K-SVFair-FBF uses the new K-Shapley value to achieve meritocratic fairness with O(T^{3/4}) regret in budgeted combinatorial bandits under full-bandit feedback.
The configurationR= 500 , L= 200 provides the best trade-off between performance and efficiency, yielding stable convergence and fairness consistency across all datasets
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
-
Meritocratic Fairness in Budgeted Combinatorial Multi-armed Bandits via Shapley Values
K-SVFair-FBF uses the new K-Shapley value to achieve meritocratic fairness with O(T^{3/4}) regret in budgeted combinatorial bandits under full-bandit feedback.