两篇新研究论文探讨了使用联邦学习个性化基础模型所面临的挑战。其中一篇论文介绍了 HyperLoRA 框架，该框架通过使用超网络生成 LoRA 和聚合产品空间来提高联邦适应的效率和准确性。另一篇论文识别并归类了联邦个性化中的“沉默故障”，例如偏见放大和公平性崩溃，这些故障由于联邦学习固有的隐私限制而难以检测。 AI
影响 解决了以保护隐私和可信的方式部署个性化基础模型中的关键问题。
排序理由 两篇在 arXiv 上发表的学术论文，讨论了用于基础模型的联邦学习的方法和挑战。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.06154v1 Announce Type: new Abstract: Federated fine-tuning of foundation models using Low-Rank Adaptation (LoRA) offers a communication efficient solution for distributed learning. However, existing federated LoRA methods suffer from two fundamental limitations: (1) st…
Federated fine-tuning of foundation models using Low-Rank Adaptation (LoRA) offers a communication efficient solution for distributed learning. However, existing federated LoRA methods suffer from two fundamental limitations: (1) structural aggregation bias, where independently a…
arXiv:2606.00947v1 Announce Type: cross Abstract: Foundation models are increasingly personalized on decentralized private data through federated learning and are now deployed at scale under growing regulatory requirements for post-market monitoring. We argue that this convergenc…