Disentangle-based Continual Graph Representation Learning

Abstract

Graph embedding (GE) methods embed nodes (and/or edges) in graph into a low-dimensional semantic space, and have shown its effectiveness in modeling multi-relational data. However, existing GE models are not practical in real-world applications since it overlooked the streaming nature of incoming data. To address this issue, we study the problem of continual graph representation learning which aims to continually train a GE model on new data to learn incessantly emerging multi-relational data while avoiding catastrophically forgetting old learned knowledge. Moreover, we propose a disentangle-based continual graph representation learning (DiCGRL) framework inspired by the human's ability to learn procedural knowledge. The experimental results show that DiCGRL could effectively alleviate the catastrophic forgetting problem and outperform state-of-the-art continual learning models.

References in corpus (7)

• Overcoming catastrophic forgetting in neural networks
• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Deep Convolutional Networks on Graph-Structured Data
• Continual Learning Through Synaptic Intelligence
• A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Efficient Lifelong Learning with A-GEM