双曲多模态持续学习
Hyperbolic Multimodal Continual Learning
浏览论文内容
中文总结 AI 辅助
本研究针对双曲多模态持续学习的遗忘问题，建立理论基础推导了保留几何结构的持续学习框架，经实验验证其有效性。
中文摘要 AI 辅助
双曲几何近来成为多模态学习的强大表示空间，因其能自然捕捉跨模态的层级语义结构。尽管取得了这一进展，但此类表示在持续学习中的表现面临着未被充分探索的根本不同挑战。本研究从几何视角探讨该问题，为双曲空间中的表示保留建立了理论基础，表明防止遗忘需要共享双曲等距变换下的跨模态不变性。我们进一步表明，双曲持续学习中的遗忘涉及语义关系漂移和层级相关的失真，这促使保留跨模态关系结构和层级几何。基于这些见解，推导了一个原则性的持续学习框架，该框架在保留必要几何结构的同时，允许有效适应新任务。在持续多模态基准上的实验证实了所提方法的有效性。
英文摘要
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. We further show that forgetting in hyperbolic continual learning involves both semantic relation drift and hierarchy-related distortion, motivating preservation of both cross-modal relational structure and hierarchical geometry. 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.
发表机构
- The Chinese University of Hong Kong（香港中文大学）
- National University of Singapore（新加坡国立大学）
- Yale University（耶鲁大学）
- The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。
