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 2104.10796cs.AI
收藏

一种高效的非抽样知识图谱嵌入方法

Efficient Non-Sampling Knowledge Graph Embedding

Rutgers University(罗格斯大学);Tsinghua University(清华大学)

Zelong Li, Jianchao Ji, Zuohui Fu, Yingqiang Ge, Shuyuan Xu, Chong Chen, Yongfeng Zhang

摘要:

知识图谱(KG)是一种能够描述数据实体之间复杂关系的灵活结构。目前,大多数KG嵌入模型都是基于负采样进行训练的,即,该模型旨在最大化KG中连接实体的某种相似性,同时最小化采样的断开实体的相似性。负采样通过仅考虑负实例的子集来帮助降低模型学习的时间复杂度,这可能由于采样过程中的不确定性而无法提供稳定的模型性能。为了克服这一缺陷,本文提出了一种新的KG嵌入框架--高效非采样知识图谱嵌入(NS-KGE)。其基本思想是考虑KG中的所有负样本进行模型学习,从而避免负采样。该框架可以应用于基于平方损失的知识图谱嵌入模型或损失可以转换为平方损失的模型。这种非采样策略的自然副作用是增加了模型学习的计算复杂性。为了解决这个问题,我们利用数学推导来降低非采样损失函数的复杂度,与现有模型相比,这最终为我们提供了更好的KG嵌入效率和更高的准确性。在基准数据集上的实验表明,该框架在效率和准确性上都优于传统的基于负采样的模型,并且适用于大类知识图谱嵌入模型.

英文摘要:

Knowledge Graph (KG) is a flexible structure that is able to describe the complex relationship between data entities. Currently, most KG embedding models are trained based on negative sampling, i.e., the model aims to maximize some similarity of the connected entities in the KG, while minimizing the similarity of the sampled disconnected entities. Negative sampling helps to reduce the time complexity of model learning by only considering a subset of negative instances, which may fail to deliver stable model performance due to the uncertainty in the sampling procedure. To avoid such deficiency, we propose a new framework for KG embedding -- Efficient Non-Sampling Knowledge Graph Embedding (NS-KGE). The basic idea is to consider all of the negative instances in the KG for model learning, and thus to avoid negative sampling. The framework can be applied to square-loss based knowledge graph embedding models or models whose loss can be converted to a square loss. A natural side-effect of this non-sampling strategy is the increased computational complexity of model learning. To solve the problem, we leverage mathematical derivations to reduce the complexity of non-sampling loss function, which eventually provides us both better efficiency and better accuracy in KG embedding compared with existing models. Experiments on benchmark datasets show that our NS-KGE framework can achieve a better performance on efficiency and accuracy over traditional negative sampling based models, and that the framework is applicable to a large class of knowledge graph embedding models.

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。

↑