Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid

By Ron Kohavi. 1996

How researchers see this paper

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

In Optimization & Training

Citations in the corpus

Private Summation in the Multi-Message Shuffle Model (2020, positive): “As a real-word dataset we used the Adult dataset [20].”
BOHB: Robust and Efficient Hyperparameter Optimization at Scale (2018, background): “, 2014): Adult (Kohavi, 1996), Higgs (Baldi et al.”
Scalable Private Learning with PATE (2018, methodology): “We evaluate with two computer vision tasks (MNIST and Street View House Numbers (Netzer et al., 2011)) and census data from the UCI Adult dataset (Kohavi, 1996).”
Missing Data Imputation for Supervised Learning (2016, background): “The state–of–the–art for the Adult dataset is a Naive Bayes classiﬁer that achieves a 14.05% generalization error after removing examples with missing values (Kohavi, 1996).”
CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models (2019, methodology): “We use the Pima Indian dataset [Smith et al., 1988] and the UCI adult dataset [Kohavi, 1996] in the following experiments.”
Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making (2019, methodology): “We evaluate our approach on 3 datasets: (A) The Default dataset of Taiwanese credit card users (Dheeru and Karra Taniskidou 2017; Yeh and Lien 2009) with |N | = 30, 000 and d = 23 features, where we predict whether individuals will default and the protected attribute is gender; (B) The Adult dataset”
Scalable Fair Clustering (2019, methodology): “The main reason is that our algorithm is particularly eﬃcient when the input pointset lies in a low dimensional space which is the case in all three datasets “Diabetes”, “Bank” and “Census”.”
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias (2018, methodology): “We currently provide an interface to seven popular datasets: Adult Census Income (Kohavi, 1996), German Credit (Dheeru & Karra Taniskidou, 2017), ProPublica Recidivism (COMPAS) (Angwin et al.”
Adaptive Sensitive Reweighting to Mitigate Bias in Fairness-aware Classification (2018, neutral): “[41], as well as with three well-known real world datasets: the Adult income dataset [32], the Bank marketing dataset [37] from the UCI repository [35] and the ProPublica COMPAS dataset [33] of criminal recidivism.”
A Convex Framework for Fair Regression (2017, methodology): “The Adult dataset [23, 24] from the UC Irvine Repository contains 1994 Census data, and the goal is to predict whether the income of an individual in the dataset is more than 50K per year or not.”
Deep Weighted Averaging Classifiers (2018, methodology): “Table 5 shows two examples from the Adult Income dataset of the kind of approximate explanation that might be offered by the DWAC model.”
Learning Optimized Risk Scores (2016, background): “Further, the work of Kotlowski et al. (2011) shows that a “balanced” version of the logistic loss forms a lower bound on 1−AUC, so minimizing the logistic loss indirectly maximizes a surrogate of AUC.”
LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning (2018, background): “• Adult dataset (Kohavi, 1996) contains samples that predict whether a person makes over 50K a year based on features in xn such as work-class, education, and marital-status.”
Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval (1998, background): “This may be because the larger amount of training data available in text categorization data sets favors algorithms which produce more complex classifiers [27], or may because the more elaborate representation and estimation tricks developed for retrieval and routing with naive Bayes have not been a”
A Novel Bayes Model: Hidden Naive Bayes (2009, methodology): “For decision tree learning, naive Bayes tree (NBTree) presented by Kohavi [21] is a typical example.”
Detecting click fraud in online advertising: a data mining approach (2014, methodology): “…decision tree that is built using the (Holmes et al., 2002) LogitBoost strategy NB tree Decision tree with Naive Bayes classiﬁers at the leaf nodes (Kohavi, 1996) Random forest Combination of tree predictors such that each tree depends on the (Breiman, 2001) values of a random vector sampled…”