Exploring How Fair Model Representations Relate to Fair Recommendations

ArXi:2603.24396v1 Announce Type: cross One of the many fairness definitions pursued in recent recommender system research targets mitigating graphic information encoded in model representations. Models optimized for this definition are typically evaluated on how well graphic attributes can be classified given model representations, with the (implicit) assumption that this measure accurately reflects \textit{recommendation parity}, i.e., how similar recommendations given to different users are.