2025-01-14-song25a.md

title	Orchestrating Plasticity and Stability: A Continual Knowledge Graph Embedding Framework with Bio-Inspired Dual-Mask Mechanism
booktitle	Proceedings of the 16th Asian Conference on Machine Learning
year	2025
volume	260
series	Proceedings of Machine Learning Research
month	0
publisher	PMLR
pdf	https://raw.githubusercontent.com/mlresearch/v260/main/assets/song25a/song25a.pdf
url	https://proceedings.mlr.press/v260/song25a.html
openreview	4itGZJzpLY
abstract	Learning in biological systems involves the intricate modeling of diverse entities and their interrelations, leading to the evolution of logical knowledge networks with accumulating experience. Analogously, knowledge graphs serve as semantic representations of entity relationships, playing a vital role in natural language processing and graph representation learning. However, contemporary knowledge graph embedding models often neglect real-world event updates, while existing continual knowledge graph research predominantly relies on conventional learning methods that inadequately leverage graph structure, thereby compromising their continual learning capabilities. This study introduces a novel Continual Mask Knowledge Graph Embedding framework (CMKGE), designed to address these limitations. CMKGE integrates semantic attributes, network structure, and continual learning mechanisms to capture the dynamic evolution of knowledge. Inspired by biological signal propagation and Dale’s principle, we introduce a dual-mask mechanism for neuronal inhibition and activation. This mechanism automatically filters critical old knowledge, enhancing model plasticity and stability. Through comprehensive evaluations on four datasets, we demonstrate CMKGE’s superiority over state-of-the-art continual embedding models.
layout	inproceedings
issn	2640-3498
id	song25a
tex_title	{Orchestrating Plasticity and Stability}: {A} Continual Knowledge Graph Embedding Framework with Bio-Inspired Dual-Mask Mechanism
firstpage	1208
lastpage	1223
page	1208-1223
order	1208
cycles	false
bibtex_editor	Nguyen, Vu and Lin, Hsuan-Tien
editor	given family Vu Nguyen given family Hsuan-Tien Lin
bibtex_author	Song, Ailin and Chen, Yuhong and Wang, Yusong and Zhong, Shuai and Xu, Mingkun
author	given family Ailin Song given family Yuhong Chen given family Yusong Wang given family Shuai Zhong given family Mingkun Xu
date	2025-01-14
address
container-title	Proceedings of the 16th Asian Conference on Machine Learning
genre	inproceedings
issued	date-parts 2025 1 14
extras