{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:04:25Z","timestamp":1780416265046,"version":"3.54.1"},"reference-count":96,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#IIS-1750074"],"award-info":[{"award-number":["#IIS-1750074"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#IIS-1900990"],"award-info":[{"award-number":["#IIS-1900990"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#IIS-1849085"],"award-info":[{"award-number":["#IIS-1849085"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"US Army Research Office Young Investigator","award":["W911NF2010240"],"award-info":[{"award-number":["W911NF2010240"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,3,1]]},"DOI":"10.1109\/tpami.2022.3174515","type":"journal-article","created":{"date-parts":[[2022,5,11]],"date-time":"2022-05-11T20:21:39Z","timestamp":1652300499000},"page":"2769-2781","source":"Crossref","is-referenced-by-count":34,"title":["Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7774-8197","authenticated-orcid":false,"given":"Tianlong","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaixiong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Rice University, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Rice University, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8283-7511","authenticated-orcid":false,"given":"Wenqing","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0657-1595","authenticated-orcid":false,"given":"Peihao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Rice University, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2050-5693","authenticated-orcid":false,"given":"Zhangyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gated graph sequence neural networks","author":"Li","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557109"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2022.1029307"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219947"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00220"},{"key":"ref7","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"You"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498416"},{"key":"ref9","article-title":"Cold brew: Distilling graph node representations with incomplete or missing neighborhoods","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zheng"},{"key":"ref10","first-page":"10 871","article-title":"When does self-supervision help graph convolutional networks?","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"You"},{"key":"ref11","article-title":"Geometric matrix completion with recurrent multi-graph neural networks","author":"Monti","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/s0262-4079(20)31342-7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2820126"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2021.3139336"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.12928\/telkomnika.v14i2A.4340"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx252"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-007-0103-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3074057"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01143"},{"key":"ref22","article-title":"Open graph benchmark: Datasets for machine learning on graphs","author":"Hu","year":"2020"},{"key":"ref23","article-title":"Graph neural networks exponentially lose expressive power for node classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Oono"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref25","article-title":"Revisiting graph neural networks: All we have is low-pass filters","author":"NT","year":"2019"},{"key":"ref26","article-title":"Anti-oversmoothing in deep vision transformers via the fourier domain analysis: From theory to practice","author":"Wang","year":"2022"},{"key":"ref27","article-title":"On the bottleneck of graph neural networks and its practical implications","author":"Alon","year":"2020"},{"key":"ref28","article-title":"Simple and deep graph convolutional networks","author":"Chen","year":"2020"},{"key":"ref29","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","author":"Klicpera","year":"2018"},{"key":"ref30","article-title":"Revisiting graph convolutional network on semi-supervised node classification from an optimization perspective","author":"Zhang","year":"2020"},{"key":"ref31","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403076"},{"key":"ref33","article-title":"Dropedge: Towards deep graph convolutional networks on node classification","volume-title":"Proc. Int. Conf. Learn. Representations.","author":"Rong"},{"key":"ref34","article-title":"Tackling over-smoothing for general graph convolutional networks","author":"Huang","year":"2020"},{"key":"ref35","article-title":"Pairnorm: Tackling oversmoothing in GNNs","author":"Zhao","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482488"},{"key":"ref37","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. 32nd Int. Conf. Int. Conf. Mach. Learn.","author":"Ioffe"},{"key":"ref38","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref40","article-title":"Revisiting \u201dover-smoothing\u201d in deep GCNs","author":"Yang","year":"2020"},{"key":"ref41","first-page":"4917","article-title":"Towards deeper graph neural networks with differentiable group normalization","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Zhou"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref43","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kipf"},{"key":"ref44","first-page":"15868","article-title":"On the equivalence between graph isomorphism testing and function approximation with gnns","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Chen"},{"key":"ref45","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327389"},{"key":"ref47","article-title":"How powerful are graph neural networks?","author":"Xu","year":"2018"},{"key":"ref48","article-title":"Graph contrastive learning automated","author":"You","year":"2021"},{"key":"ref49","first-page":"1695","article-title":"A unified lottery ticket hypothesis for graph neural networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414219"},{"key":"ref51","first-page":"1352","article-title":"Multi-channel graph neural networks","volume-title":"Proc. 29th Int. Conf. Int. Joint Conf.s Artif. Intell.","author":"Zhou"},{"key":"ref52","article-title":"GMNN: Graph Markov neural networks","author":"Qu","year":"2019"},{"key":"ref53","article-title":"Graphmix: Regularized training of graph neural networks for semi-supervised learning","author":"Verma","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c00866.s001"},{"key":"ref55","article-title":"Benchmarking graph neural networks","author":"Dwivedi","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref57","article-title":"Spectral networks and locally connected networks on graphs","author":"Bruna","year":"2013"},{"key":"ref58","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. 31st Int. Conf. Neural Informat. Process. Syst.","author":"Hamilton"},{"key":"ref59","first-page":"4509","article-title":"Interaction networks for learning about objects, relations and physics","volume-title":"Proc. 30th Int. Conf. Neural Informat. Process. Syst.","author":"Battaglia"},{"key":"ref60","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref61","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014602"},{"key":"ref63","first-page":"4663","article-title":"Relational pooling for graph representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Murphy"},{"key":"ref64","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. 30th Int. Conf. Neural Informat. Process. Syst.","author":"Defferrard"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"ref66","article-title":"Bag of tricks for node classification with graph neural networks","author":"Wang","year":"2021"},{"key":"ref67","article-title":"The logical expressiveness of graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Barcel\u00f3"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852455"},{"key":"ref69","article-title":"Dirichlet energy constrained learning for deep graph neural networks","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","volume":"34","author":"Zhou"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref72","article-title":"DeeperGCN: All you need to train deeper GCNs","author":"Li","year":"2020"},{"key":"ref73","article-title":"Break the ceiling: Stronger multi-scale deep graph convolutional networks","author":"Luan","year":"2019"},{"key":"ref74","article-title":"Scattering GCN: Overcoming oversmoothness in graph convolutional networks","author":"Min","year":"2020"},{"key":"ref75","first-page":"11249","article-title":"Layer-dependent importance sampling for training deep and large graph convolutional networks","volume-title":"Proc. 33rd Int. Conf. Neural Informat. Process. Syst.","author":"Zou"},{"key":"ref76","first-page":"4094","article-title":"Bayesian graph neural networks with adaptive connection sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hasanzadeh"},{"issue":"1","key":"ref77","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":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539445"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20316"},{"key":"ref80","first-page":"6437","article-title":"Training graph neural networks with 1000 layers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref81","article-title":"Tackling oversmoothing of GNNs with contrastive learning","author":"Zheng","year":"2021"},{"key":"ref82","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"ref83","article-title":"Evaluating deep graph neural networks","author":"Zhang","year":"2021"},{"key":"ref84","article-title":"Optimization of graph neural networks: Implicit acceleration by skip connections and more depth","author":"Xu","year":"2021"},{"key":"ref85","article-title":"Deep graph neural networks with shallow subgraph samplers","author":"Zeng","year":"2020"},{"key":"ref86","article-title":"Fast graph representation learning with PyTorch Geometric","author":"Fey","year":"2019","journal-title":"Int. Conf. Learn. Representation Workshop"},{"key":"ref87","article-title":"Layer-dependent importance sampling for training deep and large graph convolutional networks","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","volume":"32","author":"Zou"},{"key":"ref88","article-title":"Adaptive universal generalized pagerank graph neural network","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chien"},{"key":"ref89","article-title":"Pitfalls of graph neural network evaluation","author":"Shchur","year":"2018"},{"key":"ref90","article-title":"Geom-GCN: Geometric graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pei"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/214"},{"key":"ref92","article-title":"Flag: Adversarial data augmentation for graph neural networks","author":"Kong","year":"2020"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01130"},{"key":"ref94","article-title":"Revisiting semi-supervised learning with graph embeddings","author":"Yang","year":"2016"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557108"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10036240\/9773017-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10036240\/09773017.pdf?arnumber=9773017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:56:04Z","timestamp":1736970964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9773017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":96,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3174515","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,1]]}}}