Distmult

标签：bilinear inverse linear framework Distmult learned

EMBEDDING ENTITIES AND RELATIONS FOR LEARNING AND INFERENCE IN KNOWLEDGE BASES

ICLR 2015

abstract

1. most exsiting model under a unfied framework, where entities are low-dimensional vectors learned from a neural network and relations are bilinear and/or linear mapping funtions.

2. evaluate different choices of entity representations and relation representations under this framework on canonical link prediction task.
   show a simple bilinear and/or linear formulation achieve new SOTA.

3. a novel approach that utilizes the learned embeddings to mine logical rules.

bilinear-diag: DistMult
TransE: DistADD
文章里说是： hM_rt， 但是网上查的教程都说：
好像就是改了个得分函数，h+t-r改成了htr。。。
不知道为什么变成直接乘了。。
看了pykg2vec的代码，也不知道rel怎么限制成diagonal的。。。

限制

由于是对角矩阵， 所以无法对inverse有作用
但是要是直接相乘，好像非对角矩阵也无法对inverse有作用啊

标签：bilinear,inverse,linear,framework,Distmult,learned
From： https://www.cnblogs.com/boyan118/p/17989880