{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T05:38:31Z","timestamp":1732685911751,"version":"3.28.2"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61991411"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science and Technology Major","award":["2021ZD0112002"]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076148"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shandong Excellent Young Scientists Fund Program","award":["2022HWYQ-042"]},{"name":"Young Taishan Scholars Program of Shandong Province","award":["tsqn201909029"]},{"name":"Self-Developed Innovation Team of Jinan City","award":["2021GXRC038"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3404655","type":"journal-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T17:53:19Z","timestamp":1716486799000},"page":"8396-8409","source":"Crossref","is-referenced-by-count":1,"title":["IGCN: A Provably Informative GCN Embedding for Semi-Supervised Learning With Extremely Limited Labels"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-9419-9038","authenticated-orcid":false,"given":"Lin","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-1344-4415","authenticated-orcid":false,"given":"Ran","family":"Song","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"http:\/\/orcid.org\/0009-0006-4197-142X","authenticated-orcid":false,"given":"Wenhao","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-7331-6132","authenticated-orcid":false,"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan, Beijing, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-4960-3190","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Control Science and Engineering, Shandong University, Jinan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-27819-1_43"},{"key":"ref2","first-page":"610","article-title":"NetGAN: Generating graphs via random walks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bojchevski"},{"article-title":"Spectral networks and locally connected networks on graphs","year":"2013","author":"Bruna","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262033589.001.0001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00761"},{"key":"ref7","first-page":"1725","article-title":"Simple and deep graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"article-title":"Adaptive universal generalized pagerank graph neural network","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chien","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.09375"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3351938"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01612"},{"key":"ref13","first-page":"5723","article-title":"Graph neural tangent kernel: Fusing graph neural networks with graph kernels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du"},{"key":"ref14","first-page":"18674","article-title":"Learning optimal representations with the decodable information bottleneck","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dubois"},{"article-title":"Convolutional networks on graphs for learning molecular fingerprints","year":"2015","author":"Duvenaud","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/276675.276685"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref18","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref19","first-page":"12411","article-title":"Alternately optimized graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Han"},{"article-title":"Learning deep representations by mutual information estimation and maximization","year":"2018","author":"Hjelm","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01157"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref22"},{"article-title":"Semi-supervised classification with graph convolutional networks","year":"2016","author":"Kipf","key":"ref23"},{"article-title":"Variational graph auto-encoders","year":"2016","author":"Kipf","key":"ref24"},{"article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","year":"2018","author":"Klicpera","key":"ref25"},{"issue":"1","key":"ref26","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1109\/TSP.2018.2879624","volume":"67","author":"Levie","year":"2018","journal-title":"IEEE Trans. Signal Process."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00879-4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00423"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403076"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009953814988"},{"key":"ref31","first-page":"14498","article-title":"Scattering GCN: Overcoming oversmoothness in graph convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Min"},{"key":"ref32","first-page":"1330","article-title":"Semi-supervised learning with the graph laplacian: The limit of infinite unlabelled data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"22","author":"Nadler"},{"article-title":"Graph neural networks exponentially lose expressive power for node classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Oono","key":"ref33"},{"key":"ref34","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380112"},{"issue":"1","key":"ref36","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2010.04.006"},{"article-title":"Pitfalls of graph neural network evaluation","year":"2018","author":"Shchur","key":"ref39"},{"article-title":"Opening the black box of deep neural networks via information","year":"2017","author":"Shwartz-Ziv","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6048"},{"key":"ref42","first-page":"368","article-title":"The information bottleneck method","volume-title":"Proc. 37th Annu. Allerton Conf. Commun. Control Comput.","author":"Tishby"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref43"},{"issue":"11","key":"ref44","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"article-title":"Graph attention networks","year":"2017","author":"Veli\u010dkovi\u0107","key":"ref45"},{"issue":"3","key":"ref46","article-title":"Deep graph infomax","volume":"2","author":"Velickovic","year":"2019","journal-title":"ICLR (Poster)"},{"key":"ref47","first-page":"6316","article-title":"Contrastive graph poisson networks: Semi-supervised learning with extremely limited labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wan"},{"article-title":"Revisiting locally supervised learning: An alternative to end-to-end training","year":"2021","author":"Wang","key":"ref48"},{"key":"ref49","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref50","first-page":"20437","article-title":"Graph information bottleneck","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"article-title":"How powerful are graph neural networks?","year":"2018","author":"Xu","key":"ref51"},{"key":"ref52","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00169"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01650"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00419"},{"article-title":"Graph information bottleneck for subgraph recognition","year":"2020","author":"Yu","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04648-4_7"},{"article-title":"Simple spectral graph convolution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","key":"ref58"},{"key":"ref59","first-page":"7793","article-title":"Beyond homophily in graph neural networks: Current limitations and effective designs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref60","first-page":"912","article-title":"Semi-supervised learning using gaussian fields and harmonic functions","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Zhu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10746266\/10538043.pdf?arnumber=10538043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:22:04Z","timestamp":1732666924000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10538043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":60,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3404655","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}  <script>parent.window.postMessage('ixistenz.url:https://api.crossref.org/works/10.1109%2FTPAMI.2024.3404655', '*'); </script> <div id='browserdiffcontainer' style='position: fixed; right: 10px; top: 10vh; min-width: 60px;  border: 1px solid white; background: rgb(251, 189, 0);; opacity: 0.9; font-family: helvetica, arial, sans serif;  font-size: 12px; z-index: 20001; padding-bottom: 20px;'><div onclick="toggle('browserdiffcontainerlist'); return false;" style='background: rgb(151, 89, 0);; color: white; '><strong>&nbsp; <span class='glyphicon glyphicon-minus'></span> NODES</strong></div><div id='browserdiffcontainerlist' style='padding-left: 10px; padding-right: 5px; max-height: 50vh; overflow: auto; '><div><a href='#diffid117' style='color: white;' onClick="parent.window.postMessage('ixistenz.opendiff:117', '*');; return false;" style='text-decoration: none; '>chat </a> <a style='color: white;' href='#diffid117'><sup>1</sup></a></div><div><a href='#diffid120' style='color: white;' onClick="parent.window.postMessage('ixistenz.opendiff:120', '*');; return false;" style='text-decoration: none; '>innovation </a> <a style='color: white;' href='#diffid120'><sup>1</sup></a></div></div></div>
<script>
function toggle( divname ) {
  var x = document.getElementById( divname );
  if (x.style.display === 'none') {
    x.style.display = 'block';
  } else {
    x.style.display = 'none';
  }
} </script>