English(EN) Distribution Alignment for One-Shot Federated Learning via Optimal Transport

新框架对单次联邦学习中的特征进行对齐

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-15 12:46

研究人员推出了一种新颖的框架 SLOT-Align，旨在协调单次联邦学习 (OSFL) 中的特征表示。该方法解决了由异构客户端数据分布带来的挑战，特别是现有 OSFL 技术难以纠正的域偏移和标签偏移。SLOT-Align 采用共享的冻结编码器和最优传输图来高效地对齐局部表示，在各种基准测试中展示了准确性和鲁棒性的一致性改进。 AI

影响在通信约束极端的联邦学习场景中增强了鲁棒性和准确性。

排序理由该集群包含一篇学术论文，详细介绍了一种针对特定机器学习问题的新方法。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Daniele Berardini (AI for Good), Vito Paolo Pastore (AI for Good, MaLGa-DIBRIS, University of Genoa, Genoa, Italy), Vittorio Murino (AI for Good, Department of Computer Science, University of Verona, Verona, Italy) · 2026-06-16 04:00

Distribution Alignment for One-Shot Federated Learning via Optimal Transport

arXiv:2606.16655v1 Announce Type: new Abstract: One-Shot Federated Learning (OSFL) addresses extreme communication regimes in which clients interact with the server only once, amplifying the impact of heterogeneous client data distributions. In particular, the interaction of doma…
arXiv cs.LG TIER_1 English(EN) · Vittorio Murino · 2026-06-15 12:46

Distribution Alignment for One-Shot Federated Learning via Optimal Transport

One-Shot Federated Learning (OSFL) addresses extreme communication regimes in which clients interact with the server only once, amplifying the impact of heterogeneous client data distributions. In particular, the interaction of domain shift and label shift across clients induces …

报道来源 [2]

Distribution Alignment for One-Shot Federated Learning via Optimal Transport

Distribution Alignment for One-Shot Federated Learning via Optimal Transport

相关实体

相关话题