{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:24:46Z","timestamp":1760059486593,"version":"build-2065373602"},"reference-count":49,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T00:00:00Z","timestamp":1749945600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Key Research and Development Program of Hubei Province","award":["2024BAB016","2024BAB031","2023BAB074"],"award-info":[{"award-number":["2024BAB016","2024BAB031","2023BAB074"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Although machine learning (ML) models are widely used in many fields, their prediction processes are often hard to understand. This lack of transparency makes it harder for people to trust them, especially in high-stakes fields like healthcare and finance. Human-interpretable explanations for model predictions are crucial in these contexts. While existing local interpretation methods have been proposed, many suffer from low local fidelity, instability, and limited effectiveness when applied to highly nonlinear models. This paper presents SVM-X, a model-agnostic local explanation approach designed to address these challenges. By leveraging the inherent symmetry of the SVM hyperplane, SVM-X precisely captures the local decision boundaries of complex nonlinear models, providing more accurate and stable explanations. Experimental evaluations on the UCI Adult dataset, the Bank Marketing dataset, and the Amazon Product Review dataset demonstrate that SVM-X consistently outperforms state-of-the-art methods like LIME and LEMNA. Notably, SVM-X achieves up to a 27.2% improvement in accuracy. Our work introduces a reliable and interpretable framework for understanding machine learning predictions, offering a promising new direction for future research.<\/jats:p>","DOI":"10.3390\/sym17060950","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T04:20:23Z","timestamp":1750134023000},"page":"950","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Faithful Local Explanations: Leveraging SVM to Interpret Black-Box Machine Learning Models"],"prefix":"10.3390","volume":"17","author":[{"given":"Jiaxiang","family":"Xu","sequence":"first","affiliation":[{"name":"Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junfei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Economics, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benkuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxiong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanfang","family":"Ge","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Internet of Intelligence, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., and Beyer, L. (2022, January 18\u201322). Scaling vision transformers. Proceedings of the IEEE\/CVF CVPR, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3605943","article-title":"Recent advances in natural language processing via large pre-trained language models: A survey","volume":"56","author":"Min","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1109\/TAI.2021.3133846","article-title":"Recent advances in trustworthy explainable artificial intelligence: Status, challenges, and perspectives","volume":"3","author":"Rawal","year":"2022","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/TAI.2022.3153754","article-title":"Ensemble image explainable AI (XAI) algorithm for severe community-acquired pneumonia and COVID-19 respiratory infections","volume":"4","author":"Zou","year":"2023","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.neucom.2022.09.129","article-title":"Explaining deep neural networks: A survey on the global interpretation methods","volume":"513","author":"Saleem","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_6","unstructured":"Yeh, C.K., Kim, B., Arik, S., Li, C.L., Pfister, T., and Ravikumar, P. (2020, January 6\u201312). On Completeness-aware Concept-Based Explanations in Deep Neural Networks. Proceedings of the NeurIPS, Virtual."},{"key":"ref_7","unstructured":"Ghorbani, A., Wexler, J., Zou, J.Y., and Kim, B. (2019, January 8\u201314). Towards Automatic Concept-based Explanations. Proceedings of the NeurIPS, Vancouver, CA, Canada."},{"key":"ref_8","unstructured":"Yash, G., Amir, F., Uri, S., and Been, K. (2019). Explaining classifiers with causal concept effect (cace). arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2016, January 13\u201317). Why should I trust you? Explaining the predictions of any classifier. Proceedings of the ACM SIGKDD, San Francisco, CA, USA.","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref_11","first-page":"1803","article-title":"How to explain individual classification decisions","volume":"11","author":"Baehrens","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_12","first-page":"1","article-title":"An efficient explanation of individual classifications using game theory","volume":"11","author":"Strumbelj","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Guo, W., Mu, D., Xu, J., Su, P., Wang, G., and Xing, X. (2018, January 15\u201319). Lemna: Explaining deep learning based security applications. Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security, Toronto, ON, Canada.","DOI":"10.1145\/3243734.3243792"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., and Guestrin, C. (2018, January 2\u20137). Anchors: High-Precision Model-Agnostic Explanations. Proceedings of the AAAI, New Orleans, LO, USA.","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"He, Y., Lou, J., Qin, Z., and Ren, K. (2023, January 26\u201330). FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis. Proceedings of the 2023 ACM SIGSAC CCS, Copenhagen, Denmark.","DOI":"10.1145\/3576915.3616599"},{"key":"ref_16","unstructured":"Blitzer, J., Dredze, M., and Pereira, F. (2007, January 23\u201327). Biographies, bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. Proceedings of the ACL, Prague, Czech Republic."},{"key":"ref_17","unstructured":"Kohavi, R. (1996, January 2\u20134). Scaling up the accuracy of naive-bayes classifiers: A decision-tree hybrid. Proceedings of the ACM SIGKDD, Portland, OR, USA."},{"key":"ref_18","unstructured":"Moro, S., Laureano, R., and Cortez, P. (2011). Using data mining for bank direct marketing: An application of the crisp-dm methodology. EUROSIS-ETI, Available online: https:\/\/hdl.handle.net\/1822\/14838."},{"key":"ref_19","unstructured":"Wright, R.E. (1995). Logistic Regression, American Psychological Association."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1021\/ci034160g","article-title":"Random forest: A classification and regression tool for compound classification and QSAR modeling","volume":"43","author":"Svetnik","year":"2003","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the ACM SIGKDD, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1109\/21.97458","article-title":"A survey of decision tree classifier methodology","volume":"21","author":"Safavian","year":"1991","journal-title":"IEEE Trans. Syst. Man, Cybern."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.neucom.2016.12.038","article-title":"A survey of deep neural network architectures and their applications","volume":"234","author":"Liu","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_24","unstructured":"Glenn, F., Sathyakama, S., and R Bharat, R. (2005, January 21\u201324). Rule Extraction from Linear Support Vector Machines. Proceedings of the ACM SIGKDD, Chicago, IL, USA."},{"key":"ref_25","first-page":"841","article-title":"Counterfactual explanations without opening the black box: Automated decisions and the GDPR","volume":"31","author":"Wachter","year":"2017","journal-title":"Harv. JL Tech."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3561048","article-title":"Explainable AI (XAI): Core ideas, techniques, and solutions","volume":"55","author":"Dwivedi","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/0950-7051(96)81920-4","article-title":"Survey and critique of techniques for extracting rules from trained artificial neural networks","volume":"8","author":"Andrews","year":"1995","journal-title":"Knowl.-Based Syst."},{"key":"ref_28","unstructured":"Averkin, A., and Yarushev, S. (2021, January 8\u20139). Fuzzy rules extraction from deep neural networks. Proceedings of the EEKM, Moscow, Russia."},{"key":"ref_29","unstructured":"Hailesilassie, T. (2016). Rule extraction algorithm for deep neural networks: A review. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zilke, J.R., Menc\u00eda, E.L., and Janssen, F. (2016, January 24\u201328). Deepred\u2013rule extraction from deep neural networks. Proceedings of the ICDS, Venice, Italy.","DOI":"10.1007\/978-3-319-46307-0_29"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., and Fergus, R. (2014, January 6\u201312). Visualizing and understanding convolutional networks. Proceedings of the ECCV, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref_32","unstructured":"Shrikumar, A., Greenside, P., and Kundaje, A. (2017). Learning important features through propagating activation differences. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2016, January 27\u201330). Learning deep features for discriminative localization. Proceedings of the IEEE CVPR, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE ICCV, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_35","unstructured":"Smilkov, D., Thorat, N., Kim, B., Vi\u00e9gas, F., and Wattenberg, M. (2017). Smoothgrad: Removing noise by adding noise. arXiv."},{"key":"ref_36","first-page":"1","article-title":"Sanity checks for saliency maps","volume":"31","author":"Adebayo","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Kindermans, P.J., Hooker, S., Adebayo, J., Alber, M., Sch\u00fctt, K.T., D\u00e4hne, S., Erhan, D., and Kim, B. (2019). The (un) reliability of saliency methods. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, Springer.","DOI":"10.1007\/978-3-030-28954-6_14"},{"key":"ref_38","unstructured":"Jin, W., Li, X., and Hamarneh, G. (2021). One map does not Fit all: Evaluating saliency map explanation on multi-modal medical images. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Mekonnen, E.T., Longo, L., and Dondio, P. (2024). A global model-agnostic rule-based XAI method based on Parameterized Event Primitives for time series classifiers. Front. Artif. Intell., 7.","DOI":"10.3389\/frai.2024.1381921"},{"key":"ref_40","unstructured":"Mamalakis, M., Mamalakis, A., Agartz, I., M\u00f8rch-Johnsen, L.E., Murray, G., Suckling, J., and Lio, P. (2024). Solving the enigma: Deriving optimal explanations of deep networks. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Botari, T., Izbicki, R., and de Carvalho, A.C. (2019, January 16\u201320). Local Interpretation Methods to Machine Learning Using the Domain of the Feature Space. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, W\u00fcrzburg, Germany.","DOI":"10.1007\/978-3-030-43823-4_21"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Negri, F.R., Nicolosi, N., Camilli, M., and Mirandola, R. (2024, January 15\u201316). Explanation-driven Self-adaptation using Model-agnostic Interpretable Machine Learning. Proceedings of the 19th International Symposium on Software Engineering for Adaptive and Self-Managing Systems, Lisbon, Portugal.","DOI":"10.1145\/3643915.3644085"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1007\/s42484-024-00191-y","article-title":"On the interpretability of quantum neural networks","volume":"6","author":"Pira","year":"2024","journal-title":"Quantum Mach. Intell."},{"key":"ref_44","unstructured":"Delaunay, J. (2023). Explainability for Machine Learning Models: From Data Adaptability to User Perception. [Ph.D. Thesis, Universit\u00e9 de Rennes]."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Whitten, P., Wolff, F., and Papachristou, C. (2024). An AI Architecture with the Capability to Explain Recognition Results. arXiv.","DOI":"10.1109\/NAECON61878.2024.10670684"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.eswa.2019.04.029","article-title":"A rule extraction approach from support vector machines for diagnosing hypertension among diabetics","volume":"130","author":"Namrata","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.knosys.2012.12.003","article-title":"Rule extraction from support vector machines based on consistent region covering reduction","volume":"42","author":"Zhu","year":"2013","journal-title":"Knowl.-Based Syst."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.asoc.2014.01.031","article-title":"Churn prediction using comprehensible support vector machine: An analytical CRM application","volume":"19","author":"Farquad","year":"2014","journal-title":"Appl. Soft Comput. J."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1017\/S1471068420000356","article-title":"White-box induction from SVM models: Explainable ai with logic programming","volume":"20","author":"Shakerin","year":"2020","journal-title":"Theory Pract. Log. Program."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/6\/950\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:52:20Z","timestamp":1760032340000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/6\/950"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,15]]},"references-count":49,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["sym17060950"],"URL":"https:\/\/doi.org\/10.3390\/sym17060950","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,6,15]]}}}