论文标题
通过全球伪任务模拟导航记忆构建，以持续学习
Navigating Memory Construction by Global Pseudo-Task Simulation for Continual Learning
论文作者
论文摘要
持续学习面临着灾难性遗忘的关键挑战。为了应对这一挑战，经验重播（ER）通常使用了以前任务中的一小部分样本。现有的ER工作通常专注于通过静态内存构建政策来完善每个任务的学习目标。在本文中，我们将ER中的动态内存构造作为组合优化问题，旨在直接最大程度地减少所有经验丰富的任务的全球损失。我们首先采用三种策略来解决离线设置中的问题作为起点。为了在在线持续学习环境中为此问题提供大概的解决方案，我们进一步提出了全球伪任务模拟（GPS），该模拟模仿未来的灾难性灾难性忘记了当前的任务。我们的经验结果和分析表明，GP始终提高四个常用视力基准的精度。我们还表明，我们的全科医生可以作为在现有ER工作中整合各种内存构建政策的统一框架。
Continual learning faces a crucial challenge of catastrophic forgetting. To address this challenge, experience replay (ER) that maintains a tiny subset of samples from previous tasks has been commonly used. Existing ER works usually focus on refining the learning objective for each task with a static memory construction policy. In this paper, we formulate the dynamic memory construction in ER as a combinatorial optimization problem, which aims at directly minimizing the global loss across all experienced tasks. We first apply three tactics to solve the problem in the offline setting as a starting point. To provide an approximate solution to this problem in the online continual learning setting, we further propose the Global Pseudo-task Simulation (GPS), which mimics future catastrophic forgetting of the current task by permutation. Our empirical results and analyses suggest that the GPS consistently improves accuracy across four commonly used vision benchmarks. We have also shown that our GPS can serve as the unified framework for integrating various memory construction policies in existing ER works.
