arXiv：cs.LG（机器学习，全量分类）· Daniel Bethell, Charmaine Barker, Simos Gerasimou·· 14 小时前AI 评分32
Deep Repurposing：面向部署后任务过时的模型适配框架
Repurposing Obsolete Representations for Post-Deployment Adaptation
AI 导读
研究者提出 Deep Repurposing（DR），一种无需梯度更新的后处理框架，用于在任务需求变化、原有输出空间部分失效时适配模型。DR 通过估计过时与保留区域的潜在几何结构，移除支持过时行为的组件，并用解析修复映射重新分配兼容证据，从而消除过时预测。
正文
Abstract: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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.01453 [cs.LG] |
| (or arXiv:2610.01453v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01453 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Charmaine Barker [view email]
[v1]
Thu, 1 Oct 2026 10:48:58 UTC (24,091 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org