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 2610.09927cs.LGcs.AI

KGATE:一个知识图谱嵌入训练环境

KGATE : a Knowledge Graph Embedding Training Environment

Benjamin Loire, Galadriel Brière, Célia Brahimi, Antoine Toffano, Anaïs Baudot

首次发表
浏览论文内容

中文总结 AI 辅助

KGATE是一个基于PyTorch Geometric和TorchKGE的模块化Python库,用于知识图谱自编码器训练,提供可组装组件、数据泄漏控制及可复现性,性能与最快库相当。

中文摘要 AI 辅助

知识图谱嵌入(KGE)模型将知识图谱中的实体和关系编码到低维潜在空间中,从而支持分类或链接预测等任务。大多数KGE模型遵循自编码器架构,其中编码器将知识图谱投影到潜在空间,解码器对其进行重构。组合编码器和解码器组件的需求日益增长,然而现有库很少支持完整的自编码器,通常缺乏维护,依赖未记录的默认超参数,并且产生的结果无法跨库比较。在此,我们提出KGATE(知识图谱自编码器训练环境),一个基于PyTorch Geometric和TorchKGE构建的模块化Python库。KGATE允许用户将初始化器、编码器、解码器、损失函数、负采样器和评估指标作为构建块进行组装,或插入自己的模块。KGATE包含一个控制数据泄漏的预处理流程、一个内置训练管道,并设计上保证可复现性。与六个现有KGE库的基准测试表明,KGATE的训练时间与最快的库相当,同时提供更广泛的功能集。

英文摘要

Knowledge graph embedding (KGE) models encode the entities and relations of a knowledge graph into a low-dimensional latent space, enabling tasks such as classification or link prediction. Most KGE models follow an autoencoder architecture, in which an encoder projects the knowledge graph into the latent space and a decoder reconstruct it. Combining both encoder and decoder components is increasingly needed, yet existing libraries rarely support complete autoencoders, are often unmaintained, rely on undocumented default hyperparameters, and produce results that cannot be compared across libraries. Here we present KGATE (Knowledge Graph Autoencoder Training Environment), a modular Python library built on PyTorch Geometric and TorchKGE. KGATE lets users assemble initializers, encoders, decoders, losses, negative samplers, and evaluation metrics as building blocks, or plug in their own block. KGATE includes a preprocessing procedure that controls data leakage, a builtin training pipeline, and reproducibility by design. Benchmarks against six existing KGE libraries show that KGATE training time is comparable with the fastest libraries while offering a broader set of features.

发表机构

  • Aix Marseille Univ.(艾克斯-马赛大学)
  • INSERM(法国国家健康与医学研究院)
  • Marseille Medical Genetics(马赛医学遗传学)
  • Systems Biomedicine Team(系统生物医学团队)
  • Neurology Therapeutic Area, R&D Servier Paris-Saclay Institut(神经病学治疗领域,施维雅巴黎-萨克雷研究所研发部)
  • LIRMM(蒙彼利埃计算机科学、机器人及微电子实验室)
  • Univ. Montpellier(蒙彼利埃大学)
  • CNRS(法国国家科学研究中心)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑