MagMax: Leveraging Model Merging for Seamless Continual Learning
This addresses the challenge of enabling large models to learn continuously from new data, which is incremental as it builds on existing model merging techniques.
The paper tackles the problem of continual learning for large pre-trained models by introducing MagMax, a model-merging strategy that uses maximum magnitude weight selection to integrate knowledge across tasks without forgetting, and demonstrates its superiority in class- and domain-incremental settings.
This paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forgetting previously acquired knowledge. Distinct from traditional continual learning methods that aim to reduce forgetting during task training, MagMax combines sequential fine-tuning with a maximum magnitude weight selection for effective knowledge integration across tasks. Our initial contribution is an extensive examination of model merging techniques, revealing that simple approaches like weight averaging and random weight selection surprisingly hold up well in various continual learning contexts. More importantly, we present MagMax, a novel model-merging strategy that enables continual learning of large pre-trained models for successive tasks. Our thorough evaluation demonstrates the superiority of MagMax in various scenarios, including class- and domain-incremental learning settings. The code is available at this URL: https://github.com/danielm1405/magmax.