Metraipolis › archive › dc_403c16b75e97
HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling — arXiv:2610.12393
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.12393
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:50:51.233Z
- SHA-256 of the archived text
82abe1608db01b252ff1df26a3afd3275c184066c683fce756a7b2468a341fc9- Stable URL of this page
https://metraipolis.com/documento/dc_403c16b75e97
How to cite
HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling — arXiv:2610.12393 — arXiv (en), https://arxiv.org/abs/2610.12393 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_403c16b75e97 (Metraipolis archive dc_403c16b75e97, sha256 82abe1608db01b252ff1df26a3afd3275c184066c683fce756a7b2468a341fc9)
BibTeX
@misc{dc403c16b75e97,
title = {HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling — arXiv:2610.12393},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.12393},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_403c16b75e97; sha256 82abe1608db01b252ff1df26a3afd3275c184066c683fce756a7b2468a341fc9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12393. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Self-supervised multimodal representation learning has achieved remarkable success across diverse domains, yet capturing synergistic information remains challenging due to the complexity of cross-modal interactions. Unlike the shared information across individual modalities, synergy arises when task-relevant signals emerge only from the joint configuration of multiple modalities and cannot be recovered from any modality in isolation. This work focuses on how to preserve the information capacity for such synergistic signals in multimodal representations. The key observation is that synergistic information is reflected in higher-order statistical dependence among modalities, which provides a principled target for explicitly modeling joint interactions. Motivated by this insight, we propose Higher-order Representation and Information Learning (HRIL), which constructs an empirical cross-moment tensor over modality embeddings to represent multi-way interactions. HRIL employs Tucker decomposition to obtain a core tensor, complemented by a synergy-aware regularizer that prevents energy concentration and preserves higher-order coupling capacity for synergistic information capture. Experiments on the controlled synergy task and real-world benchmarks demonstrate consistent improvements over existing multimodal contrastive methods, with notable gains on tasks dominated by synergistic interactions. Code is released at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.12393 — 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 2026-10-09T05:47:01.120Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).