Research Area:  Machine Learning
We present MMKG, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs. Therefore, multi-relational link prediction and entity matching communities can benefit from this resource. We believe this data set has the potential to facilitate the development of novel multi-modal learning approaches for knowledge graphs. We validate the utility of MMKG in the 𝚜𝚊𝚖𝚎𝙰𝚜 link prediction task with an extensive set of experiments. These experiments show that the task at hand benefits from learning of multiple feature types.
Keywords:  
Multi-modal Knowledge Graphs
Entity
Machine Learning
Deep Learning
Author(s) Name:  Ye Liu, Hui Li, Alberto Garcia-Duran, Mathias Niepert, Daniel Onoro-Rubio & David S. Rosenblum
Journal name:  
Conferrence name:  European Semantic Web Conference
Publisher name:  Springer
DOI:  10.1007/978-3-030-21348-0_30
Volume Information:  
Paper Link:   https://link.springer.com/chapter/10.1007/978-3-030-21348-0_30