PulseAugur
中
实时 10:52:05

New framework aligns features for one-shot federated learning

作者 PulseAugur 编辑部 · [2 个来源] ·

Researchers have introduced SLOT-Align, a novel framework designed to harmonize feature representations in One-Shot Federated Learning (OSFL). This method addresses challenges posed by heterogeneous client data distributions, specifically domain and label shifts, which existing OSFL techniques struggle to correct. SLOT-Align employs a shared frozen encoder and optimal transport maps to align local representations efficiently, demonstrating consistent improvements in accuracy and robustness across various benchmarks. AI

影响 Enhances robustness and accuracy in federated learning scenarios with extreme communication constraints.

排序理由 The cluster contains an academic paper detailing a new method for a specific machine learning problem.

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]

  1. 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) ·

    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…

  2. arXiv cs.LG TIER_1 English(EN) · Vittorio Murino ·

    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 …

相关实体

相关话题