Metraipolis › archive › dc_49fcfb2b9457

Modality Agreement- and Conflict-Aware Prototype Hypergraph Learning for Multimodal Intent Understanding — arXiv:2608.04054

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04054
License (as archived)
CC0-1.0
Archived
2026-10-31T11:13:29.816Z
SHA-256 of the archived text
2b442a4afe01dccc750da6b7020fdb16f681acec206f7544f57af90fd28370f8
Stable URL of this page
https://metraipolis.com/documento/dc_49fcfb2b9457

How to cite

Modality Agreement- and Conflict-Aware Prototype Hypergraph Learning for Multimodal Intent Understanding — arXiv:2608.04054 — arXiv (en), https://arxiv.org/abs/2608.04054 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_49fcfb2b9457 (Metraipolis archive dc_49fcfb2b9457, sha256 2b442a4afe01dccc750da6b7020fdb16f681acec206f7544f57af90fd28370f8)
BibTeX
@misc{dc49fcfb2b9457,
  title = {Modality Agreement- and Conflict-Aware Prototype Hypergraph Learning for Multimodal Intent Understanding — arXiv:2608.04054},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04054},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_49fcfb2b9457; sha256 2b442a4afe01dccc750da6b7020fdb16f681acec206f7544f57af90fd28370f8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04054. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal intent recognition requires understanding not only what textual, acoustic, and visual signals share, but also how they disagree. Such disagreement is frequently class-informative; for example, lexical positivity accompanied by incongruent vocal or facial behavior may indicate sarcasm or taunting, yet most fusion methods either encourage modality alignment or treat inconsistency as uncertainty to be suppressed. We propose MACH (Modality Agreement- and Conflict-aware prototype Hypergraph), a hierarchical prototype-hypergraph framework that represents multimodal agreement and conflict as distinct, recurring relational structures. MACH progressively composes unimodal representations into bimodal and trimodal abstractions. At each applicable level, modality-composition anchors activate sparse agreement prototype hypergraphs that capture reusable consensus patterns, while a separate conflict pathway maps cross-modal discrepancies to dedicated conflict prototype hypergraphs. The two pathways are combined through a feature-wise, sample-adaptive arbitration mechanism, enabling the model to preserve informative disagreement while suppressing incidental modality noise. A progressive optimization strategy stabilizes the interdependent hierarchy before joint agreement-conflict learning. Experiments on benchmark datasets demonstrate the effectiveness of the proposed formulation, while component and robustness analyses validate the distinct roles of hierarchical composition, prototype-mediated semantic refinement, and agreement-conflict arbitration.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Multimedia (cs.MM) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.04054 — 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 2026-10-31T11:02:13.471Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).