Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
This addresses scalability and forgetting issues in class-incremental learning for AI systems, representing an incremental improvement over existing methods.
The paper tackles the problem of catastrophic forgetting and scalability in class-incremental learning by proposing ACMap, an exemplar-free framework that consolidates task-specific adapters into a single adapter, achieving constant inference time without sacrificing accuracy. Experiments on five benchmark datasets show it matches state-of-the-art accuracy while maintaining inference time comparable to the fastest methods.
We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability. While existing methods involve a trade-off between inference time and accuracy, ACMap consolidates task-specific adapters into a single adapter, thus achieving constant inference time across tasks without sacrificing accuracy. The framework employs adapter merging to build a shared subspace that aligns task representations and mitigates forgetting, while centroid prototype mapping maintains high accuracy by consistently adapting representations within the shared subspace. To further improve scalability, an early stopping strategy limits adapter merging as tasks increase. Extensive experiments on five benchmark datasets demonstrate that ACMap matches state-of-the-art accuracy while maintaining inference time comparable to the fastest existing methods. The code is available at https://github.com/tf63/ACMap.