A Survey on Graph Neural Networks for Knowledge Graph Completion
arXiv:2007.12374
Abstract
Knowledge Graphs are increasingly becoming popular for a variety of downstream tasks like Question Answering and Information Retrieval. However, the Knowledge Graphs are often incomplete, thus leading to poor performance. As a result, there has been a lot of interest in the task of Knowledge Base Completion. More recently, Graph Neural Networks have been used to capture structural information inherently stored in these Knowledge Graphs and have been shown to achieve SOTA performance across a variety of datasets. In this survey, we understand the various strengths and weaknesses of the proposed methodology and try to find new exciting research problems in this area that require further investigation.
10 pages, 2 figures
References in corpus (8)
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- The Consciousness Prior
- TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
- Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering
- Efficient Probabilistic Logic Reasoning with Graph Neural Networks
Cited by in corpus (5)
- Trans4E: Link Prediction on Scholarly Knowledge Graphs
- Graph neural network-based fault diagnosis: a review
- Cell Complex Neural Networks
- Analyzing the Performance of Graph Neural Networks with Pipe Parallelism
- Is There More Pattern in Knowledge Graph? Exploring Proximity Pattern for Knowledge Graph Embedding