Improving Open-world Continual Learning under the Constraints of Scarce Labeled Data

2025-02-28

AI Summary

This paper addresses the practical challenge of label scarcity in open-world continual learning (OWCL), proposing a new paradigm: Open-World Few-Shot Continual Learning (OFCL). OFCL tackles three core challenges: (1) learning novel classes from only a few labeled examples, (2) continually adapting to an unbounded sequence of tasks, and (3) jointly performing open-set detection and dynamically incorporating discovered unknown classes into the known class set. To this end, we introduce a tripartite collaborative framework: Instance-level Token Augmentation (ITA) to enhance few-shot generalization; Margin-aware Open-set Boundary learning (MOB) to construct compact, evolvable decision boundaries; and Adaptive Knowledge Space (AKS) to enable cross-task knowledge transfer and semantic evolution. Our method integrates contrastive learning, dynamic boundary optimization, meta-level feature enhancement, and knowledge distillation. Extensive experiments on multiple open-world benchmarks demonstrate significant improvements over state-of-the-art methods. Code is publicly available.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Open-world continual learning (OWCL) adapts to sequential tasks with open samples, learning knowledge incrementally while preventing forgetting. However, existing OWCL still requires a large amount of labeled data for training, which is often impractical in real-world applications. Given that new categories/entities typically come with limited annotations and are in small quantities, a more realistic situation is OWCL with scarce labeled data, i.e., few-shot training samples. Hence, this paper investigates the problem of open-world few-shot continual learning (OFCL), challenging in (i) learning unbounded tasks without forgetting previous knowledge and avoiding overfitting, (ii) constructing compact decision boundaries for open detection with limited labeled data, and (iii) transferring knowledge about knowns and unknowns and even update the unknowns to knowns once the labels of open samples are learned. In response, we propose a novel OFCL framework that integrates three key components: (1) an instance-wise token augmentation (ITA) that represents and enriches sample representations with additional knowledge, (2) a margin-based open boundary (MOB) that supports open detection with new tasks emerge over time, and (3) an adaptive knowledge space (AKS) that endows unknowns with knowledge for the updating from unknowns to knowns. Finally, extensive experiments show the proposed OFCL framework outperforms all baselines remarkably with practical importance and reproducibility. The source code is released at https://github.com/liyj1201/OFCL.

Problem

• Addresses open-world few-shot continual learning challenges
• Enhances learning with scarce labeled data and prevents forgetting
• Develops methods for knowledge transfer and updating unknowns to knowns

Innovation

• Instance-wise token augmentation enriches sample representations
• Margin-based open boundary supports open detection
• Adaptive knowledge space updates unknowns to knowns