Knowledge Graph Embedding for Link Prediction

Abstract

Knowledge Graphs (KGs) have found many applications in industrial and in academic settings, which in turn, have motivated considerable research efforts towards large-scale information extraction from a variety of sources. Despite such efforts, it is well known that even the largest KGs suffer from incompleteness; Link Prediction (LP) techniques address this issue by identifying missing facts among entities already in the KG. Among the recent LP techniques, those based on KG embeddings have achieved very promising performance in some benchmarks. Despite the fast-growing literature on the subject, insufficient attention has been paid to the effect of the design choices in those methods. Moreover, the standard practice in this area is to report accuracy by aggregating over a large number of test facts in which some entities are vastly more represented than others; this allows LP methods to exhibit good results by just attending to structural properties that include such entities, while ignoring the remaining majority of the KG. This analysis provides a comprehensive comparison of embedding-based LP methods, extending the dimensions of analysis beyond what is commonly available in the literature. We experimentally compare the effectiveness and efficiency of 18 state-of-the-art methods, consider a rule-based baseline, and report detailed analysis over the most popular benchmarks in the literature.

OWL2Vec*: embedding of OWL ontologies

“…Semantic embedding has also been extended to KGs composed of role assertions (Wang et al, 2017). The entities and relations (object properties) are represented in a vector space while retaining their relative relationships (semantics), and the resulting vectors are then applied to downstream tasks including link prediction (Rossi et al, 2020), entity alignment (Sun et al, 2020), and erroneous fact detection and correction (Chen et al, 2020a). One paradigm for learning KG representations is computing the embeddings in an end-to-end manner, iteratively adjusting the vectors using an optimization algorithm to minimize the overall loss across all the triples, where the loss is usually calculated by scoring the truth/ falsity of each triple (positive and negative samples).…”

“…Various kinds of KG embedding algorithms have been proposed and Editors: Nikos Katzouris, Alexander Artikis, Luc De Raedt, Artur d'Avila Garcez, Sebastijan Dumančić, Ute Schmid, Jay Pujara. successfully applied to KG refinement (e.g., link prediction (Rossi et al, 2020) and entity alignment Sun et al 2020), recommendation systems (Ristoski et al, 2019), zero-shot learning (Chen et al, 2020c;Wang et al, 2018), interaction prediction in bioinformatics Myklebust et al, 2019), and so on. However, most of these algorithms focus on creating embeddings for multi-relational graphs composed of RDF (Resource Description Framework) triples such as ⟨England, 1 isPartOf, UK⟩ and ⟨UK,hasCapital,London⟩.…”

[Retracted] Knowledge Graph Entity Similarity Calculation under Active Learning

“…Message queues are often used as message middleware in distributed systems, which have the functions of reducing coupling between modules, enabling asynchronous communication between modules, and reducing system traffic peaks, etc. ey are widely used in e-commerce systems, logging systems, and subscription publishing systems and are also very suitable in certain distributed computing tasks [13]. We analyse the process of knowledge graph construction and analyse the steps and algorithms that are not efficient for single-node processing in the construction process in conjunction with actual projects and select the applicable parallelization techniques to realize its parallelized processing and improve the efficiency of the algorithm without degrading its performance.…”

Biomedical Text Link Prediction for Drug Discovery: A Case Study with COVID-19

“…Moreover, prediction of missing relations is referred to as relation prediction and prediction of missing entities is called entity prediction. These tasks can be achieved by several KG embedding methods [8]. Such embedding methods first learn the vector representations for entities and relations.…”

“…Although knowledge graphs are able to model large amounts of data and facts, they still suffer from incompleteness [8] due to missing facts in the literature. Discovering missing facts using existing relationships in the literature is called link prediction.…”