{"list":"other","total":148,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"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":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"2209.14734","title":"DiGress: Discrete Denoising diffusion for graph generation","created":"2022-09-29","cited_by_count":520},{"id":"2011.02260","title":"Graph Neural Networks in Recommender Systems: A Survey","created":"2020-11-04","cited_by_count":494},{"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":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"2110.02642","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","created":"2021-10-06","cited_by_count":394},{"id":"1812.04202","title":"Deep Learning on Graphs: A Survey","created":"2018-12-11","cited_by_count":393},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"2010.09885","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","created":"2020-10-19","cited_by_count":337},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"1709.07604","title":"A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications","created":"2017-09-22","cited_by_count":260},{"id":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"id":"2106.07178","title":"A Comprehensive Survey on Graph Anomaly Detection with Deep Learning","created":"2021-06-14","cited_by_count":230},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"2201.07284","title":"TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data","created":"2022-01-18","cited_by_count":214},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"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":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"id":"2205.11172","title":"How Powerful are Spectral Graph Neural Networks","created":"2022-05-23","cited_by_count":169},{"id":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147},{"id":"2307.03759","title":"A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection","created":"2023-07-07","cited_by_count":145},{"id":"2105.00696","title":"Graph Learning: A Survey","created":"2021-05-03","cited_by_count":141},{"id":"1906.00346","title":"Pre-training of Graph Augmented Transformers for Medication Recommendation","created":"2019-06-02","cited_by_count":127},{"id":"2011.14867","title":"A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources","created":"2020-11-30","cited_by_count":126},{"id":"2106.04113","title":"Self-supervised Graph-level Representation Learning with Local and Global Structure","created":"2021-06-08","cited_by_count":125},{"id":"1904.02342","title":"Text Generation from Knowledge Graphs with Graph Transformers","created":"2019-04-04","cited_by_count":122},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"1912.12693","title":"A Gentle Introduction to Deep Learning for Graphs","created":"2019-12-29","cited_by_count":108},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107},{"id":"2104.03466","title":"Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT","created":"2021-04-08","cited_by_count":104},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2203.15876","title":"Self-Supervised Learning for Recommender Systems: A Survey","created":"2022-03-29","cited_by_count":95},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2301.07507","title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","created":"2023-01-18","cited_by_count":93},{"id":"2301.09474","title":"DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion","created":"2023-01-23","cited_by_count":87},{"id":"2301.08210","title":"Everything is Connected: Graph Neural Networks","created":"2023-01-19","cited_by_count":85},{"id":"2206.04355","title":"Graph Attention Multi-Layer Perceptron","created":"2022-06-09","cited_by_count":83},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83},{"id":"1911.07470","title":"Graph Transformer for Graph-to-Sequence Learning","created":"2019-11-18","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":"1909.00958","title":"Graph Representation Learning: A Survey","created":"2019-09-03","cited_by_count":75},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72},{"id":"2011.14203","title":"EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference","created":"2020-11-28","cited_by_count":70},{"id":"2102.01818","title":"Memorization vs. Generalization: Quantifying Data Leakage in NLP Performance Evaluation","created":"2021-02-03","cited_by_count":70},{"id":"2201.12787","title":"GRPE: Relative Positional Encoding for Graph Transformer","created":"2022-01-30","cited_by_count":70},{"id":"2005.10043","title":"Leveraging Graph to Improve Abstractive Multi-Document Summarization","created":"2020-05-20","cited_by_count":67},{"id":"2004.01389","title":"LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention","created":"2020-04-03","cited_by_count":65},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63},{"id":"2106.09876","title":"Anomaly Detection in Dynamic Graphs via Transformer","created":"2021-06-18","cited_by_count":59},{"id":"2402.03358","title":"A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation","created":"2024-01-29","cited_by_count":57},{"id":"2209.13232","title":"A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective","created":"2022-09-27","cited_by_count":56},{"id":"2306.06063","title":"Virtual Node Tuning for Few-shot Node Classification","created":"2023-06-09","cited_by_count":46},{"id":"2205.02357","title":"Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion","created":"2022-05-04","cited_by_count":44},{"id":"2010.03009","title":"GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction","created":"2020-10-06","cited_by_count":43},{"id":"2010.05315","title":"SMYRF: Efficient Attention using Asymmetric Clustering","created":"2020-10-11","cited_by_count":43},{"id":"2005.08225","title":"Deep Learning for Community Detection: Progress, Challenges and Opportunities","created":"2020-05-17","cited_by_count":42},{"id":"1904.05880","title":"Factor Graph Attention","created":"2019-04-11","cited_by_count":41},{"id":"1909.11855","title":"Universal Graph Transformer Self-Attention Networks","created":"2019-09-26","cited_by_count":41},{"id":"2302.00049","title":"Transformers Meet Directed Graphs","created":"2023-01-31","cited_by_count":40},{"id":"2208.07638","title":"Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries","created":"2022-08-16","cited_by_count":39},{"id":"2008.03639","title":"Random Walks: A Review of Algorithms and Applications","created":"2020-08-09","cited_by_count":38},{"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":"2112.00578","title":"Systematic Generalization with Edge Transformers","created":"2021-12-01","cited_by_count":38},{"id":"2203.15350","title":"End-to-End Transformer Based Model for Image Captioning","created":"2022-03-29","cited_by_count":38},{"id":"2104.08698","title":"A Simple and Effective Positional Encoding for Transformers","created":"2021-04-18","cited_by_count":37},{"id":"2203.08566","title":"EDTER: Edge Detection with Transformer","created":"2022-03-16","cited_by_count":36},{"id":"2110.14416","title":"Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphs","created":"2021-10-27","cited_by_count":35},{"id":"2207.14338","title":"Self-Supervised Hypergraph Transformer for Recommender Systems","created":"2022-07-28","cited_by_count":32},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32},{"id":"2206.03364","title":"KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction","created":"2022-06-02","cited_by_count":31},{"id":"2202.10688","title":"Graph Lifelong Learning: A Survey","created":"2022-02-22","cited_by_count":30},{"id":"2111.15143","title":"HEAT: Holistic Edge Attention Transformer for Structured Reconstruction","created":"2021-11-30","cited_by_count":29}],"next_cursor":"100"}