Optimizing Post-hoc Explainability Algorithm for Finding Faithful and Understandable Explanations for a Combination of Model, Task and Data

Tamajka, M., Vesely, M., Simko, M.

In this work, we address the problem of explaining a specific prediction of a model. First, we propose a method for finding a configuration of a post-hoc explainability algorithm, Layer-wise relevance propagation (LRP), that provides understandable and faithful explanations for a particular model, task, and data. The method is based on modified Particle Swarm Optimization. We propose a novel fitness function, which in combination with a fidelity measure Area over perturbation curve (AOPC) is used to focus the relevance assigned by the LRP algorithm to expected regions. This makes the explanations both faithful and understandable for humans. Second, we generalize the proposed method to an arbitrary set of post-hoc explainability algorithms. We evaluated the proposed method on two image classification tasks (magnetic resonance imaging datasets BraTS and ADNI) and one text sentiment classification task (dataset SST). Our method outperformed benchmark LRP configurations in all three tasks, which suggests its extensibility to different architectures, datasets and tasks.

Cite: Tamajka, M., Veselý, M., Šimko, M. Optimizing Post-hoc Explainability Algorithm for Finding Faithful and Understandable Explanations for a Combination of Model, Task and Data. Proceedings of Workshop on explainable artificial intelligence XAI at IJCAI2022, pages 103-110. International Joint Conferences on Artificial Intelligence Organization (2022).