{"list":"other","total":128,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"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":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2007.08663","title":"TUDataset: A collection of benchmark datasets for learning with graphs","created":"2020-07-16","cited_by_count":728},{"id":"2006.05582","title":"Contrastive Multi-View Representation Learning on Graphs","created":"2020-06-10","cited_by_count":652},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"id":"2209.14734","title":"DiGress: Discrete Denoising diffusion for graph generation","created":"2022-09-29","cited_by_count":520},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"id":"1911.03082","title":"Composition-based Multi-Relational Graph Convolutional Networks","created":"2019-11-08","cited_by_count":396},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2110.14446","title":"Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods","created":"2021-10-27","cited_by_count":311},{"id":"2202.02514","title":"Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations","created":"2022-02-05","cited_by_count":283},{"id":"2106.06935","title":"Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction","created":"2021-06-13","cited_by_count":275},{"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":"2006.13318","title":"A Note on Over-Smoothing for Graph Neural Networks","created":"2020-06-23","cited_by_count":249},{"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":"2308.07134","title":"Language is All a Graph Needs","created":"2023-08-14","cited_by_count":220},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2002.03230","title":"Hierarchical Generation of Molecular Graphs using Structural Motifs","created":"2020-02-08","cited_by_count":208},{"id":"1906.04817","title":"Position-aware Graph Neural Networks","created":"2019-06-11","cited_by_count":203},{"id":"2101.10320","title":"Identity-aware Graph Neural Networks","created":"2021-01-25","cited_by_count":198},{"id":"2312.02783","title":"Large Language Models on Graphs: A Comprehensive Survey","created":"2023-12-05","cited_by_count":192},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2106.06134","title":"Is Homophily a Necessity for Graph Neural Networks?","created":"2021-06-11","cited_by_count":182},{"id":"2102.01189","title":"GraphDF: A Discrete Flow Model for Molecular Graph Generation","created":"2021-02-01","cited_by_count":180},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178},{"id":"2310.04560","title":"Talk like a Graph: Encoding Graphs for Large Language Models","created":"2023-10-06","cited_by_count":176},{"id":"1905.13211","title":"What Can Neural Networks Reason About?","created":"2019-05-30","cited_by_count":159},{"id":"2210.09338","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","created":"2022-10-17","cited_by_count":156},{"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":"1903.11835","title":"A Survey on Graph Kernels","created":"2019-03-28","cited_by_count":148},{"id":"2307.01504","title":"All in One: Multi-task Prompting for Graph Neural Networks","created":"2023-07-04","cited_by_count":148},{"id":"2307.01026","title":"Temporal Graph Benchmark for Machine Learning on Temporal Graphs","created":"2023-07-03","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":"2006.01764","title":"Networks beyond pairwise interactions: structure and dynamics","created":"2020-06-02","cited_by_count":130},{"id":"2305.19420","title":"What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization","created":"2023-05-30","cited_by_count":118},{"id":"2109.01116","title":"An Empirical Study of Graph Contrastive Learning","created":"2021-09-02","cited_by_count":113},{"id":"2310.01089","title":"GraphText: Graph Reasoning in Text Space","created":"2023-10-02","cited_by_count":111},{"id":"1612.08447","title":"Higher-order organization of complex networks","created":"2016-12-26","cited_by_count":110},{"id":"2006.10141","title":"Self-supervised Learning on Graphs: Deep Insights and New Direction","created":"2020-06-17","cited_by_count":108},{"id":"2310.05845","title":"GraphLLM: Boosting Graph Reasoning Ability of Large Language Model","created":"2023-10-09","cited_by_count":107},{"id":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106},{"id":"2304.03843","title":"Why think step by step? Reasoning emerges from the locality of experience","created":"2023-04-07","cited_by_count":103},{"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":"2203.00199","title":"Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks","created":"2022-03-01","cited_by_count":94},{"id":"2106.05609","title":"GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings","created":"2021-06-10","cited_by_count":90},{"id":"2310.12397","title":"GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems","created":"2023-10-19","cited_by_count":89},{"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":"2302.04181","title":"Attending to Graph Transformers","created":"2023-02-08","cited_by_count":83},{"id":"2306.04891","title":"In-Context Learning through the Bayesian Prism","created":"2023-06-08","cited_by_count":83},{"id":"2109.05641","title":"Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?","created":"2021-09-12","cited_by_count":82},{"id":"2209.15486","title":"Graph Neural Networks for Link Prediction with Subgraph Sketching","created":"2022-09-30","cited_by_count":81},{"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":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64},{"id":"2302.00890","title":"Neural Common Neighbor with Completion for Link Prediction","created":"2023-02-02","cited_by_count":64},{"id":"2103.06064","title":"Graph Neural Networks Inspired by Classical Iterative Algorithms","created":"2021-03-10","cited_by_count":60},{"id":"2209.11142","title":"A Generalist Neural Algorithmic Learner","created":"2022-09-22","cited_by_count":59},{"id":"2306.03589","title":"How does over-squashing affect the power of GNNs?","created":"2023-06-06","cited_by_count":53},{"id":"2311.02089","title":"LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking","created":"2023-10-25","cited_by_count":53},{"id":"2210.12714","title":"Generative Knowledge Graph Construction: A Review","created":"2022-10-23","cited_by_count":49},{"id":"2305.12268","title":"Patton: Language Model Pretraining on Text-Rich Networks","created":"2023-05-20","cited_by_count":49},{"id":"2310.14753","title":"Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules","created":"2023-10-23","cited_by_count":49},{"id":"2007.04583","title":"Graph Convolutional Networks for Graphs Containing Missing Features","created":"2020-07-09","cited_by_count":47},{"id":"2112.04629","title":"Transferability Properties of Graph Neural Networks","created":"2021-12-09","cited_by_count":43},{"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":"2209.12288","title":"On Representing Linear Programs by Graph Neural Networks","created":"2022-09-25","cited_by_count":39},{"id":"2310.04292","title":"Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets","created":"2023-10-06","cited_by_count":39},{"id":"2401.08514","title":"Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness","created":"2024-01-16","cited_by_count":39}],"next_cursor":"100"}