2020/02/29 by Andrea Rossi, Donatella Firmani, Antonio Matinata +2 · 485 citations
Computer Science · Mathematics · #Advanced Graph Neural Networks #Artificial intelligence #Computer science #Data mining #Data science #Embedding #Graph #Knowledge graph #Link (geometry) #Machine learning #Scale (ratio) #Text and Document Classification Technologies #Theoretical computer science #Topic Modeling #Variety (cybernetics) #cs.DB #cs.LG #stat.ML
paper · pdf · open access · doi:10.1145/3424672
published in ACM Transactions on Knowledge Discovery from Data 15(2), 1-49 (Association for Computing Machinery) · Andrea Rossi, Donatella Firmani, Antonio Matinata, Paolo Merialdo, Denilson Barbosa. 2020. Knowledge Graph Embedding for Link Prediction: A Comparative Analysis. In ACM Transactions on Knowledge Discovery from Data. January 2021. (TKDD 2021). ACM, New York, NY, USA
openalex publication_date 2021/01/04 · openalex created_date 2021/01/18 · arxiv created 2021/01/21 · arxiv updated 2021/01/25 · openalex updated_date 2026/07/22
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.