{"list":"other","total":86,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"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":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1811.05868","title":"Pitfalls of Graph Neural Network Evaluation","created":"2018-11-14","cited_by_count":1007},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1802.09691","title":"Link Prediction Based on Graph Neural Networks","created":"2018-02-27","cited_by_count":832},{"id":"1902.07243","title":"Graph Neural Networks for Social Recommendation","created":"2019-02-19","cited_by_count":714},{"id":"1511.04508","title":"Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks","created":"2015-11-14","cited_by_count":678},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1801.10247","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","created":"2018-01-30","cited_by_count":584},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"2011.02260","title":"Graph Neural Networks in Recommender Systems: A Survey","created":"2020-11-04","cited_by_count":494},{"id":"1812.04202","title":"Deep Learning on Graphs: A Survey","created":"2018-12-11","cited_by_count":393},{"id":"1610.05755","title":"Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data","created":"2016-10-18","cited_by_count":348},{"id":"2003.01251","title":"Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud","created":"2020-03-02","cited_by_count":335},{"id":"1904.01802","title":"Correlation Congruence for Knowledge Distillation","created":"2019-04-03","cited_by_count":285},{"id":"1511.02136","title":"Diffusion-Convolutional Neural Networks","created":"2015-11-06","cited_by_count":268},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"1912.09893","title":"A Fair Comparison of Graph Neural Networks for Graph Classification","created":"2019-12-20","cited_by_count":244},{"id":"1909.01315","title":"Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks","created":"2019-09-03","cited_by_count":242},{"id":"1711.09404","title":"Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients","created":"2017-11-26","cited_by_count":236},{"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":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"1812.10528","title":"Adversarial Attack and Defense on Graph Data: A Survey","created":"2018-12-26","cited_by_count":167},{"id":"1801.03226","title":"Adaptive Graph Convolutional Neural Networks","created":"2018-01-10","cited_by_count":155},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152},{"id":"1802.07007","title":"Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting","created":"2018-02-20","cited_by_count":146},{"id":"1904.07785","title":"Graph Wavelet Neural Network","created":"2019-04-12","cited_by_count":131},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"id":"2005.07496","title":"Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey","created":"2020-05-13","cited_by_count":124},{"id":"2003.13942","title":"Spatio-Temporal Graph for Video Captioning with Knowledge Distillation","created":"2020-03-31","cited_by_count":109},{"id":"2003.00330","title":"Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective","created":"2020-02-29","cited_by_count":95},{"id":"2005.00727","title":"Heterogeneous Knowledge Distillation using Information Flow Modeling","created":"2020-05-02","cited_by_count":73},{"id":"2112.10063","title":"Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation","created":"2021-12-19","cited_by_count":67},{"id":"2003.03622","title":"Explaining Knowledge Distillation by Quantifying the Knowledge","created":"2020-03-07","cited_by_count":66},{"id":"2012.14022","title":"ALP-KD: Attention-Based Layer Projection for Knowledge Distillation","created":"2020-12-27","cited_by_count":66},{"id":"1910.03053","title":"Graph Few-shot Learning via Knowledge Transfer","created":"2019-10-07","cited_by_count":63},{"id":"2004.05304","title":"Inter-Region Affinity Distillation for Road Marking Segmentation","created":"2020-04-11","cited_by_count":58},{"id":"2111.04840","title":"Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods","created":"2021-11-08","cited_by_count":58},{"id":"1812.06597","title":"Learning Student Networks via Feature Embedding","created":"2018-12-17","cited_by_count":45},{"id":"1811.05072","title":"Private Model Compression via Knowledge Distillation","created":"2018-11-13","cited_by_count":37},{"id":"1904.09482","title":"Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding","created":"2019-04-20","cited_by_count":37},{"id":"1712.00108","title":"Graph Distillation for Action Detection with Privileged Modalities","created":"2017-11-30","cited_by_count":35},{"id":"2011.02255","title":"On Self-Distilling Graph Neural Network","created":"2020-11-04","cited_by_count":35},{"id":"2012.15823","title":"Binary Graph Neural Networks","created":"2020-12-31","cited_by_count":34},{"id":"2110.14170","title":"Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding","created":"2021-10-27","cited_by_count":32},{"id":"1907.02226","title":"Graph-based Knowledge Distillation by Multi-head Attention Network","created":"2019-07-04","cited_by_count":31},{"id":"1911.03080","title":"Deep geometric knowledge distillation with graphs","created":"2019-11-08","cited_by_count":21},{"id":"2010.12609","title":"Iterative Graph Self-Distillation","created":"2020-10-23","cited_by_count":21},{"id":"1804.10069","title":"Better and Faster: Knowledge Transfer from Multiple Self-supervised Learning Tasks via Graph Distillation for Video Classification","created":"2018-04-26","cited_by_count":20},{"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":"2009.05912","title":"DualDE: Dually Distilling Knowledge Graph Embedding for Faster and Cheaper Reasoning","created":"2020-09-13","cited_by_count":17},{"id":"2105.04181","title":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","created":"2021-05-10","cited_by_count":11},{"id":"2105.04776","title":"Graph Consistency Based Mean-Teaching for Unsupervised Domain Adaptive Person Re-Identification","created":"2021-05-11","cited_by_count":11},{"id":"2106.08541","title":"Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages","created":"2021-06-16","cited_by_count":11},{"id":"2105.14975","title":"Privileged Graph Distillation for Cold Start Recommendation","created":"2021-05-31","cited_by_count":10},{"id":"2111.02100","title":"Conditional Attention Networks for Distilling Knowledge Graphs in Recommendation","created":"2021-11-03","cited_by_count":10},{"id":"2112.04319","title":"SCR: Training Graph Neural Networks with Consistency Regularization","created":"2021-12-08","cited_by_count":10},{"id":"2109.12862","title":"Deep Structured Instance Graph for Distilling Object Detectors","created":"2021-09-27","cited_by_count":9},{"id":"1906.01829","title":"Binarized Collaborative Filtering with Distilling Graph Convolutional Networks","created":"2019-06-05","cited_by_count":8},{"id":"1911.05700","title":"Graph Representation Learning via Multi-task Knowledge Distillation","created":"2019-11-11","cited_by_count":8},{"id":"2009.00952","title":"Mutual Teaching for Graph Convolutional Networks","created":"2020-09-02","cited_by_count":8},{"id":"2106.06307","title":"Survey of Image Based Graph Neural Networks","created":"2021-06-11","cited_by_count":7},{"id":"1909.04286","title":"Knowledge Transfer Graph for Deep Collaborative Learning","created":"2019-09-10","cited_by_count":5},{"id":"2007.13839","title":"Saliency Prediction with External Knowledge","created":"2020-07-27","cited_by_count":5},{"id":"1908.06258","title":"Language Graph Distillation for Low-Resource Machine Translation","created":"2019-08-17","cited_by_count":4},{"id":"2104.13561","title":"Interpretable Embedding Procedure Knowledge Transfer via Stacked Principal Component Analysis and Graph Neural Network","created":"2021-04-28","cited_by_count":3},{"id":"2011.05705","title":"EGAD: Evolving Graph Representation Learning with Self-Attention and Knowledge Distillation for Live Video Streaming Events","created":"2020-11-11","cited_by_count":2},{"id":"1911.09046","title":"Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning","created":"2019-11-20","cited_by_count":1},{"id":"2011.05664","title":"Distill2Vec: Dynamic Graph Representation Learning with Knowledge Distillation","created":"2020-11-11","cited_by_count":1}],"next_cursor":null}