On Model Explanations with Transferable Neural Pathways
This work addresses the problem of improving interpretability in model explanations for researchers and practitioners, though it appears incremental as it builds on existing neural pathway methods.
The paper tackles the limited interpretability of existing neural pathway explanations by proposing two criteria for class-relevance and instance-specific sparsity, resulting in a GEN-CNP model that generates transferable pathways with demonstrated faithfulness and interpretability in experiments.
Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model. Existing methods primarily focus on accuracy and sparsity but the generated pathways may offer limited interpretability thus fall short in explaining the model behavior. In this paper, we suggest two interpretability criteria of neural pathways: (i) same-class neural pathways should primarily consist of class-relevant neurons; (ii) each instance's neural pathway sparsity should be optimally determined. To this end, we propose a Generative Class-relevant Neural Pathway (GEN-CNP) model that learns to predict the neural pathways from the target model's feature maps. We propose to learn class-relevant information from features of deep and shallow layers such that same-class neural pathways exhibit high similarity. We further impose a faithfulness criterion for GEN-CNP to generate pathways with instance-specific sparsity. We propose to transfer the class-relevant neural pathways to explain samples of the same class and show experimentally and qualitatively their faithfulness and interpretability.