TEC:Knowledge Graph Embedding with Triple Context

1 problem

    The knowledge map is not fully utilized , Rich information , Use its surrounding information and path information , Complete the knowledge map based on the above information .

2 Model

context The information includes ：neighbor context and path context.

2.1 Context Details

• Neighbor Context
  For its Neighbor Context Only calculate the output ,$CN(h)=(r_4,e_1),(r_3,e_2),(r_2,e_3),(r_1,e_8),(r_1,e_{1}0)$
• Path Context
  about Path Context, $CP(h,t)=(r_1,r_2),(r_2,r_1,r_2).$, Save only h and t The relationship between .
  $C(h,r,t)=CN(h)\cup CP(h,t)$

2.2 scoring function

Maximize possibilities ：

It can be written in the following form ：








Train through the above formula , Consumption of resources , Therefore, negative sampling is used for training

The other two are similar .