arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.11809cs.CLcs.LG
收藏

通过共轭共享参数实现复数空间中的知识图谱嵌入

Sharing Parameter by Conjugation for Knowledge Graph Embeddings in Complex Space

Nara Institute of Science and Technology(奈良先端科学技术大学院大学);Fujitsu Ltd.(富士通公司)

Xincan Feng, Zhi Qu, Yuchang Cheng, Taro Watanabe, Nobuhiro Yugami

AI总结:

提出在复数空间知识图谱嵌入中通过共轭参数共享方法,将关系嵌入内存效率提升2倍,并在五个基准数据集上保持与最先进模型相当的性能。

摘要:

知识图谱(KG)是现实世界中实体和关系的有向图形表示。知识图谱可应用于需要知识的多种自然语言处理(NLP)任务中。自动扩展和补全知识图谱的需求催生了知识图谱嵌入(KGE),这是一种浅层机器学习模型,但存在内存和训练时间消耗问题。为减轻计算负担,我们提出了一种参数共享方法,即在KGE模型中对复数使用共轭参数。我们的方法在关系嵌入中将内存效率提高了2倍,同时实现了与最先进的非共轭模型相当的性能,且训练时间更快或至少相当。我们在两个性能最佳的KGE模型$5^{\bigstar}\mathrm{E}$和$\mathrm{ComplEx}$上,在五个基准数据集上展示了我们方法的泛化性。

英文摘要:

A Knowledge Graph (KG) is the directed graphical representation of entities and relations in the real world. KG can be applied in diverse Natural Language Processing (NLP) tasks where knowledge is required. The need to scale up and complete KG automatically yields Knowledge Graph Embedding (KGE), a shallow machine learning model that is suffering from memory and training time consumption issues. To mitigate the computational load, we propose a parameter-sharing method, i.e., using conjugate parameters for complex numbers employed in KGE models. Our method improves memory efficiency by 2x in relation embedding while achieving comparable performance to the state-of-the-art non-conjugate models, with faster, or at least comparable, training time. We demonstrated the generalizability of our method on two best-performing KGE models $5^{\bigstar}\mathrm{E}$ and $\mathrm{ComplEx}$ on five benchmark datasets.

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。

↑