Using task-specific components within a neural network in continual learning (CL) is a compelling strategy to address the stability-plasticity dilemma in fixed-capacity models without access to past data. Current methods focus only on selecting a sub-network for a new task that reduces forgetting of past tasks. However, this selection could limit the forward transfer of relevant past knowledge that helps in future learning. Our study reveals that satisfying both objectives jointly is more challenging when a unified classifier is used for all classes of seen tasks-class-Incremental Learning (class-IL)-as it is prone to ambiguities between classes across tasks. Moreover, the challenge increases when the semantic similarity of classes across tasks increases. To address this challenge, we propose a new CL method, named AFAF, that aims to Avoid Forgetting and Allow Forward transfer in class-IL using fix-capacity models. AFAF allocates a sub-network that enables selective transfer of relevant knowledge to a new task while preserving past knowledge, reusing some of the previously allocated components to utilize the fixed-capacity, and addressing class-ambiguities when similarities exist. The experiments show the effectiveness of AFAF in providing models with multiple CL desirable properties, while outperforming state-of-the-art methods on various challenging benchmarks with different semantic similarities.
翻译:在持续学习中,使用神经网络中特定任务的组成部分是解决固定能力模型中固定能力模型中稳定-持久性难题的令人信服的战略。目前的方法仅侧重于为新任务选择子网络,以减少对过去任务的忘记。然而,这一选择可能会限制有助于未来学习的相关过去知识的前瞻性转让。我们的研究显示,如果对所有类别的任务使用统一的分类方法,即分类方法(分类方法),而所有类别的任务 -- -- 类别 -- -- 强化学习(类级) -- -- 容易在任务之间出现模糊不清之处,那么共同实现这两个目标就更具挑战性。此外,当不同任务类别之间的语义相似性增加时,挑战就会增加。为了应对这一挑战,我们提议了一个名为AFAFAF的新的CL方法,目的是避免忘记和允许利用固定能力模型在类中进行前瞻性转让,从而帮助今后的学习。AFAFAF分配了一个子网络,以便能够将相关知识有选择地转让给新任务,同时保留过去的知识,同时重新使用以前分配的一些组成部分来利用固定能力,并在存在相似之处解决类别矛盾。为了应对这一挑战,我们提出的实验表明AFAFAFAF的相似性模型在提供具有多重性特点的相同性模型时,同时提供不同的CL性模型。