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.
2d-oob: Attributing data con- tribution through joint valuation framework.Advances in Neural Information Processing Systems, 37:46764– 46790, 2024b
3 Pith papers cite this work. Polarity classification is still indexing.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Secure-CHG introduces a cascaded defense with statistical filtering early and CHG-Shapley valuation later to mitigate late-stage failure against backdoor attacks in federated learning, reporting 2.3x and 2.0x lower attack success rates than Krum and Trimmed Mean on CIFAR-10, MedMNIST, and NEU-SDDB.
A single adversary in distributed training inflates its attribution value via latent optimization on synthetic batches without degrading accuracy or triggering basic defenses.
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.
-
Secure-CHG: A Comprehensive Framework for Robust and Fair Federated Learning via Hybrid Defense and Contribution-Aware Trust
Secure-CHG introduces a cascaded defense with statistical filtering early and CHG-Shapley valuation later to mitigate late-stage failure against backdoor attacks in federated learning, reporting 2.3x and 2.0x lower attack success rates than Krum and Trimmed Mean on CIFAR-10, MedMNIST, and NEU-SDDB.
-
On the Fragility of Data Attribution When Learning Is Distributed
A single adversary in distributed training inflates its attribution value via latent optimization on synthetic batches without degrading accuracy or triggering basic defenses.