用于持续学习的参数级软掩码
Parameter-Level Soft-Masking for Continual Learning
AI总结：
本文提出参数级软掩码技术SPG，通过基于参数重要性部分阻止更新，在持续学习中同时克服灾难性遗忘、促进知识转移并解决网络容量问题。
摘要：
持续学习中关于任务增量学习的现有研究主要集中在防止灾难性遗忘（CF）上。尽管有几种技术实现了无CF的学习，但它们是通过让每个任务独占共享网络中的一个子网络来实现这一点的，这严重限制了知识转移（KT），并导致网络容量过度消耗，即随着学习的任务增多，性能会下降。本文的目标有三方面：（1）克服CF，（2）鼓励KT，（3）解决容量问题。我们提出了一种新技术（称为SPG），它基于每个参数对旧任务的重要性，在训练中软掩码（部分阻止）参数更新。每个任务仍使用整个网络，即任何任务都不独占网络的任何部分，这使得KT最大化并减少了容量使用。据我们所知，这是首个在参数级对模型进行软掩码以用于持续学习的工作。大量实验证明了SPG在实现所有三个目标方面的有效性。更值得注意的是，它在缓解CF的同时，不仅在相似任务（具有共享知识）之间，而且在不相似任务（几乎没有共享知识）之间也实现了显著的知识转移。
英文摘要：
Existing research on task incremental learning in continual learning has primarily focused on preventing catastrophic forgetting (CF). Although several techniques have achieved learning with no CF, they attain it by letting each task monopolize a sub-network in a shared network, which seriously limits knowledge transfer (KT) and causes over-consumption of the network capacity, i.e., as more tasks are learned, the performance deteriorates. The goal of this paper is threefold: (1) overcoming CF, (2) encouraging KT, and (3) tackling the capacity problem. A novel technique (called SPG) is proposed that soft-masks (partially blocks) parameter updating in training based on the importance of each parameter to old tasks. Each task still uses the full network, i.e., no monopoly of any part of the network by any task, which enables maximum KT and reduction in capacity usage. To our knowledge, this is the first work that soft-masks a model at the parameter-level for continual learning. Extensive experiments demonstrate the effectiveness of SPG in achieving all three objectives. More notably, it attains significant transfer of knowledge not only among similar tasks (with shared knowledge) but also among dissimilar tasks (with little shared knowledge) while mitigating CF.
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。
