论文标题
正确的概念的权利：通过与其解释互动来修改神经符号概念
Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations
论文作者
论文摘要
深度学习图中的大多数解释方法对模型的预测的重要性估计值估计回到原始输入空间。这些“视觉”解释通常不足，因为该模型的实际概念仍然难以捉摸。此外，如果没有对模型的语义概念的见解，很难（即使不是不可能）通过其解释来干预模型的行为，称为解释性互动学习。因此，我们建议干预神经符号的场景表示，该表征可以在语义层面上修改模型，例如“永远不要专注于做出决定的颜色”。我们编制了一个新颖的混杂视觉场景数据集，CLEVR-HANS数据集，捕获了不同对象的复杂组成。我们对CLEVR-HANS的实验的结果表明，我们的语义解释，即每个对象级别的组成解释，可以识别仅使用“视觉”解释的混杂因素。更重要的是，对这种语义水平的反馈使得可以从关注这些因素上修改模型。
Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space. These "visual" explanations are often insufficient, as the model's actual concept remains elusive. Moreover, without insights into the model's semantic concept, it is difficult -- if not impossible -- to intervene on the model's behavior via its explanations, called Explanatory Interactive Learning. Consequently, we propose to intervene on a Neuro-Symbolic scene representation, which allows one to revise the model on the semantic level, e.g. "never focus on the color to make your decision". We compiled a novel confounded visual scene data set, the CLEVR-Hans data set, capturing complex compositions of different objects. The results of our experiments on CLEVR-Hans demonstrate that our semantic explanations, i.e. compositional explanations at a per-object level, can identify confounders that are not identifiable using "visual" explanations only. More importantly, feedback on this semantic level makes it possible to revise the model from focusing on these factors.
