{"list":"other","total":55,"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"1506.04757","title":"Image-based Recommendations on Styles and Substitutes","created":"2015-06-15","cited_by_count":706},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"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":"1909.13021","title":"Multi-scale Attributed Node Embedding","created":"2019-09-28","cited_by_count":548},{"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":"1709.05584","title":"Representation Learning on Graphs: Methods and Applications","created":"2017-09-17","cited_by_count":457},{"id":"1905.00067","title":"MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing","created":"2019-04-30","cited_by_count":443},{"id":"2101.00797","title":"Beyond Low-frequency Information in Graph Convolutional Networks","created":"2021-01-04","cited_by_count":362},{"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":"2310.00149","title":"One for All: Towards Training One Graph Model for All Classification Tasks","created":"2023-09-29","cited_by_count":243},{"id":"2201.08821","title":"Representing Long-Range Context for Graph Neural Networks with Global Attention","created":"2022-01-21","cited_by_count":195},{"id":"2202.03036","title":"Structure-Aware Transformer for Graph Representation Learning","created":"2022-02-07","cited_by_count":194},{"id":"2102.06462","title":"Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks","created":"2021-02-12","cited_by_count":182},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2204.04879","title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","created":"2022-04-11","cited_by_count":102},{"id":"2310.04562","title":"Towards Foundation Models for Knowledge Graph Reasoning","created":"2023-10-06","cited_by_count":86},{"id":"2402.02216","title":"Position: Graph Foundation Models are Already Here","created":"2024-02-03","cited_by_count":86},{"id":"2402.09834","title":"All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining","created":"2024-02-15","cited_by_count":86},{"id":"2210.02997","title":"Expander Graph Propagation","created":"2022-10-06","cited_by_count":75},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72},{"id":"2310.16046","title":"A Unified, Scalable Framework for Neural Population Decoding","created":"2023-10-24","cited_by_count":61},{"id":"2209.11142","title":"A Generalist Neural Algorithmic Learner","created":"2022-09-22","cited_by_count":59},{"id":"2203.00112","title":"GraphWorld: Fake Graphs Bring Real Insights for GNNs","created":"2022-02-28","cited_by_count":56},{"id":"2405.13934","title":"Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models","created":"2024-05-22","cited_by_count":42},{"id":"2310.04292","title":"Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets","created":"2023-10-06","cited_by_count":39},{"id":"2204.01376","title":"Synthetic Graph Generation to Benchmark Graph Learning","created":"2022-04-04","cited_by_count":16},{"id":"2308.09198","title":"Half-Hop: A graph upsampling approach for slowing down message passing","created":"2023-08-17","cited_by_count":13},{"id":"2402.02054","title":"Towards Neural Scaling Laws on Graphs","created":"2024-02-03","cited_by_count":13},{"id":"2202.10581","title":"Unleashing the Power of Transformer for Graphs","created":"2022-02-18","cited_by_count":6},{"id":"2312.16788","title":"Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures","created":"2023-12-28","cited_by_count":6},{"id":"2402.09565","title":"Graph-Skeleton: ~1% Nodes are Sufficient to Represent Billion-Scale Graph","created":"2024-02-14","cited_by_count":6},{"id":"2209.06354","title":"Tuple Packing: Efficient Batching of Small Graphs in Graph Neural Networks","created":"2022-09-14","cited_by_count":1}],"next_cursor":null}