LIME2(Local interpretable model-agnostic explanations)(why should I trust you: Explaining the predictions of any classifier)通过生成的包含需要解释点周围的扰动数据和基于黑箱模型预测结果的数据集,训练一个可以解释的模型,比如逻辑回归、决策树,这个可解释模型需要在解释点周围达到较好的效果。
choosing a good reference would rely on domain-specific knowledge, and in some cases it may be best to compute DeepLIFT scores against multiple different references
the Shapely values measure the average marginal effect of including an input over all possible orderings in which inputs can be included. If we define “including” an input as setting it to its actual value instead of its reference value, DeepLIFT can be thought of as a fast approximation of the Shapely values8
Though a variety of methods exist for estimating SHAP values, we implemented a modified version of the DeepLIFT algorithm, which computes SHAP by estimating differences in model activations during backpropagation relative to a standard reference.
Ribeiro, M. T., Singh, S. & Guestrin, C. ‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 1135–1144 (2016) doi:10.1145/2939672.2939778. ↩︎
Shrikumar, A., Greenside, P., Shcherbina, A. & Kundaje, A. Not Just a Black Box: Learning Important Features Through Propagating Activation Differences. Preprint at https://doi.org/10.48550/arXiv.1605.01713 (2017). ↩︎
Shrikumar, A., Greenside, P. & Kundaje, A. Learning Important Features Through Propagating Activation Differences. Preprint at http://arxiv.org/abs/1704.02685 (2019). ↩︎