重新利用过时表示以进行部署后适应

中文摘要 AI 辅助

深度神经网络越来越多地部署在长期运行的系统中，在这些系统中，任务需求可能在训练后发生变化。在这种情况下，原始输出空间的一部分可能变得过时：某个类别、预测区域或学习到的行为可能不再有效。现有方法要么保留过时行为不变，要么需要微调，而微调可能代价高昂。我们提出了深度重新利用（Deep Repurposing, DR），这是一种用于在任务过时情况下适应模型的事后框架。DR估计过时区域和保留区域的潜在几何结构，移除支持过时的组件，并通过解析修复映射（analytic repair map）重新分配与保留区域兼容的证据，而无需梯度更新。这产生了修复后的预测和表示，其中过时区域不再作为有效输出，而有用的过时结构可以支持保留任务。在多种任务设置中，DR移除了过时行为，同时保留了保留任务的效用。更重要的是，在多个分类基准上，DR在保留准确率方面达到或超过了竞争性的机器遗忘（unlearning）和编辑（editing）基线，消除了过时预测，并且适应速度比竞争性的机器遗忘方法快高达60倍。

英文摘要

Deep neural networks are increasingly deployed in long-lived systems, where task requirements may change after training. In such settings, part of the original output space may become obsolete: a class, prediction region, or learned behaviour may no longer be valid. Existing approaches either leave the obsolete behaviour intact or require fine-tuning, which can be expensive. We propose Deep Repurposing (DR), a post-hoc framework for adapting models under task obsolescence. DR estimates the latent geometry of obsolete and retained regions, removes obsolete-supporting components, and reallocates retained-compatible evidence through an analytic repair map without gradient updates. This yields repaired predictions and representations in which obsolete regions no longer act as valid outputs, while useful obsolete structure can support the retained task. Across multiple task settings, DR removes obsolete behaviour while preserving retained utility. More importantly, across classification benchmarks, DR matches or exceeds competing unlearning and editing baselines in retained accuracy, eliminates obsolete predictions, and adapts up to $60\times$ faster than competing unlearning methods.

发表机构

• University of York（约克大学）
• Cyprus University of Technology（塞浦路斯理工大学）

机构由 AI 辅助整理，请以论文原文为准。