arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.08628cs.CVcs.AI
收藏

学习拓扑驱动的多子空间融合用于Grassmannian深度网络

Learning Topology-Driven Multi-Subspace Fusion for Grassmannian Deep Network

Xuan Yu, Tianyang Xu

AI总结:

本文提出拓扑驱动的多子空间融合框架,通过拓扑收敛分析动态选择和加权任务相关子空间,提升Grassmannian上的子空间协作能力,实验显示在3D动作识别、EEG分类和图任务中表现优异。

摘要:

Grassmannian流形通过将高维数据建模为低维子空间,为几何表示学习提供强大载体。然而,现有方法主要依赖静态单子空间表示,忽视了多个子空间之间动态交互对捕捉复杂几何结构的重要性。为此,我们提出拓扑驱动的多子空间融合框架,使Grassmannian上实现自适应子空间协作。我们的解决方案引入两项关键创新:(1) 受Kolmogorov-Arnold表示定理启发,提出自适应多子空间建模机制,通过拓扑收敛分析动态选择和加权任务相关子空间;(2) 多子空间交互块通过流形上的Fréchet均值优化融合异构几何表示。理论上,我们建立了在投影度量拓扑下自适应子空间的收敛保证,确保稳定梯度优化。实践中,我们整合Riemannian批量归一化和互信息正则化以增强判别性和鲁棒性。广泛实验在3D动作识别(HDM05, FPHA)、EEG分类(MAMEM-SSVEPII)和图任务中显示了最先进的性能。我们的工作不仅推进了几何深度学习,还成功将欧几里得网络中已证明的多通道交互哲学适应到非欧几里得领域,实现了优越的判别性和可解释性。

英文摘要:

Grassmannian manifold offers a powerful carrier for geometric representation learning by modelling high-dimensional data as low-dimensional subspaces. However, existing approaches predominantly rely on static single-subspace representations, neglecting the dynamic interplay between multiple subspaces critical for capturing complex geometric structures. To address this limitation, we propose a topology-driven multi-subspace fusion framework that enables adaptive subspace collaboration on the Grassmannian. Our solution introduces two key innovations: (1) Inspired by the Kolmogorov-Arnold representation theorem, an adaptive multi-subspace modelling mechanism is proposed that dynamically selects and weights task-relevant subspaces via topological convergence analysis, and (2) a multi-subspace interaction block that fuses heterogeneous geometric representations through Fréchet mean optimisation on the manifold. Theoretically, we establish the convergence guarantees of adaptive subspaces under a projection metric topology, ensuring stable gradient-based optimisation. Practically, we integrate Riemannian batch normalisation and mutual information regularisation to enhance discriminability and robustness. Extensive experiments on 3D action recognition (HDM05, FPHA), EEG classification (MAMEM-SSVEPII), and graph tasks demonstrate state-of-the-art performance. Our work not only advances geometric deep learning but also successfully adapts the proven multi-channel interaction philosophy of Euclidean networks to non-Euclidean domains, achieving superior discriminability and interpretability.

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。

↑