LEGATO: 优良的身份遗忘是连续的
LEGATO: Good Identity Unlearning Is Continuous
AI总结：
LEGATO通过连续轨迹建模实现生成模型的身份遗忘，采用轻量级神经ODE适配器实现可控且稳定的遗忘过程，避免灾难性崩溃并提升性能。
摘要：
生成模型在大规模数据集上训练后，去敏感、隐私或受版权保护的数据已成为关键。然而，现有的机器遗忘方法在学习生成模型的身份遗忘时面临三个挑战：1）低效，身份擦除需要微调所有模型参数；2）可控性有限，遗忘强度无法控制且缺乏可解释性；3）灾难性崩溃，随着遗忘进程的推进，模型的保留能力急剧下降。遗忘通常通过离散且不稳定的更新来处理，通常需要全模型微调，导致灾难性崩溃。在本文中，我们主张身份遗忘应建模为连续轨迹，并引入LEGATO - 通过轨迹一致的神经普通微分方程学习生成模型的身份遗忘。LEGATO在预训练生成器中添加可微调的轻量级神经ODE适配器，使遗忘过程平滑且可控，同时保持原始模型权重冻结。这种形式允许通过ODE步长精确调节遗忘强度，提供可解释性和鲁棒性。为进一步确保稳定性，我们引入轨迹一致性约束，明确防止在去学习过程中发生灾难性崩溃。在域内和域外身份去学习基准上的广泛实验表明，LEGATO实现了最先进的遗忘性能，避免了灾难性崩溃并减少了微调参数。
英文摘要：
Machine unlearning has become a crucial role in enabling generative models trained on large datasets to remove sensitive, private, or copyright-protected data. However, existing machine unlearning methods face three challenges in learning to forget identity of generative models: 1) inefficient, where identity erasure requires fine-tuning all the model's parameters; 2) limited controllability, where forgetting intensity cannot be controlled and explainability is lacking; 3) catastrophic collapse, where the model's retention capability undergoes drastic degradation as forgetting progresses. Forgetting has typically been handled through discrete and unstable updates, often requiring full-model fine-tuning and leading to catastrophic collapse. In this work, we argue that identity forgetting should be modeled as a continuous trajectory, and introduce LEGATO - Learn to ForgEt Identity in GenerAtive Models via Trajectory-consistent Neural Ordinary Differential Equations. LEGATO augments pre-trained generators with fine-tunable lightweight Neural ODE adapters, enabling smooth, controllable forgetting while keeping the original model weights frozen. This formulation allows forgetting intensity to be precisely modulated via ODE step size, offering interpretability and robustness. To further ensure stability, we introduce trajectory consistency constraints that explicitly prevent catastrophic collapse during unlearning. Extensive experiments across in-domain and out-of-domain identity unlearning benchmarks show that LEGATO achieves state-of-the-art forgetting performance, avoids catastrophic collapse and reduces fine-tuned parameters.
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。
