区别对待不同负样本：为链接预测的损失函数引入定义域与值域约束以增强其性能
Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction
AI总结：
该研究针对链接预测任务中不同负样本应区别对待的问题，提出将关系的定义域与值域约束融入三类主流损失函数，实验证明该方法能提升MRR、Hits@10指标与语义正确性，具备通用性与实用价值。
摘要：
知识图谱嵌入模型（KGEMs）被用于与知识图谱（KGs）相关的各类任务，包括链接预测。这类模型通过同时处理成批次的真实三元组和虚假三元组的损失函数进行训练。但虚假三元组存在不同类型，近期研究表明不应将它们同等看待，由此催生了特定的负采样流程。基于这一最新假设，我们提出，就关系的签名（定义域与值域）而言具备语义有效性的负三元组属于高质量负样本。因此，我们对链接预测的三类主流损失函数进行了增强，使得所有类型的负样本都能被采样，但会根据其语义有效性被区别对待。在一项大规模且受控的实验设置中，我们证明所提出的损失函数始终能取得令人满意的结果，这体现了我们所提方法的通用性与优越性。实际上，所提出的损失函数（1）能带来更优的MRR和Hits@10指标值，（2）能推动KGEMs实现更好的语义正确性，这一点通过Sem@K指标得以衡量。这凸显出关系签名能够从整体上提升KGEMs的性能，因此应当被纳入损失函数中。由于关系的定义域与值域在模式定义的知识图谱中大多是可获取的，这使得我们的方法在实际应用中既有益处又具备广泛的可用性。
英文摘要：
Knowledge graph embedding models (KGEMs) are used for various tasks related to knowledge graphs (KGs), including link prediction. They are trained with loss functions that consider batches of true and false triples. However, different kinds of false triples exist and recent works suggest that they should not be valued equally, leading to specific negative sampling procedures. In line with this recent assumption, we posit that negative triples that are semantically valid w.r.t. signatures of relations (domain and range) are high-quality negatives. Hence, we enrich the three main loss functions for link prediction such that all kinds of negatives are sampled but treated differently based on their semantic validity. In an extensive and controlled experimental setting, we show that the proposed loss functions systematically provide satisfying results which demonstrates both the generality and superiority of our proposed approach. In fact, the proposed loss functions (1) lead to better MRR and Hits@10 values, and (2) drive KGEMs towards better semantic correctness as measured by the Sem@K metric. This highlights that relation signatures globally improve KGEMs, and thus should be incorporated into loss functions. Domains and ranges of relations being largely available in schema-defined KGs, this makes our approach both beneficial and widely usable in practice.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
