{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"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":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"1606.06357","title":"Complex Embeddings for Simple Link Prediction","created":"2016-06-20","cited_by_count":902},{"id":"1902.10197","title":"RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space","created":"2019-02-26","cited_by_count":898},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"2004.02349","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","created":"2020-04-05","cited_by_count":434},{"id":"1911.03082","title":"Composition-based Multi-Relational Graph Convolutional Networks","created":"2019-11-08","cited_by_count":396},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388},{"id":"1911.06136","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","created":"2019-11-13","cited_by_count":356},{"id":"1905.07854","title":"KGAT: Knowledge Graph Attention Network for Recommendation","created":"2019-05-20","cited_by_count":343},{"id":"1909.03193","title":"KG-BERT: BERT for Knowledge Graph Completion","created":"2019-09-07","cited_by_count":324},{"id":"1911.06962","title":"Inductive Relation Prediction by Subgraph Reasoning","created":"2019-11-16","cited_by_count":239},{"id":"1909.02151","title":"KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning","created":"2019-09-04","cited_by_count":216},{"id":"1803.08035","title":"Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs","created":"2018-03-21","cited_by_count":155},{"id":"1803.03467","title":"RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems","created":"2018-03-09","cited_by_count":138},{"id":"1911.09419","title":"Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction","created":"2019-11-21","cited_by_count":133},{"id":"1904.02342","title":"Text Generation from Knowledge Graphs with Graph Transformers","created":"2019-04-04","cited_by_count":122},{"id":"2005.00646","title":"Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering","created":"2020-05-01","cited_by_count":122},{"id":"2010.12537","title":"TUTA: Tree-based Transformers for Generally Structured Table Pre-training","created":"2020-10-21","cited_by_count":100},{"id":"2203.10321","title":"Sequence-to-Sequence Knowledge Graph Completion and Question Answering","created":"2022-03-19","cited_by_count":75},{"id":"1903.08948","title":"Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning","created":"2019-03-21","cited_by_count":63},{"id":"2005.09801","title":"FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval","created":"2020-05-20","cited_by_count":55},{"id":"2008.12813","title":"HittER: Hierarchical Transformers for Knowledge Graph Embeddings","created":"2020-08-28","cited_by_count":54},{"id":"2012.08911","title":"Communicative Message Passing for Inductive Relation Reasoning","created":"2020-12-16","cited_by_count":54},{"id":"1809.05724","title":"Improving Natural Language Inference Using External Knowledge in the Science Questions Domain","created":"2018-09-15","cited_by_count":48},{"id":"2102.07339","title":"OntoZSL: Ontology-enhanced Zero-shot Learning","created":"2021-02-15","cited_by_count":45},{"id":"2205.02357","title":"Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion","created":"2022-05-04","cited_by_count":44},{"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":"2206.03364","title":"KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction","created":"2022-06-02","cited_by_count":31},{"id":"2208.00850","title":"Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs","created":"2022-07-28","cited_by_count":27},{"id":"2209.08779","title":"Neural-Symbolic Entangled Framework for Complex Query Answering","created":"2022-09-19","cited_by_count":18},{"id":"2105.00388","title":"Billion-scale Pre-trained E-commerce Product Knowledge Graph Model","created":"2021-05-02","cited_by_count":13},{"id":"2210.11151","title":"Transformer-based Entity Typing in Knowledge Graphs","created":"2022-10-20","cited_by_count":13},{"id":"2206.03739","title":"Disentangled Ontology Embedding for Zero-shot Learning","created":"2022-06-08","cited_by_count":8}],"next_cursor":null}