arXiv 2410.039552025-04-19cs.LGcs.AImath.OCstat.ML

面向持续学习的以保留为中心框架，确保模型发展安全性

A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety

Department of Computer Science & Engineering, Texas A&M University, College Station, USA（德克萨斯A&M大学计算机科学与工程系）；Department of Mathematics, The University of Iowa, Iowa City, USA（爱荷华大学数学系）；Global Research and Development, General Motors, Warren, USA（通用汽车全球研发）；Department of Electrical and Computer Engineering, The Ohio State University, Columbus, UAS（俄亥俄州立大学电气与计算机工程系）；Tippie College of Business, The University of Iowa, Iowa City, USA（爱荷华大学蒂皮学院）

Gang Li, Wendi Yu, Yao Yao, Wei Tong, Yingbin Liang, Qihang Lin, Tianbao Yang

备注：: 44 pages, 7 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一个以保留为中心的持续学习框架，通过数据依赖约束和高效优化算法，确保新模型在提升目标任务性能时严格保留旧模型的重要能力，防止灾难性遗忘，并在自动驾驶和场景识别数据集上验证了有效性。

摘要：

在现实世界应用中，学习型系统通常经历迭代式模型开发以应对具有挑战性或新兴的任务，这涉及收集新数据、训练新模型和验证模型。这一持续的模型开发过程引发了一个重要问题：获取新能力或改进现有能力可能会无意中丢失旧模型的良好能力，这被称为灾难性遗忘。虽然现有的持续学习旨在通过权衡先前任务和新任务的性能来缓解灾难性遗忘，以确保良好的平均性能，但在成本敏感的应用中，它往往表现不足，因为未能保留基本既定能力会引入不可预见的成本和风险，以及重新改进这些能力的巨大开销。为了解决这个问题，我们对学习系统施加了一个要求，以确保新模型在提高目标任务性能的同时严格保留旧模型的重要能力，我们称之为模型发展安全性。为了确保模型发展安全性，我们提出了一个具有数据依赖约束的以保留为中心的框架，并研究了如何持续开发预训练的CLIP模型以获取新的或改进现有的图像分类能力。我们提出了一种具有理论保证的高效约束优化算法，并利用其见解对带有任务相关头的CLIP模型进行微调，以促进模型发展安全性。在自动驾驶和场景识别数据集上的实验验证了我们方法的有效性。

英文摘要：

In real-world applications, learning-enabled systems often undergo iterative model development to address challenging or emerging tasks, which involve collecting new data, training a new model and validating the model. This continual model development process raises a significant issue that acquiring new or improving existing capabilities may inadvertently lose good capabilities of the old model, also known as catastrophic forgetting. While existing continual learning aims to mitigate catastrophic forgetting by trading off performance on previous tasks and new tasks to ensure good average performance, it often falls short in cost-sensitive applications, where failing to preserve essential established capabilities introduces unforeseen costs and risks and substantial expenses for re-improving these capabilities. To address this issue, we impose a requirement on learning systems to ensure that a new model strictly retains important capabilities of the old model while improving target-task performance, which we term model developmental safety. To ensure model developmental safety, we propose a retention-centric framework with data-dependent constraints, and study how to continually develop a pretrained CLIP model for acquiring new or improving existing capabilities of image classification. We propose an efficient constrained optimization algorithm with theoretical guarantees and use its insights to finetune the CLIP model with task-dependent heads for promoting the model developmental safety. Experiments on autonomous driving and scene recognition datasets validate the efficacy of our method.

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。