PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental Learning

2024-12-14

AI Summary

To address severe catastrophic forgetting of old-class knowledge in class-incremental learning with pretrained models, this paper proposes an input-agnostic global prompting mechanism coupled with a negative-feedback-regulated adaptive momentum update strategy. Methodologically: (1) a task-agnostic global prompt is designed to eliminate dependence on input samples; (2) an adaptive momentum optimizer guided by performance feedback dynamically modulates parameter update strength; and (3) cross-task semantic correlations are leveraged to enable continual prompt enhancement. Evaluated on six standard benchmarks, the method achieves state-of-the-art performance, significantly improving both old-class retention and new-class accuracy. The source code is publicly available.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

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
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Class-incremental learning (CIL) aims to continuously introduce novel categories into a classification system without forgetting previously learned ones, thus adapting to evolving data distributions. Researchers are currently focusing on leveraging the rich semantic information of pre-trained models (PTMs) in CIL tasks. Prompt learning has been adopted in CIL for its ability to adjust data distribution to better align with pre-trained knowledge. This paper critically examines the limitations of existing methods from the perspective of prompt learning, which heavily rely on input information. To address this issue, we propose a novel PTM-based CIL method called Input-Agnostic Prompt Enhancement with Negative Feedback Regulation (PEARL). In PEARL, we implement an input-agnostic global prompt coupled with an adaptive momentum update strategy to reduce the model's dependency on data distribution, thereby effectively mitigating catastrophic forgetting. Guided by negative feedback regulation, this adaptive momentum update addresses the parameter sensitivity inherent in fixed-weight momentum updates. Furthermore, it fosters the continuous enhancement of the prompt for new tasks by harnessing correlations between different tasks in CIL. Experiments on six benchmarks demonstrate that our method achieves state-of-the-art performance. The code is available at: https://github.com/qinyongchun/PEARL.

Problem

• Category Incremental Learning
• Knowledge Retention
• Model Adaptation

Innovation

• PEARL method
• Adaptive updating strategy
• Negative feedback mechanism