FL-Sailer combines adaptive leverage score sampling and an invariant VAE in a federated setup to enable privacy-preserving analysis of high-dimensional sparse scATAC-seq data, with a convergence bound and reported outperformance of centralized baselines.
We define the row-space lifting matrix Rlift∈Rd× s as: Rlift :=V (T ⊤V )†
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FL-Sailer: Efficient and Privacy-Preserving Federated Learning for Scalable Single-Cell Epigenetic Data Analysis via Adaptive Sampling
FL-Sailer combines adaptive leverage score sampling and an invariant VAE in a federated setup to enable privacy-preserving analysis of high-dimensional sparse scATAC-seq data, with a convergence bound and reported outperformance of centralized baselines.