Metraipolis › archive › dc_9270ede52cfa

FedIA: Instance-Aware Cross-Modal Representations for Federated Prompt Learning — arXiv:2611.05994

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05994
License (as archived)
CC0-1.0
Archived
2026-11-05T18:22:37.967Z
SHA-256 of the archived text
b5555c5bdf9247f54706b40145ce6e780cd1f8366ff009ebb24cff28d7cf67b2
Stable URL of this page
https://metraipolis.com/documento/dc_9270ede52cfa

How to cite

FedIA: Instance-Aware Cross-Modal Representations for Federated Prompt Learning — arXiv:2611.05994 — arXiv (en), https://arxiv.org/abs/2611.05994 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9270ede52cfa (Metraipolis archive dc_9270ede52cfa, sha256 b5555c5bdf9247f54706b40145ce6e780cd1f8366ff009ebb24cff28d7cf67b2)
BibTeX
@misc{dc9270ede52cfa,
  title = {FedIA: Instance-Aware Cross-Modal Representations for Federated Prompt Learning — arXiv:2611.05994},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05994},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9270ede52cfa; sha256 b5555c5bdf9247f54706b40145ce6e780cd1f8366ff009ebb24cff28d7cf67b2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05994. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated Prompt Learning (FPL) enables parameter-efficient adaptation of pre-trained Vision-Language Models across decentralized clients without exchanging raw data. To cope with cross-client heterogeneity, existing FPL methods typically pair a globally shared prompt with a client-specific local prompt. However, this design personalizes only at the client level: the same local prompt is applied to all samples of a client, and the global and local prompts are combined in an input-agnostic, fixed manner. Consequently, it overlooks the substantial visual variations among samples within the same client and cannot adjust the balance between shared and personalized knowledge to each input. To address these limitations, we propose Federated Prompt Learning with Instance-Aware Cross-Modal Representations (FedIA), an FPL framework that learns instance-aware cross-modal representations. Specifically, FedIA first uses global text prompts as client-invariant semantic anchors to select image patches most relevant to each candidate class, suppressing distracting regions. The selected visual evidence then conditions the generation of instance-aware local text representations. Finally, an adaptive global-local fusion module calibrates the contributions of local and global text representations for each image-class pair. In this way, FedIA shifts personalization in FPL from the client level to the instance level while preserving the semantic knowledge shared across clients. Extensive experiments under domain shift, pathological label skew, and Dirichlet-based label skew show that FedIA outperforms FPL baselines, with maximum accuracy gains of 1.44\%-4.37\% over the latest baseline across the three settings. Ablation studies and analyses further verify the complementary contributions of instance-aware representation generation and adaptive global-local fusion.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.05994 — 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 2026-11-05T18:15:49.036Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).