Construct · 1 fields · 1 citations

feature attribution disagreement problem: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Explainable artificial intelligence

different post hoc explanation methods give conflicting attributions for the same model prediction, leaving practitioners unsure which to trust.

In explainable artificial intelligence, feature attribution disagreement problem refers to different post hoc explanation methods give conflicting attributions for the same model prediction, leaving practitioners unsure which to trust. This meaning comes from Krishna (2022) in arXiv.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how feature attribution disagreement problem sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

attribution3 fields · 6 citationsjingle · one word, three constructs explainable artificial intelligence1 fields · 1 citationsanchor · a standalone construct feature2 fields · 4 citationsjingle · one word, two constructs

References

Krishna, S., Han, T., Gu, A., Wu, S., Jabbari, S., & Lakkaraju, H. (2022). The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective. arXiv. https://doi.org/10.48550/arxiv.2202.01602

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct