A Reusable Model-agnostic Framework for Faithfully Explainable Recommendation and System Scrutability
ACM Transactions on Information Systems · 31.01.2024 · 42 (1) · 1-29
DOI: 10.1145/3605357 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 21.08.2023. Verfasst von Zhichao Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 97 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF.
Abstract (Originalsprache)
State-of-the-art industrial-level recommender system applications mostly adopt complicated model structures such as deep neural networks. While this helps with the model performance, the lack of system explainability caused by these nearly blackbox models also raises concerns and potentially weakens the users’ trust in the system. Existing work on explainable recommendation mostly focuses on designing interpretable model structures to generate model-intrinsic explanations. However, most of them have complex structures, and it is difficult to directly apply these designs onto existing recommendation applications due to the effectiveness and efficiency concerns. However, while there have been some studies on explaining recommendation models without knowing their internal structures (i.e., model-agnostic explanations), these methods have been criticized for not reflecting the actual reasoning process of the recommendation model or, in other words, faithfulness . How to develop model-agnostic explanation methods and evaluate them in terms of faithfulness is mostly unknown. In this work, we propose a reusable evaluation pipeline for model-agnostic explainable recommendation. Our pipeline evaluates the quality of model-agnostic explanation from the perspectives of faithfulness and scrutability. We further propose a model-agnostic explanation framework for recommendation and verify it with the proposed evaluation pipeline. Extensive experiments on public datasets demonstrate that our model-agnostic framework is able to generate explanations that are faithful to the recommendation model. We additionally provide quantitative and qualitative study to show that our explanation framework could enhance the scrutability of blackbox recommendation model. With proper modification, our evaluation pipeline and model-agnostic explanation framework could be easily migrated to existing applications. Through this work, we hope to encourage the community to focus more on faithfulness evaluation of explainable recommender systems.
Förderung
- NSF
Zitieren
APA
Xu, Z., Zeng, H., Tan, J., Fu, Z., Zhang, Y., & Ai, Q. (2024). A Reusable Model-agnostic Framework for Faithfully Explainable Recommendation and System Scrutability. ACM Transactions on Information Systems, 42(1), 1-29. https://doi.org/10.1145/3605357
Vancouver
Xu Z, Zeng H, Tan J, Fu Z, Zhang Y, Ai Q. A Reusable Model-agnostic Framework for Faithfully Explainable Recommendation and System Scrutability. ACM Transactions on Information Systems. 2024;42(1):1-29. doi:10.1145/3605357
BibTeX
@article{Xu2024,
author = {Xu, Zhichao and Zeng, Hansi and Tan, Juntao and Fu, Zuohui and Zhang, Yongfeng and Ai, Qingyao},
title = {A Reusable Model-agnostic Framework for Faithfully Explainable Recommendation and System Scrutability},
journal = {ACM Transactions on Information Systems},
year = {2024},
volume = {42},
number = {1},
pages = {1--29},
doi = {10.1145/3605357}
}
EUVIMED