Adversarial continual learning is effective for continual learning problems because of the presence of feature alignment process generating task-invariant features having low susceptibility to the catastrophic forgetting problem. Nevertheless, the ACL method imposes considerable complexities because it relies on task-specific networks and discriminators. It also goes through an iterative training process which does not fit for online (one-epoch) continual learning problems. This paper proposes a scalable adversarial continual learning (SCALE) method putting forward a parameter generator transforming common features into task-specific features and a single discriminator in the adversarial game to induce common features. The training process is carried out in meta-learning fashions using a new combination of three loss functions. SCALE outperforms prominent baselines with noticeable margins in both accuracy and execution time.
@article{arxiv.2209.01558,
title = {Scalable Adversarial Online Continual Learning},
author = {Tanmoy Dam and Mahardhika Pratama and MD Meftahul Ferdaus and Sreenatha Anavatti and Hussein Abbas},
journal= {arXiv preprint arXiv:2209.01558},
year = {2022}
}
Comments
has been accepted for publication at European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2022 (ECML PKDD 2022)