Comprehensive Evaluation of Prototype Neural Networks
This work provides a systematic assessment tool for researchers in explainable AI, though it is incremental as it focuses on evaluating existing methods rather than introducing new ones.
The paper conducted a comprehensive evaluation of prototype neural networks, including ProtoPNet, ProtoPool, and PIPNet, using both standard and newly proposed metrics across diverse datasets, and released an open-source library for easy application and extensibility.
Prototype models are an important method for explainable artificial intelligence (XAI) and interpretable machine learning. In this paper, we perform an in-depth analysis of a set of prominent prototype models including ProtoPNet, ProtoPool and PIPNet. For their assessment, we apply a comprehensive set of metrics. In addition to applying standard metrics from literature, we propose several new metrics to further complement the analysis of model interpretability. In our experimentation, we apply the set of prototype models on a diverse set of datasets including fine-grained classification, Non-IID settings and multi-label classification to further contrast the performance. Furthermore, we also provide our code as an open-source library (https://github.com/uos-sis/quanproto), which facilitates simple application of the metrics itself, as well as extensibility -- providing the option for easily adding new metrics and models.