English(EN)Federated Class-Incremental Learning with Hierarchical Generative Prototypes
新的类增量学习方法解决遗忘和效率问题 · 追踪 7 个来源
作者PulseAugur 编辑部·[7 个来源]·
arXiv 上发表的多篇研究论文提出了类增量学习（CIL）的新方法，这是一种允许 AI 模型随着时间推移学习新类别而不会忘记先前获得的知识的技术。这些方法侧重于提高效率和减少灾难性遗忘，这是 CIL 中的一个常见挑战。方法包括使用任务自适应 LoRA（低秩自适应）模块、集成知识迁移、用于原型路由的双曲几何以及神经网络层的动态宽度扩展。一些论文还探讨了联邦学习场景，并将模型适应不断变化的类别和领域分布。
AI
影响
这些新方法旨在提高 AI 模型在不忘记过去知识的情况下持续学习的能力，这对于现实世界的动态环境至关重要。
arXiv cs.LG
TIER_1English(EN)·Hongwei Zhao (School of Computer Science,Engineering, Beihang University), Rui Liu (School of Computer Science,Engineering, Beihang University), Yansong Liu (School of Computer Science,Engineering, Beihang University), Zhiyuan Zou (School of Computer Sci…·
arXiv:2609.39390v1 Announce Type: new Abstract: Few-Shot Class-Incremental Learning (FSCIL) addresses the challenge of learning new classes from very limited samples while retaining knowledge of previously learned ones. Although parameter-efficient fine-tuning methods with pre-tr…
arXiv cs.LG
TIER_1English(EN)·HongWei Zhao (Beihang University), Rui Liu (Beihang University), Yong Chen (Beijing University of Posts,Telecommunications)·
arXiv:2609.39550v1 Announce Type: new 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 sti…
arXiv cs.LG
TIER_1English(EN)·Hongwei Zhao (School of Computer Science,Engineering, Beihang University), Rui Liu (School of Computer Science,Engineering, Beihang University), Yansong Liu (School of Computer Science,Engineering, Beihang University)·
arXiv:2609.39839v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuning with pre-trained models reduces parameter overhead but can suffer from cumulat…
arXiv:2406.02447v5 Announce Type: replace Abstract: Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accou…
arXiv cs.AI
TIER_1English(EN)·A. L. S. Conde, Y. Elkhatib, C. M. Ranieri·
arXiv:2609.37702v1 Announce Type: cross Abstract: Class Incremental Learning (Class-IL) requires models to learn new classes over time while preserving previously acquired knowledge without access to past data or task identity. This setting intensifies the stability-plasticity di…
arXiv:2609.37888v1 Announce Type: cross Abstract: Class-Incremental Learning (CIL) requires models to recognize new classes over time without forgetting previously learned ones. With the rise of vision-language pre-training, CLIP has become a strong foundation for CIL. A common d…
arXiv cs.AI
TIER_1English(EN)·Jae-Ho Lee, Min-Yeong Park, Jun-Yeong Moon, Jung Uk Kim, Gyeong-Moon Park·
arXiv:2609.36442v1 Announce Type: cross Abstract: Continual learning enables vision systems to adapt to ever-changing data distributions. Despite significant advances, existing approaches fail to capture continuous and concurrent shifts in classes and domains, a critical capabili…
