Knowledge Graph Completion (KGC) aims to conduct reasoning on the facts within knowledge graphs and automatically infer missing links. Existing methods can mainly be categorized into structure-based or description-based. On the one hand, structure-based methods effectively represent relational facts in knowledge graphs using entity embeddings. However, they struggle with semantically rich real-world entities due to limited structural information and fail to generalize to unseen entities. On the other hand, description-based methods leverage pre-trained language models (PLMs) to understand textual information. They exhibit strong robustness towards unseen entities. However, they have difficulty with larger negative sampling and often lag behind structure-based methods. To address these issues, in this paper, we propose Momentum Contrast for knowledge graph completion with Structure-Augmented pre-trained language models (MoCoSA), which allows the PLM to perceive the structural information by the adaptable structure encoder. To improve learning efficiency, we proposed momentum hard negative and intra-relation negative sampling. Experimental results demonstrate that our approach achieves state-of-the-art performance in terms of mean reciprocal rank (MRR), with improvements of 2.5% on WN18RR and 21% on OpenBG500.

翻译：知识图谱补全旨在对知识图谱中的事实进行推理并自动推断缺失的链接。现有方法主要可分为基于结构或基于描述两类。一方面，基于结构的方法利用实体嵌入有效表示知识图谱中的关系事实。然而，由于结构信息有限，这些方法在面对语义丰富的真实世界实体时表现不佳，且无法泛化至未见实体。另一方面，基于描述的方法借助预训练语言模型理解文本信息，对未见实体展现出强鲁棒性。然而，它们在处理大规模负采样时存在困难，且性能通常落后于基于结构的方法。为解决这些问题，本文提出基于动量对比与结构增强预训练语言模型的知识图谱补全方法——MoCoSA，该方法通过可适配的结构编码器使预训练语言模型感知结构信息。为提升学习效率，我们提出了动量困难负采样与关系内负采样策略。实验结果表明，我们的方法在平均倒数排名指标上取得了最新最优性能，在WN18RR数据集上提升2.5%，在OpenBG500数据集上提升21%。