Similarity of Neural Network Models: A Survey of Functional and Representational Measures
ACM Computing Surveys · 30.09.2025 · 57 (9) · 1-52
DOI: 10.1145/3728458 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 06.05.2025. Verfasst von Max Klabunde und 3 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 235 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft.
Abstract (Originalsprache)
Measuring similarity of neural networks to understand and improve their behavior has become an issue of great importance and research interest. In this survey, we provide a comprehensive overview of two complementary perspectives of measuring neural network similarity: (i) representational similarity, which considers how activations of intermediate layers differ, and (ii) functional similarity, which considers how models differ in their outputs . In addition to providing detailed descriptions of existing measures, we summarize and discuss results on the properties of and relationships between these measures, and point to open research problems. We hope our work lays a foundation for more systematic research on the properties and applicability of similarity measures for neural network models.
Förderung
- Deutsche Forschungsgemeinschaft
Zitieren
APA
Klabunde, M., Schumacher, T., Strohmaier, M., & Lemmerich, F. (2025). Similarity of Neural Network Models: A Survey of Functional and Representational Measures. ACM Computing Surveys, 57(9), 1-52. https://doi.org/10.1145/3728458
Vancouver
Klabunde M, Schumacher T, Strohmaier M, Lemmerich F. Similarity of Neural Network Models: A Survey of Functional and Representational Measures. ACM Computing Surveys. 2025;57(9):1-52. doi:10.1145/3728458
BibTeX
@article{Klabunde2025,
author = {Klabunde, Max and Schumacher, Tobias and Strohmaier, Markus and Lemmerich, Florian},
title = {Similarity of Neural Network Models: A Survey of Functional and Representational Measures},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {9},
pages = {1--52},
doi = {10.1145/3728458}
}
EUVIMED