Home > Publications database > Classifier Reconstruction Through Counterfactual-Aware Wasserstein Prototypes > print

001     1049202
005     20251217202227.0
024 7 _ |a 10.34734/FZJ-2025-05284
|2 datacite_doi
037 _ _ |a FZJ-2025-05284
041 _ _ |a English
100 1 _ |a Zhao, Xuan
|0 P:(DE-Juel1)200005
|b 0
|u fzj
111 2 _ |a ICML 2025 AIW
|c Vancouver
|d 2025-07-13 - 2025-07-19
|w Canada
245 _ _ |a Classifier Reconstruction Through Counterfactual-Aware Wasserstein Prototypes
260 _ _ |c 2025
336 7 _ |a Conference Paper
|0 33
|2 EndNote
336 7 _ |a Other
|2 DataCite
336 7 _ |a INPROCEEDINGS
|2 BibTeX
336 7 _ |a conferenceObject
|2 DRIVER
336 7 _ |a LECTURE_SPEECH
|2 ORCID
336 7 _ |a Conference Presentation
|b conf
|m conf
|0 PUB:(DE-HGF)6
|s 1765992431_17930
|2 PUB:(DE-HGF)
|x Other
520 _ _ |a Counterfactual explanations provide actionable insights by identifying minimal input changes required to achieve a desired model prediction. Beyond their interpretability benefits, counterfactuals can also be leveraged for model reconstruction, where a surrogate model is trained to replicate the behavior of a target model. In this work, we demonstrate that model reconstruction can be significantly improved by recognizing that counterfactuals, which typically lie close to the decision boundary, can serve as informative—though less representative—samples for both classes. This is particularly beneficial in settings with limited access to labeled data. We propose a method that integrates original data samples with counterfactuals to approximate class prototypes using the Wasserstein barycenter, thereby preserving the underlying distributional structure of each class. This approach enhances the quality of the surrogate model and mitigates the issue of decision boundary shift, which commonly arises when counterfactuals are naively treated as ordinary training instances. Empirical results across multiple datasets show that our method improves fidelity between the surrogate and target models, validating its effectiveness.
536 _ _ |a 5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)
|0 G:(DE-HGF)POF4-5112
|c POF4-511
|f POF IV
|x 0
700 1 _ |a Cao, Zhuo
|0 P:(DE-Juel1)199019
|b 1
|u fzj
700 1 _ |a Bangun, Arya
|0 P:(DE-Juel1)184644
|b 2
|u fzj
700 1 _ |a Scharr, Hanno
|0 P:(DE-Juel1)129394
|b 3
|u fzj
700 1 _ |a Assent, Ira
|0 P:(DE-Juel1)188313
|b 4
|u fzj
856 4 _ |u https://juser.fz-juelich.de/record/1049202/files/150_Classifier_Reconstruction_.pdf
|y OpenAccess
909 C O |o oai:juser.fz-juelich.de:1049202
|p openaire
|p open_access
|p VDB
|p driver
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 0
|6 P:(DE-Juel1)200005
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 1
|6 P:(DE-Juel1)199019
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 2
|6 P:(DE-Juel1)184644
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 3
|6 P:(DE-Juel1)129394
910 1 _ |a Forschungszentrum Jülich
|0 I:(DE-588b)5008462-8
|k FZJ
|b 4
|6 P:(DE-Juel1)188313
913 1 _ |a DE-HGF
|b Key Technologies
|l Engineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action
|1 G:(DE-HGF)POF4-510
|0 G:(DE-HGF)POF4-511
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-500
|4 G:(DE-HGF)POF
|v Enabling Computational- & Data-Intensive Science and Engineering
|9 G:(DE-HGF)POF4-5112
|x 0
914 1 _ |y 2025
915 _ _ |a OpenAccess
|0 StatID:(DE-HGF)0510
|2 StatID
920 _ _ |l yes
920 1 _ |0 I:(DE-Juel1)IAS-8-20210421
|k IAS-8
|l Datenanalyse und Maschinenlernen
|x 0
980 _ _ |a conf
980 _ _ |a VDB
980 _ _ |a UNRESTRICTED
980 _ _ |a I:(DE-Juel1)IAS-8-20210421
980 1 _ |a FullTexts

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21