Energy-Based Models for Continual Learning
This work addresses the problem of catastrophic forgetting in continual learning for machine learning practitioners, offering a new model class as a building block.
This paper proposes using Energy-Based Models (EBMs) for continual learning by modifying the training objective to reduce interference with previously learned information. Their EBM approach is simple and efficient, outperforming baseline methods significantly on several benchmarks.
We motivate Energy-Based Models (EBMs) as a promising model class for continual learning problems. Instead of tackling continual learning via the use of external memory, growing models, or regularization, EBMs change the underlying training objective to cause less interference with previously learned information. Our proposed version of EBMs for continual learning is simple, efficient, and outperforms baseline methods by a large margin on several benchmarks. Moreover, our proposed contrastive divergence-based training objective can be combined with other continual learning methods, resulting in substantial boosts in their performance. We further show that EBMs are adaptable to a more general continual learning setting where the data distribution changes without the notion of explicitly delineated tasks. These observations point towards EBMs as a useful building block for future continual learning methods.