Beyond Output Faithfulness: Learning Attributions that Preserve Computational Pathways

Faithfulness metrics such as insertion and deletion evaluate how feature removal affects model outputs but overlook whether explanations preserve the computational pathway the network actually uses. We show that external metrics can be maximized through alternative pathways -- perturbations that reroute computation via different feature detectors while preserving output behavior. To address this, we propose activation preservation as a tractable proxy for preserving computational pathways We introduce Faithfulness-guided Ensemble Interpretation (FEI), which jointly optimizes external faithfulness (via ensemble quantile optimization of insertion/deletion curves) and internal faithfulness (via selective gradient clipping). Across VGG and ResNet on ImageNet and CUB-200-2011, FEI achieves state-of-the-art insertion/deletion scores while maintaining significantly lower activation deviation, showing that both external and internal faithfulness are essential for reliable explanations.