{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:01:20Z","timestamp":1780761680417,"version":"3.54.1"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational Science"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.jocs.2026.102911","type":"journal-article","created":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T15:17:33Z","timestamp":1779549453000},"page":"102911","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Noise-adaptive bi-directional node-edge flow self-supervised method based Graph Information Bottleneck"],"prefix":"10.1016","volume":"98","author":[{"given":"Houchen","family":"Lv","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3421-4387","authenticated-orcid":false,"given":"Shanshan","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zebin","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yimin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jocs.2026.102911_b1","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: A graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J. Comput. Appl. Math."},{"issue":"1","key":"10.1016\/j.jocs.2026.102911_b2","doi-asserted-by":"crossref","first-page":"10","DOI":"10.3390\/data7010010","article-title":"The impact of global structural information in graph neural networks applications","volume":"7","author":"Buffelli","year":"2022","journal-title":"Data"},{"key":"10.1016\/j.jocs.2026.102911_b3","series-title":"Overlap-aware end-to-end supervised hierarchical graph clustering for speaker diarization","author":"Singh","year":"2024"},{"key":"10.1016\/j.jocs.2026.102911_b4","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b5","series-title":"Deep graph infomax","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"10.1016\/j.jocs.2026.102911_b6","first-page":"20437","article-title":"Graph information bottleneck","volume":"33","author":"Wu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.jocs.2026.102911_b7","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1162\/neco.1995.7.1.108","article-title":"Training with noise is equivalent to Tikhonov regularization","volume":"7","author":"Bishop","year":"1995","journal-title":"Neural Comput."},{"key":"10.1016\/j.jocs.2026.102911_b8","article-title":"Improving adversarial robustness via information bottleneck distillation","volume":"36","author":"Kuang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b9","article-title":"Interpretable prototype-based graph information bottleneck","volume":"36","author":"Seo","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b10","article-title":"Deep variational multivariate information bottleneck","author":"Martini","year":"2024","journal-title":"Bull. Am. Phys. Soc."},{"key":"10.1016\/j.jocs.2026.102911_b11","series-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"10.1016\/j.jocs.2026.102911_b12","series-title":"Data augmentation using llms: Data perspectives, learning paradigms and challenges","author":"Ding","year":"2024"},{"key":"10.1016\/j.jocs.2026.102911_b13","series-title":"Data augmentation in training CNNs: injecting noise to images","author":"Akbiyik","year":"2023"},{"key":"10.1016\/j.jocs.2026.102911_b14","doi-asserted-by":"crossref","unstructured":"B. Perozzi, R. Al-Rfou, S. Skiena, Deepwalk: Online learning of social representations, in: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014, pp. 701\u2013710.","DOI":"10.1145\/2623330.2623732"},{"key":"10.1016\/j.jocs.2026.102911_b15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-019-2914-2","article-title":"edge2vec: Representation learning using edge semantics for biomedical knowledge discovery","volume":"20","author":"Gao","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"10.1016\/j.jocs.2026.102911_b16","series-title":"Variational graph auto-encoders","author":"T. Kipf","year":"2016"},{"key":"10.1016\/j.jocs.2026.102911_b17","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b18","series-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"10.1016\/j.jocs.2026.102911_b19","article-title":"Co-embedding of nodes and edges with graph neural networks","author":"Jiang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jocs.2026.102911_b20","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"3508","article-title":"Graph contrastive learning with augmentations","author":"You","year":"2021"},{"key":"10.1016\/j.jocs.2026.102911_b21","series-title":"Semi-supervised semantic segmentation based on pseudo-labels: A survey","author":"Ran","year":"2024"},{"key":"10.1016\/j.jocs.2026.102911_b22","series-title":"2022 19th Conference on Robots and Vision","first-page":"58","article-title":"The gist and rist of iterative self-training for semi-supervised segmentation","author":"Teh","year":"2022"},{"issue":"1","key":"10.1016\/j.jocs.2026.102911_b23","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1007\/s40747-023-01167-4","article-title":"Uncertainty guided ensemble self-training for semi-supervised global field reconstruction","volume":"10","author":"Zhang","year":"2024","journal-title":"Complex & Intell. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b24","doi-asserted-by":"crossref","unstructured":"D. Kwon, S. Kwak, Semi-supervised semantic segmentation with error localization network, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9957\u20139967.","DOI":"10.1109\/CVPR52688.2022.00972"},{"key":"10.1016\/j.jocs.2026.102911_b25","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1109\/TIP.2021.3134142","article-title":"Learning from pixel-level label noise: A new perspective for semi-supervised semantic segmentation","volume":"31","author":"Yi","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jocs.2026.102911_b26","doi-asserted-by":"crossref","unstructured":"R. He, J. Yang, X. Qi, Re-distributing biased pseudo labels for semi-supervised semantic segmentation: A baseline investigation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 6930\u20136940.","DOI":"10.1109\/ICCV48922.2021.00685"},{"key":"10.1016\/j.jocs.2026.102911_b27","doi-asserted-by":"crossref","first-page":"32424","DOI":"10.52202\/068431-2349","article-title":"Debiased self-training for semi-supervised learning","volume":"35","author":"Chen","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"10.1016\/j.jocs.2026.102911_b28","doi-asserted-by":"crossref","first-page":"3599","DOI":"10.1109\/TCYB.2022.3159661","article-title":"A novel representation learning for dynamic graphs based on graph convolutional networks","volume":"53","author":"Gao","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.jocs.2026.102911_b29","doi-asserted-by":"crossref","first-page":"2803","DOI":"10.52202\/068431-0203","article-title":"Semi-supervised semantic segmentation via gentle teaching assistant","volume":"35","author":"Jin","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b30","article-title":"SFedXL: Semi-synchronous federated learning with cross-sharpness and layer-freezing","author":"Zhao","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.jocs.2026.102911_b31","series-title":"The information bottleneck method","author":"Tishby","year":"2000"},{"key":"10.1016\/j.jocs.2026.102911_b32","first-page":"20407","article-title":"Contrastive graph structure learning via information bottleneck for recommendation","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b33","series-title":"Path-based explanation for knowledge graph completion","author":"Chang","year":"2024"},{"key":"10.1016\/j.jocs.2026.102911_b34","article-title":"Task-oriented communication for graph data: A graph information bottleneck approach","author":"Li","year":"2024","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"10.1016\/j.jocs.2026.102911_b35","doi-asserted-by":"crossref","unstructured":"X. Yan, Z. Jin, F. Han, Y. Ye, Differentiable Information Bottleneck for Deterministic Multi-view Clustering, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 27435\u201327444.","DOI":"10.1109\/CVPR52733.2024.02590"},{"key":"10.1016\/j.jocs.2026.102911_b36","doi-asserted-by":"crossref","unstructured":"Z. Liu, X. Wang, X. Huang, et al., Incomplete Multi-View Representation Learning Through Anchor Graph-Based GCN and Information Bottleneck, in: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2024, pp. 1\u20135.","DOI":"10.1109\/ICASSP48485.2024.10446535"},{"key":"10.1016\/j.jocs.2026.102911_b37","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b38","first-page":"21618","article-title":"Rethinking graph transformers with spectral attention","volume":"34","author":"Kreuzer","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v091.i01","article-title":"dbscan: Fast density-based clustering with R","volume":"91","author":"Hahsler","year":"2019","journal-title":"J. Stat. Softw."},{"key":"10.1016\/j.jocs.2026.102911_b40","series-title":"Graph entropy guided node embedding dimension selection for graph neural networks","author":"Luo","year":"2021"},{"key":"10.1016\/j.jocs.2026.102911_b41","series-title":"Graph-level protein representation learning by structure knowledge refinement","author":"Wang","year":"2024"},{"key":"10.1016\/j.jocs.2026.102911_b42","doi-asserted-by":"crossref","unstructured":"C. Gallicchio, A. Micheli, Fast and deep graph neural networks, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, 2020, pp. 3898\u20133905.","DOI":"10.1609\/aaai.v34i04.5803"},{"key":"10.1016\/j.jocs.2026.102911_b43","doi-asserted-by":"crossref","unstructured":"C. Gallicchio, A. Micheli, Ring reservoir neural networks for graphs, in: 2020 International Joint Conference on Neural Networks, IJCNN, 2020, pp. 1\u20137.","DOI":"10.1109\/IJCNN48605.2020.9206723"},{"key":"10.1016\/j.jocs.2026.102911_b44","doi-asserted-by":"crossref","unstructured":"T.C. Bui, W.S. Li, Toward Interpretable Graph Classification via Concept-Focused Structural Correspondence, in: Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2024, pp. 20\u201331.","DOI":"10.1007\/978-981-97-2650-9_2"},{"key":"10.1016\/j.jocs.2026.102911_b45","doi-asserted-by":"crossref","unstructured":"B. Rozemberczki, O. Kiss, R. Sarkar, Karate Club: An API oriented open-source python framework for unsupervised learning on graphs, in: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 2020, pp. 3125\u20133132.","DOI":"10.1145\/3340531.3412757"},{"key":"10.1016\/j.jocs.2026.102911_b46","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102911_b47","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.jocs.2026.102911_b48","first-page":"1","article-title":"KNN-GCN: A deep learning approach for slope-unit-based landslide susceptibility mapping incorporating spatial correlations","author":"Xia","year":"2024","journal-title":"Math. Geosci."},{"key":"10.1016\/j.jocs.2026.102911_b49","series-title":"How powerful are graph neural networks?","author":"Xu","year":"2018"},{"key":"10.1016\/j.jocs.2026.102911_b50","unstructured":"H. Zhu, P. Koniusz, Simple spectral graph convolution, in: International Conference on Learning Representations, 2021, pp. 1\u201310."},{"key":"10.1016\/j.jocs.2026.102911_b51","doi-asserted-by":"crossref","unstructured":"J. Yu, J. Cao, R. He, Improving subgraph recognition with variational graph information bottleneck, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19396\u201319405.","DOI":"10.1109\/CVPR52688.2022.01879"},{"key":"10.1016\/j.jocs.2026.102911_b52","series-title":"Proceedings of the International Conference on Learning Representations","first-page":"1","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"10.1016\/j.jocs.2026.102911_b53","doi-asserted-by":"crossref","unstructured":"S. Feng, B. Jing, Y. Zhu, et al., Adversarial graph contrastive learning with information regularization, in: Proceedings of the ACM Web Conference 2022, 2022, pp. 1362\u20131371.","DOI":"10.1145\/3485447.3512183"},{"key":"10.1016\/j.jocs.2026.102911_b54","series-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","author":"Sohn","year":"2020"},{"key":"10.1016\/j.jocs.2026.102911_b55","series-title":"A review of pseudo-labeling for computer vision","author":"Kage","year":"2025"},{"key":"10.1016\/j.jocs.2026.102911_b56","series-title":"Self adaptive threshold pseudo-labeling and unreliable sample contrastive loss for semi-supervised image classification","author":"Zhang","year":"2024"},{"key":"10.1016\/j.jocs.2026.102911_b57","series-title":"Less is more: Pseudo-label filtering for continual test-time adaptation","author":"Tan","year":"2024"},{"issue":"3","key":"10.1016\/j.jocs.2026.102911_b58","doi-asserted-by":"crossref","DOI":"10.3390\/sym13030485","article-title":"A survey on knowledge graph embeddings for link prediction","volume":"13","author":"Wang","year":"2021","journal-title":"Symmetry"}],"container-title":["Journal of Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877750326001298?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877750326001298?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T15:40:38Z","timestamp":1780760438000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877750326001298"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":58,"alternative-id":["S1877750326001298"],"URL":"https:\/\/doi.org\/10.1016\/j.jocs.2026.102911","relation":{},"ISSN":["1877-7503"],"issn-type":[{"value":"1877-7503","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Noise-adaptive bi-directional node-edge flow self-supervised method based Graph Information Bottleneck","name":"articletitle","label":"Article Title"},{"value":"Journal of Computational Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jocs.2026.102911","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102911"}}