The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911672616091648 |
|---|---|
| author | Fröhlich, Johanna S. Heinlein, Bastian Claar, Jan U. Rosenberger, Hans Belagiannis, Vasileios Müller, Ralf R. |
| author_facet | Fröhlich, Johanna S. Heinlein, Bastian Claar, Jan U. Rosenberger, Hans Belagiannis, Vasileios Müller, Ralf R. |
| contents | Explainable artificial intelligence has emerged as a promising field of research to address reliability concerns in artificial intelligence. Despite significant progress in explainable artificial intelligence, few methods provide a systematic way to visualize and understand how classes are confused and how their relationships evolve as training progresses. In this work, we present GRAPHIC, an architecture-agnostic approach that analyzes neural networks on a class level. It leverages confusion matrices derived from intermediate layers using linear classifiers. We interpret these as adjacency matrices of directed graphs, allowing tools from network science to visualize and quantify learning dynamics across training epochs and intermediate layers. GRAPHIC provides insights into linear class separability, dataset issues, and architectural behavior, revealing, for example, similarities between flatfish and man and labeling ambiguities validated in a human study. In summary, by uncovering real confusions, GRAPHIC offers new perspectives on how neural networks learn. The code is available at https://github.com/Johanna-S-Froehlich/GRAPHIC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19770 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning Fröhlich, Johanna S. Heinlein, Bastian Claar, Jan U. Rosenberger, Hans Belagiannis, Vasileios Müller, Ralf R. Machine Learning Artificial Intelligence Explainable artificial intelligence has emerged as a promising field of research to address reliability concerns in artificial intelligence. Despite significant progress in explainable artificial intelligence, few methods provide a systematic way to visualize and understand how classes are confused and how their relationships evolve as training progresses. In this work, we present GRAPHIC, an architecture-agnostic approach that analyzes neural networks on a class level. It leverages confusion matrices derived from intermediate layers using linear classifiers. We interpret these as adjacency matrices of directed graphs, allowing tools from network science to visualize and quantify learning dynamics across training epochs and intermediate layers. GRAPHIC provides insights into linear class separability, dataset issues, and architectural behavior, revealing, for example, similarities between flatfish and man and labeling ambiguities validated in a human study. In summary, by uncovering real confusions, GRAPHIC offers new perspectives on how neural networks learn. The code is available at https://github.com/Johanna-S-Froehlich/GRAPHIC. |
| title | The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.19770 |