Explainability
Explanation Evaluation
Techniques that test whether an explanation is faithful to the model, stable and efficient, rather than producing one (e.g., deletion and insertion curves, sanity checks for saliency maps)
5 techniques
5 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Explainer Latency Benchmarking | Testing | Architecture/model Agnostic Requirements/black Box | Any | Explainer latency benchmarking measures how long an explanation method takes to produce an explanation for a single... | ||
| Deletion and Insertion Curves | Testing | Architecture/model Agnostic Requirements/black Box | Image Text Time-series | Deletion and insertion curves test whether a feature-attribution explanation, such as a heatmap over an image or... | ||
| Explanation Infidelity | Metric | Architecture/model Agnostic Requirements/black Box | Image Tabular | Explanation infidelity scores a feature-attribution explanation (one importance score per input feature) by how well it... | ||
| Explanation Max-Sensitivity | Metric | Architecture/model Agnostic Requirements/black Box | Image Tabular | Explanation max-sensitivity measures how stable an explanation is: whether inputs that differ only slightly, in ways... | ||
| Sanity Checks for Saliency Maps | Testing | Architecture/neural Networks Requirements/white Box +1 | Image Tabular Time-series | Sanity checks for saliency maps are two randomisation tests that show whether an explanation method's output depends on... |
Rows per page
Page 1 of 1