{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"2101.00797","title":"Beyond Low-frequency Information in Graph Convolutional Networks","created":"2021-01-04","cited_by_count":362},{"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":"2006.07739","title":"DeeperGCN: All You Need to Train Deeper GCNs","created":"2020-06-13","cited_by_count":250},{"id":"2308.07134","title":"Language is All a Graph Needs","created":"2023-08-14","cited_by_count":220},{"id":"2106.10994","title":"BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation","created":"2021-06-21","cited_by_count":195},{"id":"2310.04560","title":"Talk like a Graph: Encoding Graphs for Large Language Models","created":"2023-10-06","cited_by_count":176},{"id":"2311.00423","title":"LLMRec: Large Language Models with Graph Augmentation for Recommendation","created":"2023-11-01","cited_by_count":172},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169},{"id":"2210.07606","title":"Revisiting Heterophily For Graph Neural Networks","created":"2022-10-14","cited_by_count":169},{"id":"2111.00064","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","created":"2021-10-29","cited_by_count":138},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"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":"2012.14660","title":"A Theoretical Analysis of the Repetition Problem in Text Generation","created":"2020-12-29","cited_by_count":83},{"id":"2308.02565","title":"SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning","created":"2023-08-03","cited_by_count":73},{"id":"2110.00685","title":"Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification","created":"2021-10-01","cited_by_count":67},{"id":"2307.07443","title":"Can Large Language Models Empower Molecular Property Prediction?","created":"2023-07-14","cited_by_count":44},{"id":"2010.12751","title":"Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization","created":"2020-10-24","cited_by_count":40},{"id":"2309.02848","title":"Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphs","created":"2023-09-06","cited_by_count":23},{"id":"2104.07892","title":"Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks","created":"2021-04-16","cited_by_count":22},{"id":"2310.07328","title":"An Empirical Study of Instruction-tuning Large Language Models in Chinese","created":"2023-10-11","cited_by_count":17},{"id":"2402.04978","title":"An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration","created":"2024-02-07","cited_by_count":16},{"id":"2309.13885","title":"TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning","created":"2023-09-25","cited_by_count":12},{"id":"2312.16926","title":"Efficient High-Quality Clustering for Large Bipartite Graphs","created":"2023-12-28","cited_by_count":11},{"id":"2208.04609","title":"E2EG: End-to-End Node Classification Using Graph Topology and Text-based Node Attributes","created":"2022-08-09","cited_by_count":7},{"id":"2204.12802","title":"GTNet: A Tree-Based Deep Graph Learning Architecture","created":"2022-04-27","cited_by_count":3}],"next_cursor":null}