CELM uses class-wise evidence scores from client logits to compute contribution weights that upweight clients strong on underrepresented classes for stable aggregation in non-IID federated learning.
Encyclopedia of mathematics78(2001)
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
-
Data-Free Client Contribution Estimation via Logit Maximization for Federated Learning
CELM uses class-wise evidence scores from client logits to compute contribution weights that upweight clients strong on underrepresented classes for stable aggregation in non-IID federated learning.