This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation
This work addresses the challenge of improving interpretability and reducing artifacts in self-explaining models for users needing transparent AI decisions, though it is incremental as it builds on existing methods like ProtoPNet.
The authors tackled the problem of coarse and spatially imprecise explanations in self-explaining models like ProtoPNet by introducing Prototypical Relevance Propagation (PRP), which generates more precise model-aware explanations and uses multi-view clustering to suppress artifact learning.
Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the understanding and traceability of the underlying decision-making strategies. As a remedy, many post-hoc explanation and self-explanatory methods have been developed to interpret the models' behavior. These methods, in addition, enable the identification of artifacts that can be learned by the model as class-relevant features. In this work, we provide a detailed case study of the self-explaining network, ProtoPNet, in the presence of a spectrum of artifacts. Accordingly, we identify the main drawbacks of ProtoPNet, especially, its coarse and spatially imprecise explanations. We address these limitations by introducing Prototypical Relevance Propagation (PRP), a novel method for generating more precise model-aware explanations. Furthermore, in order to obtain a clean dataset, we propose to use multi-view clustering strategies for segregating the artifact images using the PRP explanations, thereby suppressing the potential artifact learning in the models.