CoChat

LEAFAGE: Example-based and Feature importance-based Explanations for Black-box ML models

Adhikari, Ajaya, Tax, David M. J., Satta, Riccardo, Faeth, Matthias · 2019 · 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Cited by 27

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

Abstract

Explainable Artificial Intelligence (XAI) is an emergent research field which tries to cope with the lack of transparency of AI systems, by providing human understandable explanations for the underlying Machine Learning models. This work presents a new explanation extraction method called LEAFAGE. Explanations are provided both in terms of feature importance and of similar classification examples. The latter is a well known strategy for problem solving and justification in social science. LEAFAGE leverages on the fact that the reasoning behind a single decision/prediction for a single data point is generally simpler to understand than the complete model; it produces explanations by generating simpler yet locally accurate approximations of the original model. LEAFAGE performs overall better than the current state of the art in terms of fidelity of the model approximation, in particular when Machine Learning models with non-linear decision boundaries are analysed. LEAFAGE was also tested in terms of usefulness for the user, an aspect still largely overlooked in the scientific literature. Results show interesting and partly counter-intuitive findings, such as the fact that providing no explanation is sometimes better than providing certain kinds of explanation.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/fuzz-ieee.2019.8858846

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 5 references

Research works printed but not linked: 15

  1. richter, 2016, CBR
  2. 10.1007/978-0-387-85820-3_15 · DOI · Paper page
  3. 10.1016/j.ijhcs.2013.12.007 · DOI · Paper page
  4. 10.1007/978-3-319-91473-2_9 · DOI
  5. dheeru, 2017, UCI ML Repository
  6. 10.1080/10691898.2011.11889627 · DOI · Paper page
  7. 10.2307/2280779 · DOI
  8. 10.1080/00401706.1964.10490181 · DOI · Paper page
  9. 10.1007/BF00155578 · DOI · Paper page
  10. 10.1016/j.artmed.2005.10.008 · DOI
  11. gill, 2018, Intr to ML Interpre
  12. ribeiro, 2016, Why should i trust you?: Expl. the predic. of any class, Proc ACM SIGKDD Int Conf Knowl Discov Data Min, 1135, 10.1145/2939672.2939778 · DOI · Paper page
  13. xu, 2015, Show, attend and tell: Neural image caption generation with visual attention, Int'l Conference on Machine Learning, 2048
  14. 10.1109/TSMCC.2010.2071862 · DOI · Paper page
  15. miller, 2017, Explainable ai: Beware of inmates running the asylum, IJCAI-17 Workshop on Explainable AI, 36

Cited by

Metadata

Authors
Adhikari, A., Tax, D. M. J., Satta, R., & Faeth, M.
Venue
2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Publisher
IEEE
Published
2019-06
Pages
1-7
ISSN
1098-7584 (ISSN-L)
OpenAlex
W2979889694
Cited by
27
References
5
FWCI
1.50
Type
conference paper
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.