arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.39550cs.LG

双曲原型路由用于无重放类增量学习

Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning

  • Beihang University(北京航空航天大学)
  • Beijing University of Posts and Telecommunications(北京邮电大学)

机构由 AI 辅助整理,请以论文原文为准。

HongWei Zhao, Rui Liu, Yong Chen

AI总结:

针对类增量学习中的灾难性遗忘问题,提出双曲原型路由框架,通过为每个任务分配LoRA专家并在庞加莱球上进行测地原型匹配,实现无重放的高效学习,在标准及少样本基准上显著提升准确率。

AI中文摘要:

类增量学习(CIL)旨在持续学习新类别,同时保留先验知识。基于预训练模型的参数高效微调能以极少的参数更新实现CIL,但现有方法仍遭受灾难性遗忘,其原因在于累积干扰和推理时模块-样本匹配次优。我们提出双曲原型路由(HyPro),一种用于持续学习的无重放框架。HyPro为每个增量任务分配专用LoRA专家模块,以实现隔离的表示学习,然后将路由特征投影到庞加莱球上,并执行测地最近原型匹配以实现可靠的任务级判别。在标准CIL和少样本CIL基准上的大量实验表明,HyPro在平均准确率和最终阶段准确率上持续优于强基线。

英文摘要:

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.

补充信息

↑