发表机构
AI Graduate School; Gwangju Institute of Science and Technology（人工智能研究生院; 光州科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对知识图谱嵌入的模式过度泛化问题，提出PogRE方法，通过密集线性变换等技术缓解该问题，在三个基准数据集的链接预测任务中优于现有最先进模型。
AI 中文摘要
知识图谱嵌入（KGE）通过将实体和关系投影到低维向量空间，展现出预测知识图谱（KG）中缺失链接的有效性。对于KGE模型而言，有效捕获KG中固有的推理模式（即模式）至关重要，例如对称性/反对称性、反转和组合。尽管近期的KGE模型在建模此类多样模式方面展现出强大能力，但它们存在源于模式过度泛化的固有局限：仅从单一模式实例学习到的嵌入，不可避免地会将该模式泛化到所有相关实例，即普遍泛化该模式。为解决此问题，我们提出PogRE（模式过度泛化鲁棒嵌入），一种简单却有效的方法，利用密集线性变换和复合操作进行关系表示。我们的理论分析表明，随着观察到某一模式的三元组增多，密集线性变换会使该模式逐渐变得普遍；此外，在观察到d+1个线性独立实体（d+1表示实体维度）后，线性变换可保证该模式在所有相关实例上的普遍泛化。在三个标准基准数据集上的实验结果显示，PogRE在链接预测任务中优于现有的最先进KGE模型，且我们的实证结果表明PogRE有效缓解了过度泛化的负面影响。
英文摘要
Knowledge graph embedding (KGE) demonstrates its effectiveness for predicting missing links in knowledge graphs (KGs) by projecting entities and relations into a low-dimensional vector space. It is crucial for KGE models to effectively capture inference patterns (patterns) inherent in KGs, such as symmetry/antisymmetry, inversion and composition. Although recent KGE models exhibit strong capabilities in modeling such diverse patterns, they suffer from inherent limitations stemming from pattern over-generalization, where embeddings learned from only a single pattern instance inevitably generalize that pattern to all related instances, i.e., generalize the pattern universally. To address this issue, we propose PogRE (Pattern Over-Generalization Robust Embedding), a simple but effective method that utilizes dense linear transformations and compound operations for relation representation. Our theoretical analysis demonstrates that a dense linear transformation allows a pattern to become progressively universal as more triples are observed in the pattern. Furthermore, after observing d+1 linearly independent entities (d+1 denotes the dimension of entity), the linear transformation guarantees universal generalization of the pattern across all related instances. Experimental results on three standard benchmark datasets show that PogRE outperforms existing state-of-the-art KGE models in link prediction. Moreover, our empirical results indicate that PogRE effectively addresses the negative impact of over-generalization.
CommentsAccepted to EMNLP 2026, 22 pages, 9 figures
