Explainable AI (XAI) is slowly becoming a key component for many AI applications. Rule-based and modified backpropagation XAI approaches however often face challenges when being applied to modern model architectures including innovative layer building blocks, which is caused by two reasons. Firstly, the high flexibility of rule-based XAI methods leads to numerous potential parameterizations. Secondly, many XAI methods break the implementation-invariance axiom because they struggle with certain model components, e.g., BatchNorm layers. The latter can be addressed with model canonization, which is the process of re-structuring the model to disregard problematic components without changing the underlying function. While model canonization is straightforward for simple architectures (e.g., VGG, ResNet), it can be challenging for more complex and highly interconnected models (e.g., DenseNet). Moreover, there is only little quantifiable evidence that model canonization is beneficial for XAI. In this work, we propose canonizations for currently relevant model blocks applicable to popular deep neural network architectures,including VGG, ResNet, EfficientNet, DenseNets, as well as Relation Networks. We further suggest a XAI evaluation framework with which we quantify and compare the effect sof model canonization for various XAI methods in image classification tasks on the Pascal-VOC and ILSVRC2017 datasets, as well as for Visual Question Answering using CLEVR-XAI. Moreover, addressing the former issue outlined above, we demonstrate how our evaluation framework can be applied to perform hyperparameter search for XAI methods to optimize the quality of explanations.
翻译:可以解释的AI (XAI) 正在慢慢地成为许多AI 应用程序的关键组成部分。 基于规则的和经过修改的反向调整的 XAI 方法在应用现代模型结构时往往面临挑战,包括创新的层构件,这是由两个原因造成的。首先,基于规则的XAI 方法的高度灵活性导致许多潜在的参数化。第二,许多 XAI 方法打破了执行偏差轴,因为它们与某些模型组件,如批量记录系统(BatchNorm 级)相争。后者可以用模型化处理。后者可以用模型化处理,这是在不改变基本功能的情况下重新构建模型以忽略有问题的组件的过程。虽然模型化对于简单的结构(例如VGG、ResNet)来说是直截了当的。但对于更复杂和高度相互关联的模型(例如DenseNet)来说,它可能具有挑战性。此外,许多可量化的证据都表明模型可帮助 XAAI 发行。我们建议当前与直线网络结构相关的自定义值结构,包括VGIG、ResNet、高效的Net、DenseNet、Deral eNet (deNet) 能够用前数据分类框架来显示我们的数据分析方法来进一步量化。