选择性遗忘：深度生成模型中基于持续学习的遗忘方法
Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models
AI总结：
针对文本到图像模型可能被滥用以生成有害内容的问题，提出基于持续学习的“选择性遗忘”方法，实现可控遗忘，可应用于变分自编码器和扩散模型，实验证明能有效遗忘多种概念。
摘要：
近年来，大规模文本到图像模型的普及引发了越来越多的担忧，即这些模型可能被滥用，以生成有害、误导性和不适当的内容。受此问题驱动，我们提出了一种受持续学习启发的技术，用于在预训练的深度生成模型中选择性地遗忘概念。我们的方法名为“选择性遗忘”（Selective Amnesia），实现了可控的遗忘，用户可指定概念应如何被遗忘。选择性遗忘可应用于条件变分似然模型，这类模型涵盖多种流行的深度生成框架，包括变分自编码器和大规模文本到图像扩散模型。跨不同模型的实验表明，我们的方法能诱导对多种概念的遗忘，从标准数据集中的整个类别到文本到图像模型中的名人和裸体提示。我们的代码公开于 https://github.com/clear-nus/selective-amnesia。
英文摘要：
The recent proliferation of large-scale text-to-image models has led to growing concerns that such models may be misused to generate harmful, misleading, and inappropriate content. Motivated by this issue, we derive a technique inspired by continual learning to selectively forget concepts in pretrained deep generative models. Our method, dubbed Selective Amnesia, enables controllable forgetting where a user can specify how a concept should be forgotten. Selective Amnesia can be applied to conditional variational likelihood models, which encompass a variety of popular deep generative frameworks, including variational autoencoders and large-scale text-to-image diffusion models. Experiments across different models demonstrate that our approach induces forgetting on a variety of concepts, from entire classes in standard datasets to celebrity and nudity prompts in text-to-image models. Our code is publicly available at https://github.com/clear-nus/selective-amnesia.
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。
