重新审视表格数据的深度学习模型
Revisiting Deep Learning Models for Tabular Data
AI总结：
本文重新审视表格数据深度学习模型，提出类似ResNet的架构和适配的Transformer架构作为强大基线，在统一协议下比较发现无普遍优越的解决方案。
摘要：
现有的关于表格数据深度学习的文献提出了多种新颖的架构，并在各种数据集上报告了具有竞争力的结果。然而，这些提出的模型通常没有得到适当的相互比较，且现有工作往往使用不同的基准和实验协议。因此，对于研究人员和从业者来说，目前尚不清楚哪些模型表现最佳。此外，该领域仍然缺乏有效的基线，即能够在不同问题上提供竞争力的易用模型。在这项工作中，我们对表格数据深度学习的主要架构家族进行了概述，并通过识别两种简单而强大的深度架构，提高了表格深度学习的基线标准。第一个是类似 ResNet 的架构，它被证明是先前工作中经常缺失的强大基线。第二个模型是我们对 Transformer 架构针对表格数据的简单适配，它在大多数任务上优于其他解决方案。这两个模型都在相同的训练和调优协议下，与许多现有架构在多样化的任务集上进行了比较。我们还将最佳的深度学习模型与梯度提升决策树（Gradient Boosted Decision Trees）进行了比较，并得出结论：目前仍然没有普遍优越的解决方案。
英文摘要：
The existing literature on deep learning for tabular data proposes a wide range of novel architectures and reports competitive results on various datasets. However, the proposed models are usually not properly compared to each other and existing works often use different benchmarks and experiment protocols. As a result, it is unclear for both researchers and practitioners what models perform best. Additionally, the field still lacks effective baselines, that is, the easy-to-use models that provide competitive performance across different problems. In this work, we perform an overview of the main families of DL architectures for tabular data and raise the bar of baselines in tabular DL by identifying two simple and powerful deep architectures. The first one is a ResNet-like architecture which turns out to be a strong baseline that is often missing in prior works. The second model is our simple adaptation of the Transformer architecture for tabular data, which outperforms other solutions on most tasks. Both models are compared to many existing architectures on a diverse set of tasks under the same training and tuning protocols. We also compare the best DL models with Gradient Boosted Decision Trees and conclude that there is still no universally superior solution.
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。
