重新思考机器遗忘：为遗忘而设计的模型
Models Designed to Forget: Machine Unlearning via Key Deletion
AI总结：
本文提出了一种新的机器遗忘方法，通过设计使模型具备遗忘能力。MUNKEY模型通过删除实例标识符实现直接零样本遗忘，无需权重更新或原始数据访问，在多个数据集上优于现有方法。
摘要：
机器遗忘正迅速成为实际需求，受隐私法规、数据错误和去除有害或损坏的训练样本的驱动。尽管如此，大多数现有方法仅从事后角度处理该问题。它们通过参数更新尝试消除目标训练样本的影响，通常需要访问完整训练数据。这与实际部署场景中可预见的遗忘请求不匹配，揭示了事后方法的根本局限性。我们提出遗忘由设计，一种新的范式，其中模型直接训练以支持遗忘作为固有能力。我们通过机器遗忘通过键删除（MUNKEY）实现这一想法，一种内存增强的Transformer，将实例特定的记忆与模型权重解耦。在此，遗忘对应于删除实例标识符的键，使直接零样本遗忘无需权重更新或原始样本或标签的访问。在自然图像基准、细粒度识别和医学数据集上，MUNKEY优于所有事后基线。我们的结果证明，遗忘由设计能够实现快速、面向部署的遗忘，同时保持预测性能。
英文摘要：
Machine unlearning for vision models is rapidly becoming a practical requirement, driven by privacy regulations, data errors, and the need to remove harmful or corrupted training images. Despite this, most existing approximate unlearning methods tackle the problem from a post-hoc perspective. They attempt to erase the influence of targeted samples through parameter updates that typically require access to the full training data. This creates a mismatch with real deployment scenarios where unlearning requests can be anticipated, revealing a fundamental limitation of post-hoc approaches. We motivate unlearning by design, a novel paradigm for approximate methods in which models are directly trained to support forgetting as an inherent architectural capability. We instantiate this idea with Machine UNlearning via KEY deletion (MUNKEY), a memory-augmented transformer that decouples instance-specific memorization from model weights. Here, unlearning corresponds to removing the instance-identifying key, enabling zero-shot forgetting without weight updates or access to the original samples or labels. Across natural image benchmarks, fine-grained visual recognition, and medical datasets, MUNKEY outperforms all post-hoc baselines. Our results establish that unlearning by design enables fast, deployment-oriented unlearning while preserving predictive performance.
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。
