AI RESEARCH
U-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanations
arXiv CS.CV
•
ArXi:2604.08295v1 Announce Type: cross As AI models grow complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off between expressivity and efficiency. Representing underlying concepts as atomic sets is fast but misses relational context, whereas full graph representations are faithful but require solving the NP-hard Graph Edit Distance (GED) problem. We propose U-CECE, a unified, model-agnostic multi-resolution framework for conceptual counterfactual explanations that adapts to data regime and compute budget.