{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"1911.03082","title":"Composition-based Multi-Relational Graph Convolutional Networks","created":"2019-11-08","cited_by_count":396},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2006.15437","title":"GPT-GNN: Generative Pre-Training of Graph Neural Networks","created":"2020-06-27","cited_by_count":303},{"id":"2106.06935","title":"Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction","created":"2021-06-13","cited_by_count":275},{"id":"1911.06962","title":"Inductive Relation Prediction by Subgraph Reasoning","created":"2019-11-16","cited_by_count":239},{"id":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211},{"id":"2009.13566","title":"Graph Neural Networks with Heterophily","created":"2020-09-28","cited_by_count":202},{"id":"1804.00891","title":"Hyperspherical Variational Auto-Encoders","created":"2018-04-03","cited_by_count":189},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184},{"id":"2106.06134","title":"Is Homophily a Necessity for Graph Neural Networks?","created":"2021-06-11","cited_by_count":182},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2202.07082","title":"Graph Neural Networks for Graphs with Heterophily: A Survey","created":"2022-02-14","cited_by_count":175},{"id":"1903.11680","title":"Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks","created":"2019-03-27","cited_by_count":159},{"id":"2210.14709","title":"Learning on Large-scale Text-attributed Graphs via Variational Inference","created":"2022-10-26","cited_by_count":155},{"id":"2010.16103","title":"Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning","created":"2020-10-30","cited_by_count":149},{"id":"2111.00064","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","created":"2021-10-29","cited_by_count":138},{"id":"1904.12058","title":"Inductive Matrix Completion Based on Graph Neural Networks","created":"2019-04-26","cited_by_count":86},{"id":"1905.13416","title":"Fine-Grained Spoiler Detection from Large-Scale Review Corpora","created":"2019-05-31","cited_by_count":77},{"id":"2111.12128","title":"On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features","created":"2021-11-23","cited_by_count":63},{"id":"2103.06064","title":"Graph Neural Networks Inspired by Classical Iterative Algorithms","created":"2021-03-10","cited_by_count":60},{"id":"2101.06323","title":"TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search","created":"2021-01-15","cited_by_count":54},{"id":"2107.01495","title":"On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs","created":"2021-07-03","cited_by_count":49},{"id":"2305.12268","title":"Patton: Language Model Pretraining on Text-Rich Networks","created":"2023-05-20","cited_by_count":49},{"id":"2104.12080","title":"AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search","created":"2021-04-25","cited_by_count":38},{"id":"2306.02592","title":"Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications","created":"2023-06-05","cited_by_count":33},{"id":"2111.06592","title":"Implicit vs Unfolded Graph Neural Networks","created":"2021-11-12","cited_by_count":13},{"id":"2306.00899","title":"Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices","created":"2023-06-01","cited_by_count":13},{"id":"2207.09980","title":"ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective","created":"2022-07-20","cited_by_count":12},{"id":"2210.04081","title":"Less is More: SlimG for Accurate, Robust, and Interpretable Graph Mining","created":"2022-10-08","cited_by_count":10},{"id":"2206.10781","title":"Efficient and effective training of language and graph neural network models","created":"2022-06-22","cited_by_count":9},{"id":"2010.12157","title":"BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks","created":"2020-10-23","cited_by_count":7}],"next_cursor":null}