arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.06596stat.MLcs.LG
收藏

特征重要性的逻辑约束

Logic Constraints to Feature Importances

SAILAB, University of Siena(锡耶纳大学SAILAB实验室);University of Pavia(帕维亚大学)

Nicola Picchiotti, Marco Gori

摘要:

近年来,人工智能(AI)算法已被证明在预测性方面优于传统的统计方法,特别是当有大量数据可用时。尽管如此,人工智能模型的“黑匣子”性质往往是一个限制,在高风险领域的可靠应用,如诊断技术,自主指南等最近的工作表明,足够的可解释性水平可以执行更一般的概念模型可信度。本文的基本思想是利用人类对特定任务的特征重要性的先验知识,以便连贯地帮助模型拟合阶段。这种“加权”AI是通过用正则化项扩展经验损失来获得的,该正则化项鼓励特征的重要性遵循预定的约束。该过程依赖于用于特征重要性计算的局部方法,例如LRP、LIME等,这些方法是待优化的模型权重与用户定义的特征重要性约束之间的联系。在公平性方面,在成人数据集上获得了有希望的实验结果。许多其他可能的应用,这个模型不可知论的理论框架进行了说明。

英文摘要:

In recent years, Artificial Intelligence (AI) algorithms have been proven to outperform traditional statistical methods in terms of predictivity, especially when a large amount of data was available. Nevertheless, the "black box" nature of AI models is often a limit for a reliable application in high-stakes fields like diagnostic techniques, autonomous guide, etc. Recent works have shown that an adequate level of interpretability could enforce the more general concept of model trustworthiness. The basic idea of this paper is to exploit the human prior knowledge of the features' importance for a specific task, in order to coherently aid the phase of the model's fitting. This sort of "weighted" AI is obtained by extending the empirical loss with a regularization term encouraging the importance of the features to follow predetermined constraints. This procedure relies on local methods for the feature importance computation, e.g. LRP, LIME, etc. that are the link between the model weights to be optimized and the user-defined constraints on feature importance. In the fairness area, promising experimental results have been obtained for the Adult dataset. Many other possible applications of this model agnostic theoretical framework are described.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑