{"list":"other","total":53,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"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":"1806.01973","title":"Graph Convolutional Neural Networks for Web-Scale Recommender Systems","created":"2018-06-06","cited_by_count":1138},{"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":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"2007.08663","title":"TUDataset: A collection of benchmark datasets for learning with graphs","created":"2020-07-16","cited_by_count":728},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"2009.03509","title":"Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification","created":"2020-09-08","cited_by_count":506},{"id":"2106.03893","title":"Rethinking Graph Transformers with Spectral Attention","created":"2021-06-07","cited_by_count":473},{"id":"1712.00468","title":"Graph Signal Processing: Overview, Challenges and Applications","created":"2017-12-01","cited_by_count":413},{"id":"1711.07553","title":"Residual Gated Graph ConvNets","created":"2017-11-20","cited_by_count":346},{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"1511.06391","title":"Order Matters: Sequence to sequence for sets","created":"2015-11-19","cited_by_count":237},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2106.10994","title":"BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation","created":"2021-06-21","cited_by_count":195},{"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":"2205.11172","title":"How Powerful are Spectral Graph Neural Networks","created":"2022-05-23","cited_by_count":169},{"id":"1905.13192","title":"Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels","created":"2019-05-30","cited_by_count":161},{"id":"2305.17589","title":"Graph Inductive Biases in Transformers without Message Passing","created":"2023-05-27","cited_by_count":153},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"1707.04926","title":"Theoretical insights into the optimization landscape of over-parameterized shallow neural networks","created":"2017-07-16","cited_by_count":128},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114},{"id":"1803.01206","title":"On the Power of Over-parametrization in Neural Networks with Quadratic Activation","created":"2018-03-03","cited_by_count":102},{"id":"1805.00165","title":"Convolutional Neural Network Architectures for Signals Supported on Graphs","created":"2018-05-01","cited_by_count":95},{"id":"1904.13107","title":"Graph Convolutional Networks with EigenPooling","created":"2019-04-30","cited_by_count":94},{"id":"2305.10498","title":"Edge Directionality Improves Learning on Heterophilic Graphs","created":"2023-05-17","cited_by_count":90},{"id":"1403.4699","title":"A Proximal Stochastic Gradient Method with Progressive Variance Reduction","created":"2014-03-19","cited_by_count":78},{"id":"1307.0468","title":"Discrete Signal Processing on Graphs: Frequency Analysis","created":"2013-07-01","cited_by_count":73},{"id":"1806.08829","title":"Diffusion Scattering Transforms on Graphs","created":"2018-06-22","cited_by_count":44},{"id":"1807.00504","title":"Deep Reasoning with Knowledge Graph for Social Relationship Understanding","created":"2018-07-02","cited_by_count":44},{"id":"2302.12432","title":"Graph Neural Networks with Learnable and Optimal Polynomial Bases","created":"2023-02-24","cited_by_count":36},{"id":"1906.04784","title":"Stability of Graph Scattering Transforms","created":"2019-06-11","cited_by_count":34},{"id":"2008.01305","title":"A User Guide to Low-Pass Graph Signal Processing and its Applications","created":"2020-08-04","cited_by_count":25},{"id":"2107.10234","title":"Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks","created":"2021-07-21","cited_by_count":19},{"id":"1510.03528","title":"$\\ell_1$-regularized Neural Networks are Improperly Learnable in Polynomial Time","created":"2015-10-13","cited_by_count":16},{"id":"2301.10808","title":"Graph Neural Tangent Kernel: Convergence on Large Graphs","created":"2023-01-25","cited_by_count":16},{"id":"2503.01805","title":"Depth-Width tradeoffs in Algorithmic Reasoning of Graph Tasks with Transformers","created":"2025-03-03","cited_by_count":11},{"id":"1609.01000","title":"Convexified Convolutional Neural Networks","created":"2016-09-04","cited_by_count":9},{"id":"2010.04686","title":"Converging to a Desired Orientation in a Flock of Agents","created":"2020-10-09","cited_by_count":1}],"next_cursor":null}