Local Feature Selection without Label or Feature Leakage for Interpretable Machine Learning Predictions
This addresses the issue of unreliable explanations in interpretable ML for users needing trustworthy model insights, though it is incremental by building on existing local feature selection methods.
The paper tackled the problem of misleading local feature selections in interpretable machine learning by formalizing label and feature leakage, and proposed SUWR, the first method proven to have no leakage, which achieved state-of-the-art predictive performance with high sparsity.
Local feature selection in machine learning provides instance-specific explanations by focusing on the most relevant features for each prediction, enhancing the interpretability of complex models. However, such methods tend to produce misleading explanations by encoding additional information in their selections. In this work, we attribute the problem of misleading selections by formalizing the concepts of label and feature leakage. We rigorously derive the necessary and sufficient conditions under which we can guarantee no leakage, and show existing methods do not meet these conditions. Furthermore, we propose the first local feature selection method that is proven to have no leakage called SUWR. Our experimental results indicate that SUWR is less prone to overfitting and combines state-of-the-art predictive performance with high feature-selection sparsity. Our generic and easily extendable formal approach provides a strong theoretical basis for future work on interpretability with reliable explanations.