LDEPrompt: Layer-importance guided Dual Expandable Prompt Pool for Pre-trained Model-based Class-Incremental Learning

2026-04-13

AI Summary

This work addresses key limitations in existing prompt-based class-incremental learning methods—namely, fixed prompt pools, manually selected prompt insertion layers, and excessive reliance on pretrained backbones—by introducing a layer-importance-guided dual-scalable prompt pool mechanism. The proposed approach adaptively selects Transformer layers based on their importance scores and enables dynamic expansion and freezing of the prompt pool, thereby overcoming the rigidity of conventional fixed architectures. Integrated with an instance-level matching strategy, the method achieves state-of-the-art performance across multiple standard class-incremental learning benchmarks, significantly enhancing model scalability and generalization capability.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Natural Language Processing: Prompt Engineering / Prompting
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Prompt-based class-incremental learning methods typically construct a prompt pool consisting of multiple trainable key-prompts and perform instance-level matching to select the most suitable prompt embeddings, which has shown promising results. However, existing approaches face several limitations, including fixed prompt pools, manual selection of prompt embeddings, and strong reliance on the pretrained backbone for prompt selection. To address these issues, we propose a \textbf{L}ayer-importance guided \textbf{D}ual \textbf{E}xpandable \textbf{P}rompt Pool (\textbf{LDEPrompt}), which enables adaptive layer selection as well as dynamic freezing and expansion of the prompt pool. Extensive experiments on widely used class-incremental learning benchmarks demonstrate that LDEPrompt achieves state-of-the-art performance, validating its effectiveness and scalability.

Problem

• class-incremental learning
• prompt pool
• pre-trained model
• prompt selection
• fixed prompt pool

Innovation

• prompt pool
• class-incremental learning
• layer importance
• dynamic expansion
• pre-trained models