On Explaining Decision Trees

Izza, Yacine; Ignatiev, Alexey; Marques-Silva, Joao

doi:10.48550/arxiv.2010.11034

Cited by 14 publications

(14 citation statements)

References 45 publications

(74 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A commonly criticised point, however, is that the resulting trees may not be the best representation of the data in terms of accuracy and size. [19,20] show that in some settings decision trees can hardly be deemed interpretable, with paths being arbitrarily larger than a minimal set of features that entails the prediction (i.e., a so-called PI-explanation). This motivated the development of optimal classification tree algorithms that globally optimise the decision tree in contrast to heuristic methods that perform a sequence of locally optimal decisions.…”

Section: Other Related Workmentioning

confidence: 99%

A Nested Genetic Algorithm for Explaining Classification Data Sets with Decision Rules

Matt¹,

Ziegler²,

Danilo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Our goal in this paper is to automatically extract a set of decision rules (rule set) that best explains a classification data set. First, a large set of decision rules is extracted from a set of decision trees trained on the data set. The rule set should be concise, accurate, have a maximum coverage and minimum number of inconsistencies. This problem can be formalized as a modified version of the weighted budgeted maximum coverage problem, known to be NP-hard. To solve the combinatorial optimization problem efficiently, we introduce a nested genetic algorithm which we then use to derive explanations for ten public data sets.

show abstract

Section: Other Related Workmentioning

confidence: 99%

A Nested Genetic Algorithm for Explaining Classification Data Sets with Decision Rules

Matt¹,

Ziegler²,

Danilo³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For linear models, promoting interpretability essentially corresponds to reducing the number of features [43,53,54,63]. For decision trees and decision rules, besides reducing the number of features, approaches exist to restrict model size, prune unnecessary parts [5,26], aggregate local models in a hierarchy [48], or promote a trade-off between accuracy and complexity by means of loss functions [30,52] or prior distributions [33,60,61]. Regarding GP (and close relatives like grammatical evolution), perhaps the most simple and popular strategy to favor interpretability is to restrain the number of model components [16,31,57], sometimes in elaborate ways or particular settings [6,32,40,49,56].…”

Section: Related Workmentioning

confidence: 99%

Model Learning with Personalized Interpretability Estimation (ML-PIE)

Virgolin¹,

Lorenzo²,

Randone³

et al. 2021

Preprint

View full text Add to dashboard Cite

Figure 1: Schematic view of the proposed approach, ML-PIE. In the implementation proposed in this paper, the user provides feedback on models that are being discovered by an evolutionary algorithm. This feedback is used to train an estimator which, in turn, shapes one of the objective functions used by the evolution. Ultimately, this steers the evolution towards discovering models that are interpretable according to the specific user. To minimize the amount of feedback needed, ML-PIE keeps track of which models cause the estimator to be most uncertain, and submits these models for user assessment.

show abstract

“…Additionally, it should be noted that when forming these local explanations, only the function in the leaf node is taken into consideration, even though the path from the root node to this leaf node is not irrelevant and most likely should be considered. However, including the paths in (both local and global) explanations should not be done carelessly since even irreducible DTs can have irrelevant splits [36].…”

Section: Extracting Feature Attributions From the Leaf Nodesmentioning

confidence: 99%

Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization

Gjærum

Strümke

Alsos

et al. 2021

JMSE

View full text Add to dashboard Cite

Deep neural networks (DNNs) can be useful within the marine robotics field, but their utility value is restricted by their black-box nature. Explainable artificial intelligence methods attempt to understand how such black-boxes make their decisions. In this work, linear model trees (LMTs) are used to approximate the DNN controlling an autonomous surface vessel (ASV) in a simulated environment and then run in parallel with the DNN to give explanations in the form of feature attributions in real-time. How well a model can be understood depends not only on the explanation itself, but also on how well it is presented and adapted to the receiver of said explanation. Different end-users may need both different types of explanations, as well as different representations of these. The main contributions of this work are (1) significantly improving both the accuracy and the build time of a greedy approach for building LMTs by introducing ordering of features in the splitting of the tree, (2) giving an overview of the characteristics of the seafarer/operator and the developer as two different end-users of the agent and receiver of the explanations, and (3) suggesting a visualization of the docking agent, the environment, and the feature attributions given by the LMT for when the developer is the end-user of the system, and another visualization for when the seafarer or operator is the end-user, based on their different characteristics.

show abstract

On Explaining Decision Trees

Cited by 14 publications

References 45 publications

A Nested Genetic Algorithm for Explaining Classification Data Sets with Decision Rules

A Nested Genetic Algorithm for Explaining Classification Data Sets with Decision Rules

Model Learning with Personalized Interpretability Estimation (ML-PIE)

Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization

Contact Info

Product

Resources

About