Metraipolis › archive › dc_3ce4a0efa3db
Synchronous Multi-view Neural Diffusion — arXiv:2609.39019
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39019
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:45:44.528Z
- SHA-256 of the archived text
927d5fdbb0073abe00cf0a88f22303487486a69e0c7773d25fedc87ac6fd179d- Stable URL of this page
https://metraipolis.com/documento/dc_3ce4a0efa3db
How to cite
Synchronous Multi-view Neural Diffusion — arXiv:2609.39019 — arXiv (en), https://arxiv.org/abs/2609.39019 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ce4a0efa3db (Metraipolis archive dc_3ce4a0efa3db, sha256 927d5fdbb0073abe00cf0a88f22303487486a69e0c7773d25fedc87ac6fd179d)
BibTeX
@misc{dc3ce4a0efa3db,
title = {Synchronous Multi-view Neural Diffusion — arXiv:2609.39019},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39019},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ce4a0efa3db; sha256 927d5fdbb0073abe00cf0a88f22303487486a69e0c7773d25fedc87ac6fd179d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39019. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-view learning seeks to learn more comprehensive representations by exploiting the complementarity and consistency across diverse modalities or views. However, existing multi-view fusion strategies treat intra- and inter-view fusion as independent stages, without simultaneously considering the evolution within views and the dependency across views. Such an asynchronous fusion paradigm inevitably constrains cross-view interactions due to conflicting view-specific structural inductive biases. As a result, information flow is prone to distortion and compression along intermediate pathways, confining the model to learn within a restricted solution space. To address this, we propose Synchronous Multi-view Neural Diffusion (SynMDiff), which conceptualizes the multi-view feature space as a unified dynamical system driven by a diffusion process. By modeling the diffusion flow across arbitrary dyadic feature interactions in a joint space, SynMDiff enables the concurrent and adaptive intra- and inter-view information fusion. While a direct implementation of this synchronized mechanism incurs prohibitive computational costs, we further introduce an energy-based topological sampling strategy and an Ego-Net style centralized training architecture, ensuring both efficiency and scalability during learning and inference. Due to its conceptual elegance and computational efficacy, evaluations on real-world datasets demonstrate that SynMDiff outperforms the baselines by a large margin. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.39019 — 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 2026-10-07T13:18:10.305Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).