[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117336-en":3,"doc-seo-117336-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117336,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Interpretable Neural-Symbolic Concept Reasoning - Deep Concept Reasoner (DCR)","Deep learning models deliver high accuracy but often fail to generate human trust because their decision process is opaque. Concept-based models improve interpretability by grounding predictions in human-understandable concepts, yet current approaches using high-dimensional concept embeddings lack clear semantic meaning across embedding dimensions. To address this gap, the Deep Concept Reasoner (DCR) builds differentiable syntactic rule structures from concept embeddings and executes them over semantically meaningful concept truth degrees, producing final predictions that remain interpretable and semantically consistent. Experiments show accuracy gains, discovery of meaningful logic rules without concept supervision, and support for counterfactual generation guided by learned rules.","POLITECNICO DI TORINO Repository ISTITUZIONALE  \nInterpretable Neural-Symbolic Concept Reasoning  \nOriginal  \nInterpretable Neural-Symbolic Concept Reasoning / Barbiero, Pietro; Ciravegna, Gabriele; Giannini, Francesco; Espinosa Zarlenga, Mateo; Charlotte Magister, Lucie; Tonda, Alberto; Lio, Pietro; Precioso, Frederic; Jamnik, Mateja; Marra, Giuseppe. -202:(2023), pp. 1801-1825. (Intervento presentato al convegno ICML International Conference on Machine Learning 2023 tenutosi a Honolulu, Hawaii (USA) nel 23-29 July 2023) .  \nAvailability:  \nThis version is available at: 11583/2984900 since: 2024-01-08T13:25:48Z  \nPublisher:  \nMachine Learning Research Press  \nPublished DOI:  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \n(Article begins on next page)  \n17 February 2025  \nInterpretable Neural-Symbolic Concept Reasoning  \nPietro Barbiero * 1 Gabriele Ciravegna * 2 Francesco Giannini * 3 Mateo Espinosa Zarlenga 1 Lucie Charlotte Magister 1 Alberto Tonda 4 Pietro Li 1 Frederic Precioso 2 Mateja Jamnik 1  \nGiuseppe Marra * 5  \nAbstract  \nDeep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning tasks based on a set of human-understandable concepts.  \nHowever, state-of-the-art concept-based models rely on high-dimensional concept embedding representations which lack a clear semantic meaning, thus questioning the interpretability of their decision process. To overcome this limitation, we propose the Deep Concept Reasoner (DCR), the first interpretable concept-based model that builds upon concept embeddings. In DCR, neural networks do not make task predictions directly, but they build syntactic rule structures using concept embeddings. DCR then executes these rules on meaningful concept truth degrees to provide a final interpretable and semantically-consistent prediction in a differentiable manner. Our experiments show that DCR: (i) improves up to +25% w.r.t. state-of-the-art interpretable concept-based models on challenging benchmarks (ii) discovers meaningful logic rules matching known ground truths even in the absence of concept supervision during training, and (iii), facilitates the generation of counterfactual examples providing the learnt rules as guidance.  \n1. Introduction  \nThe opaque decision process of deep learning (DL) models has failed to inspire human trust despite their state-of-the-art performance across multiple tasks (Rudin, 2019; Bussone  \n*Equal contribution 1University of Cambridge, Cambridge, UK 2Universit Cte d’Azur, Inria, CNRS, I3S, Maasai, Nice, France 3University of Siena, Siena, Italy 4INRA, Universit ParisSaclay, Thiverval-Grignon, France 5 KU Leuven, Leuven, Belgium. Correspondence to: Pietro Barbiero \u003C[pb737@cam.ac.uk](pb737@cam.ac.uk)>.  \nProceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023 . Copyright 2023 by the author(s) .  \net al., 2015), raising ethical (Durn & Jongsma, 2021; Lo Piano, 2020) and legal (Wachter et al., 2017; EUGDPR, 2017) concerns. For this reason, interpretability is now a core research topic in the field of responsible AI (Rudin, 2019) .  \nConcept-based models (Kim et al., 2018; Chen et al., 2020) aim to increase human trust in deep learning models by using human-understandable concepts to train interpretable models—such as logistic regression or decision trees (Rudin, 2019; Koh et al., 2020; Kazhdan et al., 2020) (Figure 1) . This approach significantly increases human trust in the AI predictor (Rudin, 2019; Shen, 2022) as it allows users to clearly understand a model’s decision process. However, state-of-the-art concept-based models, which rely on concept embeddings (Yeh et al., 2020; Kazhdan et al., 2020; Mahinpei et al., 2021; Espinosa Zarlenga et al., 2022) to attain hig","cbCaido1Iud73VZa","https://ap.wps.com/l/cbCaido1Iud73VZa","pdf",1879037,1,26,"English","en",105,"# Introduction\n## Concept-based models and the interpretability gap\n# Preliminaries\n## Concept-based models\n# Deep Concept Reasoner (DCR)\n## Differentiable fuzzy rules from concept embeddings\n# Experiments\n## Accuracy, logic-rule discovery, and counterfactual generation","[{\"question\":\"Why do concept-based models still struggle with interpretability?\",\"answer\":\"Many state-of-the-art concept-based models rely on high-dimensional concept embeddings whose dimensions do not have clear semantic meaning, reducing interpretability of the decision process.\"},{\"question\":\"How does the Deep Concept Reasoner (DCR) improve interpretability?\",\"answer\":\"DCR uses neural networks to build differentiable syntactic rule structures from concept embeddings, then executes these rules on semantically meaningful concept truth degrees to produce interpretable predictions.\"},{\"question\":\"What benefits do experiments show for DCR compared with prior interpretable concept-based models?\",\"answer\":\"DCR improves task accuracy by up to +25%, discovers meaningful logic rules matching known ground truths even without concept supervision, and facilitates counterfactual example generation using the learned rules as guidance.\"}]","Interpretable Neural-Symbolic Concept Reasoning - Deep Concept Reasoner (DCR) | PDF",1785675257,66,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"interpretable-neural-symbolic-concept-reasoning-deep-concept-reasoner-dcr","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/interpretable-neural-symbolic-concept-reasoning-deep-concept-reasoner-dcr/117336/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do concept-based models still struggle with interpretability?","Question",{"text":75,"@type":76},"Many state-of-the-art concept-based models rely on high-dimensional concept embeddings whose dimensions do not have clear semantic meaning, reducing interpretability of the decision process.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the Deep Concept Reasoner (DCR) improve interpretability?",{"text":80,"@type":76},"DCR uses neural networks to build differentiable syntactic rule structures from concept embeddings, then executes these rules on semantically meaningful concept truth degrees to produce interpretable predictions.",{"name":82,"@type":73,"acceptedAnswer":83},"What benefits do experiments show for DCR compared with prior interpretable concept-based models?",{"text":84,"@type":76},"DCR improves task accuracy by up to +25%, discovers meaningful logic rules matching known ground truths even without concept supervision, and facilitates counterfactual example generation using the learned rules as guidance.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]