The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance degradation on prior tasks. We hypothesize that forgetting can be further reduced when the model is encouraged to remember the \textit{evidence} for previously made decisions. As a first step towards exploring this hypothesis, we propose a simple novel training paradigm, called Remembering for the Right Reasons (RRR), that additionally stores visual model explanations for each example in the buffer and ensures the model has "the right reasons" for its predictions by encouraging its explanations to remain consistent with those used to make decisions at training time. Without this constraint, there is a drift in explanations and increase in forgetting as conventional continual learning algorithms learn new tasks. We demonstrate how RRR can be easily added to any memory or regularization-based approach and results in reduced forgetting, and more importantly, improved model explanations. We have evaluated our approach in the standard and few-shot settings and observed a consistent improvement across various CL approaches using different architectures and techniques to generate model explanations and demonstrated our approach showing a promising connection between explainability and continual learning. Our code is available at \url{https://github.com/SaynaEbrahimi/Remembering-for-the-Right-Reasons}.
翻译:持续学习(CL)的目标是学习一系列任务,而不会因为灾难性的遗忘现象而痛苦地忘记。 先前的工作已经表明,以回放缓冲的形式利用记忆,可以减少先前任务的业绩退化。 我们假设,如果鼓励模型记住以前做出的决定,就可以进一步减少忘记。 作为探索这一假设的第一步,我们提议了一个简单的新颖的培训模式,称为 " 牢记正确的原因 " (RRR),在缓冲中额外储存每个例子的视觉模型解释,并确保模型有预测的“正确理由”,鼓励其解释与培训时用于决策的解释保持一致。没有这种限制,解释就会有所转移,随着传统的持续学习算法学习新任务而忘却也会增加。我们展示了RRR如何容易添加到任何记忆或正规化的方法中,并导致减少忘却,更重要的是,改进了模型解释。我们评估了我们在标准环境和少镜头中的做法,并观察到了各种CL方法在使用不同的架构和技术来生成模型解释/Reurqrah/Recomimia 之间的一致性改进了我们不断学习的代码。