Generative Negative Replay for Continual Learning

Gabriele Graffieti, Davide Maltoni, Lorenzo Pellegrini, Vincenzo Lomonaco

Keywords: Continual Learning, Generative replay, Lifelong learning

Abstract:

Learning continually is a key aspect of intelligence and a necessary ability to solve many real-world problems. One of the most effective strategies to control catastrophic forgetting, the Achilles’ heel of continual learning, is storing part of the old data and replay them interleaved with new experiences (also known as the replay approach). Generative replay, that is using generative models to provide replay patterns on demand, is particularly intriguing, however, it was shown to be effective mainly under simplified assumptions, such as simple scenarios and low-dimensional benchmarks.
In this paper, we show that, while the generated data are usually not able to improve the classification accuracy for the old classes, they can be effective as negative examples (or antagonists) to learn the new classes, especially when the learning experiences are small and contain examples of just one or few classes. The proposed approach is validated on complex class-incremental and data-incremental continual learning scenarios (CORe50 and ImageNet-1000) composed of high-dimensional data and a large number of training experiences: a setup where existing generative replay approaches usually fail.