A framework and RL algorithm for long-term fairness under selective labels that decomposes the true fairness measure into observed fairness plus prediction bias and provides sufficient conditions based on predictor confidence.
Proceedings of the 14th ACM International Conference on Web Search and Data Mining , pages =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
A latent-cluster quasi-Bayesian method with restarted updates yields sublinear cumulative Wasserstein-1 regret for online distributional prediction under drift and adversarial corruption.
citing papers explorer
-
Long-term Fairness with Selective Labels
A framework and RL algorithm for long-term fairness under selective labels that decomposes the true fairness measure into observed fairness plus prediction bias and provides sufficient conditions based on predictor confidence.
-
Online Distributional Prediction via Latent Cluster Geometry Under Drift and Corruption
A latent-cluster quasi-Bayesian method with restarted updates yields sublinear cumulative Wasserstein-1 regret for online distributional prediction under drift and adversarial corruption.