Re-Evaluating Continual Learning with Few-Shot Adaptation
For researchers in continual learning, this work provides a new evaluation paradigm that offers finer-grained insights into model performance, though it is incremental in nature.
The paper proposes few-shot evaluation as a more comprehensive assessment of stability and plasticity in continual learning, revealing that meta-learning with foresight induces learning-to-learn behavior over task sequences.
Continual learning methods aim to maximize the stability and plasticity of machine learning models that are trained on a sequence of tasks. The standard measure of stability (i.e., forgetting) is the 0-shot performance of a model on previously learned tasks, and plasticity, the performance on the most recently learned task. However, 0-shot evaluation does not fully measure a model or method's ability to retain learned information or adapt quickly to new information, as it requires perfect recall across multiple tasks. In this paper, we propose few-shot evaluation as a more comprehensive assessment of the stability and plasticity of a continual learning system. We conduct a fine-grained assessment on task sequences for continual image classification and find that this paradigm produces novel insights into the performance of popular continual learning strategies. Through few-shot evaluation with a novel metric -- per-shot plasticity -- we show that adding `foresight' to continual learning methods via the meta-learning of a short sequence of future tasks induces learning-to-learn behavior over the task sequence.