On cognitive preferences and the plausibility of rule-based models
Open accessThe DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
It is conventional wisdom in machine learning and data mining that logical models such as rule sets are more interpretable than other models, and that among such rule-based models, simpler models are more interpretable than more complex ones. In this position paper, we question this latter assumption by focusing on one particular aspect of interpretability, namely the plausibility of models. Roughly speaking, we equate the plausibility of a model with the likeliness that a user accepts it as an explanation for a prediction. In particular, we argue that—all other things being equal—longer explanations may be more convincing than shorter ones, and that the predominant bias for shorter models, which is typically necessary for learning powerful discriminative models, may not be suitable when it comes to user acceptance of the learned models. To that end, we first recapitulate evidence for and against this postulate, and then report the results of an evaluation in a crowdsourcing study based on about 3000 judgments. The results do not reveal a strong preference for simple rules, whereas we can observe a weak preference for longer rules in some domains. We then relate these results to well-known cognitive biases such as the conjunction fallacy, the representative heuristic, or the recognition heuristic, and investigate their relation to rule length and plausibility.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Tversky, A., & Kahneman, D. (1974) · Science · doi:10.1126/science.185.4157.1124 · Cited by 28,810
Mining association rules between sets of items in large databases
Agrawal, R., Imieliński, T., & Swami, A. (1993) · Proceedings of the 1993 ACM SIGMOD international conference on Management of data · doi:10.1145/170035.170072 · Cited by 14,907
“Risk, Ambiguity, and the Savage Axioms.”
Ellsberg, D. (1961) · The Quarterly Journal of Economics · doi:10.2307/1884324 · Cited by 7,891
Confirmation Bias: A Ubiquitous Phenomenon in Many Guises
Nickerson, R. S. (1998) · Review of General Psychology · doi:10.1037/1089-2680.2.2.175 · Cited by 7,267
Attitudinal Effects of Mere Exposure
Zajonc, R. B. (1968) · Journal of Personality and Social Psychology · doi:10.1037/h0025848 · Cited by 6,745
A perspective on judgment and choice: mapping bounded rationality.
Kahneman, D. (2003) · American Psychologist · doi:10.1037/0003-066x.58.9.697 · Cited by 5,540
Blei, D. M. (2012) · Communications of the ACM · doi:10.1145/2133806.2133826 · Cited by 5,516 · cited 2×
“The strength of many recent learning algorithms, most notably deep learning (LeCun et al., 2015; Schmidhuber, 2015), feature learning (Mikolov et al., 2013), fuzzy systems (Alonso et al., 2015) or topic modeling (Blei, 2012), is that latent variables are formed during the learning process.”
BackgroundMethodLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 1×
“For example, Lipton (2016) still suggests that the term interpretability is ill-defined.”
BackgroundExplanation in Artificial Intelligence: Insights from the Social Sciences
Miller, T. (2017) · arXiv · doi:10.48550/arxiv.1706.07269 · Cited by 5,338
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Mining association rules between sets of items in large databases
Agrawal, R., Imieliński, T., & Swami, A. (1993) · ACM SIGMOD Record · doi:10.1145/170036.170072 · Cited by 4,551
Extensional versus intuitive reasoning: The conjunction fallacy in probability judgment.
Tversky, A., & Kahneman, D. (1983) · Psychological Review · doi:10.1037/0033-295x.90.4.293 · Cited by 3,991
Running experiments on Amazon Mechanical Turk
Paolacci, G., Chandler, J., & Ipeirotis, P. G. (2010) · Judgment and Decision Making · doi:10.1017/s1930297500002205 · Cited by 3,767
Belief in the law of small numbers.
Tversky, A., & Kahneman, D. (1971) · Psychological Bulletin · doi:10.1037/h0031322 · Cited by 3,246
Studies in the Logic of Explanation
Hempel, C. G., & Oppenheim, P. (1948) · Philosophy of Science · doi:10.1086/286983 · Cited by 3,174
Inside the Turk: Understanding Mechanical Turk as a Participant Pool
Paolacci, G., & Chandler, J. (2014) · Current Directions in Psychological Science · doi:10.1177/0963721414531598 · Cited by 2,136
The KDD process for extracting useful knowledge from volumes of data
Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996) · Communications of the ACM · doi:10.1145/240455.240464 · Cited by 1,934
Recent developments in modeling preferences: Uncertainty and ambiguity
Camerer, C., & Weber, M. (1992) · Journal of Risk and Uncertainty · doi:10.1007/bf00122575 · Cited by 1,795
Learning Logical Definitions from Relations
Quinlan, J. R. (1990) · Machine Learning · doi:10.1023/a:1022699322624 · Cited by 1,644 · cited 2×
“, 1995), inductive rule learning (Quinlan, 1990; Cohen, 1995; Pfahringer, 1995) or for pattern evaluation (Vreeken et al.”
BackgroundMethodThe Minimum Description Length Principle
Grünwald, P. D. (2007) · doi:10.7551/mitpress/4643.001.0001 · Cited by 1,644 · cited 1×
“…of Occam’s razor in machine learning is the minimum description length (MDL; Rissanen, 1978) or minimum message length (MML 18 ; Wallace & Boulton, 1968) principle which is an information-theoretic formulation of the principle that smaller models should be preferred (Gr¨unwald, 2007).”
BackgroundEvaluating amazon’s mechanical turk as a tool for experimental behavioral research
Crump, M. J. C., McDonnell, J. V., & Gureckis, T. M. (2013) · PLoS ONE · doi:10.1371/journal.pone.0057410 · Cited by 1,617
Models of ecological rationality: The recognition heuristic.
Goldstein, D. G., & Gigerenzer, G. (2002) · Psychological Review · doi:10.1037/0033-295x.109.1.75 · Cited by 1,352
Survey and critique of techniques for extracting rules from trained artificial neural networks
Andrews, R., Diederich, J., & Tickle, A. B. (1995) · Knowledge-Based Systems · doi:10.1016/0950-7051(96)81920-4 · Cited by 1,225
Blumer, A., Ehrenfeucht, A., Haussler, D., & Warmuth, M. K. (1987) · Information Processing Letters · doi:10.1016/0020-0190(87)90114-1 · Cited by 1,054
Frequency and the conference of referential validity
Hasher, L., Goldstein, D., & Toppino, T. (1977) · Journal of Verbal Learning and Verbal Behavior · doi:10.1016/s0022-5371(77)80012-1 · Cited by 920
Evaluating Learning Algorithms: A Classification Perspective
Japkowicz, N., & Shah, M. (2011) · doi:10.1017/cbo9780511921803 · Cited by 767
The Role of Occam's Razor in Knowledge Discovery
Domingos, P. (1999) · Data Mining and Knowledge Discovery · doi:10.1023/a:1009868929893 · Cited by 459 · cited 2×
“Although Domingos (1999) argues in his critical review that it is theoretically and empirically false to favor the simpler of two models with the same training-set error on the grounds that this would lead to lower generalization error, he concludes that Occam’s Razor is nevertheless relevant for…”
BackgroundMachine Invention of First-order Predicates by Inverting Resolution
MUGGLETON, S., & BUNTINE, W. (1988) · Machine Learning Proceedings 1988 · doi:10.1016/b978-0-934613-64-4.50040-2 · Cited by 436
Fürnkranz, J., Gamberger, D., & Lavrač, N. (2012) · Cognitive Technologies · doi:10.1007/978-3-540-75197-7 · Cited by 428 · cited 2×
“For example, F¨urnkranz et al. (2012) argue that rules “ offer the best trade-off between human and machine understandability ”.”
BackgroundSelf-citationHuysmans, J., Dejaeger, K., Mues, C., Vanthienen, J., & Baesens, B. (2011) · Decision Support Systems · doi:10.1016/j.dss.2010.12.003 · Cited by 425
Parameters behind “Nonparametric” Statistics: Kendall's tau, Somers’ D and Median Differences
Newson, R. (2002) · The Stata Journal: Promoting communications on statistics and Stata · doi:10.1177/1536867x0200200103 · Cited by 394
Explaining Data-Driven Document Classifications1
Martens, D., & Provost, F. (2014) · MIS Quarterly · doi:10.25300/misq/2014/38.1.04 · Cited by 264
Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited
Muggleton, S. H., Lin, D., & Tamaddoni-Nezhad, A. (2015) · Machine Learning · doi:10.1007/s10994-014-5471-y · Cited by 184
Kliegr, T., Bahník, Š., & Fürnkranz, J. (2021) · Artificial Intelligence · doi:10.1016/j.artint.2021.103458 · Cited by 139
Self-citationMartire, K. A., Kemp, R. I., Watkins, I., Sayle, M. A., & Newell, B. R. (2013) · Law and Human Behavior · doi:10.1037/lhb0000027 · Cited by 90
Cited by
Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems
(2021) · doi:10.1145/3411764 · Cited by 1,240
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Ser, J. D., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., et al. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102301 · Cited by 626
Explainable artificial intelligence: Objectives, stakeholders, and future research opportunities
Meske, C., Bunde, E., Schneider, J., & Gersch, M. (2022) · Information Systems Management · doi:10.1080/10580530.2020.1849465 · Cited by 365
Nazar, M., Alam, M. M., Yafi, E., & Su'ud, M. M. (2021) · IEEE Access · doi:10.1109/access.2021.3127881 · Cited by 312
Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-making
Rastogi, C., Zhang, Y., Wei, D., Varshney, K. R., Dhurandhar, A., & Tomsett, R. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3512930 · Cited by 216
“Recently, (Fürnkranz et al., 2020) evaluated a selection of cognitive biases in the very specific context of whether minimizing the complexity or length of a rule will also lead to increased interpretability of machine learning models.”
Background
Metadata
- Authors
- Fürnkranz, J., Kliegr, T., & Paulheim, H.
- Venue
- Machine Learning
- Published
- 2019-12-24
- Volume
- 109
- Issue
- 4
- Pages
- 853-898
- ISSN
- 0885-6125 (ISSN-L)
- 1573-0565
- OpenAlex
- W2887231081
- Cited by
- 70
- References
- 36
- FWCI
- 3.57
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.