Perturbation on Feature Coalition: Towards Interpretable Deep Neural Networks
This work addresses the transparency and reliability issues in deep neural networks for researchers and practitioners in explainable AI, but it appears incremental as it builds on existing perturbation-based methods.
The paper tackles the problem of interpretability in deep neural networks by addressing feature dependencies in perturbation-based methods, introducing a feature coalition approach with a consistency loss, and reports quantitative and qualitative experimental validation.
The inherent "black box" nature of deep neural networks (DNNs) compromises their transparency and reliability. Recently, explainable AI (XAI) has garnered increasing attention from researchers. Several perturbation-based interpretations have emerged. However, these methods often fail to adequately consider feature dependencies. To solve this problem, we introduce a perturbation-based interpretation guided by feature coalitions, which leverages deep information of network to extract correlated features. Then, we proposed a carefully-designed consistency loss to guide network interpretation. Both quantitative and qualitative experiments are conducted to validate the effectiveness of our proposed method. Code is available at github.com/Teriri1999/Perturebation-on-Feature-Coalition.