Overcoming catastrophic forgetting with hard attention to the task
Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks' information without affecting the current task's learning. A hard attention mask is learned concurrently to every task, through stochastic gradient descent, and previous masks are exploited to condition such learning. We show that the proposed mechanism is effective for reducing catastrophic forgetting, cutting current rates by 45 to 80%. We also show that it is robust to different hyperparameter choices, and that it offers a number of monitoring capabilities. The approach features the possibility to control both the stability and compactness of the learned knowledge, which we believe makes it also attractive for online learning or network compression applications.
Code (2)
Tasks
Continual LearningHard AttentionSimilar Papers 제목 키워드 기반
Attention-Based Structural-Plasticity
Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in partic…
Lifelong learningPermuted-MNISTSplit-MNISTZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
Backpropagation provides a generalized configuration for overcoming catastrophic forgetting. Like, SGD and Adam are commonly used for weight updates in continual learning and continual pre-training. In practice, permissi…
Continual LearningOnline Structured Laplace Approximations For Overcoming Catastrophic Forgetting
We introduce the Kronecker factored online Laplace approximation for overcoming catastrophic forgetting in neural networks. The method is grounded in a Bayesian online learning framework, where we recursively approximate…
Permuted-MNISTOvercoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation
Neural networks tend to gradually forget the previously learned knowledge when learning multiple tasks sequentially from dynamic data distributions. This problem is called \textit{catastrophic forgetting}, which is a fun…
Continual LearningKnowledge DistillationMachine TranslationTranslationOvercoming Catastrophic Forgetting in Graph Neural Networks
Catastrophic forgetting refers to the tendency that a neural network "forgets" the previous learned knowledge upon learning new tasks. Prior methods have been focused on overcoming this problem on convolutional neural ne…
Continual Learning