English

Continual Pre-Training Mitigates Forgetting in Language and Vision

Machine Learning 2022-05-20 v1 Artificial Intelligence

Abstract

Pre-trained models are nowadays a fundamental component of machine learning research. In continual learning, they are commonly used to initialize the model before training on the stream of non-stationary data. However, pre-training is rarely applied during continual learning. We formalize and investigate the characteristics of the continual pre-training scenario in both language and vision environments, where a model is continually pre-trained on a stream of incoming data and only later fine-tuned to different downstream tasks. We show that continually pre-trained models are robust against catastrophic forgetting and we provide strong empirical evidence supporting the fact that self-supervised pre-training is more effective in retaining previous knowledge than supervised protocols. Code is provided at https://github.com/AndreaCossu/continual-pretraining-nlp-vision .

Keywords

Cite

@article{arxiv.2205.09357,
  title  = {Continual Pre-Training Mitigates Forgetting in Language and Vision},
  author = {Andrea Cossu and Tinne Tuytelaars and Antonio Carta and Lucia Passaro and Vincenzo Lomonaco and Davide Bacciu},
  journal= {arXiv preprint arXiv:2205.09357},
  year   = {2022}
}

Comments

under review

R2 v1 2026-06-24T11:21:55.243Z