Walk-and-Relate: A Random-Walk-based Algorithm for Representation Learning on Sparse Knowledge Graphs. (arXiv:2209.08769v2 [cs.LG] UPDATED)

Knowledge graph (KG) embedding techniques use structured relationships
between entities to learn low-dimensional representations of entities and
relations. The traditional KG embedding techniques (such as TransE and
DistMult) estimate these embeddings via simple models developed over observed
KG triplets. These approaches differ in their triplet scoring loss functions.
As these models only use the observed triplets to estimate the embeddings, they
are prone to suffer through data sparsity that usually occurs in the real-world
knowledge graphs, i.e., the lack of …

algorithm arxiv graphs knowledge knowledge graphs random random-walk representation representation learning