CATA: 通过冲突厌恶任务算术实现持续机器去学习
CATA: Continual Machine Unlearning via Conflict-Averse Task Arithmetic
AI总结：
本文首次研究了视觉语言模型的持续去学习问题，提出CATA方法，通过冲突厌恶任务算术有效解决去学习中的有效性、模型保真度和持续性挑战。
摘要：
视觉语言模型（VLMs）在对齐视觉和文本表示方面表现出色，能够支持多种多模态应用。然而，其大规模训练数据不可避免地引发了隐私、版权和不良内容的担忧，这使得机器去学习变得必要。尽管现有研究主要关注单次去学习，但实际VLM部署往往涉及随时间推移的连续删除请求，从而产生持续机器去学习。在本文中，我们首次研究了VLMs的持续去学习，并识别出该设置中的三个关键挑战：去除目标知识的有效性、保留模型效用的保真度以及在连续更新下防止知识重新出现的持续性。为了解决这些挑战，我们提出了CATA，一种冲突厌恶任务算术方法，将每个遗忘请求表示为一个去学习任务向量。通过维护历史任务向量并执行符号感知的冲突厌恶聚合，CATA抑制可能削弱先前遗忘效果的冲突更新组件。在单次和持续设置下的大量实验表明，CATA在遗忘有效性、模型保真度和遗忘持续性方面均优于基线方法。
英文摘要：
Vision-language models (VLMs) have shown remarkable ability in aligning visual and textual representations, enabling a wide range of multimodal applications. However, their large-scale training data inevitably raises concerns about privacy, copyright, and undesirable content, creating a strong need for machine unlearning. While existing studies mainly focus on single-shot unlearning, practical VLM deployment often involves sequential removal requests over time, giving rise to continual machine unlearning. In this work, we make the first attempt to study continual unlearning for VLMs and identify three key challenges in this setting: effectiveness in removing target knowledge, fidelity in preserving retained model utility, and persistence in preventing knowledge re-emergence under sequential updates. To address these challenges, we propose CATA, a conflict-averse task arithmetic method that represents each forget request as an unlearning task vector. By maintaining historical task vectors and performing sign-aware conflict-averse aggregation, CATA suppresses conflicting update components that may weaken previous forgetting effects. Extensive experiments under both single-shot and continual settings show that CATA outperforms baselines in terms of forgetting effectiveness, model fidelity, and forgetting persistence.
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。
