Foundation model priors amplify worst-client disparity under extreme federated heterogeneity, creating a fairness paradox where larger models perform worse for disadvantaged clients.
InAdvances in Neural Information Processing Systems (NeurIPS), volume 33, 9143–9154
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
-
When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity
Foundation model priors amplify worst-client disparity under extreme federated heterogeneity, creating a fairness paradox where larger models perform worse for disadvantaged clients.