{"list":"other","total":58,"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"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":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"2002.05287","title":"Geom-GCN: Geometric Graph Convolutional Networks","created":"2020-02-13","cited_by_count":826},{"id":"2003.03485","title":"Neural Operator: Graph Kernel Network for Partial Differential Equations","created":"2020-03-07","cited_by_count":734},{"id":"1907.10903","title":"DropEdge: Towards Deep Graph Convolutional Networks on Node Classification","created":"2019-07-25","cited_by_count":680},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"2106.05931","title":"Score-based Generative Modeling in Latent Space","created":"2021-06-10","cited_by_count":636},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"2006.07988","title":"Adaptive Universal Generalized PageRank Graph Neural Network","created":"2020-06-14","cited_by_count":595},{"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":"2111.14522","title":"Understanding over-squashing and bottlenecks on graphs via curvature","created":"2021-11-29","cited_by_count":478},{"id":"1612.03651","title":"FastText.zip: Compressing text classification models","created":"2016-12-12","cited_by_count":335},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"id":"1611.01491","title":"Understanding Deep Neural Networks with Rectified Linear Units","created":"2016-11-04","cited_by_count":257},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"2006.15595","title":"Rethinking Positional Encoding in Language Pre-training","created":"2020-06-28","cited_by_count":197},{"id":"1908.00821","title":"Learning Lightweight Lane Detection CNNs by Self Attention Distillation","created":"2019-08-02","cited_by_count":162},{"id":"2110.08727","title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","created":"2021-10-17","cited_by_count":152},{"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":"1912.00350","title":"Online Knowledge Distillation with Diverse Peers","created":"2019-12-01","cited_by_count":128},{"id":"2008.05000","title":"Degree-Quant: Quantization-Aware Training for Graph Neural Networks","created":"2020-08-11","cited_by_count":96},{"id":"2003.03622","title":"Explaining Knowledge Distillation by Quantifying the Knowledge","created":"2020-03-07","cited_by_count":66},{"id":"2206.10991","title":"Understanding convolution on graphs via energies","created":"2022-06-22","cited_by_count":59},{"id":"1803.10225","title":"Light Gated Recurrent Units for Speech Recognition","created":"2018-03-26","cited_by_count":48},{"id":"2102.06986","title":"How Framelets Enhance Graph Neural Networks","created":"2021-02-13","cited_by_count":46},{"id":"2105.04528","title":"Accelerating Large Scale Real-Time GNN Inference using Channel Pruning","created":"2021-05-10","cited_by_count":41},{"id":"2206.06067","title":"Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation","created":"2022-06-13","cited_by_count":41},{"id":"2011.02255","title":"On Self-Distilling Graph Neural Network","created":"2020-11-04","cited_by_count":35},{"id":"2010.10090","title":"Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher","created":"2020-10-20","cited_by_count":33},{"id":"1911.03080","title":"Deep geometric knowledge distillation with graphs","created":"2019-11-08","cited_by_count":21},{"id":"1907.04786","title":"Fast Haar Transforms for Graph Neural Networks","created":"2019-07-10","cited_by_count":20},{"id":"2006.05168","title":"Manifold structure in graph embeddings","created":"2020-06-09","cited_by_count":17},{"id":"2012.06922","title":"Decimated Framelet System on Graphs and Fast G-Framelet Transforms","created":"2020-12-12","cited_by_count":17},{"id":"1910.05872","title":"Self-supervised Label Augmentation via Input Transformations","created":"2019-10-14","cited_by_count":15},{"id":"1802.09684","title":"Network Representation Using Graph Root Distributions","created":"2018-02-27","cited_by_count":12},{"id":"2206.15085","title":"Skeleton-based Action Recognition via Adaptive Cross-Form Learning","created":"2022-06-30","cited_by_count":12},{"id":"2210.04124","title":"Generalized energy and gradient flow via graph framelets","created":"2022-10-08","cited_by_count":10},{"id":"2104.13718","title":"Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification","created":"2021-04-28","cited_by_count":8},{"id":"2111.03264","title":"Graph Denoising with Framelet Regularizer","created":"2021-11-05","cited_by_count":8},{"id":"2007.05223","title":"Distillation Guided Residual Learning for Binary Convolutional Neural Networks","created":"2020-07-10","cited_by_count":6},{"id":"2012.14619","title":"MS-GWNN:multi-scale graph wavelet neural network for breast cancer diagnosis","created":"2020-12-29","cited_by_count":6},{"id":"2102.09780","title":"A Deep Graph Wavelet Convolutional Neural Network for Semi-supervised Node Classification","created":"2021-02-19","cited_by_count":4},{"id":"2111.07602","title":"Spectral Transform Forms Scalable Transformer","created":"2021-11-15","cited_by_count":4},{"id":"2206.10146","title":"KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing","created":"2022-06-21","cited_by_count":3}],"next_cursor":null}