Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks

2024/10/24 by Alba Carballo-Castro, Sonia Laguna, Carballo-Castro, Alba +5 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.2410.18705

openalex publication_date 2024/10/24 · openalex created_date 2024/11/15 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection

Related

• Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models
• Restyling Unsupervised Concept Based Interpretable Networks with Generative Models
• ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction
• Concept-Based Explainable Artificial Intelligence: Metrics and Benchmarks
• Concept Bottleneck Model with Additional Unsupervised Concepts