Continual learning (CL) has remained a persistent challenge for deep neural
networks due to catastrophic forgetting (CF) of previously learned tasks.
Several techniques such as weight regularization, experience rehearsal, and
parameter isolation have been proposed to alleviate CF. Despite their relative
success, these research directions have predominantly remained orthogonal and
suffer from several shortcomings, while missing out on the advantages of
competing strategies. On the contrary, the brain continually learns,
accommodates, and transfers knowledge across tasks by simultaneously leveraging
several neurophysiological processes, including neurogenesis, active
forgetting, neuromodulation, metaplasticity, experience rehearsal, and
context-dependent gating, rarely resulting in CF. Inspired by how the brain
exploits multiple mechanisms concurrently, we propose TriRE, a novel CL
paradigm that encompasses retaining the most prominent neurons for each task,
revising and solidifying the extracted knowledge of current and past tasks, and
actively promoting less active neurons for subsequent tasks through rewinding
and relearning. Across CL settings, TriRE significantly reduces task
interference and surpasses different CL approaches considered in isolation.

借鉴大脑同时利用多种机制的方式，我们提出了 TriRE，一种新的持续学习范式，它包括保留每个任务最突出的神经元，修订和巩固当前和过去任务的提取知识，以及通过回溯和重新学习促进次要活跃神经元用于后续任务。在持续学习设置中，TriRE 显著减少了任务干扰，并超过了考虑独立评估的不同持续学习方法。

TriRE: 持续知识保留和推进的多机制学习范式

TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge  Retention and Promotion

Intelligent systems deployed in the real world suffer from catastrophic
forgetting when exposed to a sequence of tasks. Humans, on the other hand,
acquire, consolidate, and transfer knowledge between tasks that rarely
interfere with the consolidated knowledge. Accompanied by self-regulated
neurogenesis, continual learning in the brain is governed by a rich set of
neurophysiological processes that harbor different types of knowledge, which
are then integrated by conscious processing. Thus, inspired by the Global
Workspace Theory of conscious information access in the brain, we propose
TAMiL, a continual learning method that entails task-attention modules to
capture task-specific information from the common representation space. We
employ simple, undercomplete autoencoders to create a communication bottleneck
between the common representation space and the global workspace, allowing only
the task-relevant information to the global workspace, thus greatly reducing
task interference. Experimental results show that our method outperforms
state-of-the-art rehearsal-based and dynamic sparse approaches and bridges the
gap between fixed capacity and parameter isolation approaches while being
scalable. We also show that our method effectively mitigates catastrophic
forgetting while being well-calibrated with reduced task-recency bias.

本研究提出了 TAMiL 方法，应用任务注意模块和自动编码器捕捉共同表示空间中的任务特定信息，并在全局工作区中保留任务相关信息以缓解灾难性遗忘现象。实验结果表明，该方法优于现有基于重新玩彩和动态稀疏方法的连续学习方法。