data requirements Filters
Browse and search through available filters in this category. Click on any filter to view related techniques.
| Description | Action | ||
|---|---|---|---|
no special requirements | Works with standard inputs without special requirements | 43 | |
sensitive attributes | Needs data labeled with protected attributes | 26 | |
labelled data | Requires datasets with ground truth labels | 16 | |
access to model internals | Needs access to model gradients, weights, or activations | 13 | |
access to training data | Requires the original training dataset | 7 | |
calibration set | Requires a calibration dataset for adjustment | 4 | |
reference dataset | Needs a baseline or reference dataset for comparison | 2 | |
causal graph | Requires a predefined causal structure or graph | 1 | |
pre trained model | Requires an existing trained model as input | 1 | |
prediction probabilities | Needs probabilistic predictions from the model | 1 | |
test scenarios | Requires predefined test cases or scenarios | 1 | |
validation set | Needs a separate validation dataset | 1 |
Showing 12 of 12 filters