Metraipolis › archive › dc_edd3bb1e0d47
Role-Aware Server Optimization for Multimodal Federated Learning with Missing Modalities — arXiv:2610.41193
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41193
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:11:46.469Z
- SHA-256 of the archived text
ed5fa5fa09b3944dfff69edccf5018925eeb04358ef5c164c6295b2f4b1ca654- Stable URL of this page
https://metraipolis.com/documento/dc_edd3bb1e0d47
How to cite
Role-Aware Server Optimization for Multimodal Federated Learning with Missing Modalities — arXiv:2610.41193 — arXiv (en), https://arxiv.org/abs/2610.41193 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edd3bb1e0d47 (Metraipolis archive dc_edd3bb1e0d47, sha256 ed5fa5fa09b3944dfff69edccf5018925eeb04358ef5c164c6295b2f4b1ca654)
BibTeX
@misc{dcedd3bb1e0d47,
title = {Role-Aware Server Optimization for Multimodal Federated Learning with Missing Modalities — arXiv:2610.41193},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41193},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edd3bb1e0d47; sha256 ed5fa5fa09b3944dfff69edccf5018925eeb04358ef5c164c6295b2f4b1ca654},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41193. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal federated learning (MFL) trains a shared model by aggregating client updates without exchanging raw data. Under missing modalities, clients adapt active modality encoders and a shared prediction block (fusion and classifier) to different input subsets. This raises two server-side questions: which clients should contribute to each component, and how should their aggregates be incorporated across rounds? We observe that an absent-modality encoder can still adapt through missing-input handling. Availability- based aggregation can therefore omit its update while retaining jointly learned prediction-block updates. Contributor selection also shapes server momentum, a weighted history of aggregated updates. We observe that prediction-block momentum can improve or reduce performance depending on the encoder update policy. We therefore propose Role-Aware Server Optimization (RASO), which coordinates contributor selection with role-specific server updates. RASO selects contributors through prediction dependence and inclusion in local optimization, retains encoder momentum, and synchronizes the shared prediction block to its current aggregate. Experiments across datasets and fusion architectures demonstrate the effectiveness of RASO under missing modalities. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.41193 — 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 2026-11-03T08:02:38.910Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).