Trans4E: Link Prediction on Scholarly Knowledge Graphs
arXiv:2107.03297 · doi:10.1016/j.neucom.2021.02.100
Abstract
The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the quality of AI-based services. In the scholarly domain, KGs describing research publications typically lack important information, hindering our ability to analyse and predict research dynamics. In recent years, link prediction approaches based on Knowledge Graph Embedding models became the first aid for this issue. In this work, we present Trans4E, a novel embedding model that is particularly fit for KGs which include N to M relations with NM. This is typical for KGs that categorize a large number of entities (e.g., research articles, patents, persons) according to a relatively small set of categories. Trans4E was applied on two large-scale knowledge graphs, the Academia/Industry DynAmics (AIDA) and Microsoft Academic Graph (MAG), for completing the information about Fields of Study (e.g., 'neural networks', 'machine learning', 'artificial intelligence'), and affiliation types (e.g., 'education', 'company', 'government'), improving the scope and accuracy of the resulting data. We evaluated our approach against alternative solutions on AIDA, MAG, and four other benchmarks (FB15k, FB15k-237, WN18, and WN18RR). Trans4E outperforms the other models when using low embedding dimensions and obtains competitive results in high dimensions.
References in corpus (13)
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- Graph Embedding Techniques, Applications, and Performance: A Survey
- A Review of Relational Machine Learning for Knowledge Graphs
- Graph Neural Networks: A Review of Methods and Applications
- Generalizing from a Few Examples: A Survey on Few-Shot Learning
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- Quaternion Knowledge Graph Embeddings
- OpenCitations, an infrastructure organization for open scholarship
- Meta-learning for Few-shot Natural Language Processing: A Survey
- Learning from Few Samples: A Survey
- Meta-Graph: Few Shot Link Prediction via Meta Learning
- A Survey on Graph Neural Networks for Knowledge Graph Completion
- Exploring Scholarly Data by Semantic Query on Knowledge Graph Embedding Space