U-CECE: A Universal Multi-Resolution Framework for Conceptual Counterfactual Explanations
This addresses the explainability problem for AI practitioners and users by offering a scalable solution to a known bottleneck in counterfactual methods, though it is incremental in improving existing approaches.
The paper tackles the trade-off between expressivity and efficiency in concept-based counterfactual explanations for AI models by proposing U-CECE, a universal multi-resolution framework that adapts to data and compute constraints, achieving semantic equivalence to ground-truth explanations with human preference in evaluations.
As AI models grow more 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 more 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. U-CECE spans three levels of expressivity: atomic concepts for broad explanations, relational sets-of-sets for simple interactions, and structural graphs for full semantic structure. At the structural level, both a precision-oriented transductive mode based on supervised Graph Neural Networks (GNNs) and a scalable inductive mode based on unsupervised graph autoencoders (GAEs) are supported. Experiments on the structurally divergent CUB and Visual Genome datasets characterize the efficiency-expressivity trade-off across levels, while human surveys and LVLM-based evaluation show that the retrieved structural counterfactuals are semantically equivalent to, and often preferred over, exact GED-based ground-truth explanations.