{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T07:54:28Z","timestamp":1781596468377,"version":"3.54.5"},"reference-count":77,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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":["Neural Networks"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.neunet.2026.109228","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:40:20Z","timestamp":1781278820000},"page":"109228","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Enhancing GNN learning with node augmentation"],"prefix":"10.1016","volume":"204","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1684-9506","authenticated-orcid":false,"given":"Maria","family":"Marrium","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5986-9876","authenticated-orcid":false,"given":"Arif","family":"Mahmood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9746-276X","authenticated-orcid":false,"given":"Muhammad Haris","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3729-2409","authenticated-orcid":false,"given":"M. Saad","family":"Shakeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9023-7252","authenticated-orcid":false,"given":"Wenxiong","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109228_bib0001","series-title":"ICPRAM","first-page":"249","article-title":"Gams: Graph augmentation with module swapping","author":"Bicciato","year":"2022"},{"key":"10.1016\/j.neunet.2026.109228_bib0002","series-title":"AAAI","first-page":"3913","article-title":"Regularizing graph neural networks via consistency-diversity graph augmentations","author":"Bo","year":"2022"},{"issue":"8","key":"10.1016\/j.neunet.2026.109228_bib0003","doi-asserted-by":"crossref","DOI":"10.1063\/5.0157367","article-title":"Generative pretrained autoregressive transformer graph neural network applied to the analysis and discovery of novel proteins","volume":"134","author":"Buehler","year":"2023","journal-title":"Journal of Applied Physics"},{"key":"10.1016\/j.neunet.2026.109228_bib0004","series-title":"AAAI","first-page":"3389","article-title":"A restricted black-box adversarial framework towards attacking graph embedding models","author":"Chang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109228_bib0005","series-title":"AAAI","first-page":"3438","article-title":"Measuring and relieving the over-smoothing problem for graph neural networks from the topological view","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.109228_bib0006","series-title":"Adedgedrop: Adversarial edge dropping for robust graph neural networks","author":"Chen","year":"2024"},{"key":"10.1016\/j.neunet.2026.109228_bib0007","series-title":"xAI-drop: Don\u2019t use what you cannot explain","author":"De Luca","year":"2024"},{"key":"10.1016\/j.neunet.2026.109228_bib0008","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.neunet.2023.08.039","article-title":"Self-supervised contrastive graph representation with node and graph augmentation","volume":"167","author":"Duan","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109228_bib0009","series-title":"AAAI","first-page":"4267","article-title":"Dropmessage: Unifying random dropping for graph neural networks","author":"Fang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109228_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107777","article-title":"Democratizing large language model-based graph data augmentation via latent knowledge graphs","volume":"191","author":"Feng","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109228_bib0011","unstructured":"Guo, H., & Mao, Y. (2021). ifmixup: Towards intrusion-free graph mixup for graph classification. 2110. arXiv preprint arXiv: 2110.09344."},{"key":"10.1016\/j.neunet.2026.109228_bib0012","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109228_bib0013","series-title":"TNNLS","article-title":"Structure-aware dropedge toward deep graph convolutional networks","author":"Han","year":"2023"},{"key":"10.1016\/j.neunet.2026.109228_bib0014","series-title":"G-mixup: Graph data augmentation for graph classification","author":"Han","year":"2022"},{"key":"10.1016\/j.neunet.2026.109228_bib0015","series-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"10.1016\/j.neunet.2026.109228_bib0016","series-title":"Deep anomaly detection with outlier exposure","author":"Hendrycks","year":"2018"},{"key":"10.1016\/j.neunet.2026.109228_bib0017","series-title":"CVPR","first-page":"16783","article-title":"Pixmix: Dreamlike pictures comprehensively improve safety measures","author":"Hendrycks","year":"2022"},{"key":"10.1016\/j.neunet.2026.109228_bib0018","series-title":"NeurIPS","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"Vol. 33","author":"Hu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109228_bib0019","series-title":"CVPR","first-page":"27621","article-title":"Diffusemix: Label-preserving data augmentation with diffusion models","author":"Islam","year":"2024"},{"key":"10.1016\/j.neunet.2026.109228_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.132273","article-title":"Genmix: Effective data augmentation with generative diffusion model image editing","volume":"322","author":"Islam","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109228_bib0021","series-title":"ICLR","article-title":"igraphmix: Input graph mixup method for node classification","author":"Jeong","year":"2024"},{"key":"10.1016\/j.neunet.2026.109228_bib0022","first-page":"55785","article-title":"Graphpatcher: Mitigating degree bias for graph neural networks via test-time augmentation","volume":"36","author":"Ju","year":"2023","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109228_bib0023","series-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016"},{"key":"10.1016\/j.neunet.2026.109228_bib0024","series-title":"CKIM","first-page":"4003","article-title":"S-mixup: Structural mixup for graph neural networks","author":"Kim","year":"2023"},{"key":"10.1016\/j.neunet.2026.109228_bib0025","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.neunet.2026.109228_bib0026","series-title":"CVPR","first-page":"60","article-title":"Robust optimization as data augmentation for large-scale graphs","author":"Kong","year":"2022"},{"key":"10.1016\/j.neunet.2026.109228_bib0027","series-title":"International conference on machine learning","article-title":"Aggregation buffer: Revisiting dropedge with a new parameter block","author":"Lee","year":"2025"},{"key":"10.1016\/j.neunet.2026.109228_bib0028","series-title":"Neural information processing systems NeurIPS, datasets and benchmarks track","article-title":"Evaluating graph neural networks for link prediction: Current pitfalls and new benchmarking","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.109228_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119815","article-title":"Graph neural networks with deep mutual learning for designing multi-modal recommendation systems","volume":"654","author":"Li","year":"2024","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2026.109228_bib0030","series-title":"AAAI","article-title":"Deeper insights into graph convolutional networks for semi-supervised learning","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2026.109228_bib0031","series-title":"GraphSHA: Synthesizing harder samples for class-imbalanced node classification","author":"Li","year":"2023"},{"issue":"4","key":"10.1016\/j.neunet.2026.109228_bib0032","first-page":"1","article-title":"Rationalizing graph neural networks with data augmentation","volume":"18","author":"Liu","year":"2024","journal-title":"ACM Trans. Knowl. Discov. Data."},{"key":"10.1016\/j.neunet.2026.109228_bib0033","first-page":"21039","article-title":"Data-centric learning from unlabeled graphs with diffusion model","volume":"36","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109228_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.126288","article-title":"LeDA-GNN: Learnable dual augmentation for graph neural networks","volume":"268","author":"Liu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109228_bib0035","series-title":"ICML","first-page":"14054","article-title":"Local augmentation for graph neural networks","author":"Liu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109228_bib0036","series-title":"TKDE","article-title":"Skipnode: On alleviating performance degradation for deep graph convolutional networks","author":"Lu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109228_bib0037","series-title":"International conference on learning representations","article-title":"Automated data augmentations for graph classification","author":"Luo","year":"2023"},{"key":"10.1016\/j.neunet.2026.109228_bib0038","series-title":"Data augmentation for graph data: Recent advancements","author":"Marrium","year":"2022"},{"key":"10.1016\/j.neunet.2026.109228_bib0039","first-page":"156158","article-title":"Diffusion-guided graph data augmentation","volume":"38","author":"Marrium","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109228_bib0040","series-title":"WSDM","first-page":"393-401","article-title":"Co-embedding attributed networks","author":"Meng","year":"2019"},{"key":"10.1016\/j.neunet.2026.109228_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106757","article-title":"Multi-relational graph contrastive learning with learnable graph augmentation","volume":"181","author":"Mo","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109228_bib0042","series-title":"Graph transplant: Node saliency-guided graph mixup with local structure preservation","author":"Park","year":"2021"},{"key":"10.1016\/j.neunet.2026.109228_bib0043","series-title":"ICLR","article-title":"Graphens: Neighbor-aware ego network synthesis for class-imbalanced node classification","author":"Park","year":"2021"},{"key":"10.1016\/j.neunet.2026.109228_bib0044","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1609\/aimag.v29i3.2157","article-title":"Collective classification in network data","volume":"29","author":"Prithviraj","year":"2008","journal-title":"AI Magazine"},{"key":"10.1016\/j.neunet.2026.109228_bib0045","series-title":"SIGKDD","first-page":"1390","article-title":"Imgagn: Imbalanced network embedding via generative adversarial graph networks","author":"Qu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109228_bib0046","series-title":"ICASSP","first-page":"1","article-title":"GraphVCM: Virtual center mixing with distance-aware regulation for class imbalanced node classification","author":"Ren","year":"2025"},{"key":"10.1016\/j.neunet.2026.109228_bib0047","series-title":"NeurIPS","first-page":"12559","article-title":"Self-supervised graph transformer on large-scale molecular data","volume":"Vol. 33","author":"Rong","year":"2020"},{"key":"10.1016\/j.neunet.2026.109228_bib0048","series-title":"ICLR","article-title":"Dropedge: Towards deep graph convolutional networks on node classification","author":"Rong","year":"2020"},{"key":"10.1016\/j.neunet.2026.109228_bib0049","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":"Journal of Computational and Applied Mathematics"},{"issue":"10","key":"10.1016\/j.neunet.2026.109228_bib0050","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3661821","article-title":"A survey of graph neural networks for social recommender systems","volume":"56","author":"Sharma","year":"2024","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2026.109228_bib0051","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107738","article-title":"Beyond homophily: Class imbalance graph classification via rewiring graph of graphs","volume":"192","author":"Shen","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109228_bib0052","series-title":"Topological regularization for graph neural networks augmentation","author":"Song","year":"2021"},{"issue":"8","key":"10.1016\/j.neunet.2026.109228_bib0053","doi-asserted-by":"crossref","first-page":"6267","DOI":"10.1007\/s00521-024-10923-7","article-title":"Enhancing link prediction in graph data augmentation through graphon mixup","volume":"37","author":"Sultana","year":"2025","journal-title":"Neural Computing and Applications"},{"key":"10.1016\/j.neunet.2026.109228_bib0054","series-title":"SIGKDD","first-page":"3585","article-title":"MoCL: Data-driven molecular fingerprint via knowledge-aware contrastive learning from molecular graph","author":"Sun","year":"2021"},{"key":"10.1016\/j.neunet.2026.109228_bib0055","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/j.neunet.2023.09.021","article-title":"Generalized heterophily graph data augmentation for node classification","volume":"168","author":"Tang","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109228_bib0056","first-page":"20","article-title":"Graph attention networks","volume":"1050","author":"Velickovic","year":"2017","journal-title":"stat"},{"key":"10.1016\/j.neunet.2026.109228_bib0057","series-title":"Graphmix: Improved training of gnns for semi-supervised learning","author":"Verma","year":"2019"},{"key":"10.1016\/j.neunet.2026.109228_bib0058","first-page":"1440","article-title":"Adaptive data augmentation on temporal graphs","volume":"34","author":"Wang","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109228_bib0059","series-title":"Diffusion on graph: Augmentation of graph structure for node classification","author":"Wang","year":"2025"},{"key":"10.1016\/j.neunet.2026.109228_bib0060","series-title":"Graphcrop: Subgraph cropping for graph classification","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109228_bib0061","series-title":"Web conference","first-page":"3663","article-title":"Mixup for node and graph classification","author":"Wang","year":"2021"},{"issue":"2","key":"10.1016\/j.neunet.2026.109228_bib0062","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1038\/s41562-017-0290-3","article-title":"Hiding individuals and communities in a social network","volume":"2","author":"Waniek","year":"2018","journal-title":"Nature Human Behaviour"},{"key":"10.1016\/j.neunet.2026.109228_bib0063","series-title":"How powerful are graph neural networks?","author":"Xu","year":"2018"},{"key":"10.1016\/j.neunet.2026.109228_bib0064","series-title":"International conference on machine learning","first-page":"11592","article-title":"Optimization of graph neural networks: Implicit acceleration by skip connections and more depth","author":"Xu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109228_bib0065","series-title":"CDS","first-page":"556","article-title":"Node augmentation methods for graph neural network based object classification","author":"Xue","year":"2021"},{"key":"10.1016\/j.neunet.2026.109228_bib0066","article-title":"A heterogeneous graph neural network model for list recommendation","volume":"277","author":"Yang","year":"2023","journal-title":"KBS"},{"key":"10.1016\/j.neunet.2026.109228_bib0067","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.neunet.2022.05.026","article-title":"Graph transformer networks: Learning meta-path graphs to improve gnns","volume":"153","author":"Yun","year":"2022","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109228_bib0068","series-title":"ICCV","first-page":"3713","article-title":"Be your own teacher: Improve the performance of convolutional neural networks via self distillation","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neunet.2026.109228_bib0069","series-title":"CVPR","first-page":"4320","article-title":"Deep mutual learning","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neunet.2026.109228_bib0070","series-title":"Graph data augmentation for graph machine learning: A survey","author":"Zhao","year":"2022"},{"key":"10.1016\/j.neunet.2026.109228_bib0071","series-title":"ICML","first-page":"26911","article-title":"Learning from counterfactual links for link prediction","author":"Zhao","year":"2022"},{"key":"10.1016\/j.neunet.2026.109228_bib0072","series-title":"AAAI","first-page":"11015","article-title":"Data augmentation for graph neural networks","author":"Zhao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109228_bib0073","series-title":"WSDM","first-page":"833","article-title":"Graphsmote: Imbalanced node classification on graphs with graph neural networks","author":"Zhao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109228_bib0074","series-title":"ACM SIGKDD","first-page":"4500","article-title":"Geomix: Towards geometry-aware data augmentation","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109228_bib0075","first-page":"75095","article-title":"Intramix: Intra-class mixup generation for accurate labels and neighbors","volume":"37","author":"Zheng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109228_bib0076","series-title":"TNNLS","first-page":"1","article-title":"Graph neural networks: A review of methods and applications from a robustness perspective","author":"Zhu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109228_bib0077","series-title":"ICLR","article-title":"Adversarial attacks on graph neural networks via meta learning","author":"Z\u00fcgner","year":"2019"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006891?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006891?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T07:16:51Z","timestamp":1781594211000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026006891"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":77,"alternative-id":["S0893608026006891"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109228","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing GNN learning with node augmentation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109228","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109228"}}