Benchmarking neural embeddings for link prediction in knowledge graphs under semantic and structural changes

This assumes that entities and links can be represented as a graph, where entities are nodes and links (symmetric relationships) are edges (arcs if relationships are asymmetric). This prediction problem has been most probably defined for the first time in the social network analysis community [1], however, it has soon become an important problem in other domains, and in particular in large-scale knowledge-bases [2], where it is used to add missing data and discover new facts. When we are dealing with the link prediction problem for knowledge-bases, the semantic information contained within is usually encoded as a knowledge graph (KG) [3]. For the purpose of this manuscript, we treat a knowledge graph as a graph where links may have different types, and we conform to the closed-world assumption. This means that all the existing (asserted) links are considered positive, and all the links which are unknown, and obtained via knowledge graph completion, are considered negative (Figure 1).