AI Paper Atlas

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

A Unified Approach to Interpreting Model Predictions

Scott M Lundberg, Su-In Lee

NeurIPS 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Post-hoc explanation analysis

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 Kernel SHAP weighted regression instead of Shapley sampling valuesModel-agnostic SHAP estimation · Dense and sparse decision tree modelsmodel evaluations for similar approximation accuracyImproved
Use Kernel SHAP instead of LIMELocal feature attribution · Dense and sparse decision tree modelsconsistency with local accuracy and consistency propertiesImproved
Use SHAP values instead of LIME or DeepLIFTFeature attribution · Sickness-score and max-allocation user studiesagreement with human explanationsImproved
Adapt DeepLIFT to use component-level SHAP valuesDeep SHAP · Max-function attributionsconsistency with human intuitionImproved
Use estimates closer to SHAP values instead of original DeepLIFT estimatesMNIST convolutional-network explanations · MNISTchange in log odds after masking pixelsImproved

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