BID-LoRA：一种用于持续学习和去学习的参数高效框架
BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning
AI总结：
本文提出BID-LoRA框架，通过双向低秩适应和逃逸去学习技术，解决持续学习与去学习中的知识泄露问题，实验表明其在多个适应周期中优于基线方法。
摘要：
近期深度学习的进展凸显出需要能够通过持续学习（CL）获取新知识，并通过机器去学习（MU）移除过时、敏感或私有信息的系统。然而，尽管CL方法已较为成熟，MU技术仍处于早期阶段，导致依赖两者能力的统一框架存在关键差距。我们发现，简单结合现有CL和MU方法会导致知识泄露和基础知识的逐步退化。为此，我们正式将持续学习去学习（CLU）作为统一范式，提出三个关键目标：（i）精确删除不需要的知识，（ii）高效整合新知识的同时保留先前信息，（iii）最小化周期间的知识泄露。我们提出双向低秩适应（BID-LoRA），一种新型框架，包含三个专用适配路径——保留、新、去学习，应用于注意力层，并结合逃逸去学习技术，将忘记类嵌入推至与保留知识最远的位置，仅更新5%的参数。实验表明，BID-LoRA在CIFAR-100上优于CLU基线方法。我们进一步在CASIA-Face100上评估，展示其在现实身份管理系统中的实用性，其中新用户需注册，旧用户需移除。
英文摘要：
Recent advances in deep learning underscore the need for systems that can not only acquire new knowledge through Continual Learning (CL) but also remove outdated, sensitive, or private information through Machine Unlearning (MU). However, while CL methods are well-developed, MU techniques remain in early stages, creating a critical gap for unified frameworks that depend on both capabilities. We find that naively combining existing CL and MU approaches results in knowledge leakage a gradual degradation of foundational knowledge across repeated adaptation cycles. To address this, we formalize Continual Learning Unlearning (CLU) as a unified paradigm with three key goals: (i) precise deletion of unwanted knowledge, (ii) efficient integration of new knowledge while preserving prior information, and (iii) minimizing knowledge leakage across cycles. We propose Bi-Directional Low-Rank Adaptation (BID-LoRA), a novel framework featuring three dedicated adapter pathways-retain, new, and unlearn applied to attention layers, combined with escape unlearning that pushes forget-class embeddings to positions maximally distant from retained knowledge, updating only 5% of parameters. Experiments on CIFAR-100 show that BID-LoRA outperforms CLU baselines across multiple adaptation cycles. We further evaluate on CASIA-Face100, a curated face recognition subset, demonstrating practical applicability to real-world identity management systems where new users must be enrolled and withdrawn users removed.
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。
