FEAT mitigates representation collapse and prediction bias in federated continual learning by aligning feature angular similarities to shared Equiangular Tight Frame prototypes and removing task-irrelevant directional components from embeddings.
Cross-training with prototypical distilla- tion for improving the generalization of federated learning
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
-
From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity
FEAT mitigates representation collapse and prediction bias in federated continual learning by aligning feature angular similarities to shared Equiangular Tight Frame prototypes and removing task-irrelevant directional components from embeddings.