Achieving Counterfactual Fairness for Causal Bandit
This addresses fairness in online recommendations for customers, but it is incremental as it builds on existing causal bandit methods.
The paper tackles the problem of maximizing expected reward in online recommendation while ensuring user-side fairness, proposing algorithms that achieve counterfactual individual fairness with demonstrated effectiveness in theoretical and empirical evaluations.
In online recommendation, customers arrive in a sequential and stochastic manner from an underlying distribution and the online decision model recommends a chosen item for each arriving individual based on some strategy. We study how to recommend an item at each step to maximize the expected reward while achieving user-side fairness for customers, i.e., customers who share similar profiles will receive a similar reward regardless of their sensitive attributes and items being recommended. By incorporating causal inference into bandits and adopting soft intervention to model the arm selection strategy, we first propose the d-separation based UCB algorithm (D-UCB) to explore the utilization of the d-separation set in reducing the amount of exploration needed to achieve low cumulative regret. Based on that, we then propose the fair causal bandit (F-UCB) for achieving the counterfactual individual fairness. Both theoretical analysis and empirical evaluation demonstrate effectiveness of our algorithms.