Efficient computation of contrastive explanations

Artelt A, Hammer B (2021)
In: 2021 International Joint Conference on Neural Networks (IJCNN). New York: Institute of Electrical and Electronics Engineers (IEEE): 1-9.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Abstract / Bemerkung
With the increasing deployment of machine learning systems in practice, transparency and explainability have become serious issues. Contrastive explanations are considered to be useful and intuitive, in particular when it comes to explaining decisions to lay people, since they mimic the way in which humans explain. Yet, so far, comparably little research has addressed computationally feasible technologies, which allow guarantees on uniqueness and optimality of the explanation and which enable an easy incorporation of additional constraints. Here, we will focus on specific types of models rather than black-box technologies. We study the relation of contrastive and counterfactual explanations and propose mathematical formalizations as well as a 2-phase algorithm for efficiently computing (plausible) pertinent positives of many standard machine learning models.
Erscheinungsjahr
2021
Titel des Konferenzbandes
2021 International Joint Conference on Neural Networks (IJCNN)
Seite(n)
1-9
Konferenz
2021 International Joint Conference on Neural Networks (IJCNN)
Konferenzort
Shenzhen, China
Konferenzdatum
2021-07-18 – 2021-07-22
ISBN
978-1-6654-4597-9
eISBN
978-1-6654-3900-8
Page URI
https://pub.uni-bielefeld.de/record/2957588

Zitieren

Artelt A, Hammer B. Efficient computation of contrastive explanations. In: 2021 International Joint Conference on Neural Networks (IJCNN). New York: Institute of Electrical and Electronics Engineers (IEEE); 2021: 1-9.
Artelt, A., & Hammer, B. (2021). Efficient computation of contrastive explanations. 2021 International Joint Conference on Neural Networks (IJCNN), 1-9. New York: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IJCNN52387.2021.9534454
Artelt, André, and Hammer, Barbara. 2021. “Efficient computation of contrastive explanations”. In 2021 International Joint Conference on Neural Networks (IJCNN), 1-9. New York: Institute of Electrical and Electronics Engineers (IEEE).
Artelt, A., and Hammer, B. (2021). “Efficient computation of contrastive explanations” in 2021 International Joint Conference on Neural Networks (IJCNN) (New York: Institute of Electrical and Electronics Engineers (IEEE), 1-9.
Artelt, A., & Hammer, B., 2021. Efficient computation of contrastive explanations. In 2021 International Joint Conference on Neural Networks (IJCNN). New York: Institute of Electrical and Electronics Engineers (IEEE), pp. 1-9.
A. Artelt and B. Hammer, “Efficient computation of contrastive explanations”, 2021 International Joint Conference on Neural Networks (IJCNN), New York: Institute of Electrical and Electronics Engineers (IEEE), 2021, pp.1-9.
Artelt, A., Hammer, B.: Efficient computation of contrastive explanations. 2021 International Joint Conference on Neural Networks (IJCNN). p. 1-9. Institute of Electrical and Electronics Engineers (IEEE), New York (2021).
Artelt, André, and Hammer, Barbara. “Efficient computation of contrastive explanations”. 2021 International Joint Conference on Neural Networks (IJCNN). New York: Institute of Electrical and Electronics Engineers (IEEE), 2021. 1-9.

Link(s) zu Volltext(en)
Access Level
Restricted Closed Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche