Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and ({even more importantly}) explainable predictions. Existing approaches typically explicate network outputs in a post-hoc fashion, under an implicit assumption that faithful explanations come from accurate predictions/classifications. We have an opposite claim that explanations boost (or even determine) classification. That is, end-to-end learning of explanation factors to augment discriminative representation extraction could be a more intuitive strategy to inversely assure fine-grained explainability, e.g., in those neuroimaging and neuroscience studies with high-dimensional data containing noisy, redundant, and task-irrelevant information. In this paper, we propose such an explainable geometric deep network dubbed as NeuroExplainer, with applications to uncover altered infant cortical development patterns associated with preterm birth. Given fundamental cortical attributes as network input, our NeuroExplainer adopts a hierarchical attention-decoding framework to learn fine-grained attentions and respective discriminative representations to accurately recognize preterm infants from term-born infants at term-equivalent age. NeuroExplainer learns the hierarchical attention-decoding modules under subject-level weak supervision coupled with targeted regularizers deduced from domain knowledge regarding brain development. These prior-guided constraints implicitly maximizes the explainability metrics (i.e., fidelity, sparsity, and stability) in network training, driving the learned network to output detailed explanations and accurate classifications. Experimental results on the public dHCP benchmark suggest that NeuroExplainer led to quantitatively reliable explanation results that are qualitatively consistent with representative neuroimaging studies.

翻译：在跨学科应用中部署可靠的深度学习技术，需要所学模型既能输出准确的预测结果，又（更重要的是）具备可解释性。现有方法通常以事后方式解释网络输出，隐含假设忠实解释源于准确预测/分类。我们提出相反观点：解释能提升（甚至决定）分类性能。即端到端学习解释因子以增强判别性表征提取，可能是一种更直观的策略来反向保证细粒度可解释性——例如在那些包含噪声、冗余和任务无关信息的高维数据的神经影像学和神经科学研究中。本文提出名为NeuroExplainer的可解释几何深度网络，应用于揭示与早产相关的婴儿皮层发育模式改变。以基本皮层属性作为网络输入，NeuroExplainer采用层级注意力解码框架学习细粒度注意力及其对应的判别性表征，从而在足月等效年龄准确识别早产儿与足月儿。在受试者级弱监督条件下，NeuroExplainer结合从脑发育领域知识推导的定向正则化项来学习层级注意力解码模块。这些先验引导的约束隐式最大化网络训练中的可解释性指标（即保真度、稀疏性和稳定性），驱动所学网络输出详细解释与准确分类。在公开dHCP基准上的实验结果表明，NeuroExplainer产生了定量可靠的解释结果，且这些结果在定性上与代表性神经影像学研究一致。