TransD 论文笔记

懒狗的救赎

已于 2022-03-12 09:40:42 修改

阅读量1.2k

点赞数

CC 4.0 BY-SA版权

分类专栏：知识图谱论文文章标签：自然语言处理知识图谱机器学习

于 2022-03-08 14:24:07 首次发布

本文链接：https://blog.csdn.net/Jay98/article/details/123352602

Knowledge Graph Embedding via Dynamic Mapping Matrix

- Abstract
- Background
- Algorithm
- Experiment
- Tiplets Classification
- LInk Prediction
- Conclusion

- Abstract

TransR没有考虑关系的类型问题，而CtransR是仅考虑了关系的类型问题，而没有考虑实体的类型问题。由于在通用领域中，不一样的实体是属于不一样的类型的。TransD不仅考虑了关系的多样性，还考虑了实体的多样性。

- Background

TransR/CTransR several flaws:
(1) For a typical relation r, all entities share the same mapping matrix Mr. How- ever, the entities linked by a relation always con- tains various types and attributes;
(2) The projection oper- ation is an interactive process between an entity and a relation, it is unreasonable that the map- ping matrices are determined only by relations;
(3) Matrix-vector multiplication makes it has large amount of calculation, and when relation number is large, it also has much more param- eters than TransE and TransH. As the complex- ity, TransR/CTransR is difficult to apply on large- scale knowledge graphs. 在这里插入图片描述

- Algorithm

In TransD, we de- fine two vectors for each entity and relation. The first vector represents the meaning of an entity or a relation, the other one (called projection vector) represents the way that how to project a entity em- bedding into a relation vector space and it will be used to construct mapping matrices. There- fore, every ent