_count":167},{"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":"2307.01504","title":"All in One: Multi-task Prompting for Graph Neural Networks","created":"2023-07-04","cited_by_count":148},{"id":"2111.00064","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","created":"2021-10-29","cited_by_count":138},{"id":"2110.13197","title":"Nested Graph Neural Networks","created":"2021-10-25","cited_by_count":137},{"id":"2010.02863","title":"Directional Graph Networks","created":"2020-10-06","cited_by_count":133},{"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":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2309.00367","title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","created":"2023-09-01","cited_by_count":85},{"id":"2201.12787","title":"GRPE: Relative Positional Encoding for Graph Transformer","created":"2022-01-30","cited_by_count":70},{"id":"2302.07090","title":"A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests","created":"2023-02-14","cited_by_count":64},{"id":"2301.11956","title":"On the Connection Between MPNN and Graph Transformer","created":"2023-01-27","cited_by_count":61},{"id":"2210.13978","title":"Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs","created":"2022-10-22","cited_by_count":56},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55},{"id":"2201.12884","title":"A Theoretical Comparison of Graph Neural Network Extensions","created":"2022-01-30","cited_by_count":48},{"id":"2102.08786","title":"Walking Out of the Weisfeiler Leman Hierarchy: Graph Learning Beyond Message Passing","created":"2021-02-17","cited_by_count":47},{"id":"2311.04147","title":"Multi-resolution Time-Series Transformer for Long-term Forecasting","created":"2023-11-07","cited_by_count":41},{"id":"2401.08514","title":"Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness","created":"2024-01-16","cited_by_count":39},{"id":"2304.07702","title":"An Empirical Study of Realized GNN Expressiveness","created":"2023-04-16","cited_by_count":33},{"id":"2310.02579","title":"On the Stability of Expressive Positional Encodings for Graphs","created":"2023-10-04","cited_by_count":33},{"id":"2402.14202","title":"Comparing Graph Transformers via Positional Encodings","created":"2024-02-22","cited_by_count":20},{"id":"2402.08595","title":"Homomorphism Counts for Graph Neural Networks: All About That Basis","created":"2024-02-13","cited_by_count":16},{"id":"2406.04336","title":"On the Expressive Power of Spectral Invariant Graph Neural Networks","created":"2024-06-06","cited_by_count":15},{"id":"2306.03266","title":"Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman","created":"2023-06-05","cited_by_count":13},{"id":"2309.04941","title":"Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power","created":"2023-09-10","cited_by_count":12},{"id":"2404.13604","title":"CKGConv: General Graph Convolution with Continuous Kernels","created":"2024-04-21","cited_by_count":5}],"next_cursor":null}