Liquid Ensemble Selection for Continual Learning
This addresses the challenge of forgetting in continual learning for machine learning practitioners, but it is incremental as it builds on existing ensemble and delegation techniques.
The paper tackled the problem of selecting which models in an ensemble should learn or predict during continual learning, and found that using delegation methods significantly boosts performance over naive approaches in handling distribution shifts.
Continual learning aims to enable machine learning models to continually learn from a shifting data distribution without forgetting what has already been learned. Such shifting distributions can be broken into disjoint subsets of related examples; by training each member of an ensemble on a different subset it is possible for the ensemble as a whole to achieve much higher accuracy with less forgetting than a naive model. We address the problem of selecting which models within an ensemble should learn on any given data, and which should predict. By drawing on work from delegative voting we develop an algorithm for using delegation to dynamically select which models in an ensemble are active. We explore a variety of delegation methods and performance metrics, ultimately finding that delegation is able to provide a significant performance boost over naive learning in the face of distribution shifts.