{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:01:20Z","timestamp":1776106880703,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"VMware Inc."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/tkde.2021.3072345","type":"journal-article","created":{"date-parts":[[2021,4,9]],"date-time":"2021-04-09T15:54:57Z","timestamp":1617983697000},"page":"905-916","source":"Crossref","is-referenced-by-count":143,"title":["Sparse Graph Attention Networks"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7562-8279","authenticated-orcid":false,"given":"Yang","family":"Ye","sequence":"first","affiliation":[{"name":"Department of Computer Science, Georgia State University, Atlanta, GA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3573-5379","authenticated-orcid":false,"given":"Shihao","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Georgia State University, Atlanta, GA, USA"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Learning sparse neural networks through $l_0$l0 regularization","author":"louizos","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","article-title":"Backpropagation through the void: Optimizing control variates for black-box gradient estimation","author":"grathwohl","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref31","article-title":"How to find your friendly neighborhood: Graph attention design with self-supervision","author":"kim","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441734"},{"key":"ref37","first-page":"2624","article-title":"Rebar: Low-variance, unbiased gradient estimates for discrete latent variable models","author":"tucker","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref36","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref34","article-title":"Stochastic variational optimization","author":"bird","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412139"},{"key":"ref27","article-title":"Bayesian graph neural networks with adaptive connection sampling","author":"hasanzadeh","year":"2020"},{"key":"ref29","first-page":"11458","article-title":"Robust graph representation learning via neural sparsification","author":"zheng","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx252"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref22","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","article-title":"Parallelizing word2vec in multi-core and many-core architectures","author":"ji","year":"2016","journal-title":"Proc NIPS Workshop Efficient Methods Deep Neural Networks"},{"key":"ref24","first-page":"688","article-title":"Improved large-scale graph learning through ridge spectral sparsifications","author":"calandriello","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Representation Learn"},{"key":"ref26","article-title":"Dropedge: Towards deep graph convolutional networks on node classification","author":"rong","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899979"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380219"},{"key":"ref10","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref40","article-title":"Assortative mixing in networks","volume":"89","author":"zachary","year":"2002","journal-title":"Phys Rev Lett"},{"key":"ref11","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","first-page":"1025","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref13","article-title":"Graph attention networks","author":"veli?kovi?","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806512"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939751"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref19","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref4","article-title":"Graph convolutional matrix completion","author":"den berg","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref6","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","author":"yang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","author":"duvenaud","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref49","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref7","first-page":"52","article-title":"Representation learning on graphs: Methods and applications","volume":"40","author":"hamilton","year":"2017","journal-title":"IEEE Data Eng Bull"},{"key":"ref9","article-title":"Spectral networks and locally connected networks on graphs","author":"bruna","year":"2014","journal-title":"Proc Int Conf Representation Learn"},{"key":"ref46","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1086\/jar.33.4.3629752"},{"key":"ref47","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","author":"wang","year":"2019","journal-title":"Proc ICLR Workshop Representation Learn Graphs Manifolds"},{"key":"ref42","article-title":"Geom-GCN: Geometric graph convolutional networks","author":"pei","year":"2020","journal-title":"Proc Knowl Discov Data Mining"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098061"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557108"},{"key":"ref43","article-title":"Pitfalls of graph neural network evaluation","author":"shchur","year":"2018","journal-title":"NeurIPS Relational Representation Learning Workshop"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/9973432\/09399811.pdf?arnumber=9399811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:48:34Z","timestamp":1756154914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9399811\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":50,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2021.3072345","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,1]]}}}