Exploring Local Explanations of Nonlinear Models Using Animated Linear Projections
This work addresses interpretability challenges in machine learning for researchers and practitioners using XAI methods, but it is incremental as it builds on existing local explanation techniques.
The paper tackles the problem of understanding how interactions between predictors affect local variable importance estimates in nonlinear models by converting them into linear projections and using radial tours, illustrated with examples from categorical and quantitative response models.
The increased predictive power of machine learning models comes at the cost of increased complexity and loss of interpretability, particularly in comparison to parametric statistical models. This trade-off has led to the emergence of eXplainable AI (XAI) which provides methods, such as local explanations (LEs) and local variable attributions (LVAs), to shed light on how a model use predictors to arrive at a prediction. These provide a point estimate of the linear variable importance in the vicinity of a single observation. However, LVAs tend not to effectively handle association between predictors. To understand how the interaction between predictors affects the variable importance estimate, we can convert LVAs into linear projections and use the radial tour. This is also useful for learning how a model has made a mistake, or the effect of outliers, or the clustering of observations. The approach is illustrated with examples from categorical (penguin species, chocolate types) and quantitative (soccer/football salaries, house prices) response models. The methods are implemented in the R package cheem, available on CRAN.