Jaeik Kim

SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning

This paper reinterprets FCIL as a unified multi-task learning problem, where both client and task updates are represented as adaptation vectors in a shared parameter space and proposes Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors (SUM), a purely server-side framework that performs geometric surgery on adaptation vectors during aggregation.