Abstract
Class-Incremental Learning (CIL) aims to continually learn new classes while preserving prior knowledge. Parameter-efficient fine-tuning with pre-trained models enables CIL with minimal parameter updates, but existing approaches still suffer from catastrophic forgetting caused by cumulative interference and suboptimal module-sample matching at inference. We propose Hyperbolic Prototype Routing (HyPro), a rehearsal-free framework for continual learning. HyPro allocates a dedicated LoRA-Expert module to each incremental task for isolated representation learning, then projects routing features onto a Poincare ball and performs geodesic nearest-prototype matching for reliable task-level discrimination. Extensive experiments on standard CIL and Few-Shot CIL benchmarks show that HyPro consistently improves average and final-stage accuracy over strong baselines.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Zhao, H., Liu, R., & Chen, Y. (2026). Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning. https://omanscience.com/en/articles/hyperbolic-prototype-routing-for-rehearsal-free-class-incremental-learning
MLA 9
Zhao, Hongwei, et al. "Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning." https://omanscience.com/en/articles/hyperbolic-prototype-routing-for-rehearsal-free-class-incremental-learning.
Chicago (author–date)
Zhao, Hongwei, Rui Liu, and Yong Chen. 2026. "Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning." https://omanscience.com/en/articles/hyperbolic-prototype-routing-for-rehearsal-free-class-incremental-learning.
Harvard
Zhao, H., Liu, R. and Chen, Y. (2026) 'Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning', Available at: https://omanscience.com/en/articles/hyperbolic-prototype-routing-for-rehearsal-free-class-incremental-learning.
Vancouver
Zhao H, Liu R, Chen Y. Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning. https://omanscience.com/en/articles/hyperbolic-prototype-routing-for-rehearsal-free-class-incremental-learning
IEEE
H. Zhao, R. Liu, and Y. Chen, "Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning," https://omanscience.com/en/articles/hyperbolic-prototype-routing-for-rehearsal-free-class-incremental-learning.