Learning to Explain: generating stable explanations fast

Xuelin Situ, Ingrid Zukerman, Cecile Paris, Sameen Maruf, Gholamreza Haffari

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

The importance of explaining the outcome of a machine learning model, especially a black-box model, is widely acknowledged. Recent approaches explain an outcome by identifying the contributions of input features to this outcome. In environments involving large black-box models or complex inputs, this leads to computationally demanding algorithms. Further, these algorithms often suffer from low stability, with explanations varying significantly across similar examples. In this paper, we propose a Learning to Explain (L2E) approach that learns the behaviour of an underlying explanation algorithm simultaneously from all training examples. Once the explanation algorithm is distilled into an explainer network, it can be used to explain new instances. Our experiments on three classification tasks, which compare our approach to six explanation algorithms, show that L2E is between 5 and 7.5 × 104 times faster than these algorithms, while generating more stable explanations, and having comparable faithfulness to the black-box model.

Original languageEnglish
Title of host publicationThe 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
Subtitle of host publicationProceedings of the Conference, Vol. 1 (Long Papers)
EditorsFei Xia, Wenjie Li, Roberto Navigli
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Pages5340-5355
Number of pages16
ISBN (Electronic)9781954085527
DOIs
Publication statusPublished - 2021
EventAnnual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing 2021 - Online, Bangkok, Thailand
Duration: 1 Aug 20216 Aug 2021
Conference number: 59th & 11th
https://aclanthology.org/2021.acl-long.0/ (Proceedings)
https://2021.aclweb.org (Website)
https://aclanthology.org/volumes/2021.findings-acl/ (Findings Proceedings)
https://aclanthology.org/2021.acl-short.100/ (Proceedings Short)

Conference

ConferenceAnnual Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing 2021
Abbreviated titleACL-IJCNLP 2021
Country/TerritoryThailand
CityBangkok
Period1/08/216/08/21
Internet address

Cite this