Metraipolis › archive › dc_57529fa571a7
Probe-Guided Gradient Balancing for Multimodal Learning — arXiv:2611.02651
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02651
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:48:28.082Z
- SHA-256 of the archived text
d10b022495b0b1dcdab03ebbe3f938e2591241884fa82d919953e5dc9793f3b0- Stable URL of this page
https://metraipolis.com/documento/dc_57529fa571a7
How to cite
Probe-Guided Gradient Balancing for Multimodal Learning — arXiv:2611.02651 — arXiv (en), https://arxiv.org/abs/2611.02651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57529fa571a7 (Metraipolis archive dc_57529fa571a7, sha256 d10b022495b0b1dcdab03ebbe3f938e2591241884fa82d919953e5dc9793f3b0)
BibTeX
@misc{dc57529fa571a7,
title = {Probe-Guided Gradient Balancing for Multimodal Learning — arXiv:2611.02651},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02651},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57529fa571a7; sha256 d10b022495b0b1dcdab03ebbe3f938e2591241884fa82d919953e5dc9793f3b0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Jointly trained multimodal networks frequently underutilize weaker modalities, as faster-learning modalities dominate the shared fusion objective and suppress gradients reaching slower ones. Most existing approaches throttle dominant modalities, whereas directly boosting weaker modalities often fails because monitoring signals derived from the joint loss remain dominated by stronger modalities. We propose Probe-Guided Gradient Boosting (PGGB), a gradient modulation approach that boosts weaker modalities while preserving the strength of dominant ones. PGGB attaches lightweight linear classifiers to stop-gradient features from each modality to estimate representation quality independently. The gap between these scores, termed the utilization gap, provides an imbalance signal used to adaptively scale weaker-modality gradients through bounded and smoothed modulation. PGGB is composable with throttling methods, as it leaves the loss function and fusion architecture unchanged. Experiments across eight benchmarks spanning four domains and 2-4 modalities demonstrate that PGGB outperforms state-of-the-art methods on highly imbalanced multimodal datasets while remaining competitive under low or negligible imbalance. We further establish bounded scaling, self-attenuation, and a descent bound for standard SGD under smoothness and bounded-variance assumptions. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.02651 — 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 2026-11-03T10:39:50.589Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).