Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AI
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912209704058880 |
|---|---|
| author | Huang, Qi Mezzi, Emanuele Mutlu, Osman Kofinas, Miltiadis Prasad, Vidya Khan, Shadnan Azwad Ranguelova, Elena van Stein, Niki |
| author_facet | Huang, Qi Mezzi, Emanuele Mutlu, Osman Kofinas, Miltiadis Prasad, Vidya Khan, Shadnan Azwad Ranguelova, Elena van Stein, Niki |
| contents | We introduce a novel metric for measuring semantic continuity in Explainable AI methods and machine learning models. We posit that for models to be truly interpretable and trustworthy, similar inputs should yield similar explanations, reflecting a consistent semantic understanding. By leveraging XAI techniques, we assess semantic continuity in the task of image recognition. We conduct experiments to observe how incremental changes in input affect the explanations provided by different XAI methods. Through this approach, we aim to evaluate the models' capability to generalize and abstract semantic concepts accurately and to evaluate different XAI methods in correctly capturing the model behaviour. This paper contributes to the broader discourse on AI interpretability by proposing a quantitative measure for semantic continuity for XAI methods, offering insights into the models' and explainers' internal reasoning processes, and promoting more reliable and transparent AI systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12950 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AI Huang, Qi Mezzi, Emanuele Mutlu, Osman Kofinas, Miltiadis Prasad, Vidya Khan, Shadnan Azwad Ranguelova, Elena van Stein, Niki Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning We introduce a novel metric for measuring semantic continuity in Explainable AI methods and machine learning models. We posit that for models to be truly interpretable and trustworthy, similar inputs should yield similar explanations, reflecting a consistent semantic understanding. By leveraging XAI techniques, we assess semantic continuity in the task of image recognition. We conduct experiments to observe how incremental changes in input affect the explanations provided by different XAI methods. Through this approach, we aim to evaluate the models' capability to generalize and abstract semantic concepts accurately and to evaluate different XAI methods in correctly capturing the model behaviour. This paper contributes to the broader discourse on AI interpretability by proposing a quantitative measure for semantic continuity for XAI methods, offering insights into the models' and explainers' internal reasoning processes, and promoting more reliable and transparent AI systems. |
| title | Beyond the Veil of Similarity: Quantifying Semantic Continuity in Explainable AI |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2407.12950 |