Applying Fairness Constraints on Graph Node Ranks Under Personalization Bias

摘要

In this work we address algorithmic fairness concerns that arise when graph nodes are ranked based on their structural relatedness to a personalized set of query nodes. In particular, we aim to mitigate disparate impact, i.e. the difference in average rank between nodes of a sensitive attribute compared to the rest, while also preserving node rank quality. To do this, we introduce a personalization editing mechanism that helps ranking algorithms achieve different trade-offs between fairness constraints and rank changes. In experiments across four real-world social graphs and two base ranking algorithms, our approach outperforms baseline and existing methods in uniformly mitigating disparate impact, even when personalization suffers from extreme bias. In particular, it achieves better trade-offs between fairness and node rank quality under disparate impact constraints.