Collaborative Adapter Experts for Class-Incremental Learning
IEEE Signal Processing Letters · 2025 · 32 · 1530-1534
DOI: 10.1109/lsp.2025.3553431 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2025. Verfasst von Sunyuan Qiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, Science and Technology Development Fund of Macau, Guangdong Provincial Key R&D Program.
Abstract (Originalsprache)
Pre-trained models (PTMs) with parameter-efficient fine-tuning (PEFT) techniques have been extensively utilized in class-incremental learning (CIL) scenarios. However, they still remain susceptible to performance degradation as the individual PEFT module operates as an independent learning entity during the incremental process. To this end, this work proposes a novel class-incremental collaborative adapter experts (CICAE) model, which incorporates multiple adapters operating collaboratively to facilitate CIL. Specifically, our model primarily consists of two phases. Initially, multiple adapters are employed to establish a multi-expert system aimed at acquiring diverse incremental knowledge. Through the collaborative knowledge sharing (CKS) mechanism, the expertise of each adapter expert is transferable, promoting collaborative development and mutual advancement. Subsequently, with the category prototype distributions, collaborative classifier alignment (CCA) is proposed to further align the classifiers with the representation space in a cooperative manner. Extensive experiments on CIL benchmarks validate the superior performance of our model.
Förderung
- Beijing Natural Science Foundation
- Science and Technology Development Fund of Macau
- Guangdong Provincial Key R&D Program
Zitieren
APA
Qiang, S., Yu, X., Liang, Y., Wan, J., & Zhang, D. (2025). Collaborative Adapter Experts for Class-Incremental Learning. IEEE Signal Processing Letters, 32, 1530-1534. https://doi.org/10.1109/lsp.2025.3553431
Vancouver
Qiang S, Yu X, Liang Y, Wan J, Zhang D. Collaborative Adapter Experts for Class-Incremental Learning. IEEE Signal Processing Letters. 2025;32:1530-1534. doi:10.1109/lsp.2025.3553431
BibTeX
@article{Qiang2025,
author = {Qiang, Sunyuan and Yu, Xinxing and Liang, Yanyan and Wan, Jun and Zhang, Du},
title = {Collaborative Adapter Experts for Class-Incremental Learning},
journal = {IEEE Signal Processing Letters},
year = {2025},
volume = {32},
pages = {1530--1534},
doi = {10.1109/lsp.2025.3553431}
}
EUVIMED