Knowledge Graph Embedding: A Survey of Approaches and Applications - Leitura de Artigo 1

Q. Wang, Z. Mao, B. Wang and L. Guo, "Knowledge Graph Embedding: A Survey of Approaches and Applications," in IEEE Transactions on Knowledge and Data Engineering, vol. 29, no. 12, pp. 2724-2743, 1 Dec. 2017, doi: 10.1109/TKDE.2017.2754499.

1. Techniques that conduct embedding using only facts observed in the KG
2. Techniques that further incorporate additional information besides facts. 
3. How embeddings can be applied to and benefit a wide variety of tasks (in-KG applications and out-of-KG applications)
   

A KG is a multi-relational graph composed of entities (nodes) and relations (different types of edges). Each edge is represented as a triple of the form (head entity , relation, tail entity), also called a fact, indicating that two entities are connected by a specific relation

(1)

Given a KG, such a technique first represents entities and relations in a continuous vector space, and defines a scoring function on each fact to measure its plausibility. 

two groups: translational distance models and semantic matching models. The former use distance-based scoring functions, and the latter similarity-based ones.

Translational distance models exploit distance-based scoring functions. They measure the plausibility of a fact as the distance between the two entities, usually after a translation carried out by the relation.

TransE is the most representative translational distance model. It represents both entities and relations as vectors in the same space, say Rd. Given a fact (h,r,t), the relation is interpreted as a translation vector r so that the embedded entities h and t can be connected by r with low error, i.e., h+r≈t when (h,r,t) holds.  

Semantic matching models exploit similarity-based scoring functions. They measure plausibility of facts by matching latent semantics of entities and relations embodied in their vector space representations.

RESCAL (a.k.a. the bilinear model) associates each entity with a vector to capture its latent semantics. Each relation is represented as a matrix which models pairwise interactions between latent factors. The score of a fact (h,r,t) is defined by a bilinear function

DistMult simplifies RESCAL by restricting Mr to diagonal matrices.

ComplEx extends DistMult by introducing complex-valued embeddings so as to better model asymmetric relations. In ComplEx, entity and relation embeddings h,r,t no longer lie in a real space but a complex space, say Cd.

 

Routine training procedures for KG embedding models: the open world assumption (OWA) and closed world assumption (CWA). The open world assumption (OWA) states that KGs contain only true facts and non-observed facts can be either false or just missing. The closed world assumption (CWA) assumes that all facts that are not contained in KG are false.

Here, n and m are the number of entities and relations respectively; d and k the dimensionality of entity and relation embedding space respectively (we usually have d=k). We can draw the following conclusions. First, models which represent entities and relations as vectors (e.g., TransE, TransH, DistMult, and ComplEx)