论文标题
知识图中新兴实体的可解释链接预测
Explainable Link Prediction for Emerging Entities in Knowledge Graphs
论文作者
论文摘要
尽管覆盖了大规模的覆盖范围，但跨域知识图总是遭受固有的不完整和稀疏性。链接预测可以通过推断目标实体（给定源实体和查询关系）来减轻这一点。最近的基于嵌入的方法在实体和关系的不可解释的潜在语义向量空间中运行，而基于路径的方法在符号空间中运行，从而可以解释推理过程。但是，这些方法通常考虑了知识图的静态快照，严重限制了其适用于新兴实体发展知识图的适用性。为了克服这个问题，我们提出了一个能够学习以前看不见的实体的表示形式的归纳表示学习框架。我们的方法找到了源和目标实体之间的推理路径，从而使未见实体的链接预测可解释，并为推断的链接提供支持证据。
Despite their large-scale coverage, cross-domain knowledge graphs invariably suffer from inherent incompleteness and sparsity. Link prediction can alleviate this by inferring a target entity, given a source entity and a query relation. Recent embedding-based approaches operate in an uninterpretable latent semantic vector space of entities and relations, while path-based approaches operate in the symbolic space, making the inference process explainable. However, these approaches typically consider static snapshots of the knowledge graphs, severely restricting their applicability for evolving knowledge graphs with newly emerging entities. To overcome this issue, we propose an inductive representation learning framework that is able to learn representations of previously unseen entities. Our method finds reasoning paths between source and target entities, thereby making the link prediction for unseen entities interpretable and providing support evidence for the inferred link.
