001048887 001__ 1048887
001048887 005__ 20251217202227.0
001048887 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-04992
001048887 037__ $$aFZJ-2025-04992
001048887 041__ $$aEnglish
001048887 1001_ $$0P:(DE-Juel1)199019$$aCao, Zhuo$$b0$$eCorresponding author$$ufzj
001048887 1112_ $$aNeurIPS 2025$$cSan Diego$$d2025-12-01 - 2025-12-07$$wUSA
001048887 245__ $$aLeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
001048887 260__ $$c2025
001048887 3367_ $$033$$2EndNote$$aConference Paper
001048887 3367_ $$2DataCite$$aOther
001048887 3367_ $$2BibTeX$$aINPROCEEDINGS
001048887 3367_ $$2DRIVER$$aconferenceObject
001048887 3367_ $$2ORCID$$aLECTURE_SPEECH
001048887 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1765971822_20224$$xInvited
001048887 520__ $$aThe growing integration of machine learning (ML) and artificial intelligence (AI) models into high-stakes domains such as healthcare and scientific research calls for models that are not only accurate but also interpretable. Among the existing explainable methods, counterfactual explanations offer interpretability by identifying minimal changes to inputs that would alter a model's prediction, thus providing deeper insights. However, current counterfactual generation methods suffer from critical limitations, including gradient vanishing, discontinuous latent spaces, and an overreliance on the alignment between learned and true decision boundaries. To overcome these limitations, we propose LeapFactual, a novel counterfactual explanation algorithm based on conditional flow matching. LeapFactual generates reliable and informative counterfactuals, even when true and learned decision boundaries diverge. Following a model-agnostic approach, LeapFactual is not limited to models with differentiable loss functions. It can even handle human-in-the-loop systems, expanding the scope of counterfactual explanations to domains that require the participation of human annotators, such as citizen science. We provide extensive experiments on benchmark and real-world datasets showing that LeapFactual generates accurate and in-distribution counterfactual explanations that offer actionable insights. We observe, for instance, that our reliable counterfactual samples with labels aligning to ground truth can be beneficially used as new training data to enhance the model. The proposed method is broadly applicable and enhances both scientific knowledge discovery and non-expert interpretability.
001048887 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001048887 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x1
001048887 7001_ $$0P:(DE-Juel1)200005$$aZhao, Xuan$$b1$$ufzj
001048887 7001_ $$0P:(DE-Juel1)196726$$aKrieger, Lena$$b2$$ufzj
001048887 7001_ $$0P:(DE-Juel1)129394$$aScharr, Hanno$$b3$$ufzj
001048887 7001_ $$0P:(DE-Juel1)188313$$aAssent, Ira$$b4$$ufzj
001048887 8564_ $$uhttps://arxiv.org/abs/2510.14623
001048887 8564_ $$uhttps://juser.fz-juelich.de/record/1048887/files/2510.14623v3.pdf$$yOpenAccess
001048887 909CO $$ooai:juser.fz-juelich.de:1048887$$popenaire$$popen_access$$pVDB$$pdriver
001048887 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)199019$$aForschungszentrum Jülich$$b0$$kFZJ
001048887 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)200005$$aForschungszentrum Jülich$$b1$$kFZJ
001048887 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)196726$$aForschungszentrum Jülich$$b2$$kFZJ
001048887 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129394$$aForschungszentrum Jülich$$b3$$kFZJ
001048887 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188313$$aForschungszentrum Jülich$$b4$$kFZJ
001048887 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5254$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001048887 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x1
001048887 9141_ $$y2025
001048887 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001048887 920__ $$lyes
001048887 9201_ $$0I:(DE-Juel1)IAS-8-20210421$$kIAS-8$$lDatenanalyse und Maschinenlernen$$x0
001048887 980__ $$aconf
001048887 980__ $$aVDB
001048887 980__ $$aUNRESTRICTED
001048887 980__ $$aI:(DE-Juel1)IAS-8-20210421
001048887 9801_ $$aFullTexts