New Approach to Federated Class Incremental Learning Uses Pseudo Features Without Exemplars
Researchers propose a pseudo feature-based method for federated class incremental learning that handles continuously arriving new data without storing exemplars, addressing a limitation of standard federated learning setups.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-13 05:00 · arXiv cs.CV
Federated Class Incremental Learning: A Pseudo Feature Based Approach Without Exemplars