PulseAugur
中
实时 06:19:15

FedSPDnet advances federated learning with geometry-aware aggregation strategies

作者 PulseAugur 编辑部 · [2 个来源] ·

Researchers have developed FedSPDnet, a novel federated learning framework designed for models that process symmetric positive definite (SPD) matrices with Stiefel-constrained parameters. This framework introduces two aggregation strategies, ProjAvg and RLAvg, which preserve the geometric structure of the data, unlike standard Euclidean averaging. FedSPDnet demonstrates superior performance in F1 score and robustness on EEG motor imagery benchmarks compared to federated EEGnet, while also reducing communication overhead. AI

影响 Introduces novel aggregation strategies for federated learning on geometric data, potentially improving performance in signal processing applications.

排序理由 This is a research paper detailing a new federated learning framework.

在 arXiv stat.ML 阅读 →

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

FedSPDnet advances federated learning with geometry-aware aggregation strategies

报道来源 [2]

  1. arXiv stat.ML TIER_1 English(EN) · Thibault Pautrel, Florent Bouchard, Ammar Mian, Guillaume Ginolhac ·

    FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet

    arXiv:2604.22494v1 Announce Type: new Abstract: We introduce two federated learning frameworks for the classical SPDnet model operating on symmetric positive definite (SPD) matrices with Stiefel-constrained parameters. Unlike standard Euclidean averaging, which violates orthogona…

  2. arXiv stat.ML TIER_1 English(EN) · Guillaume Ginolhac ·

    FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet

    We introduce two federated learning frameworks for the classical SPDnet model operating on symmetric positive definite (SPD) matrices with Stiefel-constrained parameters. Unlike standard Euclidean averaging, which violates orthogonality, our approach preserves geometric structure…

相关实体

相关话题