Knowledge-Adaptation Priors
This addresses the high computational cost of retraining for various tasks and models, though it appears incremental as it generalizes existing adaptation strategies.
The paper tackles the problem of machine learning models requiring full retraining when adapting to changes, by introducing Knowledge-adaptation priors (K-priors) that enable quick and accurate adaptation using a handful of past examples, achieving performance similar to full retraining.
Humans and animals have a natural ability to quickly adapt to their surroundings, but machine-learning models, when subjected to changes, often require a complete retraining from scratch. We present Knowledge-adaptation priors (K-priors) to reduce the cost of retraining by enabling quick and accurate adaptation for a wide-variety of tasks and models. This is made possible by a combination of weight and function-space priors to reconstruct the gradients of the past, which recovers and generalizes many existing, but seemingly-unrelated, adaptation strategies. Training with simple first-order gradient methods can often recover the exact retrained model to an arbitrary accuracy by choosing a sufficiently large memory of the past data. Empirical results show that adaptation with K-priors achieves performance similar to full retraining, but only requires training on a handful of past examples.