AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach

Xuan Son Nguyen, Shuo Yang

ICML 2023 · Learning theory and algorithms › Matrix and tensor methods · approach: Geometry of low-rank and SPD structure · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
Replace FRmap and ReOrth layers of GrNet with Grassmann translation layer (GyroGr)GrNet · HDM05, FPHA, NTU60accuracy (%): +3.60, +2.79, +2.14Improved
Use Grassmann scaling layer instead of translation layer in GyroGr (ablation)GyroGr · HDM05, FPHA, NTU60accuracy (%): -10.63, -18.96, -12.34Hurt
Use ONB perspective (Gr~24,12) instead of projector perspective for KG completion embeddingsGyroGr-KGC · WN18RR validationH@1: +1 point (39.5 vs 38.5)Improved
Use ONB perspective (Gr~24,12) instead of projector perspective for KG completion embeddingsGyroGr-KGC · FB15k-237 validationH@10: +1.4 points (48.2 vs 46.8)Improved
SPD MLR with AI gyrovector space on top of GyroAI-HAUNet featuresGyroAI-HAUNet · HDM05, FPHA, NTU60accuracy (%): HDM05 +1.70, FPHA mixed (MLR-LE best), NTU60 +1.76Mixed
Use Log-Cholesky MLR instead of LE or AI MLR on top of GyroAI-HAUNet (ablation)GyroAI-HAUNet MLR head · HDM05, FPHA, NTU60accuracy (%): MLR-LC 71.35, 88.62, 88.24 vs MLR-LE/AI ~96Hurt
Use GyroAI or GyroLE SPD network with AI/LE metrics instead of SPDNet/SPDNetBNSPD networks · FPHA and NTU60accuracy (%): GyroLE 94.61 vs SPDNetBN 91.34 on FPHA; GyroAI 82.75 vs 79.61 on NTU60Improved
Use Log-Cholesky metric (GyroLC) instead of LE or AI in SPD network (ablation)GyroSPD network · HDM05, FPHA, NTU60accuracy (%): 63.78, 82.43, 72.26 vs 72.64-94.61 for LE/AIHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy