On Interpretability and Similarity in Concept-Based Machine Learning

TL;DR

This paper explores how to improve interpretability in concept-based machine learning by assessing attribute contributions with game theory and reducing attribute complexity through similarity measures.

Contribution

It introduces the use of cooperative game theory for attribute importance assessment and proposes methods to reduce attributes based on similarity in large datasets.

Findings

Game theory can quantify attribute contributions in classification and clustering.

Attribute reduction techniques help manage high-dimensional data.

Enhanced interpretability aids decision-making in critical domains.

Abstract

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.