DeepAI AI Chat
Log In Sign Up

Fair Learning-to-Rank from Implicit Feedback

by   Himank Yadav, et al.
Tsinghua University
cornell university

Addressing unfairness in rankings has become an increasingly important problem due to the growing influence of rankings in critical decision making, yet existing learning-to-rank algorithms suffer from multiple drawbacks when learning fair ranking policies from implicit feedback. Some algorithms suffer from extrinsic reasons of unfairness due to inherent selection biases in implicit feedback leading to rich-get-richer dynamics. While those that address the biased nature of implicit feedback suffer from intrinsic reasons of unfairness due to the lack of explicit control over the allocation of exposure based on merit (i.e, relevance). In both cases, the learned ranking policy can be unfair and lead to suboptimal results. To this end, we propose a novel learning-to-rank framework, FULTR, that is the first to address both intrinsic and extrinsic reasons of unfairness when learning ranking policies from logged implicit feedback. Considering the needs of various applications, we define a class of amortized fairness of exposure constraints with respect to items based on their merit, and propose corresponding counterfactual estimators of disparity (aka unfairness) and utility that are also robust to click noise. Furthermore, we provide an efficient algorithm that optimizes both utility and fairness via a policy-gradient approach. To show that our proposed algorithm learns accurate and fair ranking policies from biased and noisy feedback, we provide empirical results beyond the theoretical justification of the framework.


page 1

page 2

page 3

page 4


Policy Learning for Fairness in Ranking

Conventional Learning-to-Rank (LTR) methods optimize the utility of the ...

Maximizing Marginal Fairness for Dynamic Learning to Rank

Rankings, especially those in search and recommendation systems, often d...

Sayer: Using Implicit Feedback to Optimize System Policies

We observe that many system policies that make threshold decisions invol...

Controlling Fairness and Bias in Dynamic Learning-to-Rank

Rankings are the primary interface through which many online platforms m...

Fairness of Exposure in Rankings

Rankings are ubiquitous in the online world today. As we have transition...

U-rank: Utility-oriented Learning to Rank with Implicit Feedback

Learning to rank with implicit feedback is one of the most important tas...

Pareto-Optimal Fairness-Utility Amortizations in Rankings with a DBN Exposure Model

In recent years, it has become clear that rankings delivered in many are...

Code Repositories