Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies have focused on relation types unseen in the original KG, given only one or a few instances for training. To bridge this gap, we propose CogKR for one-shot KG reasoning. The one-shot relational learning problem is tackled through two modules: the summary module summarizes the underlying relationship of the given instances, based on which the reasoning module infers the correct answers. Motivated by the dual process theory in cognitive science, in the reasoning module, a cognitive graph is built by iteratively coordinating retrieval (System 1, collecting relevant evidence intuitively) and reasoning (System 2, conducting relational reasoning over collected information). The structural information offered by the cognitive graph enables our model to aggregate pieces of evidence from multiple reasoning paths and explain the reasoning process graphically. Experiments show that CogKR substantially outperforms previous state-of-the-art models on one-shot KG reasoning benchmarks, with relative improvements of 24.3%-29.7% on MRR. The source code is available at https://github.com/THUDM/CogKR.
翻译:从现有的知识图表(KG)中得出新的事实,并解释可以解释的推理过程是一个重大问题,最近引起人们的注意。然而,很少有研究侧重于原始KG所见的关系类型,只提供了一次或几次培训实例。为了缩小这一差距,我们建议CogKR为一发KG推理。一发关系学习问题通过两个模块加以解决:摘要模块总结了特定实例的基本关系,根据这些实例,推理模块推断了正确的答案。在逻辑模块中,根据认知科学的双重过程理论,通过迭代协调检索(系统1,直接收集相关证据)和推理(系统2,对所收集的信息进行关联推理)和推理(系统2,对所收集的信息进行关联推理)构建了认知图表提供的结构信息,使我们的模型能够汇总多个推理路径的证据碎片,并用图形解释推理过程。实验显示,CogKRR大大超出先前对KG推理基准的状态-艺术模型,在推理学模块中,通过迭协调检索(系统收集的相关改进率为24.3%-2.9%/MRRRRR.在M. http源代码中提供源代码源代码。