{"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":"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":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1806.01973","title":"Graph Convolutional Neural Networks for Web-Scale Recommender Systems","created":"2018-06-06","cited_by_count":1138},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"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":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"1801.10247","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","created":"2018-01-30","cited_by_count":584},{"id":"1905.07953","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","created":"2019-05-20","cited_by_count":541},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"1808.01204","title":"Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data","created":"2018-08-03","cited_by_count":261},{"id":"1809.05343","title":"Adaptive Sampling Towards Fast Graph Representation Learning","created":"2018-09-14","cited_by_count":180},{"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":"1905.12560","title":"On the equivalence between graph isomorphism testing and function approximation with GNNs","created":"2019-05-29","cited_by_count":172},{"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":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"1809.10185","title":"Graph Convolution over Pruned Dependency Trees Improves Relation Extraction","created":"2018-09-26","cited_by_count":146},{"id":"2301.09505","title":"Rethinking the Expressive Power of GNNs via Graph Biconnectivity","created":"2023-01-23","cited_by_count":119},{"id":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118},{"id":"2005.10190","title":"Feature Purification: How Adversarial Training Performs Robust Deep Learning","created":"2020-05-20","cited_by_count":107},{"id":"1706.03175","title":"Recovery Guarantees for One-hidden-layer Neural Networks","created":"2017-06-10","cited_by_count":94},{"id":"1905.10337","title":"What Can ResNet Learn Efficiently, Going Beyond Kernels?","created":"2019-05-24","cited_by_count":91},{"id":"2205.13328","title":"How Powerful are K-hop Message Passing Graph Neural Networks","created":"2022-05-26","cited_by_count":90},{"id":"2012.07690","title":"A PAC-Bayesian Approach to Generalization Bounds for Graph Neural Networks","created":"2020-12-14","cited_by_count":85},{"id":"2206.04355","title":"Graph Attention Multi-Layer Perceptron","created":"2022-06-09","cited_by_count":83},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77},{"id":"2110.15174","title":"On Provable Benefits of Depth in Training Graph Convolutional Networks","created":"2021-10-28","cited_by_count":58},{"id":"2210.07494","title":"A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking","created":"2022-10-14","cited_by_count":56},{"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":"2112.03968","title":"Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks","created":"2021-12-07","cited_by_count":51},{"id":"1806.07243","title":"Learning Conditioned Graph Structures for Interpretable Visual Question Answering","created":"2018-06-19","cited_by_count":45},{"id":"1903.10433","title":"Dual Graph Attention Networks for Deep Latent Representation of Multifaceted Social Effects in Recommender Systems","created":"2019-03-25","cited_by_count":41},{"id":"2305.08048","title":"Towards Understanding the Generalization of Graph Neural Networks","created":"2023-05-14","cited_by_count":41},{"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":"2207.08629","title":"Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks","created":"2022-07-18","cited_by_count":18},{"id":"2006.08796","title":"Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification","created":"2020-06-15","cited_by_count":16},{"id":"2302.02922","title":"Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks","created":"2023-02-06","cited_by_count":16},{"id":"2411.05464","title":"Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs","created":"2024-11-08","cited_by_count":14},{"id":"2410.10051","title":"Towards Bridging Generalization and Expressivity of Graph Neural Networks","created":"2024-10-14","cited_by_count":12},{"id":"2405.16435","title":"Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning","created":"2024-05-26","cited_by_count":10},{"id":"2207.03615","title":"Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data","created":"2022-07-07","cited_by_count":8},{"id":"2309.07452","title":"Is Solving Graph Neural Tangent Kernel Equivalent to Training Graph Neural Network?","created":"2023-09-14","cited_by_count":8},{"id":"2403.07310","title":"How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance","created":"2024-03-12","cited_by_count":6}],"next_cursor":null}