Learning to Prompt Knowledge Transfer for Open-World Continual Learning

TL;DR

This paper introduces Pro-KT, a prompt-based model for open-world continual learning that effectively transfers knowledge and identifies unknown classes, outperforming existing methods on real-world datasets.

Contribution

Pro-KT is the first prompt-enhanced knowledge transfer approach designed specifically for open-world continual learning, addressing task boundary adaptability and unknown detection.

Findings

Pro-KT outperforms state-of-the-art methods in unknown detection.

Pro-KT achieves higher accuracy in classifying knowns.

Pro-KT effectively transfers task-generic and task-specific knowledge.

Abstract

This paper studies the problem of continual learning in an open-world scenario, referred to as Open-world Continual Learning (OwCL). OwCL is increasingly rising while it is highly challenging in two-fold: i) learning a sequence of tasks without forgetting knowns in the past, and ii) identifying unknowns (novel objects/classes) in the future. Existing OwCL methods suffer from the adaptability of task-aware boundaries between knowns and unknowns, and do not consider the mechanism of knowledge transfer. In this work, we propose Pro-KT, a novel prompt-enhanced knowledge transfer model for OwCL. Pro-KT includes two key components: (1) a prompt bank to encode and transfer both task-generic and task-specific knowledge, and (2) a task-aware open-set boundary to identify unknowns in the new tasks. Experimental results using two real-world datasets demonstrate that the proposed Pro-KT outperforms the state-of-the-art counterparts in both the detection of unknowns and the classification of knowns markedly.