Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization

The paper proposes a fairness-aware Mixture-of-Experts (MoE) framework that tackles routing-induced bias by applying subgroup reweighting to correct data imbalance and gate entropy regularization to prevent the gating network from collapsing onto subgroup attributes. This end-to-end approach keeps expert utilization balanced and interpretable, offering a clear view of how subgroups are allocated across experts. Experiments show that the method improves fairness while maintaining competitive predictive performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• safety