Metraipolis › archive › dc_bdfb33b45cb1
PolarFlow: Spectral Geometric Flow Matching for Directed Graph Generation via Polar Decomposition — arXiv:2610.41471
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41471
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:32:49.255Z
- SHA-256 of the archived text
9916b61df8e8e1a63bb5cd2830091a1cca69ed3e02c66d35e4f5e39c6d291abc- Stable URL of this page
https://metraipolis.com/documento/dc_bdfb33b45cb1
How to cite
PolarFlow: Spectral Geometric Flow Matching for Directed Graph Generation via Polar Decomposition — arXiv:2610.41471 — arXiv (en), https://arxiv.org/abs/2610.41471 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bdfb33b45cb1 (Metraipolis archive dc_bdfb33b45cb1, sha256 9916b61df8e8e1a63bb5cd2830091a1cca69ed3e02c66d35e4f5e39c6d291abc)
BibTeX
@misc{dcbdfb33b45cb1,
title = {PolarFlow: Spectral Geometric Flow Matching for Directed Graph Generation via Polar Decomposition — arXiv:2610.41471},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41471},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bdfb33b45cb1; sha256 9916b61df8e8e1a63bb5cd2830091a1cca69ed3e02c66d35e4f5e39c6d291abc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41471. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Directed graphs model asymmetric relationships in biology, transportation, social networks, and electronic design automation. Recent discrete diffusion and flow-matching methods generate directed graphs effectively, but their edge-wise categorical formulations require dense predictions over all ordered node pairs and repeated categorical updates during generation. This motivates a fundamental question: can comparable generative quality be achieved through a more computationally efficient formulation that better exploits the structure of directed adjacency matrices? Existing benchmarks also cover limited network structures, restricting comprehensive evaluation. We introduce PolarFlow, a continuous geometric flow-matching framework based on polar decomposition and truncated spectral coordinates. Its representation comprises four coupled components: a Stiefel frame and rotation angles encoding the orthogonal factor, and a second Stiefel frame and nonnegative eigenvalues characterizing the positive-semidefinite factor. PolarFlow learns a joint velocity field along geometry-aware conditional paths on this product space, reconstructs a continuous adjacency-score matrix, and discretizes it into a binary directed graph. By replacing discrete edge-wise generation with joint continuous transport, PolarFlow improves computational efficiency while retaining global adjacency structure. To broaden evaluation, we introduce complementary Circuit and Twitter benchmarks spanning engineered functional and naturally evolved social networks. Across synthetic and real-world datasets, PolarFlow achieves generative quality comparable to competitive discrete methods while substantially reducing training and sampling time. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv eess.SP, nuovi lavori del giorno). Categorie arXiv: Signal Processing (eess.SP). Pagina del lavoro: https://arxiv.org/abs/2610.41471 — 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 2026-11-03T08:15:39.261Z dalla pagina https://arxiv.org/list/eess.SP/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).