{"list":"other","total":55,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"1806.01973","title":"Graph Convolutional Neural Networks for Web-Scale Recommender Systems","created":"2018-06-06","cited_by_count":1138},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"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":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2006.05582","title":"Contrastive Multi-View Representation Learning on Graphs","created":"2020-06-10","cited_by_count":652},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"1801.10247","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","created":"2018-01-30","cited_by_count":584},{"id":"1503.03578","title":"LINE: Large-scale Information Network Embedding","created":"2015-03-12","cited_by_count":582},{"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":"2006.04131","title":"Deep Graph Contrastive Representation Learning","created":"2020-06-07","cited_by_count":539},{"id":"2006.10637","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","created":"2020-06-18","cited_by_count":530},{"id":"2010.14945","title":"Graph Contrastive Learning with Adaptive Augmentation","created":"2020-10-27","cited_by_count":519},{"id":"2006.09963","title":"GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training","created":"2020-06-17","cited_by_count":463},{"id":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"id":"1902.10191","title":"EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs","created":"2019-02-26","cited_by_count":447},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"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":"2202.07082","title":"Graph Neural Networks for Graphs with Heterophily: A Survey","created":"2022-02-14","cited_by_count":175},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152},{"id":"2304.04779","title":"GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner","created":"2023-04-10","cited_by_count":132},{"id":"2201.07858","title":"Decoupling the Depth and Scope of Graph Neural Networks","created":"2022-01-19","cited_by_count":94},{"id":"1908.09710","title":"Variational Graph Recurrent Neural Networks","created":"2019-08-26","cited_by_count":87},{"id":"2111.15367","title":"A Review on Graph Neural Network Methods in Financial Applications","created":"2021-11-27","cited_by_count":78},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72},{"id":"2402.13630","title":"UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs","created":"2024-02-21","cited_by_count":66},{"id":"2110.13094","title":"Gophormer: Ego-Graph Transformer for Node Classification","created":"2021-10-25","cited_by_count":63},{"id":"2405.13873","title":"FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering","created":"2024-05-22","cited_by_count":39},{"id":"1705.04969","title":"Attributed Social Network Embedding","created":"2017-05-14","cited_by_count":34},{"id":"2212.02229","title":"GPS++: An Optimised Hybrid MPNN/Transformer for Molecular Property Prediction","created":"2022-11-18","cited_by_count":28},{"id":"1912.10206","title":"How Robust Are Graph Neural Networks to Structural Noise?","created":"2019-12-21","cited_by_count":15},{"id":"2202.03392","title":"Large-scale Personalized Video Game Recommendation via Social-aware Contextualized Graph Neural Network","created":"2022-02-07","cited_by_count":14},{"id":"2204.02338","title":"MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering","created":"2022-04-05","cited_by_count":11},{"id":"2112.04319","title":"SCR: Training Graph Neural Networks with Consistency Regularization","created":"2021-12-08","cited_by_count":10},{"id":"2202.08391","title":"Graph Masked Autoencoders with Transformers","created":"2022-02-17","cited_by_count":10},{"id":"1901.10204","title":"Approximating Spectral Clustering via Sampling: a Review","created":"2019-01-29","cited_by_count":9},{"id":"2307.00228","title":"InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphs","created":"2023-07-01","cited_by_count":4}],"next_cursor":null}