Decomposition of Global Feature Importance into Direct and Associative Components (DEDACT)
This work addresses the need for clearer causal insights and information leakage detection in feature importance analysis for machine learning practitioners, though it appears incremental as it builds on existing measures.
The authors tackled the problem of distinguishing between direct and associative feature importance in model-agnostic explanations, introducing DEDACT to decompose existing measures into these components, with results demonstrated on simulated examples.
Global model-agnostic feature importance measures either quantify whether features are directly used for a model's predictions (direct importance) or whether they contain prediction-relevant information (associative importance). Direct importance provides causal insight into the model's mechanism, yet it fails to expose the leakage of information from associated but not directly used variables. In contrast, associative importance exposes information leakage but does not provide causal insight into the model's mechanism. We introduce DEDACT - a framework to decompose well-established direct and associative importance measures into their respective associative and direct components. DEDACT provides insight into both the sources of prediction-relevant information in the data and the direct and indirect feature pathways by which the information enters the model. We demonstrate the method's usefulness on simulated examples.