{"list":"other","total":52,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"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":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2003.00982","title":"Benchmarking Graph Neural Networks","created":"2020-03-02","cited_by_count":680},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"1801.10247","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","created":"2018-01-30","cited_by_count":584},{"id":"1909.03211","title":"Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View","created":"2019-09-07","cited_by_count":545},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"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":"2310.01889","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","created":"2023-10-03","cited_by_count":457},{"id":"2205.05198","title":"Reducing Activation Recomputation in Large Transformer Models","created":"2022-05-10","cited_by_count":302},{"id":"2206.11990","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","created":"2022-06-23","cited_by_count":264},{"id":"2010.09990","title":"The Open Catalyst 2020 (OC20) Dataset and Community Challenges","created":"2020-10-20","cited_by_count":246},{"id":"2309.14509","title":"DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models","created":"2023-09-25","cited_by_count":245},{"id":"2012.09852","title":"SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning","created":"2020-12-17","cited_by_count":234},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"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":"2001.05140","title":"Graph-Bert: Only Attention is Needed for Learning Graph Representations","created":"2020-01-15","cited_by_count":177},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"id":"1911.02972","title":"Blockwise Self-Attention for Long Document Understanding","created":"2019-11-07","cited_by_count":159},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133},{"id":"2105.13120","title":"Sequence Parallelism: Long Sequence Training from System Perspective","created":"2021-05-26","cited_by_count":126},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"2301.09474","title":"DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion","created":"2023-01-23","cited_by_count":87},{"id":"2006.04862","title":"$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers","created":"2020-06-08","cited_by_count":83},{"id":"2010.00130","title":"Computing Graph Neural Networks: A Survey from Algorithms to Accelerators","created":"2020-09-30","cited_by_count":81},{"id":"2110.13094","title":"Gophormer: Ego-Graph Transformer for Node Classification","created":"2021-10-25","cited_by_count":63},{"id":"2011.07682","title":"A Large-Scale Database for Graph Representation Learning","created":"2020-11-16","cited_by_count":55},{"id":"2006.06608","title":"GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUs","created":"2020-06-11","cited_by_count":51},{"id":"2001.10667","title":"Interpretable Rumor Detection in Microblogs by Attending to User Interactions","created":"2020-01-29","cited_by_count":44},{"id":"1711.02782","title":"Block-Sparse Recurrent Neural Networks","created":"2017-11-08","cited_by_count":39},{"id":"2201.13311","title":"Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer","created":"2022-01-25","cited_by_count":13},{"id":"1307.7729","title":"Spectral methods for network community detection and graph partitioning","created":"2013-07-29","cited_by_count":1}],"next_cursor":null}