Metraipolis › archive › dc_9045d79e76bf

Canonical Correlation Neural Networks — arXiv:2611.07212

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07212
License (as archived)
CC0-1.0
Archived
2026-11-06T14:44:11.182Z
SHA-256 of the archived text
4e80de73850d6453b921047ddc0a0be3910a6bdd1c5c468f57342e4d08aedcfe
Stable URL of this page
https://metraipolis.com/documento/dc_9045d79e76bf

How to cite

Canonical Correlation Neural Networks — arXiv:2611.07212 — arXiv (en), https://arxiv.org/abs/2611.07212 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9045d79e76bf (Metraipolis archive dc_9045d79e76bf, sha256 4e80de73850d6453b921047ddc0a0be3910a6bdd1c5c468f57342e4d08aedcfe)
BibTeX
@misc{dc9045d79e76bf,
  title = {Canonical Correlation Neural Networks — arXiv:2611.07212},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07212},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9045d79e76bf; sha256 4e80de73850d6453b921047ddc0a0be3910a6bdd1c5c468f57342e4d08aedcfe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07212. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Relational inductive biases such as grids or graphs allow neural networks with fewer trainable parameters and improved generalization, but require a known structure beforehand. When no structure is available, the covariance matrix provides a principled substitute, and coVariance Neural Networks (VNNs) have shown that using it yields models that are theoretically grounded in Principal Component Analysis, stable to finite-sample estimation errors and parameter-efficient. This framework, however, is limited to single-view data, whereas many applications observe the same phenomenon through multiple views, each with its own in-view covariance and a cross-view covariance linking them. To incorporate these matrices as inductive biases in a principled way, we introduce CAnonical correlation NEural networks (CANEs), architectures that use in-view and cross-view covariances as distinct relational biases to solve downstream tasks. Via spectral analysis, CANEs draw analogies with Canonical Correlation Analysis (CCA), a classical technique to project two-view data onto a correlated subspace. However, while CCA's objective is to compute shared view representations, CANEs are trained to solve a downstream task directly. We bound their output error under finite-sample covariance perturbations and show that it depends on controllable Lipschitz constants of the learned filters in place of the singular-value gap that governs the stability of CCA, thus guaranteeing better robustness. Experiments on seven datasets from brain imaging and motion sensing show that CANEs match or outperform single-view, two-view and CCA-based baselines, often with fewer parameters, and retain their performance when covariances are re-estimated from fewer samples.

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/2611.07212 — 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 2026-11-06T14:21:42.617Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).