{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:58:54Z","timestamp":1764939534896,"version":"3.46.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Siamese Neural Networks (SNNs) have shown promise in addressing a variety of tasks, even with limited data availability. However, their adoption is hindered by the lack of transparency in their decision-making processes. A key challenge in explaining SNNs lies in the absence of an inverse mapping between high-dimensional input feature vectors and the low-dimensional embedding space. Therefore, computing direct distances between input features becomes meaningless. Existing autoencoder-based explanation methods face several limitations. These include poor image reconstruction quality due to insufficient data and the omission of final distance layer of the SNN during the explanation process. While the Siamese Network Explainer (SINEX) can explain audio and grayscale images, it does not support RGB images. To overcome these challenges, we propose a method called Features Distance-based eXplanation (FDbX). This approach identifies salient features using ridge regression, trained on perturbed SLIC-segmented images. To enhance the selection of important features, we incorporate Bayesian analysis, which assigns importance scores to features. To provide a comprehensive explanation of the decision route, we construct a mathematical model that represents important features and their Hamming distances as a bipartite graph. In this graph, nodes represent features and edges denote distances between feature pairs. The resulting explanation heatmaps highlight critical image segments, offering more intuitive and visually informative explanations than existing methods. We evaluate stability and faithfulness of our method using stability indices such as\n                    <jats:inline-formula>\n                      <jats:tex-math>$$R^2$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    and mean squared error. To the best of our knowledge, this is the first work to introduce Variable and Coefficient Stability Indices for image datasets.\n                  <\/jats:p>","DOI":"10.1007\/s10618-025-01154-y","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T02:29:20Z","timestamp":1755570560000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Stable graph based decision route explanation in siamese neural networks"],"prefix":"10.1007","volume":"39","author":[{"given":"Rabia","family":"Saleem","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashiq","family":"Anjum","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"unstructured":"Leventi-Peetz A-M, \u00d6streich T (2022) Deep learning reproducibility and explainable ai (xai). arXiv preprint arXiv:2202.11452","key":"1154_CR1"},{"doi-asserted-by":"crossref","unstructured":"Roy SK, Harandi M, Nock R, Hartley R (2019) Siamese networks The tale of two manifolds In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3046\u20133055","key":"1154_CR2","DOI":"10.1109\/ICCV.2019.00314"},{"doi-asserted-by":"crossref","unstructured":"Bromley J, Guyon I, LeCun Y, S\u00e4ckinger E, Shah R (1993) Signature verification using a\" siamese\" time delay neural network. Adv Neural Inf Process Syst 6","key":"1154_CR3","DOI":"10.1142\/9789812797926_0003"},{"doi-asserted-by":"crossref","unstructured":"Bromley J, Bentz JW, Bottou L, Guyon I, Lecun Y, Moore C, Sackinger E, Shah R (1993) Signature verification using a siamese time delay neural network. Int J Pattern Recognit Artif Intell 7(4)","key":"1154_CR4","DOI":"10.1142\/9789812797926_0003"},{"key":"1154_CR5","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1109\/ITOEC53115.2022.9734583","volume":"6","author":"L Zhao","year":"2022","unstructured":"Zhao L, Yang J, Zhang Y, Huang J (2022) Research on feature matching of an improved orb algorithm. In 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC) 6:765\u2013769. https:\/\/doi.org\/10.1109\/ITOEC53115.2022.9734583","journal-title":"In 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)"},{"issue":"5","key":"1154_CR6","doi-asserted-by":"publisher","first-page":"1903","DOI":"10.1007\/s10994-022-06167-y","volume":"111","author":"R Wilming","year":"2022","unstructured":"Wilming R, Budding C, M\u00fcller K-R, Haufe S (2022) Scrutinizing xai using linear ground-truth data with suppressor variables. Mach Learn 111(5):1903\u20131923","journal-title":"Mach Learn"},{"unstructured":"Kadir MA, Mosavi A, Sonntag D Assessing xai: Unveiling evaluation metrics for local explanation, taxonomies, key concepts, and practical applications","key":"1154_CR7"},{"unstructured":"Garreau D, Mardaoui D (2021) What does lime really see in images? In: International Conference on Machine Learning, pp. 3620\u20133629. PMLR","key":"1154_CR8"},{"doi-asserted-by":"crossref","unstructured":"Utkin L, Kovalev M, Kasimov E (2021) An explanation method for siamese neural networks. In: Proceedings of International Scientific Conference on Telecommunications, Computing and Control: TELECCON 2019, pp. 219\u2013230. Springer","key":"1154_CR9","DOI":"10.1007\/978-981-33-6632-9_19"},{"doi-asserted-by":"publisher","unstructured":"Sheng T, Huber, M (2019) Siamese networks for weakly supervised human activity recognition. In: 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 4069\u20134075. https:\/\/doi.org\/10.1109\/SMC.2019.8914045","key":"1154_CR10","DOI":"10.1109\/SMC.2019.8914045"},{"doi-asserted-by":"crossref","unstructured":"Fedele A, Guidotti R, Pedreschi D (2022) Explaining siamese networks in few-shot learning for audio data In: Discovery Science: 25th International Conference, DS 2022, Montpellier, France, October 10\u201312, 2022, Proceedings, pp. 509\u2013524 . Springer","key":"1154_CR11","DOI":"10.1007\/978-3-031-18840-4_36"},{"doi-asserted-by":"crossref","unstructured":"Schallner L, Rabold J, Scholz O, Schmid U (2020) Effect of superpixel aggregation on explanations in lime-a case study with biological data In: Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, W\u00fcrzburg, Germany, September 16\u201320, 2019, Proceedings, Part I, pp. 147\u2013158. Springer","key":"1154_CR12","DOI":"10.1007\/978-3-030-43823-4_13"},{"unstructured":"Rong H-g, Li Y-j, Zhang X-s (2022) An image matching algorithm based on bipartite graph. In: ISCTT 2022; 7th International Conference on Information Science, Computer Technology and Transportation, pp. 1\u20134. VDE","key":"1154_CR13"},{"doi-asserted-by":"crossref","unstructured":"Caro-Mart\u00ednez M, Jim\u00e9nez-D\u00edaz G, Recio-Garcia JA (2023) A graph-based approach for minimising the knowledge requirement of explainable recommender systems. Knowl Inf Syst 1\u201331","key":"1154_CR14","DOI":"10.1007\/s10115-023-01903-9"},{"issue":"1","key":"1154_CR15","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1080\/01605682.2020.1865846","volume":"73","author":"G Visani","year":"2022","unstructured":"Visani G, Bagli E, Chesani F, Poluzzi A, Capuzzo D (2022) Statistical stability indices for lime: obtaining reliable explanations for machine learning models. J Operation Res Soc 73(1):91\u2013101","journal-title":"J Operation Res Soc"},{"doi-asserted-by":"crossref","unstructured":"Saleem R, Yuan B, Kurugollu F, Anjum A, Liu L (2022) Explaining deep neural networks: A survey on the global interpretation methods. Neurocomputing","key":"1154_CR16","DOI":"10.1016\/j.neucom.2022.09.129"},{"key":"1154_CR17","doi-asserted-by":"publisher","first-page":"115736","DOI":"10.1016\/j.eswa.2021.115736","volume":"186","author":"L Antwarg","year":"2021","unstructured":"Antwarg L, Miller RM, Shapira B, Rokach L (2021) Explaining anomalies detected by autoencoders using shapley additive explanations. Expert Syst Appl 186:115736","journal-title":"Expert Syst Appl"},{"doi-asserted-by":"crossref","unstructured":"Chakraborty T, Trehan U, Mallat K, Dugelay J-L (2022) Generalizing adversarial explanations with grad-cam. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 187\u2013193","key":"1154_CR18","DOI":"10.1109\/CVPRW56347.2022.00031"},{"doi-asserted-by":"crossref","unstructured":"Riaz H, Smeaton AF (2023) Vision based machine learning algorithms for out-of-distribution generalisation arXiv preprint arXiv:2301.06975","key":"1154_CR19","DOI":"10.1007\/978-3-031-37963-5_60"},{"doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2016) \" why should i trust you?\" explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135\u20131144","key":"1154_CR20","DOI":"10.1145\/2939672.2939778"},{"unstructured":"Zafar MR, Khan NM (2019) Dlime A deterministic local interpretable model-agnostic explanations approach for computer-aided diagnosis systems arXiv preprint arXiv:1906.10263","key":"1154_CR21"},{"doi-asserted-by":"crossref","unstructured":"Rabold J, Deininger H, Siebers M, Schmid U (2020) Enriching visual with verbal explanations for relational concepts-combining lime with aleph In: Machine Learning and Knowledge Discovery in Databases: International Workshops of ECML PKDD 2019, W\u00fcrzburg, Germany, September 16\u201320, 2019, Proceedings, Part I, pp. 180\u2013192. Springer","key":"1154_CR22","DOI":"10.1007\/978-3-030-43823-4_16"},{"unstructured":"Sangroya A, Rastogi M, Anantaram C, Vig L (2020) Guided-lime Structured sampling based hybrid approach towards explaining blackbox machine learning models In: CIKM (Workshops)","key":"1154_CR23"},{"unstructured":"Shi S, Zhang X, Fan W (2020) A modified perturbed sampling method for local interpretable model-agnostic explanation arXiv preprint arXiv:2002.07434","key":"1154_CR24"},{"issue":"1","key":"1154_CR25","first-page":"4","volume":"3","author":"S Bramhall","year":"2020","unstructured":"Bramhall S, Horn H, Tieu M, Lohia N (2020) Qlime-a quadratic local interpretable model-agnostic explanation approach. SMU Data Sci Rev 3(1):4","journal-title":"SMU Data Sci Rev"},{"doi-asserted-by":"crossref","unstructured":"Gaudel R, Gal\u00e1rraga L, Delaunay J, Roz\u00e9 L, Bhargava V (2022) s-lime Reconciling locality and fidelity in linear explanations In: Advances in Intelligent Data Analysis XX: 20th International Symposium on Intelligent Data Analysis, IDA 2022, Rennes, France, April 20\u201322, 2022, Proceedings, pp. 102\u2013114. Springer","key":"1154_CR26","DOI":"10.1007\/978-3-031-01333-1_9"},{"doi-asserted-by":"crossref","unstructured":"Chen C, Shen Y, Ma G, Kong X, Rangarajan S, Zhang X, Xie S (2021) Self-learn to explain siamese networks robustly In: 2021 IEEE International Conference on Data Mining (ICDM), pp. 1018\u20131023. IEEE","key":"1154_CR27","DOI":"10.1109\/ICDM51629.2021.00116"},{"issue":"11","key":"1154_CR28","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta R, Shaji A, Smith K, Lucchi A, Fua P, S\u00fcsstrunk S (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274\u20132282","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"1154_CR29","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/j.neucom.2020.08.017","volume":"425","author":"JL Su\u00e1rez","year":"2021","unstructured":"Su\u00e1rez JL, Garc\u00eda S, Herrera F (2021) A tutorial on distance metric learning: Mathematical foundations, algorithms, experimental analysis, prospects and challenges. Neurocomputing 425:300\u2013322","journal-title":"Neurocomputing"},{"issue":"1","key":"1154_CR30","doi-asserted-by":"publisher","first-page":"15210","DOI":"10.1038\/s41598-022-19419-7","volume":"12","author":"S Ucer","year":"2022","unstructured":"Ucer S, Ozyer T, Alhajj R (2022) Explainable artificial intelligence through graph theory by generalized social network analysis-based classifier. Sci Rep 12(1):15210","journal-title":"Sci Rep"},{"doi-asserted-by":"crossref","unstructured":"Shankaranarayana SM, Runje D (2019) ALIME: autoencoder based approach for local interpretability. CoRR abs\/1909.02437","key":"1154_CR31","DOI":"10.1007\/978-3-030-33607-3_49"},{"doi-asserted-by":"crossref","unstructured":"Polela JA et al (2020) The influence of loss function usage at siamese network in measuring text similarity. Int J Adv Comput Sci Appl 11(12)","key":"1154_CR32","DOI":"10.14569\/IJACSA.2020.0111290"},{"unstructured":"IBM Corp.: IBM SPSS Statistics for Windows. https:\/\/hadoop.apache.org","key":"1154_CR33"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-025-01154-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10618-025-01154-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-025-01154-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:53:04Z","timestamp":1764939184000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10618-025-01154-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"references-count":33,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["1154"],"URL":"https:\/\/doi.org\/10.1007\/s10618-025-01154-y","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"type":"print","value":"1384-5810"},{"type":"electronic","value":"1573-756X"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"2 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2025","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":"73"}}