Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Topology-Driven Multi-Subspace Fusion for Grassmannian Deep Networks
Xuan Yu, Tianyang Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-subspace interaction (adaptive subspaces) (ablation) | GMSF-Net-1Block · FPHA | accuracy: 80.68% -> 90.43% | Improved |
| add multi-subspace interaction (adaptive subspaces) (ablation) | GMSF-Net-1Block · HDM05 | accuracy: 56.49% -> 63.64% | Improved |
| add multi-subspace interaction (adaptive subspaces) (ablation) | GMSF-Net-1Block · MAMEM-SSVEP-II | accuracy: 59.83% -> 66.74% | Improved |
| use adaptive instead of random subspace construction (ablation) | GMSF-Net-1Block with interaction · HDM05 | accuracy: 50.29% -> 63.64% | Improved |
| use adaptive instead of fixed subspace construction (ablation) | GMSF-Net-1Block with interaction · FPHA | accuracy: 83.06% -> 90.43% | Improved |
| use adaptive instead of fixed subspace construction (ablation) | GMSF-Net-1Block with interaction · MAMEM-SSVEP-II | accuracy: 66.05% -> 66.74% | Improved |
| stack more interaction blocks (1 to 3) (ablation) | GMSF-Net · FPHA | accuracy: 90.43% -> 91.22% | Improved |
| stack more interaction blocks (1 to 3) (ablation) | GMSF-Net · MAMEM-SSVEP-II | accuracy: 66.74% -> 66.87% | No clear effect |
| GMSF-Net vs HNN on graph datasets | GMSF-Net-1Block · PubMed LP | accuracy: 94.9% -> 94.6% | No clear effect |
| GMSF-Net vs HNN on graph datasets | GMSF-Net-1Block · Disease NC | accuracy: 41.0% -> 79.7% | Improved |
Closest papers by meaning
- Matrix Manifold Neural Networks++ (ICLR 2024 · similarity 0.87)
- Random features for Grassmannian kernel approximation with bounded rank-one projections (NeurIPS 2026 · similarity 0.85)
- Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves (NeurIPS 2026 · similarity 0.85)
- Building Transformation Layers for Riemannian Neural Networks (NeurIPS 2026 · similarity 0.85)
- Spiking Graph Neural Network on Riemannian Manifolds (NeurIPS 2024 · similarity 0.84)
- Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
