基于概念的可解释人工智能的统一框架及其完备性保证
A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees
AI总结：
本文提出统一理论框架，用共同数学语言描述基于概念的可解释AI方法，通过概念自编码器视图界定概念不完备性，并给出归因完备性保证。
AI中文摘要：
基于概念的解释通过输入的人类可理解属性（称为概念）来描述神经网络预测。该领域包含的方法在如何定义和表示概念以及如何将概念与模型预测联系起来方面各不相同。我们引入了一个理论框架，该框架以共同的数学语言描述这些方法，并支持对其属性进行共同分析。对于概念发现（即在训练好的模型的潜在空间内自动识别概念），我们采用概念自编码器视图。编码器从模型的潜在空间中提取概念表示，解码器使用这些表示来重建原始潜在表示。自编码器的重建误差衡量其解码器恢复原始潜在表示的准确程度。我们重新审视模型完备性：概念能在多大程度上重现模型的输出。我们证明，概念的不完备性可以通过自编码器的重建误差来界定。自编码器视图还提供了一种共同的方式来定义单个概念归因，该归因衡量每个概念对预测的贡献。我们确定了这些归因何时总和等于模型的预测，并在其他情况下界定差异，从而提供归因完备性保证。
英文摘要：
Concept-based explanations describe neural network predictions through human-understandable properties of inputs called concepts. The field encompasses approaches that differ in how they define and represent concepts and connect them to model predictions. We introduce a theoretical framework that describes these approaches in a common mathematical language and supports a shared analysis of their properties. For concept discovery, which identifies concepts automatically within a latent space of a trained model, we employ a concept autoencoder view. An encoder extracts concept representations from the model's latent space, and a decoder uses them to reconstruct the original latent representation. The autoencoder's reconstruction error measures how accurately its decoder recovers the original latent representation. We revisit model completeness: how well the concepts can reproduce the model's outputs. We show that model incompleteness of the concepts can be bounded by the autoencoder's reconstruction error. The autoencoder view also provides a common way to define individual concept attributions, which measure each concept's contribution to a prediction. We establish when these attributions sum to the model's prediction, and bound the discrepancy otherwise, thus providing attribution completeness guarantees.
