Metraipolis › archive › dc_90a2d4998aed

Alignment Matters Inside and Out in Equivariant Graph Flow Matching — arXiv:2608.26961

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26961
License (as archived)
CC0-1.0
Archived
2026-10-17T16:12:25.071Z
SHA-256 of the archived text
33ff843b351f2c7f6d6724fc47ed3e642fd2eb02d826348b38eb5c73f1139282
Stable URL of this page
https://metraipolis.com/documento/dc_90a2d4998aed

How to cite

Alignment Matters Inside and Out in Equivariant Graph Flow Matching — arXiv:2608.26961 — arXiv (en), https://arxiv.org/abs/2608.26961 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90a2d4998aed (Metraipolis archive dc_90a2d4998aed, sha256 33ff843b351f2c7f6d6724fc47ed3e642fd2eb02d826348b38eb5c73f1139282)
BibTeX
@misc{dc90a2d4998aed,
  title = {Alignment Matters Inside and Out in Equivariant Graph Flow Matching — arXiv:2608.26961},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26961},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90a2d4998aed; sha256 33ff843b351f2c7f6d6724fc47ed3e642fd2eb02d826348b38eb5c73f1139282},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26961. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graphs are invariant under node permutations, motivating permutation-equivariant architectures in generative models. In flow matching, however, symmetry also affects the source-target coupling: one must choose both which graphs to pair and which node representatives to align. We study these two forms of alignment, termed outer and inner alignment, and their effect on equivariant graph flow matching. We connect inner alignment to transport on the graph quotient space, whose Euclidean quotient metric coincides with Gromov-Monge distance, and show that quotient couplings admit aligned representative lifts while symmetrization yields equivariant flow-matching minimizers, including for categorical endpoints. In practice, we compare random augmentation, permutation-blind minibatch optimal transport, approximate Gromov-Wasserstein alignment, and combinations of inner and outer alignment. Across continuous graph and molecular generation, alignment can substantially simplify trajectories and improve few-step generation, while its benefits depend on the alignment and computational budget. Our results highlight that effective graph flow matching benefits from alignment both inside and across graph pairs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.26961 — 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 2026-10-17T15:34:49.934Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).