Disentangle-based Continual Graph Representation Learning
This addresses the practical limitation of graph embedding methods for real-world applications with incremental data, though it appears incremental as it builds on existing continual learning approaches.
The paper tackles the problem of catastrophic forgetting in graph embedding models when learning from streaming data, proposing a disentangle-based continual learning framework that outperforms state-of-the-art methods in alleviating this issue.
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.