Scalable Adversarial Online Continual Learning
This work addresses scalability issues in online continual learning for AI systems, though it is incremental as it builds on existing adversarial approaches.
The paper tackled the problem of high complexity and iterative training in adversarial continual learning by proposing SCALE, a scalable method using a parameter generator and single discriminator, which achieved higher accuracy and faster execution time compared to baselines.
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.