Evaluation of Similarity-based Explanations
Evaluation of Similarity-based Explanations
复制标题
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Kazuaki Hanawa;Sho Yokoi;Satoshi Hara;Kentaro Inui
中科院分区：
文献类型：
--
作者：
Kazuaki Hanawa;Sho Yokoi;Satoshi Hara;Kentaro Inui
解释复杂机器学习模型的预测有助于用户理解并自信地接受预测结果。一种有希望的方法是使用基于相似性的解释，提供相似的实例作为证据来支持模型预测。为此目的，使用了几个相关性度量。在这项研究中，我们研究了相关性度量，可以提供合理的解释给用户。具体来说，我们采用了三个测试，以评估相关性度量是否满足基于相似性的解释的最低要求。我们的实验表明，损失梯度的余弦相似性表现最好，这将是实践中的推荐选择。此外，我们还发现一些指标在测试中表现不佳，并分析了失败的原因。我们希望我们的见解，以帮助从业者在选择适当的相关性指标，也有助于进一步的研究，设计更好的相关性指标的解释。
Explaining the predictions made by complex machine learning models helps users to understand and accept the predicted outputs with confidence. One promising way is to use similarity-based explanation that provides similar instances as evidence to support model predictions. Several relevance metrics are used for this purpose. In this study, we investigated relevance metrics that can provide reasonable explanations to users. Specifically, we adopted three tests to evaluate whether the relevance metrics satisfy the minimal requirements for similarity-based explanation. Our experiments revealed that the cosine similarity of the gradients of the loss performs best, which would be a recommended choice in practice. In addition, we showed that some metrics perform poorly in our tests and analyzed the reasons of their failure. We expect our insights to help practitioners in selecting appropriate relevance metrics and also aid further researches for designing better relevance metrics for explanations.