{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"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":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"1806.03536","title":"Representation Learning on Graphs with Jumping Knowledge Networks","created":"2018-06-09","cited_by_count":877},{"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":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"id":"1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","created":"2017-06-26","cited_by_count":571},{"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":"1904.08082","title":"Self-Attention Graph Pooling","created":"2019-04-17","cited_by_count":421},{"id":"1911.05485","title":"Diffusion Improves Graph Learning","created":"2019-10-28","cited_by_count":414},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"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":"2206.08164","title":"Long Range Graph Benchmark","created":"2022-06-16","cited_by_count":263},{"id":"2106.10994","title":"BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation","created":"2021-06-21","cited_by_count":195},{"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":"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":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153},{"id":"2010.02863","title":"Directional Graph Networks","created":"2020-10-06","cited_by_count":133},{"id":"1905.04497","title":"Stability Properties of Graph Neural Networks","created":"2019-05-11","cited_by_count":127},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"2102.11391","title":"MagNet: A Neural Network for Directed Graphs","created":"2021-02-22","cited_by_count":107},{"id":"2206.04301","title":"Unveiling Transformers with LEGO: a synthetic reasoning task","created":"2022-06-09","cited_by_count":106},{"id":"2303.01028","title":"Specformer: Spectral Graph Neural Networks Meet Transformers","created":"2023-03-02","cited_by_count":102},{"id":"2106.04319","title":"Breaking the Limits of Message Passing Graph Neural Networks","created":"2021-06-08","cited_by_count":101},{"id":"2203.00199","title":"Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks","created":"2022-03-01","cited_by_count":94},{"id":"2212.13350","title":"A Generalization of ViT/MLP-Mixer to Graphs","created":"2022-12-27","cited_by_count":93},{"id":"2305.10498","title":"Edge Directionality Improves Learning on Heterophilic Graphs","created":"2023-05-17","cited_by_count":90},{"id":"2202.03580","title":"Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited","created":"2022-02-04","cited_by_count":87},{"id":"2310.04562","title":"Towards Foundation Models for Knowledge Graph Reasoning","created":"2023-10-06","cited_by_count":86},{"id":"2402.08678","title":"Graph Mamba: Towards Learning on Graphs with State Space Models","created":"2024-02-13","cited_by_count":86},{"id":"2309.00367","title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","created":"2023-09-01","cited_by_count":85},{"id":"1901.01484","title":"LanczosNet: Multi-Scale Deep Graph Convolutional Networks","created":"2019-01-06","cited_by_count":73},{"id":"2004.13970","title":"Directed Graph Convolutional Network","created":"2020-04-29","cited_by_count":73},{"id":"2403.01232","title":"Polynormer: Polynomial-Expressive Graph Transformer in Linear Time","created":"2024-03-02","cited_by_count":65},{"id":"2301.11956","title":"On the Connection Between MPNN and Graph Transformer","created":"2023-01-27","cited_by_count":61},{"id":"2006.12179","title":"Hierarchical Inter-Message Passing for Learning on Molecular Graphs","created":"2020-06-22","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":"2303.04791","title":"Ewald-based Long-Range Message Passing for Molecular Graphs","created":"2023-03-08","cited_by_count":46},{"id":"2302.00049","title":"Transformers Meet Directed Graphs","created":"2023-01-31","cited_by_count":40},{"id":"2302.12432","title":"Graph Neural Networks with Learnable and Optimal Polynomial Bases","created":"2023-02-24","cited_by_count":36},{"id":"2306.05955","title":"Path Neural Networks: Expressive and Accurate Graph Neural Networks","created":"2023-06-09","cited_by_count":32},{"id":"2302.05631","title":"A Survey on Spectral Graph Neural Networks","created":"2023-02-11","cited_by_count":26},{"id":"2002.03864","title":"Deep Graph Mapper: Seeing Graphs through the Neural Lens","created":"2020-02-10","cited_by_count":22},{"id":"2310.02232","title":"HoloNets: Spectral Convolutions do extend to Directed Graphs","created":"2023-10-03","cited_by_count":20},{"id":"2101.00079","title":"Graph Networks with Spectral Message Passing","created":"2020-12-31","cited_by_count":17},{"id":"2308.11129","title":"Enhancing Graph Transformers with Hierarchical Distance Structural Encoding","created":"2023-08-22","cited_by_count":16},{"id":"2308.13490","title":"TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs","created":"2023-08-25","cited_by_count":16},{"id":"1812.04379","title":"On the expressive power of linear algebra on graphs","created":"2018-12-11","cited_by_count":14},{"id":"2209.12054","title":"From Local to Global: Spectral-Inspired Graph Neural Networks","created":"2022-09-24","cited_by_count":11},{"id":"2305.11424","title":"Graph Propagation Transformer for Graph Representation Learning","created":"2023-05-19","cited_by_count":9},{"id":"2305.12322","title":"Learning Large Graph Property Prediction via Graph Segment Training","created":"2023-05-21","cited_by_count":9},{"id":"2205.15678","title":"Automatic Relation-aware Graph Network Proliferation","created":"2022-05-31","cited_by_count":6},{"id":"2302.08647","title":"Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures","created":"2023-02-17","cited_by_count":4},{"id":"2305.06102","title":"Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering","created":"2023-05-10","cited_by_count":4},{"id":"2310.10434","title":"Equivariant Matrix Function Neural Networks","created":"2023-10-16","cited_by_count":3}],"next_cursor":null}