{"list":"other","total":51,"rows":[{"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":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1806.01973","title":"Graph Convolutional Neural Networks for Web-Scale Recommender Systems","created":"2018-06-06","cited_by_count":1138},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"1905.05178","title":"Graph U-Nets","created":"2019-05-11","cited_by_count":492},{"id":"1809.09401","title":"Hypergraph Neural Networks","created":"2018-09-25","cited_by_count":488},{"id":"1611.08402","title":"Geometric deep learning on graphs and manifolds using mixture model CNNs","created":"2016-11-25","cited_by_count":468},{"id":"1804.06561","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","created":"2018-04-18","cited_by_count":466},{"id":"1805.09545","title":"On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport","created":"2018-05-24","cited_by_count":426},{"id":"1908.05355","title":"The generalization error of random features regression: Precise asymptotics and double descent curve","created":"2019-08-14","cited_by_count":413},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"2103.09177","title":"Deep learning: a statistical viewpoint","created":"2021-03-16","cited_by_count":240},{"id":"1511.06391","title":"Order Matters: Sequence to sequence for sets","created":"2015-11-19","cited_by_count":237},{"id":"1905.13210","title":"Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks","created":"2019-05-30","cited_by_count":222},{"id":"2002.06157","title":"Generalization and Representational Limits of Graph Neural Networks","created":"2020-02-14","cited_by_count":218},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"1902.06015","title":"Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit","created":"2019-02-16","cited_by_count":187},{"id":"1905.13192","title":"Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels","created":"2019-05-30","cited_by_count":161},{"id":"1904.12191","title":"Linearized two-layers neural networks in high dimension","created":"2019-04-27","cited_by_count":155},{"id":"1603.05629","title":"Discriminative Embeddings of Latent Variable Models for Structured Data","created":"2016-03-17","cited_by_count":131},{"id":"1803.02349","title":"Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba","created":"2018-03-06","cited_by_count":105},{"id":"1811.01287","title":"Towards Sparse Hierarchical Graph Classifiers","created":"2018-11-03","cited_by_count":100},{"id":"1905.10337","title":"What Can ResNet Learn Efficiently, Going Beyond Kernels?","created":"2019-05-24","cited_by_count":91},{"id":"2012.07690","title":"A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks","created":"2020-12-14","cited_by_count":85},{"id":"1905.01004","title":"Stability and Generalization of Graph Convolutional Neural Networks","created":"2019-05-03","cited_by_count":81},{"id":"2010.11418","title":"Rethinking pooling in graph neural networks","created":"2020-10-22","cited_by_count":73},{"id":"1810.09665","title":"A jamming transition from under- to over-parametrization affects loss landscape and generalization","created":"2018-10-22","cited_by_count":67},{"id":"2202.00645","title":"Generalization Analysis of Message Passing Neural Networks on Large Random Graphs","created":"2022-02-01","cited_by_count":59},{"id":"2110.15174","title":"On Provable Benefits of Depth in Training Graph Convolutional Networks","created":"2021-10-28","cited_by_count":58},{"id":"2112.03968","title":"Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks","created":"2021-12-07","cited_by_count":51},{"id":"1905.07769","title":"Mean-Field Langevin Dynamics and Energy Landscape of Neural Networks","created":"2019-05-19","cited_by_count":50},{"id":"1910.12799","title":"Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space","created":"2019-10-28","cited_by_count":46},{"id":"1903.04440","title":"Mean Field Analysis of Deep Neural Networks","created":"2019-03-11","cited_by_count":42},{"id":"2305.08048","title":"Towards Understanding the Generalization of Graph Neural Networks","created":"2023-05-14","cited_by_count":41},{"id":"2302.04451","title":"Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion","created":"2023-02-09","cited_by_count":40},{"id":"2006.08550","title":"Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks","created":"2020-06-15","cited_by_count":31},{"id":"2006.14117","title":"Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Case","created":"2020-06-25","cited_by_count":24},{"id":"2207.03584","title":"Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling","created":"2022-07-07","cited_by_count":23},{"id":"2012.15477","title":"Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis","created":"2020-12-31","cited_by_count":21},{"id":"2102.10234","title":"Generalization bounds for graph convolutional neural networks via Rademacher complexity","created":"2021-02-20","cited_by_count":17},{"id":"2012.13982","title":"Mathematical Models of Overparameterized Neural Networks","created":"2020-12-27","cited_by_count":15},{"id":"2306.11623","title":"Mean-field Analysis of Generalization Errors","created":"2023-06-20","cited_by_count":5}],"next_cursor":null}