Disentangle-based continual graph representation learning

12Citations
Citations of this article
101Readers
Mendeley users who have this article in their library.

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. The code and datasets are released on https://github.com/KXY-PUBLIC/DiCGRL.

Cite

CITATION STYLE

APA

Kou, X., Lin, Y., Liu, S., Li, P., Zhou, J., & Zhang, Y. (2020). Disentangle-based continual graph representation learning. In EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 2961–2972). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2020.emnlp-main.237

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free