Metraipolis › archive › dc_b36627107d04
Permutation-Equivariant Flow Matching for Alignment-Free Neural Weight Generation — arXiv:2609.32833
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32833
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:36:54.068Z
- SHA-256 of the archived text
77a7da3fcee3b4766e1c49024a7cf97b27b23f601ae2ef5822ebbfefc0090940- Stable URL of this page
https://metraipolis.com/documento/dc_b36627107d04
How to cite
Permutation-Equivariant Flow Matching for Alignment-Free Neural Weight Generation — arXiv:2609.32833 — arXiv (en), https://arxiv.org/abs/2609.32833 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b36627107d04 (Metraipolis archive dc_b36627107d04, sha256 77a7da3fcee3b4766e1c49024a7cf97b27b23f601ae2ef5822ebbfefc0090940)
BibTeX
@misc{dcb36627107d04,
title = {Permutation-Equivariant Flow Matching for Alignment-Free Neural Weight Generation — arXiv:2609.32833},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32833},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b36627107d04; sha256 77a7da3fcee3b4766e1c49024a7cf97b27b23f601ae2ef5822ebbfefc0090940},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32833. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A trained neural network can be represented by a parameter vector in high dimensions. Learning distributions over these vectors enables the generation of new models across various tasks and architectures. A central challenge is permutation symmetry: permuting hidden neurons can produce distant parameter vectors representing the same function. This introduces variations that a generative model must account for when learning from trained networks. Existing methods typically address this using networks derived from a common base model or costly approximate neuron alignment. We instead parameterize a flow-matching velocity field with a permutation-equivariant Graph Meta Network, enabling direct learning from independently trained networks without alignment. Extensive experiments show that our method closely reproduces the joint statistics of accuracy, functional similarity, and weight similarity of independently trained collections, providing evidence of generation beyond checkpoint memorization. A single conditional model also generates task-specific networks on heterogeneous architectures and generalizes to unseen hidden-width configurations. On a tabular domain-shift task, intermediate conditioning produces individual networks with performance comparable to logit ensembles across both domains. Taken together, our results show how permutation equivariance enables learning from diverse collections of independently trained networks without permutation alignment. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.32833 — 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 2026-10-07T22:14:27.783Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).