Contreras Jhonatan, Winterfeld Andreea, Popp Juergen, Bocklitz Thomas
Institute of Physical Chemistry (IPC) and Abbe Center of Photonics (ACP), Member of the Leibniz Centre for Photonics in Infection Research (LPI), Friedrich Schiller University Jena, Helmholtzweg 4, 07743 Jena, Germany.
Leibniz Institute of Photonic Technology, Member of the Leibniz Centre for Photonics in Infection Research (LPI), Member of Leibniz Health Technologies, Albert Einstein Straße 9, 07745 Jena, Germany.
Anal Chem. 2024 Oct 1;96(39):15588-15597. doi: 10.1021/acs.analchem.4c02329. Epub 2024 Sep 17.
Interpretability is just as important as accuracy when it comes to complex models, especially in the context of deep learning models. Explainable artificial intelligence (XAI) approaches have been developed to address this problem. The literature on XAI for spectroscopy mainly emphasizes independent feature analysis with limited application of zone analysis. Individual feature analysis methods, such as shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME), have limitations due to their dependence on perturbations. These methods measure how AI models respond to sudden changes in the individual feature values. While they can help identify the most impactful features, the abrupt shifts introduced by replacing these values with zero or the expected ones may not accurately represent real-world scenarios. This can lead to mathematical and computational interpretations that are neither physically realistic nor intuitive to humans. Our proposed method does not rely on individual disturbances. Instead, it targets "spectral zones" to directly estimate the effect of group disturbances on a trained model. Consequently, factors such as sample size, hyperparameter selection, and other training-related considerations are not the primary focus of the XAI methods. To achieve this, we have developed a modified version of LIME and SHAP capable of performing group perturbations, enhancing explainability and realism while minimizing noise in the plots used for interpretability. Additionally, we employed an efficient approach to calculate spectral zones for complex spectra with indistinct spectral boundaries. Users can also define the zones themselves using their domain-specific knowledge.
对于复杂模型而言，可解释性与准确性同样重要，尤其是在深度学习模型的背景下。为了解决这一问题，人们开发了可解释人工智能（XAI）方法。关于光谱学的XAI文献主要强调独立特征分析，而区域分析的应用有限。诸如夏普利值加法解释（SHAP）和局部可解释模型无关解释（LIME）等个体特征分析方法存在局限性，因为它们依赖于扰动。这些方法衡量人工智能模型如何响应个体特征值的突然变化。虽然它们有助于识别最具影响力的特征，但用零或预期值替换这些值所引入的突然变化可能无法准确代表现实世界的情况。这可能导致数学和计算解释既不符合物理现实，对人类来说也不直观。我们提出的方法不依赖于个体扰动。相反，它针对“光谱区域”直接估计群体扰动对训练模型的影响。因此，样本大小、超参数选择和其他与训练相关的考虑因素并非XAI方法的主要关注点。为了实现这一点，我们开发了LIME和SHAP的改进版本，能够进行群体扰动，在提高可解释性和现实性的同时，尽量减少用于可解释性的图中的噪声。此外，我们采用了一种有效的方法来计算光谱边界不清晰的复杂光谱的光谱区域。用户也可以利用其特定领域的知识自行定义区域。
