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.
Joan Serrà (Telefónica Research, Barcelona)
Didac Suris (Universitat Politecnica de Catalunya)
Marius Miron (Joint Research Centre of the European Commission)
Alexandros Karatzoglou (Telefonica)
Related Events (a corresponding poster, oral, or spotlight)
2018 Oral: Overcoming Catastrophic Forgetting with Hard Attention to the Task »
Fri Jul 13th 02:20 -- 02:40 PM Room Victoria