HetPFL adaptively samples performance-fairness preferences per client and fuses client hypernetworks preference-by-preference to learn better local and global Pareto fronts.
The reference point r in calculating hypervol- ume is set to (1, 1)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Heterogeneous Performance-Fairness Trade-offs in Federated Learning
HetPFL adaptively samples performance-fairness preferences per client and fuses client hypernetworks preference-by-preference to learn better local and global Pareto fronts.