Intelligible models for classification and regression

By Yin Lou, R. Caruana, Johannes Gehrke. 2012

575 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Safety, Robustness & Interpretability

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “It can be considered as intelligibility as stated in [171].”
Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, methodology): “If the model is fitted using boosting methods (Freund and Schapire, 1997; Friedman, 2001, 2002), we learn a tree on each single feature in each iteration and then aggregate them together (Lou et al., 2012).”
The mythos of model interpretability (2016, background): “Our investigation of”
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “7 X Backwards model for interpretability of linear models [106] 7 7 GDM (Generative Discriminative Models): ridge regression + least square [99] 7 7 GAM, GA2M (Generative Additive Model) [81], [101], [102] 7 7 ProtoAttend [104] 7 X Other content-subject-speciﬁc models: N.A. N.A. Pre-deﬁned models + ”
Learning Optimal Decision Trees with SAT (2018, background): “…range of work in the recent past ([Li et al. , 2018; Lakkaraju et al. , 2017; Angelino et al. , 2017; Lakkaraju et al. , 2016; Letham et al. , 2015; Lou et al. , 2012] among others), by a number of recent events dedicated to the topic [IJ-CAI XAI Workshop, 2017; ICML WHI Workshop, 2017; NIPS IML…”
Local Rule-Based Explanations of Black Box Decision Systems (2018, methodology): “Only few methods for global explanation are agnostic with respect to the black box [19, 24].”
Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning (2018, methodology): “a proxy to test interpretability [50], [62], [49] or (2) the model is learned using a speciﬁc hypothesis class already established to be interpretable (e.g., a sparse linear model or a decision tree) [63]. Our evaluation falls under the ﬁrst category: exemplars returned by our model simplify downstr”
A Survey of Methods for Explaining Black Box Models (2018, background): “Probably the first attempt of an agnostic solution was proposed in Reference [69].”
Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation (2017, methodology): “ a statistical test to determine if the audit data is missing key features used to train the black-box model. 5) An ancillary contribution of this paper is a new confidence interval estimate for iGAM [9, 24, 25], a type of transparent model, to compare two models of this class. 2 AUDIT APPROACH Our ”
Interpretability via Model Extraction (2017, background): “Complimentary approaches to interpretability focus on learning interpretable models [7, 26, 30] or on explaining the model’s behavior on specific inputs rather than the model as a whole [23].”
SmoothGrad: removing noise by adding noise (2017, background): “For example, the pneumonia risk prediction case study in (Lou et al., 2012) showed that more interpretable models can reveal important but surprising patterns in the data that complex models overlooked.”
Neural Additive Models: Interpretable Machine Learning with Neural Nets (2020, background): “, 2002] are the GAM [Lou et al., 2012] and GAM [Lou et al.”
InterpretML: A Unified Framework for Machine Learning Interpretability (2019, methodology): “The algorithmic details for the training procedure, selection of pairwise interaction terms, and case studies can be found in (Lou et al., 2012, 2013; Caruana et al., 2015).”
Deep Weighted Averaging Classifiers (2018, background): “This category includes classic models that can easily be simulated by humans, such as decision lists, as well as sparse linear models, where the prediction is based on a weighted sum of features [6, 24, 29, 49, 50, 56].”
Manipulating and Measuring Model Interpretability (2018, background): “simple models, such as point systems that can be memorized [35, 69] or generative additive models in which the impact of each feature on the model’s prediction should be relatively easy to understand [12, 50, 51]. The second is to provide post-hoc explanations for (potentially complex) models. One t”
Interpretable Decision Sets: A Joint Framework for Description and Prediction (2016, background): “For example, prototype vector machines [4], regression models [36, 35], generalized additive models [16, 40, 26, 27], Bayesian case models [19] mind-the-gap models [20], and scoring systems [37] have all been proposed as interpretable models.”
Causal Interpretability for Machine Learning - Problems, Methods and Evaluation (2020, methodology): “[62] use a generalized version of linear regression called generalized additive models (GAM) in the form of g(y) = ∑ fi(xi) = f1(x1) + .”