arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.14175cs.LGcs.AIstat.ML
收藏

PyKEEN 1.0:用于训练和评估知识图谱嵌入的Python库

PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings

Smart Data Analytics Group, University of Bonn & Fraunhofer IAIS(波恩大学智能数据分析组与弗劳恩霍夫智能分析与信息系统研究所);Ludwig-Maximilians-Universität München(慕尼黑大学);Enveda Therapeutics;Technical University of Denmark(丹麦技术大学);Ludwig-Maximilians-Universität München & Siemens AG(慕尼黑大学与西门子股份公司)

Mehdi Ali, Max Berrendorf, Charles Tapley Hoyt, Laurent Vermue, Sahand Sharifzadeh, Volker Tresp, Jens Lehmann

摘要:

近年来,知识图谱嵌入(KGE)受到了广泛的关注,并开发了几个软件库用于训练和评估KGE。虽然每个库都满足特定的需求,但我们在社区的努力下重新设计和重新实现了PyKEEN,这是第一个KGE库之一。PyKEEN 1.0使用户能够基于广泛的交互模型、训练方法、损失函数来构建知识图谱嵌入模型(KGEM),并允许对逆关系进行显式建模。此外,还实现了自动内存优化,以最佳地利用所提供的硬件,并通过集成Optuna提供了广泛的超参数优化(HPO)功能。

英文摘要:

Recently, knowledge graph embeddings (KGEs) received significant attention, and several software libraries have been developed for training and evaluating KGEs. While each of them addresses specific needs, we re-designed and re-implemented PyKEEN, one of the first KGE libraries, in a community effort. PyKEEN 1.0 enables users to compose knowledge graph embedding models (KGEMs) based on a wide range of interaction models, training approaches, loss functions, and permits the explicit modeling of inverse relations. Besides, an automatic memory optimization has been realized in order to exploit the provided hardware optimally, and through the integration of Optuna extensive hyper-parameter optimization (HPO) functionalities are provided.

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。

↑