Sökning: onr:"swepub:oai:DiVA.org:hj-63086" >
Approximating Score...
Approximating Score-based Explanation Techniques Using Conformal Regression
-
- Alkhatib, Amr (författare)
- KTH,Programvaruteknik och datorsystem, SCS,School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Sweden
-
- Boström, Henrik (författare)
- KTH,Programvaruteknik och datorsystem, SCS,School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Sweden
-
- Ennadir, Sofiane (författare)
- KTH,Programvaruteknik och datorsystem, SCS,School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Sweden
-
visa fler...
-
- Johansson, Ulf (författare)
- Jönköping University,Jönköping AI Lab (JAIL),Dept. of Computing, Jönköping University, Sweden
-
visa färre...
-
(creator_code:org_t)
- ML Research Press, 2023
- 2023
- Engelska.
-
Ingår i: Proceedings of Machine Learning Research. - : ML Research Press. ; , s. 450-469, s. 450-469
- Relaterad länk:
-
https://proceedings....
-
visa fler...
-
https://urn.kb.se/re...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- Score-based explainable machine-learning techniques are often used to understand the logic behind black-box models. However, such explanation techniques are often computationally expensive, which limits their application in time-critical contexts. Therefore, we propose and investigate the use of computationally less costly regression models for approximating the output of score-based explanation techniques, such as SHAP. Moreover, validity guarantees for the approximated values are provided by the employed inductive conformal prediction framework. We propose several non-conformity measures designed to take the difficulty of approximating the explanations into account while keeping the computational cost low. We present results from a large-scale empirical investigation, in which the approximate explanations generated by our proposed models are evaluated with respect to efficiency (interval size). The results indicate that the proposed method can significantly improve execution time compared to the fast version of SHAP, TreeSHAP. The results also suggest that the proposed method can produce tight intervals, while providing validity guarantees. Moreover, the proposed approach allows for comparing explanations of different approximation methods and selecting a method based on how informative (tight) are the predicted intervals.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Explainable machine learning
- Inductive conformal prediction
- Multi-target regression
- Computation theory
- Conformal mapping
- Regression analysis
- Black box modelling
- Conformal predictions
- Machine learning techniques
- Machine-learning
- Multi-targets
- Target regression
- Time-critical
- Machine learning
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)