The principle underlying most existing continual learning (CL) methods is to
prioritize stability by penalizing changes in parameters crucial to old tasks,
while allowing for plasticity in other parameters. The importance of weights
for each task can be determined either explicitly through learning a
task-specific mask during training (e.g., parameter isolation-based approaches)
or implicitly by introducing a regularization term (e.g., regularization-based
approaches). However, all these methods assume that the importance of weights
for each task is unknown prior to data exposure. In this paper, we propose
ScrollNet as a scrolling neural network for continual learning. ScrollNet can
be seen as a dynamic network that assigns the ranking of weight importance for
each task before data exposure, thus achieving a more favorable
stability-plasticity tradeoff during sequential task learning by reassigning
this ranking for different tasks. Additionally, we demonstrate that ScrollNet
can be combined with various CL methods, including regularization-based and
replay-based approaches. Experimental results on CIFAR100 and TinyImagenet
datasets show the effectiveness of our proposed method. We release our code at
this https URL

ScrollNet 是一种滚动神经网络，通过在数据曝光之前为每个任务分配权重重要性排名，从而实现序贯任务学习中更有利的稳定性和可塑性权衡。我们的实验结果表明 ScrollNet 与各种持续学习方法的结合方法是有效的。

ScrollNet：动态权重重要性的持续学习

ScrollNet: Dynamic Weight Importance for Continual Learning

Class-incremental learning (CIL) aims to train a classification model while
the number of classes increases phase-by-phase. An inherent challenge of CIL is
the stability-plasticity tradeoff, i.e., CIL models should keep stable to
retain old knowledge and keep plastic to absorb new knowledge. However, none of
the existing CIL models can achieve the optimal tradeoff in different
data-receiving settings--where typically the training-from-half (TFH) setting
needs more stability, but the training-from-scratch (TFS) needs more
plasticity. To this end, we design an online learning method that can
adaptively optimize the tradeoff without knowing the setting as a priori.
Specifically, we first introduce the key hyperparameters that influence the
trade-off, e.g., knowledge distillation (KD) loss weights, learning rates, and
classifier types. Then, we formulate the hyperparameter optimization process as
an online Markov Decision Process (MDP) problem and propose a specific
algorithm to solve it. We apply local estimated rewards and a classic bandit
algorithm Exp3 [4] to address the issues when applying online MDP methods to
the CIL protocol. Our method consistently improves top-performing CIL methods
in both TFH and TFS settings, e.g., boosting the average accuracy of TFH and
TFS by 2.2 percentage points on ImageNet-Full, compared to the state-of-the-art
[23].

该研究设计了一种在线学习方法，可以自适应地优化稳定性 - 可塑性权衡，具有优异的性能表现。