Affiliation:
1. Data and Web Science Group, University of Mannheim, Germany
2. SAP SE, Germany
Abstract
Knowledge Graph Embeddings, i.e., projections of entities and relations to lower dimensional spaces, have been proposed for two purposes: (1) providing an encoding for data mining tasks, and (2) predicting links in a knowledge graph. Both lines of research have been pursued rather in isolation from each other so far, each with their own benchmarks and evaluation methodologies. In this paper, we argue that both tasks are actually related, and we show that the first family of approaches can also be used for the second task and vice versa. In two series of experiments, we provide a comparison of both families of approaches on both tasks, which, to the best of our knowledge, has not been done so far. Furthermore, we discuss the differences in the similarity functions evoked by the different embedding approaches.
Subject
Computer Networks and Communications,Computer Science Applications,Information Systems
Reference47 articles.
1. PyKEEN 1.0: A Python library for training and evaluating knowledge graph embeddings;Ali;Journal of Machine Learning Research,2021
2. Literal2Feature: An Automatic Scalable RDF Graph Feature Extractor
3. ERLKG: Entity Representation Learning and Knowledge Graph based association analysis of COVID-19 through mining of unstructured biomedical corpora
4. A. Bordes, N. Usunier, A. Garcia-Duran, J. Weston and O. Yakhnenko, Translating embeddings for modeling multi-relational data, in: Advances in Neural Information Processing Systems, 2013, pp. 2787–2795.
5. Evaluation of knowledge graph embedding approaches for drug-drug interaction prediction in realistic settings;Celebi;BMC Bioinformatics,2019
Cited by
22 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献