[Summary] Add perturbation feature attribution methods

[gsarti]

🚀 Feature Request

The following is a non-exhaustive list of perturbation-based feature attribution methods that could be added to the library:

Method name	Source	In Captum	Code implementation	Status
(Layer) Feature Ablation1	-	✅	pytorch/captum
Occlusion	Zeiler and Fergus '13	✅	pytorch/captum	✅
Shapley Value Sampling	Castro et al. '09	✅	pytorch/captum
Lime	Ribeiro et al. '16	✅	pytorch/captum	✅
KernelShap	Lundberg and Lee '17	✅	pytorch/captum
Editing 2	-	-	-
Greedy Rationalization 3	Vafa et al. '21	-	keyonvafa/sequential-rationales
Information Bottleneck	Jiang et al. '20	-	DFKI-NLP/thermostat
BayesLime	Slack et al. '21	-	dylan-slack/Modeling-Uncertainty-Local-Explainability
BayesSHAP	Slack et al. '21	-	dylan-slack/Modeling-Uncertainty-Local-Explainability
Input Reduction	Feng et al. '18	-	-
Input Marginalization	Kim et al. '20	-	-
Occlusion & Language Modeling	Harbecke and Alt '20	-	DFKI-NLP/OLM
Context Probing 4	Cífka and Liutkus '22	-	cifkao/context-probing
Weighted SHAP	Kwon and Zou '22	-	ykwon0407/WeightedSHAP
Value Zeroing	Mohebbi et al. '23	-	hmohebbi/ValueZeroing	✅
Comprehensiveness-as-a-metric	Zhou et al. '23	-	YilunZhou/solvability-explainer
Sufficiency-as-a-metric	Zhou et al. '23	-	YilunZhou/solvability-explainer
Causal Tracing	Meng et al. '22	-	kmeng01/rome
Attention Knockout5	Geva et al. '23	-	-
ReAGent	Zhao et al. '24	-	casszhao/ReAGent	✅
SyntaxSHAP	Amara et al. '24	-	k-amara/syntax-shap

Notes:

1. For more information on Editing, see point 3 in [Summary] Add metrics for feature attribution evaluation #112 .

Footnotes

1. Called ablation, but perform masking of features using a baseline.
2. Editing replaces tokens with their nearest neighbors in the vocabulary embedding space and measures saliency as the drop in performance for the target. In the future, this can allow users to specify a custom editing strategy via an input Callable.
3. Possibly overlapping with feature ablation up to some measure.
4. Valid only for decoder-only models.
5. Verify whether it would be exactly equivalent to Value Zeroing, include only if functionally different (alias otherwise).

[nfelnlp]

More methods related to Occlusion:

• Input Reduction (Feng et al., 2018)
• Input Marginalization (Kim et al., 2020)
• OLM (Harbecke & Alt, 2020)

[gsarti]

Added to method table!