In federated learning, model averaging progressively degrades feature quality and feature-classifier alignment with network depth, a pattern the authors call Cumulative Feature Degradation.
Preservation of the global knowledge by not-true distillation in federated learning.Advances in Neural Information Processing Systems, 35:38461–38474, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
The Other Side of the Coin: Unveiling the Downsides of Model Aggregation in Federated Learning from a Layer-peeled Perspective
In federated learning, model averaging progressively degrades feature quality and feature-classifier alignment with network depth, a pattern the authors call Cumulative Feature Degradation.