LEAFAGE: Example-based and Feature importance-based Explanations for Black-box ML models
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.
Integrity signals
Registry
Cites
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.
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
Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches
Aamodt, A., & Plaza, E. (1994) · AI Communications · doi:10.3233/aic-1994-7104 · Cited by 5,624 · cited 2×
“This type of reasoning lies very close to how humans think [3], [1].”
BackgroundExplanation in Artificial Intelligence: Insights from the Social Sciences
Miller, T. (2017) · arXiv · doi:10.48550/arxiv.1706.07269 · Cited by 5,338
Likert scales, levels of measurement, and the “laws” of statistics
Norman, G. (2010) · Advances in Health Sciences Education · doi:10.1007/s10459-010-9222-y · Cited by 4,850 · cited 1×
“s can be found in gure 11. After looking at an house and an explanation for the prediction, the participants are asked to do two things. First, they have to rate the given explanation in Likert scale [19] according to transparency, information suciency, competence and condence. The chosen scale has ve values namely st…”
BackgroundModel-Agnostic Interpretability of Machine Learning
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · arXiv · doi:10.48550/arxiv.1606.05386 · Cited by 699
The effects of transparency on trust in and acceptance of a content-based art recommender
Cramer, H., Evers, V., Ramlal, S., van Someren, M., Rutledge, L., Stash, N., Aroyo, L., & Wielinga, B. (2008) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-008-9051-3 · Cited by 448 · cited 2×
“, one can test whether users have understood the reasoning behind the recommendations [13], measure the interaction time [12] or check whether the user agrees to buy a recommended item.”
Background
Research works printed but not linked: 15
- richter, 2016, CBR
- 10.1007/978-0-387-85820-3_15 · DOI · Paper page
- 10.1016/j.ijhcs.2013.12.007 · DOI · Paper page
- 10.1007/978-3-319-91473-2_9 · DOI
- dheeru, 2017, UCI ML Repository
- 10.1080/10691898.2011.11889627 · DOI · Paper page
- 10.2307/2280779 · DOI
- 10.1080/00401706.1964.10490181 · DOI · Paper page
- 10.1007/BF00155578 · DOI · Paper page
- 10.1016/j.artmed.2005.10.008 · DOI
- gill, 2018, Intr to ML Interpre
- 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
- xu, 2015, Show, attend and tell: Neural image caption generation with visual attention, Int'l Conference on Machine Learning, 2048
- 10.1109/TSMCC.2010.2071862 · DOI · Paper page
- miller, 2017, Explainable ai: Beware of inmates running the asylum, IJCAI-17 Workshop on Explainable AI, 36
Cited by
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., & Hussain, A. (2024) · Cognitive Computation · doi:10.1007/s12559-023-10179-8 · Cited by 2,495
“For some datasets and problems, this approach may provide more accurate and trustworthy explanations than other methods [110, 111].”
Evaluating XAI: A comparison of rule-based and example-based explanations
van der Waa, J., Nieuwburg, E., Cremers, A., & Neerincx, M. (2021) · Artificial Intelligence · doi:10.1016/j.artint.2020.103404 · Cited by 393
“In addition, this practice allows results to be meaningful even if hypotheses are rejected, as they falsify a scientific theory that may have been accepted as true.”
BackgroundHuman-centered evaluation of explainable AI applications: a systematic review
Kim, J., Maathuis, H., & Sent, D. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1456486 · Cited by 130
Cabitza, F., Campagner, A., Malgieri, G., Natali, C., Schneeberger, D., Stoeger, K., & Holzinger, A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118888 · Cited by 89
Relevance Metric for Counterfactuals Selection in Decision Trees
Fernández, R. R., de Diego, I. M., Aceña, V., Moguerza, J. M., & Fernández-Isabel, A. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-33607-3_10 · Cited by 7
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.