DOLFIN：在联邦持续学习中平衡稳定性与可塑性
DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning
AI总结：
DOLFIN结合视觉Transformer与低秩适配器及双梯度投影记忆，在联邦持续学习中平衡稳定性与可塑性，以低通信开销和内存占用超越六个基线。
摘要：
联邦持续学习（FCL）使模型能够在多个分布式客户端上学习新任务，同时保护隐私且不遗忘先前获得的知识。然而，当前方法在平衡性能、隐私保护和通信效率方面面临挑战。我们提出了一种分布式在线LoRA用于联邦增量学习的方法DOLFIN，这是一种新颖的方法，将视觉Transformer与低秩适配器相结合，旨在联邦环境中高效且稳定地学习新任务。我们的方法利用LoRA实现最小化通信开销，并引入双梯度投影记忆（DualGPM）以防止遗忘。在CIFAR-100、ImageNet-R、ImageNet-A和CUB-200上，在两种Dirichlet异质性设置下进行评估，DOLFIN在最终平均准确率上持续超越六个强基线，同时匹配其内存占用。正交低秩适配器为联邦设置中保护隐私的持续学习提供了一种有效且可扩展的解决方案。
英文摘要：
Federated continual learning (FCL) enables models to learn new tasks across multiple distributed clients, protecting privacy and without forgetting previously acquired knowledge. However, current methods face challenges balancing performance, privacy preservation, and communication efficiency. We introduce a Distributed Online LoRA for Federated INcremental learning method DOLFIN, a novel approach combining Vision Transformers with low-rank adapters designed to efficiently and stably learn new tasks in federated environments. Our method leverages LoRA for minimal communication overhead and incorporates DualGradient Projection Memory (DualGPM) to prevent forgetting. Evaluated on CIFAR-100, ImageNet-R, ImageNet-A, and CUB-200 under two Dirichlet heterogeneity settings, DOLFIN consistently surpasses six strong baselines in final average accuracy while matching their memory footprint. Orthogonal low-rank adapters offer an effective and scalable solution for privacy-preserving continual learning in federated settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
