Knowledge graph embedding for link prediction: A comparative analysis
| Autor: | Donatella Firmani, Denilson Barbosa, Andrea Rossi, Paolo Merialdo, Antonio Matinata |
|---|---|
| Přispěvatelé: | Rossi, A., Barbosa, D., Firmani, D., Matinata, A., Merialdo, P. |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning comparative analysis General Computer Science Computer science Machine Learning (stat.ML) Link prediction 02 engineering and technology Machine learning computer.software_genre Machine Learning (cs.LG) Computer Science - Databases Statistics - Machine Learning 020204 information systems 0202 electrical engineering electronic engineering information engineering Baseline (configuration management) Link (knot theory) knowledge graph embeddings link prediction Knowledge graph Comparative analysi business.industry Subject (documents) Databases (cs.DB) Variety (cybernetics) knowledge graphs Information extraction Knowledge graph embedding Embedding 020201 artificial intelligence & image processing Artificial intelligence business computer |
| Popis: | Knowledge Graphs (KGs) have found many applications in industry and 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 state-of-the-art KGs suffer from incompleteness. Link Prediction (LP), the task of predicting missing facts among entities already a KG, is a promising and widely studied task aimed at addressing KG incompleteness. Among the recent LP techniques, those based on KG embeddings have achieved very promising performances in some benchmarks. Despite the fast growing literature in the subject, insufficient attention has been paid to the effect of the various 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 over-represented; this allows LP methods to exhibit good performance 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 effectiveness and efficiency of 16 state-of-the-art methods, consider a rule-based baseline, and report detailed analysis over the most popular benchmarks in the literature. 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 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|