AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Distribution-Based Feature Attribution for Explaining the Predictions of Any Classifier

Xinpeng Li, Kai Ming Ting

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Feature attribution methods · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use DFAX distribution-based attribution instead of DLIMEfeature attribution · Average over 10 datasetsDeletion score: .4595 -> .3244Improved
use DFAX instead of DLIMEfeature attribution · Average over 10 datasetsInsertion score: .6612 -> .7708Improved
use DFAX instead of DLIMEfeature attribution · DiabetesInsertion score: .8781 vs .8738No clear effect
use GKDE instead of SiNNE in DFAX (ablation)DFAX · Average over 10 datasetsInsertion score: .7470 -> .7708Improved
use DFAX instead of DLIME for HER2st gene selectionHER2st classifier · HER2stAccuracy after masking: 79.51% -> 95.64%Improved
SHAP and MAPLE as attribution methods vs randomfeature attribution · Average over 10 datasetsInsertion score: SHAP .5463, MAPLE .5800 vs Random .5838Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy