{"list":"other","total":60,"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":"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"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":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2002.10957","title":"MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers","created":"2020-02-25","cited_by_count":1463},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"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":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"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":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"id":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333},{"id":"2408.08921","title":"Graph Retrieval-Augmented Generation: A Survey","created":"2024-08-15","cited_by_count":324},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"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":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2106.05819","title":"Adversarial Graph Augmentation to Improve Graph Contrastive Learning","created":"2021-06-10","cited_by_count":200},{"id":"2312.02783","title":"Large Language Models on Graphs: A Comprehensive Survey","created":"2023-12-05","cited_by_count":192},{"id":"2402.08170","title":"LLaGA: Large Language and Graph Assistant","created":"2024-02-13","cited_by_count":181},{"id":"2302.08043","title":"GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks","created":"2023-02-16","cited_by_count":167},{"id":"2210.14709","title":"Learning on Large-scale Text-attributed Graphs via Variational Inference","created":"2022-10-26","cited_by_count":155},{"id":"2307.01504","title":"All in One: Multi-task Prompting for Graph Neural Networks","created":"2023-07-04","cited_by_count":148},{"id":"2105.02605","title":"GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph","created":"2021-05-06","cited_by_count":143},{"id":"2310.01089","title":"GraphText: Graph Reasoning in Text Space","created":"2023-10-02","cited_by_count":111},{"id":"2311.12399","title":"A Survey of Graph Meets Large Language Model: Progress and Future Directions","created":"2023-11-21","cited_by_count":85},{"id":"2402.11235","title":"ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs","created":"2024-02-17","cited_by_count":85},{"id":"2402.12984","title":"Can GNN be Good Adapter for LLMs?","created":"2024-02-20","cited_by_count":71},{"id":"2305.03324","title":"Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting","created":"2023-05-05","cited_by_count":62},{"id":"2401.15569","title":"Efficient Tuning and Inference for Large Language Models on Textual Graphs","created":"2024-01-28","cited_by_count":54},{"id":"2407.07457","title":"GLBench: A Comprehensive Benchmark for Graph with Large Language Models","created":"2024-07-10","cited_by_count":36},{"id":"2209.05227","title":"DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization","created":"2022-09-12","cited_by_count":35},{"id":"2302.12449","title":"SGL-PT: A Strong Graph Learner with Graph Prompt Tuning","created":"2023-02-24","cited_by_count":35},{"id":"2310.07365","title":"GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning","created":"2023-10-11","cited_by_count":33},{"id":"2305.14321","title":"ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings","created":"2023-05-23","cited_by_count":32},{"id":"2405.01926","title":"Auto-Encoding Morph-Tokens for Multimodal LLM","created":"2024-05-03","cited_by_count":30},{"id":"2303.12314","title":"Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization","created":"2023-03-22","cited_by_count":15},{"id":"2309.13078","title":"LPML: LLM-Prompting Markup Language for Mathematical Reasoning","created":"2023-09-21","cited_by_count":15},{"id":"2406.12608","title":"Bridging Local Details and Global Context in Text-Attributed Graphs","created":"2024-06-18","cited_by_count":15},{"id":"2310.08279","title":"Enhancing Text-based Knowledge Graph Completion with Zero-Shot Large Language Models: A Focus on Semantic Enhancement","created":"2023-10-12","cited_by_count":14},{"id":"2204.13846","title":"RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning","created":"2022-04-29","cited_by_count":12},{"id":"2303.01092","title":"ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations","created":"2023-03-02","cited_by_count":10},{"id":"2307.13055","title":"MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learning","created":"2023-07-24","cited_by_count":7},{"id":"2407.19420","title":"UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks","created":"2024-07-28","cited_by_count":3},{"id":"2408.07654","title":"Graph Triple Attention Network: A Decoupled Perspective","created":"2024-08-14","cited_by_count":2}],"next_cursor":null}