Similarity of Neural Network Models: A Survey of Functional and Representational Measures
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908372470595584 |
|---|---|
| author | Klabunde, Max Schumacher, Tobias Strohmaier, Markus Lemmerich, Florian |
| author_facet | Klabunde, Max Schumacher, Tobias Strohmaier, Markus Lemmerich, Florian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_06329 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Similarity of Neural Network Models: A Survey of Functional and Representational Measures Klabunde, Max Schumacher, Tobias Strohmaier, Markus Lemmerich, Florian Machine Learning 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. |
| title | Similarity of Neural Network Models: A Survey of Functional and Representational Measures |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2305.06329 |