Benchmarking explanation methods for mental state decoding with deep learning models.
Benchmarking explanation methods for mental state decoding with deep learning models.
复制标题
DOI：
10.1016/j.neuroimage.2023.120109
复制
发表时间：
2023-06
期刊：
影响因子：
5.7
通讯作者：
Poldrack, Russell A.
中科院分区：
文献类型：
--
作者：
Thomas, Armin W.;Re, Christopher;Poldrack, Russell A.
深度学习（DL）模型在精神状态解码中的应用越来越多，研究人员试图了解精神状态之间的映射（例如，经历愤怒或喜悦）和大脑活动的关系（即，解码）这些状态。一旦DL模型被训练成准确解码一组心理状态，神经成像研究人员通常会利用可解释人工智能研究的方法来理解模型在心理状态和大脑活动之间的学习映射。在这里，我们基准突出的解释方法在精神状态解码分析的多功能磁共振成像（fMRI）数据集。我们的研究结果表明，在心理状态解码中，解释的两个关键特征之间存在梯度，即其忠实性和与大脑活动和解码心理状态之间映射的其他经验证据的一致性：具有较高解释可信度的解释方法，能够很好地捕捉模型的决策过程，通常提供的解释与其他经验证据的一致性较差，而不是对不太忠实的方法的解释。基于我们的研究结果，我们提供了指导神经影像学研究人员如何选择一种解释方法，以深入了解DL模型的心理状态解码决策。
Deep learning (DL) models find increasing application in mental state decoding, where researchers seek to understand the mapping between mental states (e.g., experiencing anger or joy) and brain activity by identifying those spatial and temporal features of brain activity that allow to accurately identify (i.e., decode) these states. Once a DL model has been trained to accurately decode a set of mental states, neuroimaging researchers often make use of methods from explainable artificial intelligence research to understand the model’s learned mappings between mental states and brain activity. Here, we benchmark prominent explanation methods in a mental state decoding analysis of multiple functional Magnetic Resonance Imaging (fMRI) datasets. Our findings demonstrate a gradient between two key characteristics of an explanation in mental state decoding, namely, its faithfulness and its alignment with other empirical evidence on the mapping between brain activity and decoded mental state: explanation methods with high explanation faithfulness, which capture the model’s decision process well, generally provide explanations that align less well with other empirical evidence than the explanations of methods with less faithfulness. Based on our findings, we provide guidance for neuroimaging researchers on how to choose an explanation method to gain insight into the mental state decoding decisions of DL models.
登录
查看更多内容
影响因子：
3.5
作者：
Gorgolewski K;Burns CD;Madison C;Clark D;Halchenko YO;Waskom ML;Ghosh SS
通讯作者：
Ghosh SS
影响因子：
3.5
作者：
Abraham A;Pedregosa F;Eickenberg M;Gervais P;Mueller A;Kossaifi J;Gramfort A;Thirion B;Varoquaux G
通讯作者：
Varoquaux G
影响因子：
9.2
作者：
Chyzhyk D;Varoquaux G;Milham M;Thirion B
通讯作者：
Thirion B
影响因子：
5.7
作者：
Fischl, Bruce
通讯作者：
Fischl, Bruce
影响因子：
5.7
作者：
Grosenick, Logan;Klingenberg, Brad;Taylor, Jonathan E.
通讯作者：
Taylor, Jonathan E.