{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T10:04:59Z","timestamp":1784887499367,"version":"3.55.0"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"ARC","doi-asserted-by":"publisher","award":["DP210101347"],"award-info":[{"award-number":["DP210101347"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tnnls.2023.3339770","type":"journal-article","created":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T19:52:40Z","timestamp":1704743560000},"page":"11681-11691","source":"Crossref","is-referenced-by-count":22,"title":["Affinity Uncertainty-Based Hard Negative Mining in Graph Contrastive Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4529-8560","authenticated-orcid":false,"given":"Chaoxi","family":"Niu","sequence":"first","affiliation":[{"name":"Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9877-2716","authenticated-orcid":false,"given":"Guansong","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Bras Basah, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6468-5729","authenticated-orcid":false,"given":"Ling","family":"Chen","sequence":"additional","affiliation":[{"name":"Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3076021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3570906"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref4","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref5","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref6","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Veli\u010dkovi\u0107"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170559"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3172903"},{"issue":"3","key":"ref9","first-page":"4","article-title":"Deep graph infomax","volume-title":"Proc. Int. Conf. Learn. Represent.","volume":"2","author":"Velickovic"},{"key":"ref10","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hassani"},{"key":"ref11","article-title":"InfoGraph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sun"},{"key":"ref12","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume-title":"Proc. NIPS","volume":"33","author":"You"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449802"},{"key":"ref14","first-page":"12121","article-title":"Graph contrastive learning automated","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512156"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403168"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583441"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/math10173047"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3216630"},{"key":"ref20","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kalantidis"},{"key":"ref21","article-title":"Contrastive learning with hard negative samples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Robinson"},{"key":"ref22","first-page":"8765","article-title":"Debiased contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chuang"},{"key":"ref23","first-page":"24332","article-title":"ProGCL: Rethinking hard negative mining in graph contrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xia"},{"key":"ref24","article-title":"Conditional negative sampling for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wu"},{"key":"ref25","article-title":"i-mix: A domain-agnostic strategy for contrastive representation learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref26","article-title":"An empirical study of graph contrastive learning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3291358"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26071"},{"key":"ref29","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref33","first-page":"19580","article-title":"Directed graph contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tong"},{"key":"ref34","article-title":"Deep graph contrastive representation learning","author":"Zhu","year":"2020","journal-title":"arXiv:2006.04131"},{"key":"ref35","first-page":"30414","article-title":"InfoGCL: Information-aware graph contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3248871"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3278183"},{"key":"ref38","article-title":"The information bottleneck method","author":"Tishby","year":"2000","journal-title":"arXiv:physics\/0004057"},{"key":"ref39","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref40","first-page":"10530","article-title":"Towards domain-agnostic contrastive learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref41","first-page":"27356","article-title":"Robust contrastive learning using negative samples with diminished semantics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ge"},{"key":"ref42","first-page":"1510","article-title":"Self-PU: Self boosted and calibrated positive-unlabeled training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3297607"},{"key":"ref44","article-title":"Selective classification for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Geifman"},{"key":"ref45","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lakshminarayanan"},{"key":"ref46","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref48","first-page":"21464","article-title":"Energy-based out-of-distribution detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_15"},{"key":"ref50","article-title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref51","article-title":"Deep gamblers: Learning to abstain with portfolio theory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Liu"},{"key":"ref52","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Caron"},{"key":"ref53","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3191086"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/473"},{"key":"ref56","first-page":"11548","article-title":"Self-supervised graph-level representation learning with local and global structure","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512208"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3177775"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref60","article-title":"Wiki-CS: A Wikipedia-based benchmark for graph neural networks","author":"Mernyei","year":"2020","journal-title":"arXiv:2007.02901"},{"key":"ref61","article-title":"Pitfalls of graph neural network evaluation","author":"Shchur","year":"2018","journal-title":"arXiv:1811.05868"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"},{"key":"ref63","article-title":"Graph2Vec: Learning distributed representations of graphs","author":"Narayanan","year":"2017","journal-title":"arXiv:1707.05005"},{"key":"ref64","first-page":"488","article-title":"Efficient graphlet kernels for large graph comparison","volume-title":"Artificial Intelligence and Statistics","author":"Shervashidze"},{"issue":"9","key":"ref65","first-page":"2539","article-title":"Weisfeiler\u2013Lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93037-4_14"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref69","article-title":"Variational graph auto-encoders","author":"Kipf","year":"2016","journal-title":"arXiv:1611.07308"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380112"},{"key":"ref71","first-page":"2702","article-title":"Discriminative embeddings of latent variable models for structured data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref72","article-title":"Using self-supervised learning can improve model robustness and uncertainty","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hendrycks"},{"key":"ref73","first-page":"2983","article-title":"Adversarial self-supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kim"},{"key":"ref74","first-page":"1115","article-title":"Adversarial attack on graph structured data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref75","article-title":"On spectral clustering: Analysis and an algorithm","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"14","author":"Ng"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10663876\/10382709.pdf?arnumber=10382709","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:13:43Z","timestamp":1725473623000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10382709\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":75,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3339770","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}