{"list":"other","total":53,"rows":[{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"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":"2003.02320","title":"Knowledge Graphs","created":"2020-03-04","cited_by_count":621},{"id":"1904.03751","title":"DeepGCNs: Can GCNs Go as Deep as CNNs?","created":"2019-04-07","cited_by_count":527},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"2005.10203","title":"Graph Structure Learning for Robust Graph Neural Networks","created":"2020-05-20","cited_by_count":371},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"2106.06947","title":"Graph Neural Network-Based Anomaly Detection in Multivariate Time Series","created":"2021-06-13","cited_by_count":301},{"id":"2012.09816","title":"Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning","created":"2020-12-17","cited_by_count":297},{"id":"1903.04197","title":"Structured Knowledge Distillation for Dense Prediction","created":"2019-03-11","cited_by_count":279},{"id":"2101.11174","title":"Graph Neural Network for Traffic Forecasting: A Survey","created":"2021-01-27","cited_by_count":261},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"2001.06362","title":"Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks","created":"2020-01-17","cited_by_count":153},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152},{"id":"2110.07580","title":"Graph Condensation for Graph Neural Networks","created":"2021-10-14","cited_by_count":150},{"id":"2110.04126","title":"3D Infomax improves GNNs for Molecular Property Prediction","created":"2021-10-08","cited_by_count":146},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"id":"2006.03548","title":"Graphon Neural Networks and the Transferability of Graph Neural Networks","created":"2020-06-05","cited_by_count":118},{"id":"2102.06790","title":"A Unified Lottery Ticket Hypothesis for Graph Neural Networks","created":"2021-02-12","cited_by_count":118},{"id":"2111.04840","title":"Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods","created":"2021-11-08","cited_by_count":58},{"id":"2207.04869","title":"Graph-based Molecular Representation Learning","created":"2022-07-08","cited_by_count":51},{"id":"2208.09957","title":"Heterogeneous Graph Masked Autoencoders","created":"2022-08-21","cited_by_count":47},{"id":"2108.09987","title":"Efficient Medical Image Segmentation Based on Knowledge Distillation","created":"2021-08-23","cited_by_count":43},{"id":"2210.05801","title":"Linkless Link Prediction via Relational Distillation","created":"2022-10-11","cited_by_count":39},{"id":"2011.02255","title":"On Self-Distilling Graph Neural Network","created":"2020-11-04","cited_by_count":35},{"id":"2208.10205","title":"LTE4G: Long-Tail Experts for Graph Neural Networks","created":"2022-08-22","cited_by_count":30},{"id":"2203.05180","title":"Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability","created":"2022-03-10","cited_by_count":21},{"id":"2009.00934","title":"SAIL: Self-Augmented Graph Contrastive Learning","created":"2020-09-02","cited_by_count":20},{"id":"2107.11789","title":"ROD: Reception-aware Online Distillation for Sparse Graphs","created":"2021-07-25","cited_by_count":18},{"id":"1908.05474","title":"Adaptive Regularization of Labels","created":"2019-08-15","cited_by_count":16},{"id":"2208.10010","title":"NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs","created":"2022-08-22","cited_by_count":14},{"id":"2104.04909","title":"Edge: Enriching Knowledge Graph Embeddings with External Text","created":"2021-04-11","cited_by_count":13},{"id":"2205.14005","title":"RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation","created":"2022-05-24","cited_by_count":13},{"id":"2205.12396","title":"Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks","created":"2022-05-24","cited_by_count":12},{"id":"2211.15899","title":"FakeEdge: Alleviate Dataset Shift in Link Prediction","created":"2022-11-29","cited_by_count":12},{"id":"2108.03084","title":"Transferring Knowledge Distillation for Multilingual Social Event Detection","created":"2021-08-06","cited_by_count":7}],"next_cursor":null}