Author

Yukihiko Okada

h-index 3 View on Semantic Scholar

We have 2 of 27 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

FedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge Editing

Multiple institutions may each hold their own private knowledge edits and wish to integrate them into a single large language model without sharing raw edit requests. Null-space-constrained editing methods such as AlphaEdit mathematically guarantee that each update leaves unrelated knowledge intact, while collaborative...

Sota Sugawara, Yukihiko Okada · 0 citations

#machine learning Preprint Aug 2026

Geometric Data Perturbation with Noisy-Anchor Alignment for Privacy-Preserving Collaborative Learning

Experiments on MNIST and CelebA show that, across the evaluated attacks and deployment settings, anchor noise achieves higher learning accuracy than private-data noise at comparable measured leakage, yielding a more favorable privacy-utility trade-off under the specified collusion model.

Keiyu Nosaka, Yamato Suetake, Y. Takano et al. · 0 citations