Papers › Instance-wise Causal Feature Selection for Model Interpretation

Instance-wise Causal Feature Selection for Model Interpretation

26 Apr 2021arXiv:2104.12759archive 2025-07-28

Pranoy Panda, Sai Srinivas Kancheti, Vineeth N Balasubramanian

We formulate a causal extension to the recently introduced paradigm of instance-wise feature selection to explain black-box visual classifiers. Our method selects a subset of input features that has the greatest causal effect on the models output. We quantify the causal influence of a subset of features by the Relative Entropy Distance measure. Under certain assumptions this is equivalent to the conditional mutual information between the selected subset and the output variable. The resulting causal selections are sparser and cover salient objects in the scene. We show the efficacy of our approach on multiple vision datasets by measuring the post-hoc accuracy and Average Causal Effect of selected features on the models output.

PaperPDFCode

Code

pranoy-panda/Causal-Feature-Subset-Selection officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

feature selectionmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Feature Selection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections