{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:50:41Z","timestamp":1776491441265,"version":"3.51.2"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:00:00Z","timestamp":1774051200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T00:00:00Z","timestamp":1774051200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004913","name":"Universit\u00e0 degli Studi di Palermo","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004913","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Graph Neural Networks (GNNs) are powerful models that can manage complex data sources and their interconnection links. Still, one of GNNs\u2019 main drawbacks is their lack of explainability, which limits their application in sensitive fields. In this paper, we introduce a new approach involving graph communities to address the explainability of graph classification problems, called Graph Neural Network Explainer based on Communities (GECo). Taking into consideration that a community is a subset of graph nodes that are densely connected, GECo exploits the idea that these subgraphs should play a key role in graph classification. This assumption is reasonable, especially if we consider the message-passing mechanism, which is the basic mechanism of GNNs. GECo analyzes the contribution to the classification result of the communities in the graph, building a mask that highlights graph-relevant structures. GECo is tested for Graph Convolutional Networks on six artificial and four real-world graph datasets and is compared to the main explainability methods, such as PGMExplainer, PGExplainer, GNNExplainer, TAGE, and SubgraphX, using six different metrics. The obtained results outperform the other methods for artificial graph datasets and most real-world datasets. Furthermore, GECo is faster than most of the competitors since it does not need to make use of any sampling process.<\/jats:p>","DOI":"10.1007\/s00607-026-01642-z","type":"journal-article","created":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T07:04:48Z","timestamp":1774076688000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GECo: a community-based graph neural network explainer"],"prefix":"10.1007","volume":"108","author":[{"given":"Domenico","family":"Amato","sequence":"first","affiliation":[]},{"given":"Salvatore","family":"Calderaro","sequence":"additional","affiliation":[]},{"given":"Giosu\u00e8","family":"Lo Bosco","sequence":"additional","affiliation":[]},{"given":"Riccardo","family":"Rizzo","sequence":"additional","affiliation":[]},{"given":"Filippo","family":"Vella","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,21]]},"reference":[{"key":"1642_CR1","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/978-3-030-34585-3_11","volume-title":"Computational intelligence methods for bioinformatics and biostatistics","author":"D Amato","year":"2020","unstructured":"Amato D, Di Gangi MA, Lo Bosco G, Rizzo R (2020) Recurrent deep neural networks for nucleosome classification. In: Raposo M, Ribeiro P, S\u00e9rio S, Staiano A, Ciaramella A (eds) Computational intelligence methods for bioinformatics and biostatistics. Springer, Cham, pp 118\u2013127"},{"key":"1642_CR2","doi-asserted-by":"publisher","unstructured":"Amato D, Di Gangi MA, Fiannaca A, La Paglia L, La Rosa M, Lo Bosco G, Rizzo R, Urso A (2021) In: Elloumi, M. (ed.) Classification of sequences with deep artificial neural networks: representation and architectural issues, pp 27\u201359. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-71676-9_2","DOI":"10.1007\/978-3-030-71676-9_2"},{"key":"1642_CR3","doi-asserted-by":"crossref","unstructured":"Amato D, Calderaro S, Lo\u00a0Bosco G, Rizzo R, Vella F (2024) Explainable histopathology image classification with self-organizing maps: a granular computing perspective. Cognitive Computation, 1\u201321","DOI":"10.1007\/s12559-024-10312-1"},{"issue":"13","key":"1642_CR4","doi-asserted-by":"publisher","first-page":"6003","DOI":"10.3390\/s23136003","volume":"23","author":"D Amato","year":"2023","unstructured":"Amato D, Calderaro S, Lo Bosco G, Rizzo R, Vella F (2023) Metric learning in histopathological image classification: opening the black box. Sensors 23(13):6003","journal-title":"Sensors"},{"key":"1642_CR5","doi-asserted-by":"crossref","unstructured":"Calderaro S, Lo Bosco G, Vella F, Rizzo R (2023) Breast cancer histologic grade identification by graph neural network embeddings. In: International work-conference on bioinformatics and biomedical engineering, pp 283\u2013296. Springer","DOI":"10.1007\/978-3-031-34960-7_20"},{"key":"1642_CR6","doi-asserted-by":"crossref","unstructured":"Amato D, Calderaro S, Lo\u00a0Bosco G, Rizzo R, Vella F (2024) Semantic segmentation of gliomas on brain mris by graph convolutional neural networks. In: 2024 international conference on AI X data and knowledge engineering (AIxDKE), pp 143\u2013149. IEEE","DOI":"10.1109\/AIxDKE63520.2024.00036"},{"key":"1642_CR7","doi-asserted-by":"crossref","unstructured":"Amato D, Calderaro S, Lo Bosco G, Rizzo R, Vella F (2024) Bacteria taxonomic classification using graph neural networks. In: 2024 IEEE international conference on evolving and adaptive intelligent systems (EAIS), pp 1\u20136. IEEE","DOI":"10.1109\/EAIS58494.2024.10569104"},{"key":"1642_CR8","doi-asserted-by":"crossref","unstructured":"Amato D, Calderaro S, Lo\u00a0Bosco G, Vella F, Rizzo R (2025) Proteins transcription factor prediction using graph neural networks. In: International meeting on computational intelligence methods for bioinformatics and biostatistics, pp 15\u201327. Springer","DOI":"10.1007\/978-3-031-89704-7_2"},{"key":"1642_CR9","unstructured":"Fortunato S, Castellano C (2007) Community structure in graphs. arXiv preprint arXiv:0712.2716"},{"issue":"5","key":"1642_CR10","first-page":"5782","volume":"45","author":"H Yuan","year":"2022","unstructured":"Yuan H, Yu H, Gui S, Ji S (2022) Explainability in graph neural networks: a taxonomic survey. IEEE Trans Pattern Anal Mach Intell 45(5):5782\u20135799","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1642_CR11","unstructured":"Ying Z, Bourgeois D, You J, Zitnik M, Leskovec J (2019) Gnnexplainer: Generating explanations for graph neural networks. Adv Neural Inform Processing Syst 32"},{"key":"1642_CR12","first-page":"19620","volume":"33","author":"D Luo","year":"2020","unstructured":"Luo D, Cheng W, Xu D, Yu W, Zong B, Chen H, Zhang X (2020) Parameterized explainer for graph neural network. Adv Neural Inf Process Syst 33:19620\u201319631","journal-title":"Adv Neural Inf Process Syst"},{"key":"1642_CR13","unstructured":"Xie Y, Katariya S, Tang X, Huang E, Rao N, Subbian K, Ji S (2022) Task-agnostic graph explanations. In: Proceedings of the 36th international conference on neural information processing systems. NIPS \u201922. Curran Associates Inc., Red Hook, NY, USA"},{"key":"1642_CR14","unstructured":"Schlichtkrull MS, Cao ND, Titov I (2021) Interpreting graph neural networks for NLP with differentiable edge masking. In: International conference on learning representations"},{"key":"1642_CR15","unstructured":"Yuan H, Yu H, Wang J, Li K, Ji S (2021) On explainability of graph neural networks via subgraph explorations. In: International Conference on Machine Learning, pp 12241\u201312252. PMLR"},{"key":"1642_CR16","unstructured":"Baldassarre F, Azizpour H (2019) Explainability techniques for graph convolutional networks. In: International conference on machine learning (ICML) workshops, 2019 workshop on learning and reasoning with graph-structured representations"},{"key":"1642_CR17","doi-asserted-by":"crossref","unstructured":"Pope PE, Kolouri S, Rostami M, Martin CE, Hoffmann H (2019) Explainability methods for graph convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.01103"},{"key":"1642_CR18","doi-asserted-by":"crossref","unstructured":"Huang Q, Yamada M, Tian Y, Singh D, Chang Y (2022) Graphlime: Local interpretable model explanations for graph neural networks. IEEE Transactions on Knowledge and Data Engineering","DOI":"10.1109\/TKDE.2022.3187455"},{"key":"1642_CR19","doi-asserted-by":"crossref","unstructured":"Zhang Y, Defazio D, Ramesh A (2021) Relex: A model-agnostic relational model explainer. In: Proceedings of the 2021 AAAI\/ACM Conference on AI, Ethics, and Society, pp 1042\u20131049","DOI":"10.1145\/3461702.3462562"},{"key":"1642_CR20","first-page":"12225","volume":"33","author":"M Vu","year":"2020","unstructured":"Vu M, Thai MT (2020) Pgm-explainer: probabilistic graphical model explanations for graph neural networks. Adv Neural Inf Process Syst 33:12225\u201312235","journal-title":"Adv Neural Inf Process Syst"},{"key":"1642_CR21","doi-asserted-by":"crossref","unstructured":"Schwarzenberg R, H\u00fcbner M, Harbecke D, Alt C, Hennig L (2019) Layerwise relevance visualization in convolutional text graph classifiers. In: Proceedings of the thirteenth workshop on graph-based methods for natural language processing (TextGraphs-13), pp. 58\u201362. Association for Computational Linguistics, Hong Kong","DOI":"10.18653\/v1\/D19-5308"},{"issue":"11","key":"1642_CR22","doi-asserted-by":"publisher","first-page":"7581","DOI":"10.1109\/TPAMI.2021.3115452","volume":"44","author":"T Schnake","year":"2022","unstructured":"Schnake T, Eberle O, Lederer J, Nakajima S, Sch\u00fctt KT, M\u00fcller K-R, Montavon G (2022) Higher-order explanations of graph neural networks via relevant walks. IEEE Trans Pattern Anal Mach Intell 44(11):7581\u20137596","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1642_CR23","doi-asserted-by":"crossref","unstructured":"Yuan H, Tang J, Hu X, Ji S (2020) Xgnn: Towards model-level explanations of graph neural networks. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining. KDD \u201920, pp. 430\u2013438. Association for Computing Machinery, New York, NY, USA","DOI":"10.1145\/3394486.3403085"},{"key":"1642_CR24","doi-asserted-by":"crossref","unstructured":"Blondel VD, Guillaume J-L, Lambiotte R, Lefebvre E (2008) Fast unfolding of communities in large networks. J Stat Mech: Theory Exp 2008(10):10008","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"issue":"1","key":"1642_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-41695-z","volume":"9","author":"VA Traag","year":"2019","unstructured":"Traag VA, Waltman L, Van Eck NJ (2019) From louvain to leiden: guaranteeing well-connected communities. Sci Rep 9(1):1\u201312","journal-title":"Sci Rep"},{"issue":"5","key":"1642_CR26","doi-asserted-by":"publisher","first-page":"104208","DOI":"10.1016\/j.ipm.2025.104208","volume":"62","author":"X Wu","year":"2025","unstructured":"Wu X, Hu J, Quan Y, Miao Q, Sun PG (2025) Motif-based contrastive graph clustering with clustering-oriented prompt. Inform Processing Manag 62(5):104208. https:\/\/doi.org\/10.1016\/j.ipm.2025.104208","journal-title":"Inform Processing Manag"},{"key":"1642_CR27","doi-asserted-by":"publisher","first-page":"122182","DOI":"10.1016\/j.eswa.2023.122182","volume":"238","author":"X Wu","year":"2024","unstructured":"Wu X, Lu W, Quan Y, Miao Q, Sun PG (2024) Deep dual graph attention auto-encoder for community detection. Expert Syst Appl 238:122182. https:\/\/doi.org\/10.1016\/j.eswa.2023.122182","journal-title":"Expert Syst Appl"},{"key":"1642_CR28","doi-asserted-by":"crossref","unstructured":"Wu X, Hu J, Zhang A, Quan Y, Miao Q, Sun PG (2025) Structure-enhanced contrastive learning for graph clustering. IEEE Transactions on Network Science and Engineering","DOI":"10.1109\/TNSE.2025.3595737"},{"key":"1642_CR29","unstructured":"Xu K, Hu W, Leskovec J, Jegelka S (2019) How powerful are graph neural networks? In: International Conference on Learning Representations"},{"key":"1642_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01588-5","volume-title":"Graph representation learning","author":"WL Hamilton","year":"2020","unstructured":"Hamilton WL (2020) Graph representation learning. Morgan & Claypool Publishers, San Rafael, CA(USA)"},{"key":"1642_CR31","doi-asserted-by":"publisher","first-page":"026113","DOI":"10.1103\/PhysRevE.69.026113","volume":"69","author":"MEJ Newman","year":"2004","unstructured":"Newman MEJ, Girvan M (2004) Finding and evaluating community structure in networks. Phys Rev E 69:026113","journal-title":"Phys Rev E"},{"key":"1642_CR32","doi-asserted-by":"publisher","first-page":"066111","DOI":"10.1103\/PhysRevE.70.066111","volume":"70","author":"A Clauset","year":"2004","unstructured":"Clauset A, Newman MEJ, Moore C (2004) Finding community structure in very large networks. Phys Rev E 70:066111","journal-title":"Phys Rev E"},{"key":"1642_CR33","doi-asserted-by":"crossref","unstructured":"Erd\u00f6s P, R\u00e9nyi A (1959) On random graphs i. Publ math debrecen 6(290\u2013297):18","DOI":"10.5486\/PMD.1959.6.3-4.12"},{"issue":"4","key":"1642_CR34","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1214\/aoms\/1177706098","volume":"30","author":"EN Gilbert","year":"1959","unstructured":"Gilbert EN (1959) Random graphs. Ann Math Stat 30(4):1141\u20131144","journal-title":"Ann Math Stat"},{"issue":"5439","key":"1642_CR35","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1126\/science.286.5439.509","volume":"286","author":"A-L Barab\u00e1si","year":"1999","unstructured":"Barab\u00e1si A-L, Albert R (1999) Emergence of scaling in random networks. Science 286(5439):509\u2013512","journal-title":"Science"},{"key":"1642_CR36","first-page":"5898","volume":"33","author":"B Sanchez-Lengeling","year":"2020","unstructured":"Sanchez-Lengeling B, Wei J, Lee B, Reif E, Wang P, Qian W, McCloskey K, Colwell L, Wiltschko A (2020) Evaluating attribution for graph neural networks. Adv Neural Inf Process Syst 33:5898\u20135910","journal-title":"Adv Neural Inf Process Syst"},{"issue":"11","key":"1642_CR37","doi-asserted-by":"publisher","first-page":"2324","DOI":"10.1021\/acs.jcim.5b00559","volume":"55","author":"T Sterling","year":"2015","unstructured":"Sterling T, Irwin JJ (2015) Zinc 15-ligand discovery for everyone. J Chem Inf Model 55(11):2324\u20132337","journal-title":"J Chem Inf Model"},{"issue":"1","key":"1642_CR38","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1021\/jm040835a","volume":"48","author":"J Kazius","year":"2005","unstructured":"Kazius J, McGuire R, Bursi R (2005) Derivation and validation of toxicophores for mutagenicity prediction. J Med Chem 48(1):312\u2013320","journal-title":"J Med Chem"},{"key":"1642_CR39","unstructured":"Amara K, Ying Z, Zhang Z, Han Z, Zhao Y, Shan Y, Brandes U, Schemm S, Zhang C (2022) Graphframex: Towards systematic evaluation of explainability methods for graph neural networks. In: The First Learning on Graphs Conference"},{"key":"1642_CR40","unstructured":"Zheng X, Shirani F, Wang T, Cheng W, Chen Z, Chen H, Wei H, Luo D (2024) Towards robust fidelity for evaluating explainability of graph neural networks. In: The twelfth international conference on learning representations"},{"issue":"1","key":"1642_CR41","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1038\/s41597-023-01974-x","volume":"10","author":"C Agarwal","year":"2023","unstructured":"Agarwal C, Queen O, Lakkaraju H, Zitnik M (2023) Evaluating explainability for graph neural networks. Sci Data 10(1):144","journal-title":"Sci Data"},{"key":"1642_CR42","unstructured":"Kingma D, Ba J (2015) Adam: A method for stochastic optimization. In: International conference on learning representations (ICLR), San Diego, CA, USA"},{"key":"1642_CR43","unstructured":"Calderaro S (2026) GECo explainer: official github repository. https:\/\/github.com\/salvatorecalderaro\/geco_explainer Accessed 2026-01-24"},{"key":"1642_CR44","unstructured":"Python Package for GECo Explainer. https:\/\/pypi.org\/project\/geco-explainer\/ Accessed 2026-01-24"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-026-01642-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00607-026-01642-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-026-01642-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:13:19Z","timestamp":1776489199000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00607-026-01642-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,21]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["1642"],"URL":"https:\/\/doi.org\/10.1007\/s00607-026-01642-z","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,21]]},"assertion":[{"value":"12 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"55"}}