Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning
This addresses the challenge of catastrophic forgetting in continual learning for AI systems, offering an incremental improvement without a rehearsal buffer.
The paper tackled the problem of semantic drift and prototype interference in rehearsal-free continual learning by introducing the Contrastive Prototypical Prompt (CPP) approach, which achieved a 4% to 6% improvement over state-of-the-art methods on four benchmarks.
In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting. However, challenges related to semantic drift and prototype interference persist. In this study, we introduce the Contrastive Prototypical Prompt (CPP) approach. Through task-specific prompt-tuning, underpinned by a contrastive learning objective, we effectively address both aforementioned challenges. Our evaluations on four challenging class-incremental benchmarks reveal that CPP achieves a significant 4% to 6% improvement over state-of-the-art methods. Importantly, CPP operates without a rehearsal buffer and narrows the performance divergence between continual and offline joint-learning, suggesting an innovative scheme for Transformer-based continual learning systems.