Relational learning is an essential task in the domain of knowledge representation, particularly in knowledge graph completion (KGC).While relational learning in traditional single-modal settings has been extensively studied, exploring it within a multimodal KGC context presents distinct challenges and opportunities. One of the major challenges is inference on newly discovered relations without any associated training data. This zero-shot relational learning scenario poses unique requirements for multimodal KGC, i.e., utilizing multimodality to facilitate relational learning. However, existing works fail to support the leverage of multimodal information and leave the problem unexplored. In this paper, we propose a novel end-to-end framework, consisting of three components, i.e., multimodal learner, structure consolidator, and relation embedding generator, to integrate diverse multimodal information and knowledge graph structures to facilitate the zero-shot relational learning. Evaluation results on two multimodal knowledge graphs demonstrate the superior performance of our proposed method.

翻译：关系学习是知识表示领域的一项关键任务，尤其在知识图谱补全（KGC）中。尽管传统单模态场景下的关系学习已被广泛研究，但在多模态KGC背景下探索该任务仍面临独特挑战与机遇。其中一个主要挑战是如何对无任何训练数据的新发现关系进行推理。这种零样本关系学习场景为多模态KGC提出了独特要求，即利用多模态信息促进关系学习。然而现有工作未能支持多模态信息的利用，导致该问题尚未被探索。本文提出了一种新颖的端到端框架，包含三个组件：多模态学习器、结构整合器和关系嵌入生成器，通过融合多样化多模态信息与知识图谱结构来促进零样本关系学习。在两个多模态知识图谱上的评估结果表明，我们提出的方法具有优越性能。