{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"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":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"1503.03578","title":"LINE: Large-scale Information Network Embedding","created":"2015-03-12","cited_by_count":582},{"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":"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":"1812.04202","title":"Deep Learning on Graphs: A Survey","created":"2018-12-11","cited_by_count":393},{"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":"2305.10037","title":"Can Language Models Solve Graph Problems in Natural Language?","created":"2023-05-17","cited_by_count":252},{"id":"2305.15066","title":"GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking","created":"2023-05-24","cited_by_count":210},{"id":"2312.02783","title":"Large Language Models on Graphs: A Comprehensive Survey","created":"2023-12-05","cited_by_count":192},{"id":"2102.10757","title":"Self-Supervised Learning of Graph Neural Networks: A Unified Review","created":"2021-02-22","cited_by_count":184},{"id":"2402.08170","title":"LLaGA: Large Language and Graph Assistant","created":"2024-02-13","cited_by_count":181},{"id":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"1805.11080","title":"Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting","created":"2018-05-28","cited_by_count":158},{"id":"2111.00064","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","created":"2021-10-29","cited_by_count":138},{"id":"2105.07342","title":"Self-supervised Learning on Graphs: Contrastive, Generative,or Predictive","created":"2021-05-16","cited_by_count":136},{"id":"2304.04779","title":"GraphMAE2: A Decoding-Enhanced Masked Self-Supervised Graph Learner","created":"2023-04-10","cited_by_count":132},{"id":"2310.01089","title":"GraphText: Graph Reasoning in Text Space","created":"2023-10-02","cited_by_count":111},{"id":"2305.12600","title":"PRODIGY: Enabling In-context Learning Over Graphs","created":"2023-05-21","cited_by_count":98},{"id":"2402.11235","title":"ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs","created":"2024-02-17","cited_by_count":85},{"id":"2411.06070","title":"GFT: Graph Foundation Model with Transferable Tree Vocabulary","created":"2024-11-09","cited_by_count":85},{"id":"2403.01121","title":"OpenGraph: Towards Open Graph Foundation Models","created":"2024-03-02","cited_by_count":78},{"id":"2308.02565","title":"SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning","created":"2023-08-03","cited_by_count":73},{"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":"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":"2408.10700","title":"AnyGraph: Graph Foundation Model in the Wild","created":"2024-08-20","cited_by_count":53},{"id":"2405.13934","title":"Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models","created":"2024-05-22","cited_by_count":42},{"id":"2310.18152","title":"Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs","created":"2023-10-27","cited_by_count":36},{"id":"2503.03313","title":"LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models","created":"2025-03-05","cited_by_count":22},{"id":"2502.00829","title":"When Do LLMs Help With Node Classification? A Comprehensive Analysis","created":"2025-02-02","cited_by_count":21},{"id":"2308.14522","title":"Graph Meets LLMs: Towards Large Graph Models","created":"2023-08-28","cited_by_count":20},{"id":"2404.14986","title":"$\\texttt{MiniMol}$: A Parameter-Efficient Foundation Model for Molecular Learning","created":"2024-04-23","cited_by_count":20},{"id":"2305.14826","title":"Building Transportation Foundation Model via Generative Graph Transformer","created":"2023-05-24","cited_by_count":19},{"id":"2208.09905","title":"MentorGNN: Deriving Curriculum for Pre-Training GNNs","created":"2022-08-21","cited_by_count":18},{"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":"2404.07198","title":"A Foundation Model for Zero-shot Logical Query Reasoning","created":"2024-04-10","cited_by_count":14},{"id":"2502.18771","title":"Exploring Graph Learning Tasks with Pure LLMs: A Comprehensive Benchmark and Investigation","created":"2025-02-26","cited_by_count":12},{"id":"2305.15743","title":"TransWorldNG: Traffic Simulation via Foundation Model","created":"2023-05-25","cited_by_count":9},{"id":"2502.08346","title":"Graph Foundation Models for Recommendation: A Comprehensive Survey","created":"2025-02-12","cited_by_count":4}],"next_cursor":null}