Knowledge graph embedding (KGE) aims at learning powerful representations to benefit various artificial intelligence applications. Meanwhile, contrastive learning has been widely leveraged in graph learning as an effective mechanism to enhance the discriminative capacity of the learned representations. However, the complex structures of KG make it hard to construct appropriate contrastive pairs. Only a few attempts have integrated contrastive learning strategies with KGE. But, most of them rely on language models ( e.g., Bert) for contrastive pair construction instead of fully mining information underlying the graph structure, hindering expressive ability. Surprisingly, we find that the entities within a relational symmetrical structure are usually similar and correlated. To this end, we propose a knowledge graph contrastive learning framework based on relation-symmetrical structure, KGE-SymCL, which mines symmetrical structure information in KGs to enhance the discriminative ability of KGE models. Concretely, a plug-and-play approach is proposed by taking entities in the relation-symmetrical positions as positive pairs. Besides, a self-supervised alignment loss is designed to pull together positive pairs. Experimental results on link prediction and entity classification datasets demonstrate that our KGE-SymCL can be easily adopted to various KGE models for performance improvements. Moreover, extensive experiments show that our model could outperform other state-of-the-art baselines.

翻译：知识图谱嵌入旨在学习强大的表示，以服务于各种人工智能应用。同时，对比学习作为一种有效机制，已被广泛应用于图学习领域，以增强所学表示的判别能力。然而，知识图谱的复杂结构使得构建合适的对比对变得困难。仅有少数研究尝试将对比学习策略与知识图谱嵌入相结合。但这些方法大多依赖语言模型（如BERT）进行对比对构建，而非充分挖掘图结构底层的信息，从而限制了表达能力。令人惊喜的是，我们发现关系对称结构中的实体通常具有相似性和相关性。为此，我们提出了一种基于关系对称结构的知识图谱对比学习框架——KGE-SymCL，该框架通过挖掘知识图谱中的对称结构信息，增强知识图谱嵌入模型的判别能力。具体而言，我们提出了一种即插即用的方法，将关系对称位置上的实体作为正对比对。此外，我们还设计了一种自监督对齐损失函数，用于拉近正对比对。在链接预测和实体分类数据集上的实验结果表明，我们的KGE-SymCL可轻松应用于多种知识图谱嵌入模型，以提升性能。此外，大量实验证明，我们的模型能够超越其他最先进的基线方法。