Interpretable Concept-Based Classification with Shapley Values

Ignatov, Dmitry I.; Kwuida, Léonard

doi:10.1007/978-3-030-57855-8_7

Cited by 7 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the simplest case, as explained in [57], the function value v is binary, 1 for winning coalitions, and 0, otherwise. If the coalition S [ {a} is winning (e.g., if x is classified correctly), while S is not, the attribute a receives a non-zero importance value.…”

Section: Determine the Importance Of Featurementioning

confidence: 99%

Identifying dyslexia in school pupils from eye movement and demographic data using artificial intelligence

Shalileh,

Ignatov,

Lopukhina

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

This paper represents our research results in the pursuit of the following objectives: (i) to introduce a novel multi-sources data set to tackle the shortcomings of the previous data sets, (ii) to propose a robust artificial intelligence-based solution to identify dyslexia in primary school pupils, (iii) to investigate our psycholinguistic knowledge by studying the importance of the features in identifying dyslexia by our best AI model. In order to achieve the first objective, we collected and annotated a new set of eye-movement-during-reading data. Furthermore, we collected demographic data, including the measure of non-verbal intelligence, to form our three data sources. Our data set is the largest eye-movement data set globally. Unlike the previously introduced binary-class data sets, it contains (A) three class labels and (B) reading speed. Concerning the second objective, we formulated the task of dyslexia prediction as regression and classification problems and scrutinized the performance of 12 classifications and eight regressions approaches. We exploited the Bayesian optimization method to fine-tune the hyperparameters of the models: and reported the average and the standard deviation of our evaluation metrics in a stratified ten-fold cross-validation. Our studies showed that multi-layer perceptron, random forest, gradient boosting, and k-nearest neighbor form the group having the most acceptable results. Moreover, we showed that although separately using each data source did not lead to accurate results, their combination led to a reliable solution. We also determined the importance of the features of our best classifier: our findings showed that the IQ, gender, and age are the top three important features; we also showed that fixation along the y-axis is more important than other fixation data. Dyslexia detection, eye fixation, eye movement, demographic, classification, regression, artificial intelligence.

show abstract

Section: Determine the Importance Of Featurementioning

confidence: 99%

Identifying dyslexia in school pupils from eye movement and demographic data using artificial intelligence

Shalileh,

Ignatov,

Lopukhina

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…In this section, we discuss how interpretable concept-based learning for JSMmethod can be achieved with Shapley Values following our previous study on the problem [20]. Let us start with a piece of history of inductive reasoning.…”

Section: Supervised Learning: From Hypotheses To Attribute Importancementioning

confidence: 99%

“…For the Zoo dataset we obtain 357 concepts in total. The top-3 most stable are c 1 , c 2 , c 3 with extent stability indices: σ e (G, ∅) = 1, σ e (∅, M) = 0.997, σ e (A, A ) = 0.625, respectively, where A = {f eathers, eggs, backbone, breathes, legs 2 , tail} and A = {11, 16,20,21,23,33,37,41,43,56,57,58,59, 71, 78, 79, 83, 87, 95, 100}. The most important attributes are six legs, eight legs, five legs, feathers, and four legs for c 2 (Fig.…”

Section: Theorem 2 ([21]mentioning

confidence: 99%

On Interpretability and Similarity in Concept-Based Machine Learning

Kwuida

Ignatov

2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Machine Learning (ML) provides important techniques for classification and predictions. Most of these are black-box models for users and do not provide decision-makers with an explanation. For the sake of transparency or more validity of decisions, the need to develop explainable/interpretable ML-methods is gaining more and more importance. Certain questions need to be addressed:-How does an ML procedure derive the class for a particular entity? -Why does a particular clustering emerge from a particular unsupervised ML procedure? -What can we do if the number of attributes is very large? -What are the possible reasons for the mistakes for concrete cases and models? For binary attributes, Formal Concept Analysis (FCA) offers techniques in terms of intents of formal concepts, and thus provides plausible reasons for model prediction. However, from the interpretable machine learning viewpoint, we still need to provide decision-makers with the importance of individual attributes to the classification of a particular object, which may facilitate explanations by experts in various domains with high-cost errors like medicine or finance.We discuss how notions from cooperative game theory can be used to assess the contribution of individual attributes in classification and clustering processes in concept-based machine learning. To address the 3rd question, we present some ideas on how to reduce the number of attributes using similarities in large contexts.

show abstract

“…Theorem 1 ( [20]). The Shapley value, ϕ m (g), of an attribute m for the JSMclassification of an object g, fulfils the following properties:…”

Section: Shapley Values and Jsm-hypothesesmentioning

confidence: 99%

On Interpretability and Similarity in Concept-Based Machine Learning

Kwuida¹,

Ignatov²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Machine Learning (ML) provides important techniques for classification and predictions. Most of these are black-box models for users and do not provide decision-makers with an explanation. For the sake of transparency or more validity of decisions, the need to develop explainable/interpretable ML-methods is gaining more and more importance. Certain questions need to be addressed:-How does an ML procedure derive the class for a particular entity? -Why does a particular clustering emerge from a particular unsupervised ML procedure? -What can we do if the number of attributes is very large? -What are the possible reasons for the mistakes for concrete cases and models? For binary attributes, Formal Concept Analysis (FCA) offers techniques in terms of intents of formal concepts, and thus provides plausible reasons for model prediction. However, from the interpretable machine learning viewpoint, we still need to provide decision-makers with the importance of individual attributes to the classification of a particular object, which may facilitate explanations by experts in various domains with high-cost errors like medicine or finance. We discuss how notions from cooperative game theory can be used to assess the contribution of individual attributes in classification and clustering processes in concept-based machine learning. To address the 3rd question, we present some ideas on how to reduce the number of attributes using similarities in large contexts.

show abstract

Interpretable Concept-Based Classification with Shapley Values

Cited by 7 publications

References 17 publications

Identifying dyslexia in school pupils from eye movement and demographic data using artificial intelligence

Identifying dyslexia in school pupils from eye movement and demographic data using artificial intelligence

On Interpretability and Similarity in Concept-Based Machine Learning

On Interpretability and Similarity in Concept-Based Machine Learning

Contact Info

Product

Resources

About