{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T06:14:04Z","timestamp":1771049644657,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100007845","name":"Ministry of Science and Information and Communication Technology (MSIT), Korea, under the Information Technology Research Center (ITRC) support programs","doi-asserted-by":"publisher","award":["IITP-2025-RS-2023-00258649"],"award-info":[{"award-number":["IITP-2025-RS-2023-00258649"]}],"id":[{"id":"10.13039\/100007845","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007845","name":"Ministry of Science and Information and Communication Technology (MSIT), Korea, under the Information Technology Research Center (ITRC) support programs","doi-asserted-by":"publisher","award":["IITP-2025-RS-2023-00259004"],"award-info":[{"award-number":["IITP-2025-RS-2023-00259004"]}],"id":[{"id":"10.13039\/100007845","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute for Information and Communications Technology Planning and Evaluation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3658657","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:00:22Z","timestamp":1769634022000},"page":"22274-22288","source":"Crossref","is-referenced-by-count":0,"title":["Clean-Anchor Alignment: Toward Robust and Stable Graph Neural Networks"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2030-9602","authenticated-orcid":false,"given":"Joseph","family":"Cho","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Kyung Hee University, Yongin-si, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6007-6099","authenticated-orcid":false,"given":"Chaoning","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2677-3186","authenticated-orcid":false,"given":"Sung-Ho","family":"Bae","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Kyung Hee University, Yongin-si, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5962-1587","authenticated-orcid":false,"given":"Sungyoung","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2024.3489412"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3558752"},{"key":"ref3","first-page":"1972","article-title":"Learning discrete structures for graph neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Franceschi"},{"key":"ref4","article-title":"DynGEM: Deep embedding method for dynamic graphs","author":"Goyal","year":"2018","journal-title":"arXiv:1805.11273"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3546874"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2025.118794"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3096845"},{"key":"ref8","article-title":"Graph neural networks exponentially lose expressive power for node classification","author":"Oono","year":"2019","journal-title":"arXiv:1905.10947"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1609.02907"},{"key":"ref11","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Hamilton"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403049"},{"key":"ref13","article-title":"Dual perspectives on non-contrastive self-supervised learning","author":"Ponce","year":"2025","journal-title":"arXiv:2507.01028"},{"key":"ref14","article-title":"Exponential moving average of weights in deep learning: Dynamics and benefits","author":"Morales-Brotons","year":"2024","journal-title":"arXiv:2411.18704"},{"key":"ref15","article-title":"Robust anomaly detection under normality distribution shift in dynamic graphs","author":"Xu","year":"2025","journal-title":"arXiv:2509.17400"},{"key":"ref16","first-page":"11458","article-title":"Robust graph representation learning via neural sparsification","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"1","author":"Zheng"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371851"},{"key":"ref18","article-title":"DropEdge: Towards deep graph convolutional networks on node classification","author":"Rong","year":"2019","journal-title":"arXiv:1907.10903"},{"key":"ref19","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"You"},{"key":"ref20","article-title":"Deep graph contrastive representation learning","author":"Zhu","year":"2020","journal-title":"arXiv:2006.04131"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3367598"},{"key":"ref22","first-page":"1171","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"29","author":"Sajjadi"},{"key":"ref23","first-page":"1115","article-title":"Adversarial attack on graph structured data","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Dai"},{"key":"ref24","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Tarvainen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539321"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330905"},{"key":"ref27","article-title":"Temporal ensembling for semi-supervised learning","author":"Laine","year":"2016","journal-title":"arXiv:1610.02242"},{"key":"ref28","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Yang"},{"key":"ref29","article-title":"Bootstrapped representation learning on graphs","volume-title":"Proc. ICLR Workshop Geometrical Topological Represent. Learn.","author":"Thakoor"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2957786"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/872"},{"key":"ref33","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv:1706.06083"},{"key":"ref34","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Hassani"},{"key":"ref35","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Guo"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.108143"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129827"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2025.114599"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.114402"},{"key":"ref40","first-page":"15288","article-title":"Calibrating deep neural networks using focal loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Mukhoti"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2172\/1525811"},{"key":"ref42","article-title":"Addressing failure prediction by learning model confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Corbi\u00e8re"},{"key":"ref43","first-page":"1311","article-title":"Automated curriculum learning for neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Graves"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3015245"},{"key":"ref45","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Xie"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref47","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"key":"ref48","article-title":"Training deep neural networks on noisy labels with bootstrapping","author":"Reed","year":"2014","journal-title":"arXiv:1412.6596"},{"key":"ref49","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018","journal-title":"arXiv:1803.05407"},{"key":"ref50","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sohn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref52","first-page":"1","article-title":"Query-driven active surveying for collective classification","volume-title":"Proc. 10th Int. Workshop Mining Learn. Graphs","author":"Namata"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti1007"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref56","article-title":"Regularizing neural networks by penalizing confident output distributions","author":"Pereyra","year":"2017","journal-title":"arXiv:1701.06548"},{"key":"ref57","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ovadia"},{"key":"ref58","article-title":"Graph data augmentation for graph machine learning: A survey","author":"Zhao","year":"2022","journal-title":"arXiv:2202.08871"},{"key":"ref59","first-page":"110097","article-title":"Robust graph neural networks via unbiased aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Hou"},{"key":"ref60","article-title":"Provable robustness of (graph) neural networks against data poisoning and backdoor attacks","author":"Gosch","year":"2024","journal-title":"arXiv:2407.10867"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11366644.pdf?arnumber=11366644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T05:44:08Z","timestamp":1771047848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11366644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3658657","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}