Induction of decision trees

By J. Ross Quinlan. 2004

17,198 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Statistical Learning Theory, Algorithms & Complexity

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 Information Systems

In Statistical Learning Theory

In Algorithms & Complexity

Citations in the corpus

IBM Federated Learning: an Enterprise Framework White Paper V0.1 (2020, methodology): “IBM Federated Learning supports a FL variant of the ID3 algorithm [25], where the tree is grown at the aggregator side and the local training function, L only performs light computations to generate replies r containing the counts information.”
Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers (2013, background): “5 [52] algorithm, which is an extended version of the ID 3 algorithm [51]. top-down, greedy search through the space of all possible decision trees.”
Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View (2019, methodology): “Random: it selects a subset of features randomly and, by using the selected features, generating as many binary splitting criteria as possible depending on the type of the feature [1], [2], [107].”
Learning Optimal Decision Trees with SAT (2018, background): “Decision trees have been actively investigated since the early 80s [Breiman et al. , 1984; Quinlan, 1986; Quinlan, 1993; Mitchell, 1997; Cockett and Hierrera, 1990], and ﬁnd important practical applications in a wide range of domains, including ML and DM [Quinlan, 1993; Murthy, 1998; Rokach and…”
Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking (2017, background): “train the following learning models to nd our best estimate f̂ : Decision Trees (DT) [18], which can be thought of as a special case of an ensemble with a single tree; Gradient Boosted Decision Trees (GBDT) [9], and Random Forests (RF) [2].”
Distilling Knowledge from Deep Networks with Applications to Healthcare Domain (2015, background): “Decision trees [36] - due to their easy interpretability - have been quite successfully employed in the healthcare domain [6, 45, 14] and clinicians have embraced it to make informed decisions.”
Learning Optimal Decision Trees with MaxSAT and its Integration in AdaBoost (2020, methodology): “The most widely used techniques for computing decision trees (e.g. CART [Breiman et al. , 1984], ID3 [Quinlan, 1986] and C4.5 [Quinlan, 1993]) are greedy heuristics, typically build trees from top to bottom selecting the feature yielding the highest information gain.”
Learning Optimal Classification Trees: Strong Max-Flow Formulations (2020, methodology): “stics that employ very intuitive, yet ad-hoc, rules for constructing the decision trees. For example, CART uses the Gini Index to decide on the splitting, see Breiman (1984); ID3 employs entropy, see Quinlan (1986); and C4.5 leverages normalized information gain, see Quinlan (2014). The high quality”
Learning Optimal Classification Trees Using a Binary Linear Program Formulation (2019, methodology): “Hence, greedy based heuristics such as CART (Breiman et al. 1984) and ID3 (Quinlan 1986) have been widely used to construct sub-optimal trees.”
Optimal Decision Trees for the Algorithm Selection Problem: Integer Programming Based Approaches (2019, methodology): “dicting the class of new instances. The production of compact and accurate decision trees is an NP-Hard problem (Hyal and Rivest, 1976). Thus, many greedy heuristics have been proposed, such as ID3 (Quinlan, 1986), C4.5 (Quinlan, 1993) and CART (Breiman et al., 1984). These heuristics recursively an”
Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy (2019, background): “They are trees that start at a root node and branch based on conditions [Quinlan, 1986].”
Interval Coded Scoring: a toolbox for interpretable scoring systems (2018, methodology): “Well-known approaches include Support Vector Machines (SVM) (Vapnik, 1995), Naive Bayes (NB) classiﬁers (Lewis, 1998), decision trees (DT) (Quinlan, 1986), random forests (RF) (Ho, 1995) and neural networks (NN) (Bishop, 1995).”
An optimization approach to learning falling rule lists (2017, methodology): “The proposed algorithms are competitors for decision tree methods like CART [5], ID3 [21], C4.5 [22], and C5.”
Falling Rule Lists (2014, methodology): “The vast majority of other methods that discretize the input space are also greedy, such as decision tree (Quinlan, 1986, 1993) and decision list methods (Rivest, 1987; Fawcett, 2008).”
Efficient Non-greedy Optimization of Decision Trees (2015, background): “They grow a tree one node at a time following procedures laid out decades ago by frameworks such as ID3 [22] and CART [6].”