There is a recent growing interest in applying Deep Learning techniques to tabular data, in order to replicate the success of other Artificial Intelligence areas in this structured domain. Specifically interesting is the case in which tabular data have a time dependence, such as, for instance financial transactions. However, the heterogeneity of the tabular values, in which categorical elements are mixed with numerical items, makes this adaptation difficult. In this paper we propose a Transformer architecture to represent heterogeneous time-dependent tabular data, in which numerical features are represented using a set of frequency functions and the whole network is uniformly trained with a unique loss function.

翻译：近年来，将深度学习技术应用于表格数据以复制其在其他人工智能领域成功的兴趣日益增长。尤其值得关注的是当表格数据具有时间依赖性时的情况，例如金融交易。然而，表格数据中类别元素与数值项混合的异构性使得这种适应变得困难。本文提出了一种Transformer架构，用于表示具有时间依赖性的异构表格数据，其中数值特征通过一组频率函数表示，整个网络使用统一的损失函数进行训练。