Framework for Evaluating Faithfulness of Local Explanations

Michal Moshkovitz; Nave Frost; Sanjoy Dasgupta

Framework for Evaluating Faithfulness of Local Explanations

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2202.00734 v1 pith:ZNC4IXRL submitted 2022-02-01 cs.LG stat.ML

Sanjoy Dasgupta , Nave Frost , Michal Moshkovitz This is my paper · ORCID

classification cs.LGstat.ML

keywords explanationfaithfulnessestimatorsmeasurespropertiessystemsanalyticallyanchors

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

We study the faithfulness of an explanation system to the underlying prediction model. We show that this can be captured by two properties, consistency and sufficiency, and introduce quantitative measures of the extent to which these hold. Interestingly, these measures depend on the test-time data distribution. For a variety of existing explanation systems, such as anchors, we analytically study these quantities. We also provide estimators and sample complexity bounds for empirically determining the faithfulness of black-box explanation systems. Finally, we experimentally validate the new properties and estimators.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Advancing Attribution-Based Neural Network Explainability through Relative Absolute Magnitude Layer-Wise Relevance Propagation and Multi-Component Evaluation
cs.CV 2024-12 conditional novelty 5.0 of 10

A new LRP rule that scales attributions by absolute activation magnitude, plus a unified evaluation metric, is tested across three architectures and two datasets.

Pith tools