Metraipolis › archive › dc_31bbd385f103

Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization — arXiv:2608.22820

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.22820
License (as archived): CC0-1.0
Archived: 2026-10-18T07:45:03.629Z
SHA-256 of the archived text: 9eacc5768109e5d6926a397e9068bb595637dc9b6b5c1e2948cfdd932506600c
Stable URL of this page: https://metraipolis.com/documento/dc_31bbd385f103

How to cite

Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization — arXiv:2608.22820 — arXiv (en), https://arxiv.org/abs/2608.22820 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31bbd385f103 (Metraipolis archive dc_31bbd385f103, sha256 9eacc5768109e5d6926a397e9068bb595637dc9b6b5c1e2948cfdd932506600c)

BibTeX

@misc{dc31bbd385f103,
  title = {Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization — arXiv:2608.22820},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22820},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31bbd385f103; sha256 9eacc5768109e5d6926a397e9068bb595637dc9b6b5c1e2948cfdd932506600c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22820. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep learning models often produce performance disparities across demographic groups, due to the training data imbalance with respect to sensitive attributes such as gender or age. To address this problem, existing work has explored fair representation learning, data re-sampling, and adversarial training, which can be broadly categorized into two main approaches. Single-stage methods typically learn a shared representation for fairness, but often struggle to handle heterogeneous subgroup distributions. Two-stage methods learn representations separately from the final prediction task, which can lead to misalignment between fairness objectives and downstream predictions. We identify routing-induced bias, a failure mode in which subgroup imbalance drives the gating network to route subgroups onto a few experts, and propose an end-to-end Mixture-of-Experts (MoE) framework that corrects it. Specifically, we apply subgroup reweighting to correct data imbalance, and introduce gate entropy regularization to prevent routing from collapsing onto subgroup attributes, keeping expert utilization both balanced and interpretable. Beyond improving fairness, the routing distribution offers an interpretable view of how subgroups are allocated across experts. Experimental results demonstrate that the proposed approach improves fairness while maintaining competitive predictive performance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.22820 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T07:37:52.902Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).