Shapley Based Residual Decomposition for Instance Analysis
This addresses the need for instance-level explainability in AI, particularly for regression tasks, though it appears incremental as it adapts residual decomposition from features to instances.
The paper tackles the problem of analyzing individual data instances' effects on regression models by decomposing residuals per instance, enabling model-agnostic identification of interesting instances and assessing model and data appropriateness.
In this paper, we introduce the idea of decomposing the residuals of regression with respect to the data instances instead of features. This allows us to determine the effects of each individual instance on the model and each other, and in doing so makes for a model-agnostic method of identifying instances of interest. In doing so, we can also determine the appropriateness of the model and data in the wider context of a given study. The paper focuses on the possible applications that such a framework brings to the relatively unexplored field of instance analysis in the context of Explainable AI tasks.