Neurosymbolic AI is an increasingly active area of research that combines symbolic reasoning methods with deep learning to leverage their complementary benefits. As knowledge graphs are becoming a popular way to represent heterogeneous and multi-relational data, methods for reasoning on graph structures have attempted to follow this neurosymbolic paradigm. Traditionally, such approaches have utilized either rule-based inference or generated representative numerical embeddings from which patterns could be extracted. However, several recent studies have attempted to bridge this dichotomy to generate models that facilitate interpretability, maintain competitive performance, and integrate expert knowledge. Therefore, we survey methods that perform neurosymbolic reasoning tasks on knowledge graphs and propose a novel taxonomy by which we can classify them. Specifically, we propose three major categories: (1) logically-informed embedding approaches, (2) embedding approaches with logical constraints, and (3) rule learning approaches. Alongside the taxonomy, we provide a tabular overview of the approaches and links to their source code, if available, for more direct comparison. Finally, we discuss the unique characteristics and limitations of these methods, then propose several prospective directions toward which this field of research could evolve.

翻译：神经符号人工智能是一个日益活跃的研究领域，它结合了符号推理方法与深度学习，以发挥两者互补的优势。随着知识图谱成为表示异构和多关系数据的常用方式，基于图结构的推理方法也开始遵循这一神经符号范式。传统上，此类方法要么使用基于规则的推理，要么生成代表性的数值嵌入，从中提取模式。然而，近期多项研究试图弥合这一分野，构建既能保持可解释性、维持竞争性性能，又能整合专家知识的模型。因此，我们综述了在知识图谱上执行神经符号推理任务的方法，并提出了一种新的分类体系来归类这些方法。具体而言，我们提出了三大类别：（1）逻辑引导的嵌入方法，（2）带逻辑约束的嵌入方法，以及（3）规则学习方法。除分类体系外，我们还提供了方法概览表格及其源代码链接（如有），以便更直接地比较。最后，我们讨论了这些方法的独特特征与局限性，并提出了该研究领域未来发展的若干潜在方向。