Neural Architecture for Online Ensemble Continual Learning
This addresses the challenge of efficient and scalable continual learning for AI systems that process data streams, though it is incremental as it builds on ensemble techniques.
The paper tackles the problem of online continual learning with increasing classes by introducing a fully differentiable ensemble method, achieving state-of-the-art results without a memory buffer and showing significant performance gains for small ensembles.
Continual learning with an increasing number of classes is a challenging task. The difficulty rises when each example is presented exactly once, which requires the model to learn online. Recent methods with classic parameter optimization procedures have been shown to struggle in such setups or have limitations like non-differentiable components or memory buffers. For this reason, we present the fully differentiable ensemble method that allows us to efficiently train an ensemble of neural networks in the end-to-end regime. The proposed technique achieves SOTA results without a memory buffer and clearly outperforms the reference methods. The conducted experiments have also shown a significant increase in the performance for small ensembles, which demonstrates the capability of obtaining relatively high classification accuracy with a reduced number of classifiers.