Ziheng Chen
Scholar

Ziheng Chen

Google Scholar ID: 47Y-sn4AAAAJ
University of Trento
Geometric Deep Learning
Citations & Impact
All-time
Citations
230
 
H-index
8
 
i10-index
8
 
Publications
20
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • NeurIPS 2025: Riemannian attention via gyrovector spaces (GyroAtt)
  • TNNLS 2025: Riemannian BatchNorm via Cholesky geometry
  • IJCAI 2025: Riemannian self-attention
  • CVPR 2025: Riemannian BatchNorm for ill-conditioned SPD matrices
  • ICLR 2025: Gyrogroup Batch Normalization (GyroBN) and analysis of high-order pooling
  • NeurIPS 2024: RMLR – Multinomial Logistic Regression extended to general geometries
  • IEEE TIP 2024: Adaptive Riemannian metrics
  • IJCAI 2024: Grassmannian self-attention
  • CVPR 2024: SPD manifold classifier (SPDMLR)
  • ICLR 2024: Lie group approach to Riemannian Batch Normalization (LieBN)
  • Multiple papers selected for oral/poster presentation at VALSE 2024/2025
Background
  • Ph.D. student affiliated with the Multimedia and Human Understanding Group (MHUG) at University of Trento, Italy
  • Research focuses on the intersection of machine learning and differential geometry, particularly deep learning over Riemannian manifolds
  • Co-supervises students with Rui Wang
  • Maintains the GitHub repository 'Awesome-Riemannian-Deep-Learning' collecting resources on Riemannian deep learning
  • Contributor to geoopt, a popular Riemannian optimization library compatible with PyTorch