FedBST2 min read
FedBST: Bilateral Self-Training for Unsupervised Federated Classification
Unsupervised federated learning with Vision-Language Models (e.g., CLIP) offers a promising solution for label-free classification, yet its performance often degrades under severe non-IID shifts.
By Aijing Yu, Kuangpu Guo, Jian Liang, Xiao-Yu ZhangarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Oct 23, 2026.
Comments
Sign in to join the discussion.