加权集成模型是强大的持续学习器
Weighted Ensemble Models Are Strong Continual Learners
AI总结：
针对持续学习的稳定性-可塑性权衡问题，提出持续模型平均CoMA及其费希尔信息加权改进版CoFiMA，通过模型参数加权集成实现新老任务性能平衡，在多个基准上达SOTA。
摘要：
在本研究中，我们探讨持续学习（continual learning, CL）问题，其目标是在一系列任务上学习模型，使得在学习当前任务数据时，先前任务的数据不再可用。持续学习本质上是在新任务学习能力（即可塑性）与已学概念性能维持能力（即稳定性）之间的平衡。为解决稳定性-可塑性权衡问题，我们提出对先前任务与当前任务的模型参数进行加权集成。这种加权集成模型被我们称为持续模型平均（Continual Model Averaging, CoMA），它通过利用可塑性在当前任务上取得高精度，同时不会与先前的权重配置偏离过远，从而保障稳定性。我们还提出了CoMA的改进变体，名为持续费希尔加权模型平均（Continual Fisher-weighted Model Averaging, CoFiMA），该变体利用模型权重的费希尔信息对权重集成中的每个参数进行选择性加权。两种变体在概念上都很简单，易于实现，并且在多个标准持续学习基准上取得了当前最优性能。代码可在以下链接获取：https://github.com/IemProg/CoFiMA。
英文摘要：
In this work, we study the problem of continual learning (CL) where the goal is to learn a model on a sequence of tasks, such that the data from the previous tasks becomes unavailable while learning on the current task data. CL is essentially a balancing act between being able to learn on the new task (i.e., plasticity) and maintaining the performance on the previously learned concepts (i.e., stability). Intending to address the stability-plasticity trade-off, we propose to perform weight-ensembling of the model parameters of the previous and current tasks. This weighted-ensembled model, which we call Continual Model Averaging (or CoMA), attains high accuracy on the current task by leveraging plasticity, while not deviating too far from the previous weight configuration, ensuring stability. We also propose an improved variant of CoMA, named Continual Fisher-weighted Model Averaging (or CoFiMA), that selectively weighs each parameter in the weights ensemble by leveraging the Fisher information of the weights of the model. Both variants are conceptually simple, easy to implement, and effective in attaining state-of-the-art performance on several standard CL benchmarks. Code is available at: https://github.com/IemProg/CoFiMA.
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。
