{"list":"other","total":52,"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":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1802.04364","title":"Junction Tree Variational Autoencoder for Molecular Graph Generation","created":"2018-02-12","cited_by_count":652},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1709.05584","title":"Representation Learning on Graphs: Methods and Applications","created":"2017-09-17","cited_by_count":457},{"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":"1703.02930","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","created":"2017-03-08","cited_by_count":311},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"1712.06541","title":"Size-Independent Sample Complexity of Neural Networks","created":"2017-12-18","cited_by_count":290},{"id":"1912.09893","title":"A Fair Comparison of Graph Neural Networks for Graph Classification","created":"2019-12-20","cited_by_count":244},{"id":"2002.04025","title":"Can Graph Neural Networks Count Substructures?","created":"2020-02-10","cited_by_count":236},{"id":"2009.11848","title":"How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks","created":"2020-09-24","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":"1802.03685","title":"Learning a SAT Solver from Single-Bit Supervision","created":"2018-02-11","cited_by_count":200},{"id":"1905.13192","title":"Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels","created":"2019-05-30","cited_by_count":161},{"id":"1905.13211","title":"What Can Neural Networks Reason About?","created":"2019-05-30","cited_by_count":159},{"id":"2005.03675","title":"Machine Learning on Graphs: A Model and Comprehensive Taxonomy","created":"2020-05-07","cited_by_count":156},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"1901.05353","title":"A Primer on PAC-Bayesian Learning","created":"2019-01-16","cited_by_count":132},{"id":"1603.05629","title":"Discriminative Embeddings of Latent Variable Models for Structured Data","created":"2016-03-17","cited_by_count":131},{"id":"2010.08853","title":"From Local Structures to Size Generalization in Graph Neural Networks","created":"2020-10-17","cited_by_count":124},{"id":"1902.03736","title":"A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm","created":"2019-02-11","cited_by_count":106},{"id":"2006.15646","title":"Expressive Power of Invariant and Equivariant Graph Neural Networks","created":"2020-06-28","cited_by_count":100},{"id":"2012.07690","title":"A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks","created":"2020-12-14","cited_by_count":85},{"id":"2009.09623","title":"The Complexity of Constrained Min-Max Optimization","created":"2020-09-21","cited_by_count":82},{"id":"1905.01004","title":"Stability and Generalization of Graph Convolutional Neural Networks","created":"2019-05-03","cited_by_count":81},{"id":"1905.03684","title":"Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation","created":"2019-05-09","cited_by_count":71},{"id":"1905.10261","title":"Approximation Ratios of Graph Neural Networks for Combinatorial Problems","created":"2019-05-24","cited_by_count":69},{"id":"2204.07697","title":"Theory of Graph Neural Networks: Representation and Learning","created":"2022-04-16","cited_by_count":61},{"id":"1905.12600","title":"Generalization bounds for deep convolutional neural networks","created":"2019-05-29","cited_by_count":59},{"id":"2112.03968","title":"Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks","created":"2021-12-07","cited_by_count":51},{"id":"2002.08253","title":"Distance-Based Regularisation of Deep Networks for Fine-Tuning","created":"2020-02-19","cited_by_count":48},{"id":"2111.04578","title":"Improved Regularization and Robustness for Fine-tuning in Neural Networks","created":"2021-11-08","cited_by_count":45},{"id":"1307.2118","title":"A PAC-Bayesian Tutorial with A Dropout Bound","created":"2013-07-08","cited_by_count":43},{"id":"2206.02659","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","created":"2022-06-06","cited_by_count":34},{"id":"2107.04835","title":"Noise Stability Regularization for Improving BERT Fine-tuning","created":"2021-07-10","cited_by_count":29},{"id":"2102.05242","title":"Patterns, predictions, and actions: A story about machine learning","created":"2021-02-10","cited_by_count":14}],"next_cursor":null}