Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review
ACM Computing Surveys · 30.06.2024 · 56 (6) · 1-35
DOI: 10.1145/3645103 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift ACM Computing Surveys, online erschienen am 13.03.2024. Verfasst von Giovanni Ciatto und 4 weiteren Autor:innen. Die Arbeit wurde bisher 39-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CHIST-ERA IV, FAIR–Future Artificial Intelligence Research, European Commission.
Abstract (Originalsprache)
In this article, we focus on the opacity issue of sub-symbolic machine learning predictors by promoting two complementary activities— symbolic knowledge extraction (SKE) and symbolic knowledge injection (SKI)—from and into sub-symbolic predictors. We consider as symbolic any language being intelligible and interpretable for both humans and computers. Accordingly, we propose general meta-models for both SKE and SKI, along with two taxonomies for the classification of SKE and SKI methods. By adopting an explainable artificial intelligence (XAI) perspective, we highlight how such methods can be exploited to mitigate the aforementioned opacity issue. Our taxonomies are attained by surveying and classifying existing methods from the literature, following a systematic approach, and by generalising the results of previous surveys targeting specific sub-topics of either SKE or SKI alone. More precisely, we analyse 132 methods for SKE and 117 methods for SKI, and we categorise them according to their purpose, operation, expected input/output data and predictor types. For each method, we also indicate the presence/lack of runnable software implementations. Our work may be of interest for data scientists aiming at selecting the most adequate SKE/SKI method for their needs, and may also work as suggestions for researchers interested in filling the gaps of the current state-of-the-art as well as for developers willing to implement SKE/SKI-based technologies.
Förderung
- CHIST-ERA IV
- FAIR–Future Artificial Intelligence Research
- European Commission
- ENGINES – ENGineering INtElligent Systems around intelligent agent technologies
Zitieren
APA
Ciatto, G., Sabbatini, F., Agiollo, A., Magnini, M., & Omicini, A. (2024). Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review. ACM Computing Surveys, 56(6), 1-35. https://doi.org/10.1145/3645103
Vancouver
Ciatto G, Sabbatini F, Agiollo A, Magnini M, Omicini A. Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review. ACM Computing Surveys. 2024;56(6):1-35. doi:10.1145/3645103
BibTeX
@article{Ciatto2024,
author = {Ciatto, Giovanni and Sabbatini, Federico and Agiollo, Andrea and Magnini, Matteo and Omicini, Andrea},
title = {Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review},
journal = {ACM Computing Surveys},
year = {2024},
volume = {56},
number = {6},
pages = {1--35},
doi = {10.1145/3645103}
}
EUVIMED