2 papers
cs.LG2026
Geometric Data Perturbation with Noisy-Anchor Alignment for Privacy-Preserving Collaborative Learning
Keiyu Nosaka, Yamato Suetake, Yuichi Takano +2
Geometric data perturbation enables one-shot representation sharing for privacy-preserving collaborative learning: each participant applies a secret distance-preserving transformat…
cs.LG2024
Data Collaboration Analysis with Orthonormal Basis Selection and Alignment
Keiyu Nosaka, Yamato Suetake, Yuichi Takano +1
Data Collaboration (DC) enables multiple parties to jointly train a model by sharing only linear projections of their private datasets. The core challenge in DC is to align the bas…