双曲空间与欧几里得空间多模态对比学习中的机器遗忘：将对齐校准适配到MERU
Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
AI总结：
本文研究双曲对比学习中的机器遗忘，通过将对齐校准适配到双曲多模态模型MERU，证明双曲几何在概念移除上的优势，揭示其与欧几里得模型遗忘动态的差异，推进机器遗忘技术并提供几何特性对概念表示的见解。
摘要：
机器遗忘方法对于大型预训练模型中的选择性概念移除变得日益重要。尽管近期研究探索了欧几里得对比视觉语言模型中的遗忘，但双曲空间中概念移除的有效性仍未被研究。本文通过将对齐校准适配到MERU（一种将图像和文本嵌入双曲空间以更好捕捉语义层次的模型），研究了双曲对比学习中的机器遗忘。通过系统实验和消融研究，我们证明双曲几何为概念移除提供了显著优势，在保留概念上实现了近乎完美的遗忘且性能合理，尤其是在扩展到多概念移除时。我们的方法引入了双曲特定组件，包括利用双曲空间独特性质的蕴含校准和范数正则化。与欧几里得模型的对比分析揭示了遗忘动态的根本差异：双曲遗忘会重组语义层次，而欧几里得方法仅断开跨模态关联。这些发现不仅推进了机器遗忘技术，还为影响多模态模型中概念表示和移除的几何特性提供了见解。源代码可在https://github.com/alex-pv01/HAC获取
英文摘要：
Machine unlearning methods have become increasingly important for selective concept removal in large pre-trained models. While recent work has explored unlearning in Euclidean contrastive vision-language models, the effectiveness of concept removal in hyperbolic spaces remains unexplored. This paper investigates machine unlearning in hyperbolic contrastive learning by adapting Alignment Calibration to MERU, a model that embeds images and text in hyperbolic space to better capture semantic hierarchies. Through systematic experiments and ablation studies, we demonstrate that hyperbolic geometry offers distinct advantages for concept removal, achieving near perfect forgetting with reasonable performance on retained concepts, particularly when scaling to multiple concept removal. Our approach introduces hyperbolic-specific components including entailment calibration and norm regularization that leverage the unique properties of hyperbolic space. Comparative analysis with Euclidean models reveals fundamental differences in unlearning dynamics, with hyperbolic unlearning reorganizing the semantic hierarchy while Euclidean approaches merely disconnect cross-modal associations. These findings not only advance machine unlearning techniques but also provide insights into the geometric properties that influence concept representation and removal in multimodal models. Source code available at https://github.com/alex-pv01/HAC
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
