Data-centric Prediction Explanation via Kernelized Stein Discrepancy

arXiv:2403.15576v1 Announce Type: new
Abstract: Existing example-based prediction explanation methods often bridge test and training data points through the model's parameters or latent representations. While these methods offer clues to the causes of model predictions, they often exhibit innate shortcomings, such as incurring significant computational overhead or producing coarse-grained explanations. This paper presents a Highly-precise and Data-centric Explanation (HD-Explain), a straightforward prediction explanation method exploiting properties of Kernelized Stein Discrepancy (KSD). Specifically, the KSD uniquely defines a parameterized kernel function …

abstract arxiv bridge computational cs.lg data data-centric example paper parameters prediction predictions test through training training data type via