Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks
This work addresses the problem of making neural networks more interpretable for researchers and practitioners, but it appears incremental as it builds on existing concept-based methods.
The paper tackles the challenge of limited concept annotations in interpretable machine learning by proposing concept-enriched models, specifically Concept-Guided Conditional Diffusion for generating visual concept representations and Concept-Guided Prototype Networks for interpretable concept prediction.
Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are generally challenging to obtain, making it crucial to leverage all their prior knowledge. By creating concept-enriched models that incorporate concept information into existing architectures, we exploit their interpretable capabilities to the fullest extent. In particular, we propose Concept-Guided Conditional Diffusion, which can generate visual representations of concepts, and Concept-Guided Prototype Networks, which can create a concept prototype dataset and leverage it to perform interpretable concept prediction. These results open up new lines of research by exploiting pre-existing information in the quest for rendering machine learning more human-understandable.