{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:59:44Z","timestamp":1768525184584,"version":"3.49.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T00:00:00Z","timestamp":1691712000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T00:00:00Z","timestamp":1691712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"NCSR - Demokritos Library"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this paper, we propose a novel framework, called STAL, which makes use of unlabeled graph data, through a combination of Active Learning and Self-Training, in order to improve node labeling by Graph Neural Networks (GNNs). GNNs have been shown to perform well on many tasks, when sufficient labeled data are available. Such data, however, is often scarce, leading to the need for methods that leverage unlabeled data that are abundant. Active Learning and Self-training are two common approaches towards this goal and we investigate here their combination, in the context of GNN training. Specifically, we propose a new framework that first uses active learning to select highly uncertain unlabeled nodes to be labeled and be included in the training set. In each iteration of active labeling, the proposed method expands also the label set through self-training. In particular, highly certain pseudo-labels are obtained and added automatically to the training set. This process is repeated, leading to good classifiers, with a limited amount of labeled data. Our experimental results on various datasets confirm the efficiency of the proposed approach.<\/jats:p>","DOI":"10.1007\/s10618-023-00959-z","type":"journal-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T07:02:25Z","timestamp":1691737345000},"page":"110-127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Improving Graph Neural Networks by combining active learning with self-training"],"prefix":"10.1007","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3697-941X","authenticated-orcid":false,"given":"Georgios","family":"Katsimpras","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Paliouras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,11]]},"reference":[{"key":"959_CR1","unstructured":"Aggarwal CC, Kong X, Gu Q, Han J, Philip SY (2014) Active learning: a survey. In: Data Classification, pp 599\u2013634"},{"key":"959_CR2","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.ins.2018.05.028","volume":"460\u2013461","author":"A Appice","year":"2018","unstructured":"Appice A, Loglisci C, Malerba D (2018) Active learning via collective inference in network regression problems. Inf Sci 460\u2013461:293\u2013317. https:\/\/doi.org\/10.1016\/j.ins.2018.05.028","journal-title":"Inf Sci"},{"key":"959_CR3","doi-asserted-by":"crossref","unstructured":"Beluch WH, Genewein T, N\u00fcrnberger A, K\u00f6hler JM (2018) The power of ensembles for active learning in image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9368\u20139377","DOI":"10.1109\/CVPR.2018.00976"},{"key":"959_CR4","unstructured":"Bilgic M, Mihalkova L, Getoor L (2010) Active learning for networked data. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 79\u201386"},{"key":"959_CR5","unstructured":"Brockschmidt M (2020) GNN-film: Graph Neural Networks with feature-wise linear modulation. In: International conference on machine learning, PMLR, pp 1144\u20131152"},{"key":"959_CR6","unstructured":"Cai H, Zheng VW, Chang KC-C (2017) Active learning for graph embedding. Preprint arXiv:1705.05085"},{"key":"959_CR7","doi-asserted-by":"crossref","unstructured":"Caron M, Bojanowski P, Joulin A, Douze M (2018) Deep clustering for unsupervised learning of visual features. In: Proceedings of the European conference on computer vision (ECCV), pp 132\u2013149","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"959_CR8","doi-asserted-by":"crossref","unstructured":"Chan Y-C, Li M, Oymak S (2021) On the marginal benefit of active learning: Does self-supervision eat its cake? In: ICASSP 2021-2021 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 3455\u20133459","DOI":"10.1109\/ICASSP39728.2021.9414665"},{"key":"959_CR9","first-page":"13086","volume":"34","author":"DS Chaplot","year":"2021","unstructured":"Chaplot DS, Dalal M, Gupta S, Malik J, Salakhutdinov RR (2021) Seal: self-supervised embodied active learning using exploration and 3d consistency. Adv Neural Inf Process Syst 34:13086\u201313098","journal-title":"Adv Neural Inf Process Syst"},{"key":"959_CR11","doi-asserted-by":"publisher","unstructured":"Dai E, Aggarwal C, Wang S (2021) NRGNN: learning a label noise resistant Graph Neural Network on sparsely and noisily labeled graphs. In: Zhu F, Ooi BC, Miao C (eds) KDD \u201921: the 27th ACM SIGKDD conference on knowledge discovery and data mining, virtual event, Singapore, pp 227\u2013236. https:\/\/doi.org\/10.1145\/3447548.3467364","DOI":"10.1145\/3447548.3467364"},{"issue":"10","key":"959_CR12","doi-asserted-by":"publisher","first-page":"988","DOI":"10.3390\/e21100988","volume":"21","author":"N Fazakis","year":"2019","unstructured":"Fazakis N, Kanas VG, Aridas CK, Karlos S, Kotsiantis S (2019) Combination of active learning and semi-supervised learning under a self-training scheme. Entropy 21(10):988","journal-title":"Entropy"},{"key":"959_CR13","unstructured":"Feng Q, He K, Wen H, Keskin C, Ye Y (2021) Active learning with pseudo-labels for multi-view 3d pose estimation. Preprint arXiv:2112.13709"},{"key":"959_CR14","unstructured":"Fey M, Lenssen JE (2019) Fast graph representation learning with PyTorch Geometric. In: ICLR workshop on representation learning on graphs and manifolds"},{"key":"959_CR15","doi-asserted-by":"crossref","unstructured":"Gao L, Yang H, Zhou C, Wu J, Pan S, Hu Y (2018) Active discriminative network representation learning. In: IJCAI international joint conference on artificial intelligence","DOI":"10.24963\/ijcai.2018\/296"},{"key":"959_CR16","doi-asserted-by":"crossref","unstructured":"Gu Q, Aggarwal C, Liu J, Han J (2013) Selective sampling on graphs for classification. In: Proceedings of the 19th ACM SIGKDD international conference on knowledge discovery and data mining, pp 131\u2013139","DOI":"10.1145\/2487575.2487641"},{"key":"959_CR17","unstructured":"Hamilton WL, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: Guyon I, von Luxburg U, Bengio S, Wallach HM, Fergus R, Vishwanathan SVN, Garnett R (eds) NIPS, pp 1024\u20131034. http:\/\/dblp.uni-trier.de\/db\/conf\/nips\/nips2017.htmlHamiltonYL17"},{"key":"959_CR18","doi-asserted-by":"crossref","unstructured":"Hao Z, Lu C, Huang Z, Wang H, Hu Z, Liu Q, Chen E, Lee C (2020) Asgn: an active semi-supervised Graph Neural Network for molecular property prediction. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp 731\u2013752","DOI":"10.1145\/3394486.3403117"},{"key":"959_CR19","first-page":"10174","volume":"33","author":"S Hu","year":"2020","unstructured":"Hu S, Xiong Z, Qu M, Yuan X, C\u00f4t\u00e9 M-A, Liu Z, Tang J (2020) Graph policy network for transferable active learning on graphs. Adv Neural Inf Process Syst 33:10174\u201310185","journal-title":"Adv Neural Inf Process Syst"},{"key":"959_CR20","unstructured":"Hu W, Fey M, Zitnik M, Dong Y, Ren H, Liu B, Catasta M, Leskovec J (2020) Open graph benchmark: datasets for machine learning on graphs. Preprint arXiv:2005.00687"},{"key":"959_CR21","unstructured":"Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations, ICLR 2015\u2014conference track proceedings"},{"key":"959_CR22","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: 5th international conference on learning representations, ICLR 2017, Toulon, Conference Track Proceedings"},{"key":"959_CR23","doi-asserted-by":"crossref","unstructured":"Kwak B-w, Kim Y, Kim YJ, Hwang S-w, Yeo J (2022) Trustal: Trustworthy active learning using knowledge distillation. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 7263\u20137271","DOI":"10.1609\/aaai.v36i7.20688"},{"key":"959_CR24","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1016\/j.neucom.2022.08.010","volume":"514","author":"J Li","year":"2022","unstructured":"Li J (2022) Nang-st: a natural neighborhood graph-based self-training method for semi-supervised classification. Neurocomputing 514:268\u2013284. https:\/\/doi.org\/10.1016\/j.neucom.2022.08.010","journal-title":"Neurocomputing"},{"key":"959_CR25","doi-asserted-by":"crossref","unstructured":"Li Q, Han Z, Wu X (2018) Deeper insights into graph convolutional networks for semi-supervised learning. In: McIlraith SA, Weinberger KQ (eds) Proceedings of the thirty-second AAAI conference on artificial intelligence (AAAI-18), the 30th innovative applications of artificial intelligence (IAAI-18), and the 8th AAAI symposium on educational advances in artificial intelligence (EAAI-18), New Orleans, pp 3538\u20133545. https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16098","DOI":"10.1609\/aaai.v32i1.11604"},{"issue":"9","key":"959_CR26","first-page":"1","volume":"54","author":"P Ren","year":"2021","unstructured":"Ren P, Xiao Y, Chang X, Huang P-Y, Li Z, Gupta BB, Chen X, Wang X (2021) A survey of deep active learning. ACM Comput Survs (CSUR) 54(9):1\u201340","journal-title":"ACM Comput Survs (CSUR)"},{"key":"959_CR27","unstructured":"Schr\u00f6der C, Niekler A (2020) A survey of active learning for text classification using deep neural networks. Preprint arXiv:2008.07267"},{"key":"959_CR28","unstructured":"Settles B (2009) Active learning literature survey"},{"key":"959_CR29","doi-asserted-by":"crossref","unstructured":"Settles B, Craven M (2008) An analysis of active learning strategies for sequence labeling tasks. In: Proceedings of the 2008 conference on empirical methods in natural language processing, pp 1070\u20131079","DOI":"10.3115\/1613715.1613855"},{"key":"959_CR30","unstructured":"Shui C, Zhou F, Gagn\u00e9 C, Wang B (2020) Deep active learning: unified and principled method for query and training. In: International conference on artificial intelligence and statistics, PMLR, pp 1308\u20131318"},{"key":"959_CR31","doi-asserted-by":"crossref","unstructured":"Sun K, Lin Z, Zhu Z (2020) Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes. In: The thirty-Fourth AAAI conference on artificial intelligence, AAAI 2020, The thirty-second innovative applications of artificial intelligence conference, IAAI 2020, The tenth AAAI symposium on educational advances in artificial intelligence, EAAI 2020, New York, pp 5892\u20135899. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/6048","DOI":"10.1609\/aaai.v34i04.6048"},{"key":"959_CR32","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y (2017) Graph attention networks. In: ICLR 2018, Preprint arXiv:1710.10903"},{"key":"959_CR33","doi-asserted-by":"crossref","unstructured":"Wang C, Pan S, Hu R, Long G, Jiang J, Zhang C (2019) Attributed graph clustering: a deep attentional embedding approach. Preprint arXiv:1906.06532","DOI":"10.24963\/ijcai.2019\/509"},{"key":"959_CR35","unstructured":"Wang X, Liu H, Shi C, Yang C (2021) Be confident! Towards trustworthy graph neural networks via confidence calibration. In: Ranzato M, Beygelzimer A, Dauphin YN, Liang P, Vaughan JW (eds) Advances in neural information processing systems 34: annual conference on neural information processing systems 2021, NeurIPS 2021, Virtual, pp 23768\u201323779"},{"key":"959_CR36","unstructured":"Wu F, Jr, AHS, Zhang T, Fifty C, Yu T, Weinberger KQ (2019) Simplifying graph convolutional networks. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th international conference on machine learning, ICML 2019, Long Beach, Proceedings of machine learning research, vol 97, pp 6861\u20136871. http:\/\/proceedings.mlr.press\/v97\/wu19e.html"},{"issue":"4","key":"959_CR37","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1109\/TBDATA.2021.3140205","volume":"8","author":"Y Xie","year":"2022","unstructured":"Xie Y, Lv S, Qian Y, Wen C, Liang J (2022) Active and semi-supervised graph neural networks for graph classification. IEEE Trans Big Data 8(4):920\u2013932. https:\/\/doi.org\/10.1109\/TBDATA.2021.3140205","journal-title":"IEEE Trans Big Data"},{"key":"959_CR38","unstructured":"Xu K, Hu W, Leskovec J, Jegelka S (2019) How powerful are graph neural networks? In: 7th international conference on learning representations, ICLR 2019, New Orleans. https:\/\/openreview.net\/forum?id=ryGs6iA5Km"},{"key":"959_CR39","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s11263-014-0781-x","volume":"113","author":"Y Yang","year":"2015","unstructured":"Yang Y, Ma Z, Nie F, Chang X, Hauptmann AG (2015) Multi-class active learning by uncertainty sampling with diversity maximization. Int J Comput Vis 113:113\u2013127","journal-title":"Int J Comput Vis"},{"key":"959_CR40","unstructured":"Yang Z, Cohen WW, Salakhutdinov R (2016) Revisiting semi-supervised learning with graph embeddings. In: Balcan M, Weinberger KQ (eds) Proceedings of the 33nd international conference on machine learning, ICML 2016, New York City, JMLR Workshop and conference proceedings, vol 48, pp 40\u201348. http:\/\/proceedings.mlr.press\/v48\/yanga16.html"},{"key":"959_CR41","doi-asserted-by":"publisher","unstructured":"Yang H, Yan X, Dai X, Chen Y, Cheng J (2021) Self-enhanced GNN: improving Graph Neural Networks using model outputs. In: International joint conference on neural networks, IJCNN 2021, Shenzhen, IEEE, pp 1\u20138. https:\/\/doi.org\/10.1109\/IJCNN52387.2021.9533748","DOI":"10.1109\/IJCNN52387.2021.9533748"},{"key":"959_CR42","doi-asserted-by":"crossref","unstructured":"Yi JSK, Seo M, Park J, Choi D-G (2022) Pt4al: Using self-supervised pretext tasks for active learning. In: Computer vision\u2013ECCV 2022: 17th European conference, Tel Aviv, Proceedings, Part XXVI, Springer, pp 596\u2013612","DOI":"10.1007\/978-3-031-19809-0_34"},{"key":"959_CR43","first-page":"5812","volume":"33","author":"Y You","year":"2020","unstructured":"You Y, Chen T, Sui Y, Chen T, Wang Z, Shen Y (2020) Graph contrastive learning with augmentations. Adv Neural Inf Process Syst 33:5812\u20135823","journal-title":"Adv Neural Inf Process Syst"},{"key":"959_CR44","doi-asserted-by":"crossref","unstructured":"Yu Y, Kong L, Zhang J, Zhang R, Zhang C (2022) Actune: uncertainty-based active self-training for active fine-tuning of pretrained language models. In: Proceedings of the 2022 conference of the North American chapter of the association for computational linguistics: human language technologies, pp 1422\u20131436","DOI":"10.18653\/v1\/2022.naacl-main.102"},{"key":"959_CR45","unstructured":"Zhan X, Wang Q, Huang K-h, Xiong H, Dou D, Chan AB (2022) A comparative survey of deep active learning. Preprint arXiv:2203.13450"},{"key":"959_CR46","unstructured":"Zhang M, Chen Y (2018) Link prediction based on Graph Neural Networks. Adv Neural Inf Process Syst 31"},{"key":"959_CR47","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","volume":"1","author":"J Zhou","year":"2020","unstructured":"Zhou J, Cui G, Hu S, Zhang Z, Yang C, Liu Z, Wang L, Li C, Sun M (2020) Graph Neural Networks: a review of methods and applications. AI Open 1:57\u201381. https:\/\/doi.org\/10.1016\/j.aiopen.2021.01.001","journal-title":"AI Open"},{"issue":"1","key":"959_CR48","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1145\/3495161","volume":"13","author":"Y Zhou","year":"2022","unstructured":"Zhou Y, Zheng H, Huang X, Hao S, Li D, Zhao J (2022) Graph Neural Networks: taxonomy, advances, and trends. ACM Trans Intell Syst Technol 13(1):15\u201311554. https:\/\/doi.org\/10.1145\/3495161","journal-title":"ACM Trans Intell Syst Technol"},{"key":"959_CR49","doi-asserted-by":"publisher","unstructured":"Zhu X, Goldberg AB (2009) Introduction to semi-supervised learning. In: Synthesis lectures on artificial intelligence and machine learning. Morgan & Claypool Publishers. https:\/\/doi.org\/10.2200\/S00196ED1V01Y200906AIM006","DOI":"10.2200\/S00196ED1V01Y200906AIM006"},{"key":"959_CR50","doi-asserted-by":"crossref","unstructured":"Zhu J, Wang H, Yao T, Tsou BK (2008) Active learning with sampling by uncertainty and density for word sense disambiguation and text classification. In: Proceedings of the 22nd international conference on computational linguistics (Coling 2008), pp 1137\u20131144","DOI":"10.3115\/1599081.1599224"},{"key":"959_CR51","unstructured":"Zhu Y, Xu W, Liu Q, Wu S (2020) When contrastive learning meets active learning: a novel graph active learning paradigm with self-supervision. Preprint arXiv:2010.16091"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-023-00959-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10618-023-00959-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-023-00959-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T17:50:20Z","timestamp":1705513820000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10618-023-00959-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,11]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["959"],"URL":"https:\/\/doi.org\/10.1007\/s10618-023-00959-z","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,11]]},"assertion":[{"value":"11 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}