Metraipolis › archive › dc_44bcd789903b
MedMix: Specialization-Consistent Federated Sparse MoEs under Modality Heterogeneity — arXiv:2608.13911
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13911
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:30:27.567Z
- SHA-256 of the archived text
6325248b5d08b984ec70dc2e0a4077319a029b90400e685c4212f561ec10b36d- Stable URL of this page
https://metraipolis.com/documento/dc_44bcd789903b
How to cite
MedMix: Specialization-Consistent Federated Sparse MoEs under Modality Heterogeneity — arXiv:2608.13911 — arXiv (en), https://arxiv.org/abs/2608.13911 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44bcd789903b (Metraipolis archive dc_44bcd789903b, sha256 6325248b5d08b984ec70dc2e0a4077319a029b90400e685c4212f561ec10b36d)
BibTeX
@misc{dc44bcd789903b,
title = {MedMix: Specialization-Consistent Federated Sparse MoEs under Modality Heterogeneity — arXiv:2608.13911},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13911},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44bcd789903b; sha256 6325248b5d08b984ec70dc2e0a4077319a029b90400e685c4212f561ec10b36d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13911. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated multimodal medical AI faces modality heterogeneity at both the client and sample levels: clients may systematically lack access to specific modality types, while individual records within the same client may contain different partial modality subsets. Sparse Mixture-of-Experts (MoE) architectures are a promising remedy for modality-adaptive computation, but their use in federated learning is fragile under cross-client modality heterogeneity, where locally learned routing policies can diverge across clients and drive experts toward incompatible specializations. Different clients may assign the same observed modality configuration to different experts, or train similarly indexed experts on different missing-modality configurations, causing standard aggregation to misalign or overwrite the expert specialization that sparse MoEs are intended to learn. To address this challenge, we propose MedMix, a semantic-alignment framework for federated multimodal sparse MoEs that coordinates cross-client routing and expert specialization using modality context. At the client side, MedMix uses modality-context-aware routing to guide expert selection using each token's modality identity, position, and incompleteness context. Across clients, it uses consensus-guided routing alignment to construct server-side consensus anchors for shared modality patterns and align local routing distributions across clients. Complementing these routing mechanisms, client-adaptive expert aggregation leverages client-specific modality-pattern prototypes to match and aggregate functionally similar experts across clients. Experiments on real-world multimodal medical datasets show that MedMix achieves the best average F1 across diverse modality heterogeneity and modality incompleteness settings, with especially clear gains under severe heterogeneity. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.13911 — 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 2026-10-19T02:26:17.780Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).