Federated Unsupervised Skeletal Action Recognition From Condensation to Expansion

Summary

Fed-C&E is a federated learning method for unsupervised skeleton-based action recognition that uses a closed-loop condensation-expansion paradigm. Clients condense their data, and the server expands it through a dual-level mechanism that synthesizes samples with a prototype-to-sequence similarity transformation matrix pool and supplements global information using second-order client statistics. The authors report that it outperforms aggregate-then-adapt FL methods across multiple datasets while preserving data privacy.