001049627 001__ 1049627
001049627 005__ 20251217202229.0
001049627 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-05415
001049627 037__ $$aFZJ-2025-05415
001049627 041__ $$aEnglish
001049627 1001_ $$0P:(DE-Juel1)199019$$aCao, Zhuo$$b0$$eCorresponding author$$ufzj
001049627 1112_ $$aThe Thirty-Ninth Annual Conference on Neural Information Processing$$cSan Diego$$d2025-12-01 - 2025-12-07$$gNeurIPS2025$$wUSA
001049627 245__ $$aLeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching
001049627 260__ $$c2025
001049627 3367_ $$033$$2EndNote$$aConference Paper
001049627 3367_ $$2BibTeX$$aINPROCEEDINGS
001049627 3367_ $$2DRIVER$$aconferenceObject
001049627 3367_ $$2ORCID$$aCONFERENCE_POSTER
001049627 3367_ $$2DataCite$$aOutput Types/Conference Poster
001049627 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1765991702_9816$$xInvited
001049627 520__ $$aThe growing integration of machine learning (ML) and artificial intelligence (AI) models into high-stakes domains such as healthcare and scientific research calls for models that are not only accurate but also interpretable. Among the existing explainable methods, counterfactual explanations offer interpretability by identifying minimal changes to inputs that would alter a model's prediction, thus providing deeper insights. However, current counterfactual generation methods suffer from critical limitations, including gradient vanishing, discontinuous latent spaces, and an overreliance on the alignment between learned and true decision boundaries. To overcome these limitations, we propose LeapFactual, a novel counterfactual explanation algorithm based on conditional flow matching. LeapFactual generates reliable and informative counterfactuals, even when true and learned decision boundaries diverge. Following a model-agnostic approach, LeapFactual is not limited to models with differentiable loss functions. It can even handle human-in-the-loop systems, expanding the scope of counterfactual explanations to domains that require the participation of human annotators, such as citizen science. We provide extensive experiments on benchmark and real-world datasets showing that LeapFactual generates accurate and in-distribution counterfactual explanations that offer actionable insights. We observe, for instance, that our reliable counterfactual samples with labels aligning to ground truth can be beneficially used as new training data to enhance the model. The proposed method is broadly applicable and enhances both scientific knowledge discovery and non-expert interpretability.
001049627 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001049627 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x1
001049627 7001_ $$0P:(DE-Juel1)200005$$aZhao, Xuan$$b1$$ufzj
001049627 7001_ $$0P:(DE-Juel1)196726$$aKrieger, Lena$$b2$$ufzj
001049627 7001_ $$0P:(DE-Juel1)129394$$aScharr, Hanno$$b3$$ufzj
001049627 7001_ $$0P:(DE-Juel1)188313$$aAssent, Ira$$b4$$ufzj
001049627 8564_ $$uhttps://juser.fz-juelich.de/record/1049627/files/LeapFactual_poster.pdf$$yOpenAccess
001049627 909CO $$ooai:juser.fz-juelich.de:1049627$$popenaire$$popen_access$$pVDB$$pdriver
001049627 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)199019$$aForschungszentrum Jülich$$b0$$kFZJ
001049627 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)200005$$aForschungszentrum Jülich$$b1$$kFZJ
001049627 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)196726$$aForschungszentrum Jülich$$b2$$kFZJ
001049627 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129394$$aForschungszentrum Jülich$$b3$$kFZJ
001049627 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188313$$aForschungszentrum Jülich$$b4$$kFZJ
001049627 9131_ $$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
001049627 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$$x1
001049627 9141_ $$y2025
001049627 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001049627 920__ $$lyes
001049627 9201_ $$0I:(DE-Juel1)IAS-8-20210421$$kIAS-8$$lDatenanalyse und Maschinenlernen$$x0
001049627 980__ $$aposter
001049627 980__ $$aVDB
001049627 980__ $$aUNRESTRICTED
001049627 980__ $$aI:(DE-Juel1)IAS-8-20210421
001049627 9801_ $$aFullTexts