Explainability in AI is crucial for model development, compliance with
regulation, and providing operational nuance to predictions. The Shapley
framework for explainability attributes a model's predictions to its input
features in a mathematically principled and model-agnostic way. However,
general implementations of Shapley explainability make an untenable assumption:
that the model's features are uncorrelated. In this work, we demonstrate
unambiguous drawbacks of this assumption and develop two solutions to Shapley
explainability that respect the data manifold. One solution, based on
generative modelling, provides flexible access to data imputations; the other
directly learns the Shapley value-function, providing performance and stability
at the cost of flexibility. While "off-manifold" Shapley values can (i) give
rise to incorrect explanations, (ii) hide implicit model dependence on
sensitive attributes, and (iii) lead to unintelligible explanations in
higher-dimensional data, on-manifold explainability overcomes these problems.

本研究旨在介绍 Shapley 可解释性的一个数学根据和模型独立的框架，但是通常的 Shapley 可解释性实现做了一个不切实际的假设，即模型的特征是不相关的，而作者这里提出了两种策略去解决这个问题，基于生成建模的方法提供灵活的数据归因，另一种直接学习了 Shapley 价值函数，提供了性能和稳定性，但缺陷是没有灵活性，通过我们的研究表明该假设会导致展示效果错误，隐藏敏感性属性的隐含模型依赖性和意义不明的高维数据。

数据流形上的 Shapley 可解释性

Shapley explainability on the data manifold

Explaining AI systems is fundamental both to the development of high
performing models and to the trust placed in them by their users. The Shapley
framework for explainability has strength in its general applicability combined
with its precise, rigorous foundation: it provides a common, model-agnostic
language for AI explainability and uniquely satisfies a set of intuitive
mathematical axioms. However, Shapley values are too restrictive in one
significant regard: they ignore all causal structure in the data. We introduce
a less restrictive framework, Asymmetric Shapley values (ASVs), which are
rigorously founded on a set of axioms, applicable to any AI system, and
flexible enough to incorporate any causal structure known to be respected by
the data. We demonstrate that ASVs can (i) improve model explanations by
incorporating causal information, (ii) provide an unambiguous test for unfair
discrimination in model predictions, (iii) enable sequentially incremental
explanations in time-series models, and (iv) support feature-selection studies
without the need for model retraining.

通过介绍 Asymmetric Shapley values (ASVs) 这种较少限制的框架，本文提出了这种框架可以改善模型解释、为模型预测中的不公平歧视提供测试、在时序模型中支持逐步增量解释以及支持特征选择研究而无需进行模型重新训练。