Update occlusion to new method of constructing ablated batches #1616
+142
−24
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
This pull request was exported from Phabricator. Differential Revision: D76483214 |
sarahtranfb
force-pushed
the
export-D76483214
branch
from
e5356e4 to
41bfd1c
Compare
sarahtranfb
added a commit
to sarahtranfb/captum
that referenced
this pull request
Jun 23, 2025
…ch#1616) Summary: Pull Request resolved: pytorch#1616 Differential Revision: D76483214
|
This pull request was exported from Phabricator. Differential Revision: D76483214 |
sarahtranfb
added a commit
to sarahtranfb/captum
that referenced
this pull request
Jun 23, 2025
…ch#1616) Summary: `FeaturePermutation` and `Occlusion` are subclasses of `FeatureAblation`, which contains the bulk of the logic around iterating through and processing perturbed inputs. Previously, `FeatureAblation` only constructed the perturbed input by looking at each input tensor individually, as there wasn't an explicit use-case that needed cross-tensor feature grouping. However this behavior has been modified to support cross-tensor masking, as different sparse features at Meta are represented by different tensors when they're finally passed to Captum, and we need to support grouping across features and feature types for various Ads workstreams/asks. The new behavior is mostly rolled out internally, and is controlled by the `enable_cross_tensor_attribution` flag. We do not want to support both behaviors indefinitely. `Occlusion` does not use the custom masks parameter exposed via `FeatureAblation`, but constructs the masks internally. There's no use-case requiring cross-tensor masking for occlusion, so it's not a requirement that it still follows the logic in `FeatureAblation`. However, it's been adapted in this diff in order to just reuse the code from `FeatureAblation`, as the logic specific to `enable_cross_tensor_attribution=False` will be going away. Differential Revision: D76483214
sarahtranfb
force-pushed
the
export-D76483214
branch
from
41bfd1c to
6e288fa
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76483214 |
sarahtranfb
force-pushed
the
export-D76483214
branch
from
6e288fa to
0fea20c
Compare
sarahtranfb
added a commit
to sarahtranfb/captum
that referenced
this pull request
Jul 3, 2025
…ch#1616) Summary: `FeaturePermutation` and `Occlusion` are subclasses of `FeatureAblation`, which contains the bulk of the logic around iterating through and processing perturbed inputs. Previously, `FeatureAblation` only constructed the perturbed input by looking at each input tensor individually, as there wasn't an explicit use-case that needed cross-tensor feature grouping. However this behavior has been modified to support cross-tensor masking, as different sparse features at Meta are represented by different tensors when they're finally passed to Captum, and we need to support grouping across features and feature types for various Ads workstreams/asks. The new behavior is mostly rolled out internally, and is controlled by the `enable_cross_tensor_attribution` flag. We do not want to support both behaviors indefinitely. `Occlusion` does not use the custom masks parameter exposed via `FeatureAblation`, but constructs the masks internally. There's no use-case requiring cross-tensor masking for occlusion, so it's not a requirement that it still follows the logic in `FeatureAblation`. However, it's been adapted in this diff in order to just reuse the code from `FeatureAblation`, as the logic specific to `enable_cross_tensor_attribution=False` will be going away. Reviewed By: cyrjano Differential Revision: D76483214
|
This pull request was exported from Phabricator. Differential Revision: D76483214 |
…ch#1616) Summary: `FeaturePermutation` and `Occlusion` are subclasses of `FeatureAblation`, which contains the bulk of the logic around iterating through and processing perturbed inputs. Previously, `FeatureAblation` only constructed the perturbed input by looking at each input tensor individually, as there wasn't an explicit use-case that needed cross-tensor feature grouping. However this behavior has been modified to support cross-tensor masking, as different sparse features at Meta are represented by different tensors when they're finally passed to Captum, and we need to support grouping across features and feature types for various Ads workstreams/asks. The new behavior is mostly rolled out internally, and is controlled by the `enable_cross_tensor_attribution` flag. We do not want to support both behaviors indefinitely. `Occlusion` does not use the custom masks parameter exposed via `FeatureAblation`, but constructs the masks internally. There's no use-case requiring cross-tensor masking for occlusion, so it's not a requirement that it still follows the logic in `FeatureAblation`. However, it's been adapted in this diff in order to just reuse the code from `FeatureAblation`, as the logic specific to `enable_cross_tensor_attribution=False` will be going away. Reviewed By: cyrjano Differential Revision: D76483214
sarahtranfb
force-pushed
the
export-D76483214
branch
from
0fea20c to
a2bb059
Compare
|
This pull request was exported from Phabricator. Differential Revision: D76483214 |
|
This pull request has been merged in f282901. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Differential Revision: D76483214