arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2108.04855cs.LGcs.AI
收藏

表格数据的类注意特征解释

Attention-like feature explanation for tabular data

Peter the Great St.Petersburg Polytechnic University(彼得大帝圣彼得堡理工大学)

Andrei V. Konstantinov, Lev V. Utkin

摘要:

提出了一种利用表格数据对机器学习黑箱模型预测进行局部和全局解释的新方法。它被实现为一个称为AFEX(Attention-like Feature EXplanation)的系统,由两个主要部分组成。第一部分是一组单特征神经子网络,其目的是以形状函数的基的形式获得每个特征的特定表示。子网络使用具有可训练参数的快捷连接来提高网络性能。AFEX的第二部分产生特征的形状函数作为基础形状函数的加权和,其中通过使用类似注意力的机制来计算权重。AFEX基于对应于不同特征的形状函数的成对乘法来识别特征之间的成对交互。提出了一种改进的AFEX算法,并在其基础上增加了一个近似于黑箱模型的代理模型。AFEX只在整个数据集上进行一次端到端的训练,使得它不需要在解释阶段再次训练神经网络。模拟和实际数据的数值实验说明了AFEX。

英文摘要:

A new method for local and global explanation of the machine learning black-box model predictions by tabular data is proposed. It is implemented as a system called AFEX (Attention-like Feature EXplanation) and consisting of two main parts. The first part is a set of the one-feature neural subnetworks which aim to get a specific representation for every feature in the form of a basis of shape functions. The subnetworks use shortcut connections with trainable parameters to improve the network performance. The second part of AFEX produces shape functions of features as the weighted sum of the basis shape functions where weights are computed by using an attention-like mechanism. AFEX identifies pairwise interactions between features based on pairwise multiplications of shape functions corresponding to different features. A modification of AFEX with incorporating an additional surrogate model which approximates the black-box model is proposed. AFEX is trained end-to-end on a whole dataset only once such that it does not require to train neural networks again in the explanation stage. Numerical experiments with synthetic and real data illustrate AFEX.

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。

↑