001049199 001__ 1049199
001049199 005__ 20251217202227.0
001049199 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-05281
001049199 037__ $$aFZJ-2025-05281
001049199 041__ $$aEnglish
001049199 1001_ $$0P:(DE-Juel1)200005$$aZhao, Xuan$$b0
001049199 1112_ $$aNeurIPS 2025 - Reliable ML Workshop$$cSan Diego$$d2025-12-02 - 2025-12-08$$wUSA
001049199 245__ $$aProbabilistic Framework for Robustness of Counterfactual Explanations Under Data Shifts
001049199 260__ $$c2025
001049199 3367_ $$033$$2EndNote$$aConference Paper
001049199 3367_ $$2DataCite$$aOther
001049199 3367_ $$2BibTeX$$aINPROCEEDINGS
001049199 3367_ $$2DRIVER$$aconferenceObject
001049199 3367_ $$2ORCID$$aLECTURE_SPEECH
001049199 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1765992376_17930$$xOther
001049199 520__ $$aCounterfactual explanations (CEs) are a powerful method for interpreting machine learning models, but CEs might be not valid when the model is updated due to distribution shifts in the underlying data. Existing approaches to robust CEs often impose explicit bounds on model parameters to ensure stability, but such bounds can be difficult to estimate and overly restrictive in practice. In this work, we propose a data shift-driven probabilistic framework for robust counterfactual explanations with plausible data shift modeling via a Wasserstein ball. We formalize a linearized Wasserstein perturbation scheme that captures realistic distributional changes which enables Monte Carlo estimation of CE robustness probabilities with domain-specific data shift tolerances. Theoretical analysis reveals that our framework is equivalent in spirit to model parameter bounding approaches but offers greater flexibility, avoids the need to estimate maximal model parameter shifts. Experiments on real-world datasets demonstrate that the proposed method maintains high robustness of CEs under plausible distribution shifts, outperforming conventional parameter-bounding techniques in both validity and proximity costs.
001049199 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001049199 7001_ $$0P:(DE-Juel1)196726$$aKrieger, Lena$$b1$$ufzj
001049199 7001_ $$0P:(DE-Juel1)199019$$aCao, Zhuo$$b2$$ufzj
001049199 7001_ $$0P:(DE-Juel1)184644$$aBangun, Arya$$b3$$ufzj
001049199 7001_ $$0P:(DE-Juel1)129394$$aScharr, Hanno$$b4$$ufzj
001049199 7001_ $$0P:(DE-Juel1)188313$$aAssent, Ira$$b5$$ufzj
001049199 8564_ $$uhttps://openreview.net/forum?id=sLcLSPx6N4#discussion
001049199 8564_ $$uhttps://juser.fz-juelich.de/record/1049199/files/184_Probabilistic_Framework_fo.pdf$$yOpenAccess
001049199 909CO $$ooai:juser.fz-juelich.de:1049199$$popenaire$$popen_access$$pVDB$$pdriver
001049199 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)200005$$aForschungszentrum Jülich$$b0$$kFZJ
001049199 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)196726$$aForschungszentrum Jülich$$b1$$kFZJ
001049199 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)199019$$aForschungszentrum Jülich$$b2$$kFZJ
001049199 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)184644$$aForschungszentrum Jülich$$b3$$kFZJ
001049199 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129394$$aForschungszentrum Jülich$$b4$$kFZJ
001049199 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188313$$aForschungszentrum Jülich$$b5$$kFZJ
001049199 9131_ $$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$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001049199 9141_ $$y2025
001049199 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001049199 920__ $$lyes
001049199 9201_ $$0I:(DE-Juel1)IAS-8-20210421$$kIAS-8$$lDatenanalyse und Maschinenlernen$$x0
001049199 980__ $$aconf
001049199 980__ $$aVDB
001049199 980__ $$aUNRESTRICTED
001049199 980__ $$aI:(DE-Juel1)IAS-8-20210421
001049199 9801_ $$aFullTexts