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 2101.04817cs.IRcs.AIcs.CLcs.LG
收藏

基于离散优化的离散知识图谱嵌入

Discrete Knowledge Graph Embedding based on Discrete Optimization

Rutgers University(罗格斯大学);JD Finance America Corporation(京东金融美国公司);University College London(伦敦大学学院)

Yunqi Li, Shuyuan Xu, Bo Liu, Zuohui Fu, Shuchang Liu, Xu Chen, Yongfeng Zhang

摘要:

提出一种离散知识图谱(KG)嵌入方法(DKGE),该方法基于一种易于计算的离散优化算法将KG实体和关系投影到汉明空间中,以解决传统连续图嵌入方法中存储和计算开销大的问题.理论上可以保证DKGE的收敛性。大量的实验表明,DKGE实现了优越的精度比经典的散列函数,映射到离散代码的有效连续嵌入。此外,与许多连续图嵌入方法相比,DKGE以低得多的计算复杂性和存储达到相当的精度。

英文摘要:

This paper proposes a discrete knowledge graph (KG) embedding (DKGE) method, which projects KG entities and relations into the Hamming space based on a computationally tractable discrete optimization algorithm, to solve the formidable storage and computation cost challenges in traditional continuous graph embedding methods. The convergence of DKGE can be guaranteed theoretically. Extensive experiments demonstrate that DKGE achieves superior accuracy than classical hashing functions that map the effective continuous embeddings into discrete codes. Besides, DKGE reaches comparable accuracy with much lower computational complexity and storage compared to many continuous graph embedding methods.

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。

↑