{"list":"other","total":61,"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":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"1806.03536","title":"Representation Learning on Graphs with Jumping Knowledge Networks","created":"2018-06-09","cited_by_count":877},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"1906.00121","title":"Graph WaveNet for Deep Spatial-Temporal Graph Modeling","created":"2019-05-31","cited_by_count":829},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"2302.11640","title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","created":"2023-02-22","cited_by_count":343},{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1909.12223","title":"PairNorm: Tackling Oversmoothing in GNNs","created":"2019-09-26","cited_by_count":297},{"id":"2007.09296","title":"Towards Deeper Graph Neural Networks","created":"2020-07-18","cited_by_count":296},{"id":"1603.00856","title":"Molecular Graph Convolutions: Moving Beyond Fingerprints","created":"2016-03-02","cited_by_count":238},{"id":"1810.02281","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","created":"2018-10-04","cited_by_count":184},{"id":"2011.08843","title":"Design Space for Graph Neural Networks","created":"2020-11-17","cited_by_count":182},{"id":"1806.00900","title":"Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced","created":"2018-06-04","cited_by_count":177},{"id":"1911.07323","title":"Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks","created":"2019-11-17","cited_by_count":177},{"id":"1905.02850","title":"Understanding Attention and Generalization in Graph Neural Networks","created":"2019-05-08","cited_by_count":169},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169},{"id":"1702.08591","title":"The Shattered Gradients Problem: If resnets are the answer, then what is the question?","created":"2017-02-28","cited_by_count":157},{"id":"2001.06362","title":"Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks","created":"2020-01-17","cited_by_count":153},{"id":"2203.05962","title":"Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice","created":"2022-03-09","cited_by_count":136},{"id":"1511.06422","title":"All you need is a good init","created":"2015-11-19","cited_by_count":124},{"id":"2005.06398","title":"Implicit Regularization in Deep Learning May Not Be Explainable by Norms","created":"2020-05-13","cited_by_count":119},{"id":"2111.06283","title":"DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks","created":"2021-11-11","cited_by_count":118},{"id":"2009.03294","title":"GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training","created":"2020-09-07","cited_by_count":117},{"id":"2006.06972","title":"Towards Deeper Graph Neural Networks with Differentiable Group Normalization","created":"2020-06-12","cited_by_count":114},{"id":"2108.01938","title":"PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations","created":"2021-08-04","cited_by_count":106},{"id":"1904.00687","title":"On the Power and Limitations of Random Features for Understanding Neural Networks","created":"2019-04-01","cited_by_count":103},{"id":"2204.04879","title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","created":"2022-04-11","cited_by_count":102},{"id":"2012.04728","title":"Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics","created":"2020-12-08","cited_by_count":96},{"id":"1603.05201","title":"Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units","created":"2016-03-16","cited_by_count":86},{"id":"1904.12058","title":"Inductive Matrix Completion Based on Graph Neural Networks","created":"2019-04-26","cited_by_count":86},{"id":"2001.05992","title":"Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks","created":"2020-01-16","cited_by_count":73},{"id":"2204.07697","title":"Theory of Graph Neural Networks: Representation and Learning","created":"2022-04-16","cited_by_count":61},{"id":"2110.15174","title":"On Provable Benefits of Depth in Training Graph Convolutional Networks","created":"2021-10-28","cited_by_count":58},{"id":"2105.04550","title":"Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth","created":"2021-05-10","cited_by_count":55},{"id":"2006.07107","title":"Understanding and Resolving Performance Degradation in Graph Convolutional Networks","created":"2020-06-12","cited_by_count":53},{"id":"1904.06963","title":"The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent","created":"2019-04-15","cited_by_count":46},{"id":"2110.14377","title":"Node Dependent Local Smoothing for Scalable Graph Learning","created":"2021-10-27","cited_by_count":45},{"id":"1802.06093","title":"Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks","created":"2018-02-16","cited_by_count":44},{"id":"2103.04886","title":"Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks","created":"2021-03-08","cited_by_count":39},{"id":"2009.02027","title":"Rethinking Graph Regularization for Graph Neural Networks","created":"2020-09-04","cited_by_count":36},{"id":"2108.10521","title":"Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study","created":"2021-08-24","cited_by_count":36},{"id":"2201.11968","title":"Training invariances and the low-rank phenomenon: beyond linear networks","created":"2022-01-28","cited_by_count":33},{"id":"2206.04361","title":"Model Degradation Hinders Deep Graph Neural Networks","created":"2022-06-09","cited_by_count":26},{"id":"2109.11338","title":"Orthogonal Graph Neural Networks","created":"2021-09-23","cited_by_count":19},{"id":"2210.17224","title":"Improving Graph Neural Networks with Learnable Propagation Operators","created":"2022-10-31","cited_by_count":19},{"id":"2207.07408","title":"pathGCN: Learning General Graph Spatial Operators from Paths","created":"2022-07-15","cited_by_count":15},{"id":"2210.08122","title":"Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again","created":"2022-10-14","cited_by_count":11}],"next_cursor":null}