{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T11:03:41Z","timestamp":1781780621618,"version":"3.54.5"},"reference-count":62,"publisher":"Association for Computing Machinery (ACM)","issue":"2","funder":[{"name":"National Science and Technology Council (NSTC) of Taiwan","award":["113-2221-E-006-201-MY3, 112-2628-E-006-012-MY3, and 113-2634-F-002-007"],"award-info":[{"award-number":["113-2221-E-006-201-MY3, 112-2628-E-006-012-MY3, and 113-2634-F-002-007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2026,4,30]]},"abstract":"<jats:p>\n                    <jats:bold>Graph Neural Networks (GNNs)<\/jats:bold>\n                    have recently achieved remarkable performance on the node classification task. While most typical GNN models presume that the graph data is clean, however, graphs could be polluted by various noises that hurt the prediction accuracy. Besides, while GNNs rely on sufficient labeled data to propagate the supervision signal, we should move to a more realistic setting\u2014to learn with a limited amount of labeled data, i.e., label scarcity. In this work, we aim at building a\n                    <jats:bold>Holistically Robust Graph Neural Network (HRGNN)<\/jats:bold>\n                    against four different types of graph noise, including adversarial attacks, edge sparsity, noisy labels, and high heterophily, in the presence of label scarcity. We proposed a novel GNN framework, HRGNN, to fulfill the goal. The main idea of HRGNN is to create synthetic nodes with labels and learn to properly connect them with existing nodes. With synthetic nodes, HRGNN can inject reliable information into existing nodes due to the message-passing mechanism of GNNs that helps purify the polluted representations of nodes and alleviate the negative effect caused by various noises. Furthermore, edge filtering in HRGNN helps remove the noisy edges to prevent the propagation of incorrect information, while pseudo-labeling provides more label information to defend against label scarcity and label noise. Experiments conducted on eight graph datasets exhibit that HRGNN consistently outperforms the state-of-the-art GNN competing models on four types of noisy settings with label scarcity. To the best of our knowledge, HRGNN is the first GNN model that is holistically robust to various types of noise and label scarcity.\n                  <\/jats:p>","DOI":"10.1145\/3786603","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T13:45:51Z","timestamp":1767015951000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["HRGNN: Learning Holistically Robust Graph Neural Networks on Noisy Graphs with Label Scarcity"],"prefix":"10.1145","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3783-0209","authenticated-orcid":false,"given":"Jun-Wei","family":"Chiu","sequence":"first","affiliation":[{"name":"National Cheng Kung University, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7995-4787","authenticated-orcid":false,"given":"Cheng-Te","family":"Li","sequence":"additional","affiliation":[{"name":"National Cheng Kung University, Tainan, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,2,19]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2022. BEiT: BERT pre-training of image transformers. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/361002.361007"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16514"},{"key":"e_1_3_2_5_2","unstructured":"Eli Chien Jianhao Peng Pan Li and Olgica Milenkovic. 2020. Adaptive universal generalized PageRank graph neural network. arXiv:2006.07988. Retrieved from https:\/\/arxiv.org\/abs\/2006.07988"},{"key":"e_1_3_2_6_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Chien Eli","year":"2021","unstructured":"Eli Chien, Jianhao Peng, Pan Li, and Olgica Milenkovic. 2021. Adaptive universal generalized PageRank graph neural network. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467364"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3488560.3498408"},{"key":"e_1_3_2_9_2","first-page":"1115","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Dai Hanjun","year":"2018","unstructured":"Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, and Le Song. 2018. Adversarial attack on graph structured data. In Proceedings of the International Conference on Machine Learning, 1115\u20131124."},{"key":"e_1_3_2_10_2","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, 4171\u20134186."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371789"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009778005914"},{"key":"e_1_3_2_13_2","volume-title":"Proceedings of the 2019 International Conference on Machine Learning (ICML)","author":"Gao Hongyang","year":"2019","unstructured":"Hongyang Gao and Shuiwang Ji. 2019. Graph U-nets. In Proceedings of the 2019 International Conference on Machine Learning (ICML)."},{"key":"e_1_3_2_14_2","first-page":"3419","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Garg Vikas","year":"2020","unstructured":"Vikas Garg, Stefanie Jegelka, and Tommi Jaakkola. 2020. Generalization and representational limits of graph neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 3419\u20133430."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/276675.276685"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/645925.671516"},{"key":"e_1_3_2_17_2","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton Will","year":"2017","unstructured":"Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 30.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539321"},{"key":"e_1_3_2_20_2","unstructured":"Wei Jin Tyler Derr Haochen Liu Yiqi Wang Suhang Wang Zitao Liu and Jiliang Tang. 2020. Self-supervised learning on graphs: Deep insights and new direction. arXiv:2006.10141. Retrieved from https:\/\/arxiv.org\/abs\/2006.10141"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437963.3441735"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447556.3447566"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403049"},{"key":"e_1_3_2_24_2","first-page":"6314","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Ju Haotian","year":"2023","unstructured":"Haotian Ju, Dongyue Li, Aneesh Sharma, and Hongyang R. Zhang. 2023. Generalization in graph neural networks: Improved PAC-Bayesian bounds on graph diffusion. In Proceedings of the International Conference on Artificial Intelligence and Statistics. PMLR, 6314\u20136341."},{"key":"e_1_3_2_25_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Kim Dongkwan","year":"2021","unstructured":"Dongkwan Kim and Alice Oh. 2021. How to find your friendly neighborhood: Graph attention design with self-supervision. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_26_2","volume-title":"Proceedings of the NIPS Workshop on Bayesian Deep Learning 2016","author":"Kipf Thomas N.","year":"2016","unstructured":"Thomas N. Kipf and Max Welling. 2016. Variational graph auto-encoders. In Proceedings of the NIPS Workshop on Bayesian Deep Learning 2016."},{"key":"e_1_3_2_27_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"e_1_3_2_29_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Liao Renjie","year":"2021","unstructured":"Renjie Liao, Raquel Urtasun, and Richard Zemel. 2021. A PAC-Bayesian approach to generalization bounds for graph neural networks. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3134200"},{"key":"e_1_3_2_31_2","unstructured":"Sitao Luan Chenqing Hua Qincheng Lu Jiaqi Zhu Mingde Zhao Shuyuan Zhang Xiao-Wen Chang and Doina Precup. 2021. Is heterophily a real nightmare for graph neural networks to do node classification? arXiv:2109.05641. Retrieved from https:\/\/arxiv.org\/abs\/2109.05641"},{"key":"e_1_3_2_32_2","unstructured":"Shaogao Lv. 2021. Generalization bounds for graph convolutional neural networks via Rademacher complexity. arXiv:2102.10234. Retrieved from https:\/\/arxiv.org\/abs\/2102.10234"},{"key":"e_1_3_2_33_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Ma Yao","year":"2022","unstructured":"Yao Ma, Xiaorui Liu, Neil Shah, and Jiliang Tang. 2022. Is homophily a necessity for graph neural networks? In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_34_2","first-page":"4805","article-title":"Generalization analysis of message passing neural networks on large random graphs","volume":"35","author":"Maskey Sohir","year":"2022","unstructured":"Sohir Maskey, Ron Levie, Yunseok Lee, and Gitta Kutyniok. 2022. Generalization analysis of message passing neural networks on large random graphs. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 35, 4805\u20134817.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009953814988"},{"key":"e_1_3_2_36_2","volume-title":"Proceedings of the ICLR 2019 Workshop on Learning from Limited Labeled Data","author":"NT Hoang","year":"2019","unstructured":"Hoang NT, Jun Jin Choong, and Tsuyoshi Murata. 2019. Learning graph neural networks with noisy labels. In Proceedings of the ICLR 2019 Workshop on Learning from Limited Labeled Data."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.5555\/3304889.3305023"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00662"},{"key":"e_1_3_2_39_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Pei Hongbin","year":"2020","unstructured":"Hongbin Pei, Bingzhe Wei, Kevin Chen-Chuan Chang, Yu Lei, and Bo Yang. 2020. Geom-GCN: Geometric graph convolutional networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467334"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5997"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17147"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557108"},{"key":"e_1_3_2_45_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467295"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132967"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00070"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330836"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/669"},{"key":"e_1_3_2_51_2","unstructured":"Xugang Wu Huijun Wu Xu Zhou and Kai Lu. 2021. CoG: A two-view co-training framework for defending adversarial attacks on graph. arXiv:2109.05558. Retrieved from https:\/\/arxiv.org\/abs\/2109.05558"},{"key":"e_1_3_2_52_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How powerful are graph neural networks? In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_53_2","first-page":"1417","volume-title":"Proceedings of International Conference on Joint Conferences on Artificial Intelligence (IJCAI)","author":"Yang Xiaoyu","year":"2021","unstructured":"Xiaoyu Yang, Yuefei Lyu, Tian Tian, Yifei Liu, Yudong Liu, and Xi Zhang. 2021. Rumor detection on social media with graph structured adversarial learning. In Proceedings of International Conference on Joint Conferences on Artificial Intelligence (IJCAI), 1417\u20131423."},{"key":"e_1_3_2_54_2","first-page":"4805","volume-title":"Proceedings of the 2018 Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Ying Rex","year":"2018","unstructured":"Rex Ying, Jiaxuan You, Christopher Morris, Xiang Ren, William L. Hamilton, and Jure Leskovec. 2018. Hierarchical graph representation learning with differentiable pooling. In Proceedings of the 2018 Annual Conference on Neural Information Processing Systems (NeurIPS), 4805\u20134815."},{"key":"e_1_3_2_55_2","first-page":"7164","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Yu Xingrui","year":"2019","unstructured":"Xingrui Yu, Bo Han, Jiangchao Yao, Gang Niu, Ivor Tsang, and Masashi Sugiyama. 2019. How does disagreement help generalization against label corruption? In Proceedings of the International Conference on Machine Learning (ICML), 7164\u20137173."},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM50108.2020.00088"},{"key":"e_1_3_2_57_2","first-page":"9263","article-title":"GNNGuard: Defending graph neural networks against adversarial attacks","volume":"33","author":"Zhang Xiang","year":"2020","unstructured":"Xiang Zhang and Marinka Zitnik. 2020. GNNGuard: Defending graph neural networks against adversarial attacks. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 9263\u20139275.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"issue":"7","key":"e_1_3_2_58_2","first-page":"7251","article-title":"Multi-grained semantics-aware graph neural networks","volume":"35","author":"Zhong Zhiqiang","year":"2022","unstructured":"Zhiqiang Zhong, Cheng-Te Li, and Jun Pang. 2022. Multi-grained semantics-aware graph neural networks. IEEE Transactions on Knowledge and Data Engineering 35, 7 (2022), 7251\u20137262.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00890-9"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330851"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539418"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220078"},{"key":"e_1_3_2_63_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Z\u00fcgner Daniel","year":"2019","unstructured":"Daniel Z\u00fcgner and Stephan G\u00fcnnemann. 2019. Adversarial attacks on graph neural networks via meta learning. In Proceedings of the International Conference on Learning Representations (ICLR)."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T12:33:11Z","timestamp":1772800391000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,19]]},"references-count":62,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,30]]}},"alternative-id":["10.1145\/3786603"],"URL":"https:\/\/doi.org\/10.1145\/3786603","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,19]]},"assertion":[{"value":"2025-02-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}