EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning

Yuyang Gao iD, Siyi Gu iD, Junji Jiang iD, Sungsoo Ray Hong iD, Dazhou Yu iD, Liang Zhao iD

ACM Computing Surveys · 31.07.2024 · 56 (7) · 1-39

DOI: 10.1145/3644073 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 09.04.2024. Verfasst von Yuyang Gao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Emory University, Atlanta, USA. Die Arbeit wurde bisher 69-mal zitiert (Crossref) und nennt 184 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NCI NIH HHS, National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the societal impact of Deep Neural Networks (DNNs) grows, the goals for advancing DNNs become more complex and diverse, ranging from improving a conventional model accuracy metric to infusing advanced human virtues such as fairness, accountability, transparency, and unbiasedness. Recently, techniques in Explainable Artificial Intelligence (XAI) have been attracting considerable attention and have tremendously helped Machine Learning (ML) engineers in understand AI models. However, at the same time, we started to witness the emerging need beyond XAI among AI communities; based on the insights learned from XAI, how can we better empower ML engineers in steering their DNNs so that the model’s reasonableness and performance can be improved as intended? This article provides a timely and extensive literature overview of the field Explanation-Guided Learning (EGL), a domain of techniques that steer the DNNs’ reasoning process by adding regularization, supervision, or intervention on model explanations. In doing so, we first provide a formal definition of EGL and its general learning paradigm. Second, an overview of the key factors for EGL evaluation, as well as summarization and categorization of existing evaluation procedures and metrics for EGL are provided. Finally, the current and potential future application areas and directions of EGL are discussed, and an extensive experimental study is presented aiming at providing comprehensive comparative studies among existing EGL models in various popular application domains, such as Computer Vision and Natural Language Processing domains. Additional resources related to event prediction are included in the article website: https://kugaoyang.github.io/EGL/

Schlagwörter

Stichwörter der Autor:innen

Explainable AI (XAI)Explanation-Guided Learning (EGL)attention supervisiondeep learningexplanation alignmentexplanation supervisionfaithfulnesstrustworthiness

Autor:innen und Institutionen

  • Emory University, Atlanta, USA.
  • George Mason University, Fairfax, USA.

ORCID-Profile: Yuyang Gao, Siyi Gu, Junji Jiang, Sungsoo Ray Hong, Dazhou Yu, Liang Zhao

Förderung

  • NIA NIH HHS
  • NCI NIH HHS
  • National Science Foundation
  • Cisco Faculty Research Award
  • Oracle for Research Grant Award
  • Amazon Research Award
  • NVIDIA GPU
  • Design Knowledge Company

Zitieren

APA

Gao, Y., Gu, S., Jiang, J., Hong, S. R., Yu, D., & Zhao, L. (2024). Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning. ACM Computing Surveys, 56(7), 1-39. https://doi.org/10.1145/3644073

Vancouver

Gao Y, Gu S, Jiang J, Hong SR, Yu D, Zhao L. Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning. ACM Computing Surveys. 2024;56(7):1-39. doi:10.1145/3644073

BibTeX
@article{Gao2024,
  author = {Gao, Yuyang and Gu, Siyi and Jiang, Junji and Hong, Sungsoo Ray and Yu, Dazhou and Zhao, Liang},
  title = {Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning},
  journal = {ACM Computing Surveys},
  year = {2024},
  volume = {56},
  number = {7},
  pages = {1--39},
  doi = {10.1145/3644073}
}
Kostenlos starten →