Hyperbolic Multimodal Continual Learning
Jiahong Liu, Ming Shen, Xiaohao Liu, ZHITAO YING, Menglin Yang, Tat-Seng Chua, Irwin King
Abstract
Hyperbolic geometry has recently emerged as a powerful representation space for multimodal learning, as it naturally captures hierarchical semantic structure across modalities. Despite this progress, how such representations behave under continual learning poses fundamentally different challenges that remain underexplored. This work provides a geometric perspective on this problem and establishes a theoretical foundation for representation preservation in hyperbolic space, showing that preventing forgetting requires cross-modal invariance under a shared hyperbolic isometry. Guided by these insights, a principled continual learning framework is derived that preserves essential geometric structure while allowing effective adaptation to new tasks. Experiments on continual multimodal benchmarks corroborate the effectiveness of the proposed approach.
BibTeX
@inproceedings{
liu2026hyperbolic,
title={Hyperbolic Multimodal Continual Learning},
author={Jiahong Liu and Ming Shen and Xiaohao Liu and Rex Ying and Menglin Yang and Tat-Seng Chua and Irwin King},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=e4tSzgWjXU}
}