You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When applying MuFidelity on tabular data or time series, the number of features set to 0 with the mask does not correspond to subset_percent. Indeed, the formula to compute the subset_size depends on grid_size ** 2 which is adapted to images.
Therefore, the number of features set to zero is much higher than expected, all features may be set to zero if grid_size is big. For tabular data or time series, the default value corresponds to the number of features, which is too big and results in fidelity scores of only zeros.
Expected Behavior
Remove the attribute self.subset_size line 91.
Then in lines 201, 208, and 220:
Replace: subset_masks = tf.argsort(subset_masks, axis=-1) > self.subset_size
By: subset_masks = subset_masks > self.subset_percent
!!! See the direction of the > or < depending on the meaning of subset percent.
Version
1.3.1
Environment
No response
Relevant log output
No response
To Reproduce
See Attributions: Time Series and Regression tutorial, in the metric part, for MuFidelity, set subset_percent to 0.5 (perturb half) and grid_size to 48 (treat each time step differently).
It will return only zeros, but the configuration is far from absurd.
The text was updated successfully, but these errors were encountered:
Module
None
Current Behavior
When applying MuFidelity on tabular data or time series, the number of features set to 0 with the mask does not correspond to
subset_percent
. Indeed, the formula to compute thesubset_size
depends ongrid_size ** 2
which is adapted to images.Therefore, the number of features set to zero is much higher than expected, all features may be set to zero if
grid_size
is big. For tabular data or time series, the default value corresponds to the number of features, which is too big and results in fidelity scores of only zeros.Expected Behavior
Remove the attribute
self.subset_size
line 91.Then in lines 201, 208, and 220:
Replace:
subset_masks = tf.argsort(subset_masks, axis=-1) > self.subset_size
By:
subset_masks = subset_masks > self.subset_percent
!!! See the direction of the > or < depending on the meaning of subset percent.
Version
1.3.1
Environment
No response
Relevant log output
No response
To Reproduce
See Attributions: Time Series and Regression tutorial, in the metric part, for
MuFidelity
, setsubset_percent
to0.5
(perturb half) andgrid_size
to48
(treat each time step differently).It will return only zeros, but the configuration is far from absurd.
The text was updated successfully, but these errors were encountered: