Lifelong Explainer for Lifelong Learners

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


Abstract
Lifelong Learning (LL) black-box models are dynamic in that they keep learning from new tasks and constantly update their parameters. Owing to the need to utilize information from previously seen tasks, and capture commonalities in potentially diverse data, it is hard for automatic explanation methods to explain the outcomes of these models. In addition, existing explanation methods, e.g., LIME, which are computationally expensive when explaining a static black-box model, are even more inefficient in the LL setting. In this paper, we propose a novel Lifelong Explanation (LLE) approach that continuously trains a student explainer under the supervision of a teacher – an arbitrary explanation algorithm – on different tasks undertaken in LL. We also leverage the Experience Replay (ER) mechanism to prevent catastrophic forgetting in the student explainer. Our experiments comparing LLE to three baselines on text classification tasks show that LLE can enhance the stability of the explanations for all seen tasks and maintain the same level of faithfulness to the black-box model as the teacher, while being up to 10ˆ2 times faster at test time. Our ablation study shows that the ER mechanism in our LLE approach enhances the learning capabilities of the student explainer. Our code is available at https://github.com/situsnow/LLE.
Anthology ID:
2021.emnlp-main.233
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2933–2940
Language:
URL:
https://aclanthology.org/2021.emnlp-main.233
DOI:
10.18653/v1/2021.emnlp-main.233
Bibkey:
Cite (ACL):
Xuelin Situ, Sameen Maruf, Ingrid Zukerman, Cecile Paris, and Gholamreza Haffari. 2021. Lifelong Explainer for Lifelong Learners. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2933–2940, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Lifelong Explainer for Lifelong Learners (Situ et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/2021.emnlp-main.233.pdf
Video:
 https://preview.aclanthology.org/auto-file-uploads/2021.emnlp-main.233.mp4
Code
 situsnow/lle