{"list":"other","total":73,"rows":[{"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":"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"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":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"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":"2302.11640","title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","created":"2023-02-22","cited_by_count":343},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2103.00111","title":"Graph Self-Supervised Learning: A Survey","created":"2021-02-27","cited_by_count":289},{"id":"2307.03393","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","created":"2023-07-07","cited_by_count":274},{"id":"2310.00149","title":"One for All: Towards Training One Graph Model for All Classification Tasks","created":"2023-09-29","cited_by_count":243},{"id":"2310.13023","title":"GraphGPT: Graph Instruction Tuning for Large Language Models","created":"2023-10-19","cited_by_count":226},{"id":"2402.07630","title":"G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering","created":"2024-02-12","cited_by_count":223},{"id":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211},{"id":"2312.02783","title":"Large Language Models on Graphs: A Comprehensive Survey","created":"2023-12-05","cited_by_count":192},{"id":"2102.06514","title":"Large-Scale Representation Learning on Graphs via Bootstrapping","created":"2021-02-12","cited_by_count":186},{"id":"2402.08170","title":"LLaGA: Large Language and Graph Assistant","created":"2024-02-13","cited_by_count":181},{"id":"2310.04560","title":"Talk like a Graph: Encoding Graphs for Large Language Models","created":"2023-10-06","cited_by_count":176},{"id":"2302.08043","title":"GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks","created":"2023-02-16","cited_by_count":167},{"id":"2210.09338","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","created":"2022-10-17","cited_by_count":156},{"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":"2105.02605","title":"GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph","created":"2021-05-06","cited_by_count":143},{"id":"2111.00064","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","created":"2021-10-29","cited_by_count":138},{"id":"2305.19523","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","created":"2023-05-31","cited_by_count":133},{"id":"2309.10313","title":"Investigating the Catastrophic Forgetting in Multimodal Large Language Models","created":"2023-09-19","cited_by_count":119},{"id":"2402.05862","title":"Let Your Graph Do the Talking: Encoding Structured Data for LLMs","created":"2024-02-08","cited_by_count":118},{"id":"2310.01089","title":"GraphText: Graph Reasoning in Text Space","created":"2023-10-02","cited_by_count":111},{"id":"2310.05845","title":"GraphLLM: Boosting Graph Reasoning Ability of Large Language Model","created":"2023-10-09","cited_by_count":107},{"id":"2310.11829","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","created":"2023-10-18","cited_by_count":103},{"id":"2305.12600","title":"PRODIGY: Enabling In-context Learning Over Graphs","created":"2023-05-21","cited_by_count":98},{"id":"2012.06002","title":"Overcoming Catastrophic Forgetting in Graph Neural Networks","created":"2020-12-10","cited_by_count":95},{"id":"2009.05204","title":"Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization","created":"2020-09-11","cited_by_count":93},{"id":"2310.04562","title":"Towards Foundation Models for Knowledge Graph Reasoning","created":"2023-10-06","cited_by_count":86},{"id":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83},{"id":"2209.15486","title":"Graph Neural Networks for Link Prediction with Subgraph Sketching","created":"2022-09-30","cited_by_count":81},{"id":"2308.02565","title":"SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning","created":"2023-08-03","cited_by_count":73},{"id":"2310.04668","title":"Label-free Node Classification on Graphs with Large Language Models (LLMS)","created":"2023-10-07","cited_by_count":72},{"id":"2402.12984","title":"Can GNN be Good Adapter for LLMs?","created":"2024-02-20","cited_by_count":71},{"id":"2306.13089","title":"GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning","created":"2023-05-28","cited_by_count":70},{"id":"2306.10453","title":"Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking","created":"2023-06-18","cited_by_count":69},{"id":"2405.18512","title":"Understanding Transformer Reasoning Capabilities via Graph Algorithms","created":"2024-05-28","cited_by_count":67},{"id":"2402.07197","title":"GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks","created":"2024-02-11","cited_by_count":63},{"id":"2301.11956","title":"On the Connection Between MPNN and Graph Transformer","created":"2023-01-27","cited_by_count":61},{"id":"2402.08785","title":"InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment","created":"2024-02-13","cited_by_count":56},{"id":"2210.02330","title":"Revisiting Graph Contrastive Learning from the Perspective of Graph Spectrum","created":"2022-10-05","cited_by_count":43},{"id":"2306.01323","title":"Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?","created":"2023-06-02","cited_by_count":41},{"id":"2106.13092","title":"BotRGCN: Twitter Bot Detection with Relational Graph Convolutional Networks","created":"2021-06-24","cited_by_count":39},{"id":"2404.14928","title":"Graph Machine Learning in the Era of Large Language Models (LLMs)","created":"2024-04-23","cited_by_count":33},{"id":"2402.11139","title":"LiGNN: Graph Neural Networks at LinkedIn","created":"2024-02-17","cited_by_count":31},{"id":"2007.12002","title":"Grale: Designing Networks for Graph Learning","created":"2020-07-23","cited_by_count":28},{"id":"2303.16458","title":"When to Pre-Train Graph Neural Networks? From Data Generation Perspective!","created":"2023-03-29","cited_by_count":18},{"id":"2401.00529","title":"GraphGPT: Generative Pre-trained Graph Eulerian Transformer","created":"2023-12-31","cited_by_count":17},{"id":"2406.02953","title":"GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment","created":"2024-06-05","cited_by_count":15},{"id":"2311.01038","title":"Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks","created":"2023-11-02","cited_by_count":14},{"id":"2402.02212","title":"A Survey to Recent Progress Towards Understanding In-Context Learning","created":"2024-02-03","cited_by_count":14},{"id":"2312.13583","title":"Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns","created":"2023-12-21","cited_by_count":13},{"id":"2402.00904","title":"Graph Domain Adaptation: Challenges, Progress and Prospects","created":"2024-02-01","cited_by_count":11}],"next_cursor":null}