TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction

Abstract

Link prediction is an important and frequently studied task that contributes to an understanding of the structure of knowledge graphs (KGs) in statistical relational learning. Inspired by the success of graph convolutional networks (GCN) in modeling graph data, we propose a unified GCN framework, named TransGCN, to address this task, in which relation and entity embeddings are learned simultaneously. To handle heterogeneous relations in KGs, we introduce a novel way of representing heterogeneous neighborhood by introducing transformation assumptions on the relationship between the subject, the relation, and the object of a triple. Specifically, a relation is treated as a transformation operator transforming a head entity to a tail entity. Both translation assumption in TransE and rotation assumption in RotatE are explored in our framework. Additionally, instead of only learning entity embeddings in the convolution-based encoder while learning relation embeddings in the decoder as done by the state-of-art models, e.g., R-GCN, the TransGCN framework trains relation embeddings and entity embeddings simultaneously during the graph convolution operation, thus having fewer parameters compared with R-GCN. Experiments show that our models outperform the-state-of-arts methods on both FB15K-237 and WN18RR.

References in corpus (12)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Complex Embeddings for Simple Link Prediction
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Large-Scale Learnable Graph Convolutional Networks
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Adaptive Graph Convolutional Neural Networks
• Modeling Relation Paths for Representation Learning of Knowledge Bases

Cited by in corpus (9)

• A Review of Location Encoding for GeoAI: Methods and Applications
• A Review of Knowledge Graph Completion
• SE-KGE: A Location-Aware Knowledge Graph Embedding Model for Geographic Question Answering and Spatial Semantic Lifting
• A Survey on Graph Neural Networks for Knowledge Graph Completion
• Knowledge Embedding Based Graph Convolutional Network
• Effective Model Integration Algorithm for Improving Link and Sign Prediction in Complex Networks
• Narrative Cartography with Knowledge Graphs
• Network Representation Learning: From Traditional Feature Learning to Deep Learning
• Towards Fast Evaluation of Unsupervised Link Prediction by Random Sampling Unobserved Links