SimplE
Tags: #machine learning #KGEquation
$$s(e_{i}, r, e_{j}) = \frac{1}{2}(Latex Code
s(e_{i}, r, e_{j}) = \frac{1}{2}( + )
Have Fun
Let's Vote for the Most Difficult Equation!
Introduction
Equation
Latex Code
s(e_{i}, r, e_{j}) = \frac{1}{2}( + )
Explanation
The similarity function for a triple (e1 , r , e2 ) is ?he1 , vr , te2 ?. SimplE considers two vectors he,te ? Rd as the embedding of each entity (similar to CP), and two vectors vr , vr?1 ? Rd for each relation r. The similarity function of SimplE foratriple(ei,r,ej)isdefinedas 1(?hei,vr,tej?+?hej,vr?1,tei?),i.e. theaverageoftheCP 2 scoresfor(ei,r,ej)and(ej,r?1,ei). See paper SimplE Embedding for Link Prediction in Knowledge Graphs for more details.
Reply