{"list":"other","total":92,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"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":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1509.09292","title":"Convolutional Networks on Graphs for Learning Molecular Fingerprints","created":"2015-09-30","cited_by_count":754},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"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":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"id":"1308.0850","title":"Generating Sequences With Recurrent Neural Networks","created":"2013-08-04","cited_by_count":554},{"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":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2004.05718","title":"Principal Neighbourhood Aggregation for Graph Nets","created":"2020-04-12","cited_by_count":478},{"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":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"2110.07875","title":"Graph Neural Networks with Learnable Structural and Positional Representations","created":"2021-10-15","cited_by_count":333},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"2303.10993","title":"A Survey on Oversmoothing in Graph Neural Networks","created":"2023-03-20","cited_by_count":247},{"id":"2002.04025","title":"Can Graph Neural Networks Count Substructures?","created":"2020-02-10","cited_by_count":236},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2101.10320","title":"Identity-aware Graph Neural Networks","created":"2021-01-25","cited_by_count":198},{"id":"2202.03036","title":"Structure-Aware Transformer for Graph Representation Learning","created":"2022-02-07","cited_by_count":194},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188},{"id":"2202.13013","title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","created":"2022-02-25","cited_by_count":179},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"id":"2205.11172","title":"How Powerful are Spectral Graph Neural Networks","created":"2022-05-23","cited_by_count":169},{"id":"2302.02941","title":"On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology","created":"2023-02-06","cited_by_count":166},{"id":"2110.03753","title":"From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness","created":"2021-10-07","cited_by_count":155},{"id":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147},{"id":"2110.13197","title":"Nested Graph Neural Networks","created":"2021-10-25","cited_by_count":137},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136},{"id":"2402.00789","title":"Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces","created":"2024-02-01","cited_by_count":134},{"id":"2010.02863","title":"Directional Graph Networks","created":"2020-10-06","cited_by_count":133},{"id":"2306.10759","title":"SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations","created":"2023-06-19","cited_by_count":133},{"id":"2206.11140","title":"Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries","created":"2022-06-22","cited_by_count":112},{"id":"2205.12156","title":"Not too little, not too much: a theoretical analysis of graph (over)smoothing","created":"2022-05-24","cited_by_count":106},{"id":"2303.14526","title":"Selective Structured State-Spaces for Long-Form Video Understanding","created":"2023-03-25","cited_by_count":105},{"id":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102},{"id":"2211.15779","title":"Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature","created":"2022-11-28","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":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87},{"id":"2402.08678","title":"Graph Mamba: Towards Learning on Graphs with State Space Models","created":"2024-02-13","cited_by_count":86},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58},{"id":"2210.13978","title":"Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs","created":"2022-10-22","cited_by_count":56},{"id":"2011.07682","title":"A Large-Scale Database for Graph Representation Learning","created":"2020-11-16","cited_by_count":55},{"id":"1407.5107","title":"PageRank beyond the Web","created":"2014-07-18","cited_by_count":51},{"id":"2010.05315","title":"SMYRF: Efficient Attention using Asymmetric Clustering","created":"2020-10-11","cited_by_count":43},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43},{"id":"1905.10881","title":"Optimizing Generalized PageRank Methods for Seed-Expansion Community Detection","created":"2019-05-26","cited_by_count":35},{"id":"2210.15956","title":"Generalized Laplacian Positional Encoding for Graph Representation Learning","created":"2022-10-28","cited_by_count":21},{"id":"2206.11941","title":"Affinity-Aware Graph Networks","created":"2022-06-23","cited_by_count":17},{"id":"2305.00156","title":"Taming graph kernels with random features","created":"2023-04-29","cited_by_count":17},{"id":"2406.04336","title":"On the Expressive Power of Spectral Invariant Graph Neural Networks","created":"2024-06-06","cited_by_count":15},{"id":"2402.12535","title":"Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics","created":"2024-02-19","cited_by_count":12},{"id":"2312.01538","title":"Recurrent Distance Filtering for Graph Representation Learning","created":"2023-12-03","cited_by_count":11},{"id":"2305.12470","title":"Quasi-Monte Carlo Graph Random Features","created":"2023-05-21","cited_by_count":9},{"id":"2405.13915","title":"HeteGraph-Mamba: Heterogeneous Graph Learning via Selective State Space Model","created":"2024-05-22","cited_by_count":3}],"next_cursor":null}