Concept Tree: High-Level Representation of Variables for More Interpretable Surrogate Decision Trees

Renard, Xavier; Woloszko, Nicolas; Aigrain, Jonathan; Detyniecki, Marcin

doi:10.48550/arxiv.1906.01297

Cited by 2 publications

(4 citation statements)

References 11 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…C4.5 uses interval-based splitting points, and generates shallower but wider trees compared to TREPAN. Concept Tree (Renard et al 2019). Concept tree is a recent extension of TREPAN by Renard et al (2019) that adds automatic grouping of correlated features into the candidate concepts to use for the tree nodes.…”

Section: Object Of Explanationmentioning

confidence: 99%

“…Concept Tree (Renard et al 2019). Concept tree is a recent extension of TREPAN by Renard et al (2019) that adds automatic grouping of correlated features into the candidate concepts to use for the tree nodes.…”

Section: Object Of Explanationmentioning

confidence: 99%

“…Examples The mentioned exemplary rule-extraction methods DeepRED (Zilke et al 2016) and VIA (Thrun 1995), as well as decision tree extractors TREPAN (Craven and Shavlik 1995), Concept Tree (Renard et al 2019), and C4.5 (Quinlan 1993) all provide global, rule-based output. For further rule extraction examples, we refer the reader to the comprehensive surveys Hailesilassie (2016), Wang et al (2018a), Augasta and Kathirvalavakumar (2012) on the topic and the survey by Wang et al (2018b) for recurrent DNNs.…”

Section: Contrastive / Counterfactual / Near Miss Examples Including ...mentioning

confidence: 99%

See 2 more Smart Citations

A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts

Schwalbe

Finzel

2023

Data Min Knowl Disc

View full text Add to dashboard Cite

In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation criteria have been developed within the research field of explainable artificial intelligence (XAI). With the amount of XAI methods vastly growing, a taxonomy of methods is needed by researchers as well as practitioners: To grasp the breadth of the topic, compare methods, and to select the right XAI method based on traits required by a specific use-case context. Many taxonomies for XAI methods of varying level of detail and depth can be found in the literature. While they often have a different focus, they also exhibit many points of overlap. This paper unifies these efforts and provides a complete taxonomy of XAI methods with respect to notions present in the current state of research. In a structured literature analysis and meta-study, we identified and reviewed more than 50 of the most cited and current surveys on XAI methods, metrics, and method traits. After summarizing them in a survey of surveys, we merge terminologies and concepts of the articles into a unified structured taxonomy. Single concepts therein are illustrated by more than 50 diverse selected example methods in total, which we categorize accordingly. The taxonomy may serve both beginners, researchers, and practitioners as a reference and wide-ranging overview of XAI method traits and aspects. Hence, it provides foundations for targeted, use-case-oriented, and context-sensitive future research.

show abstract

Section: Object Of Explanationmentioning

confidence: 99%

Section: Object Of Explanationmentioning

confidence: 99%

Section: Contrastive / Counterfactual / Near Miss Examples Including ...mentioning

confidence: 99%

See 1 more Smart Citation

A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts

Schwalbe

Finzel

2023

Data Min Knowl Disc

View full text Add to dashboard Cite

show abstract

“…Indeed, CA-based explanation methods construct the explanation based on human-defined concepts rather than representing the inputs based on features and internal model (activation) states. Hence, this idea of high-level features might be more familiar to humans, that can be more likely to accept it (Hartmann et al 2022;Renard et al 2019). Formally, given a set of images belonging to a concept [x (1) , x (2) , .…”

Section: Concept Attributionmentioning

confidence: 99%

Benchmarking and survey of explanation methods for black box models

Bodria

Giannotti

Guidotti

et al. 2023

Data Min Knowl Disc

View full text Add to dashboard Cite

The rise of sophisticated black-box machine learning models in Artificial Intelligence systems has prompted the need for explanation methods that reveal how these models work in an understandable way to users and decision makers. Unsurprisingly, the state-of-the-art exhibits currently a plethora of explainers providing many different types of explanations. With the aim of providing a compass for researchers and practitioners, this paper proposes a categorization of explanation methods from the perspective of the type of explanation they return, also considering the different input data formats. The paper accounts for the most representative explainers to date, also discussing similarities and discrepancies of returned explanations through their visual appearance. A companion website to the paper is provided as a continuous update to new explainers as they appear. Moreover, a subset of the most robust and widely adopted explainers, are benchmarked with respect to a repertoire of quantitative metrics.

show abstract

Concept Tree: High-Level Representation of Variables for More Interpretable Surrogate Decision Trees

Cited by 2 publications

References 11 publications

A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts

A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts

Benchmarking and survey of explanation methods for black box models

Contact Info

Product

Resources

About