Continual Pre-training Mitigates Forgetting In Language And Vision

Cossu Andrea, Tuytelaars Tinne, Carta Antonio, Passaro Lucia, Lomonaco Vincenzo, Bacciu Davide. Arxiv 2022

[Paper] [Code]    
Has Code Pretraining Methods Reinforcement Learning Training Techniques

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 .

Similar Work