论文标题
神经树的调查
A Survey of Neural Trees
论文作者
论文摘要
神经网络（NNS）和决策树（DTS）都是机器学习的流行模型，但具有相互排斥的优势和局限性。为了带来两个世界中的最好，提出了各种方法来明确或隐式地整合NN和DTS。在这项调查中，这些方法是在我们称为神经树（NTS）的学校中组织的。这项调查旨在对NTS进行全面的审查，并尝试确定它们如何增强模型的解释性。我们首先提出了NTS的彻底分类，该分类法表达了NNS和DTS的逐步整合和共同进化。之后，我们根据其可解释性和绩效分析了NT，并建议解决其余挑战的可能解决方案。最后，这项调查结束了关于其他考虑因素等其他考虑因素以及对该领域有希望的方向的讨论。该调查中审查的论文列表及其相应的代码可在以下网址提供：https：//github.com/zju-vipa/awesome-neural-trees
Neural networks (NNs) and decision trees (DTs) are both popular models of machine learning, yet coming with mutually exclusive advantages and limitations. To bring the best of the two worlds, a variety of approaches are proposed to integrate NNs and DTs explicitly or implicitly. In this survey, these approaches are organized in a school which we term as neural trees (NTs). This survey aims to present a comprehensive review of NTs and attempts to identify how they enhance the model interpretability. We first propose a thorough taxonomy of NTs that expresses the gradual integration and co-evolution of NNs and DTs. Afterward, we analyze NTs in terms of their interpretability and performance, and suggest possible solutions to the remaining challenges. Finally, this survey concludes with a discussion about other considerations like conditional computation and promising directions towards this field. A list of papers reviewed in this survey, along with their corresponding codes, is available at: https://github.com/zju-vipa/awesome-neural-trees
