Metraipolis › archive › dc_44aa2e4b0979
Balancing Multimodal Learning via Functional Progress — arXiv:2610.03035
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.03035
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:10:04.444Z
- SHA-256 of the archived text
a0a276dab150e343b795f202bd180feeee083630ac74ae950c466e913b2e1674- Stable URL of this page
https://metraipolis.com/documento/dc_44aa2e4b0979
How to cite
Balancing Multimodal Learning via Functional Progress — arXiv:2610.03035 — arXiv, https://arxiv.org/abs/2610.03035 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44aa2e4b0979 (Metraipolis archive dc_44aa2e4b0979, sha256 a0a276dab150e343b795f202bd180feeee083630ac74ae950c466e913b2e1674)
BibTeX
@misc{dc44aa2e4b0979,
title = {Balancing Multimodal Learning via Functional Progress — arXiv:2610.03035},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.03035},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44aa2e4b0979; sha256 a0a276dab150e343b795f202bd180feeee083630ac74ae950c466e913b2e1674},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03035. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal learning often suffers from modality imbalance, where the joint optimization process is dominated by a single modality. Existing methods typically estimate modality imbalance from score disparities derived from prediction uncertainty or optimization statistics. However, due to distinct prediction uncertainty and learning dynamics across modalities, direct comparison of such scores may misinterpret intrinsic modality differences as progress gaps, leading to biased imbalance estimation. In this paper, we propose Function-Space Guided Multimodal Optimization (FGMO), which leverages a function-space progress signal to assess modality-wise optimization progress and coordinate optimization across modalities to alleviate modality imbalance. Specifically, we introduce Functional Progress Estimation (FPE) to measure each modality's update-induced function-space response and calibrate it against a loss-aligned unimodal reference, producing a comparable progress signal. Based on this signal, Functional Response Control (FRC) redistributes modality-level function-space budgets and realizes the target responses through tensor-wise learning-rate adjustment. Theoretical analysis establishes a one-step target-contraction property of FRC under bounded controller-state mismatch, and extensive experiments demonstrate the effectiveness of FGMO across multiple multimodal benchmarks. 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/2610.03035 — 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 2026-10-05T23:01:38.663Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).