Metraipolis › archive › dc_f27bb96b4df7
Latent Flow Matching for Molecular Graph Generation — arXiv:2610.06468
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06468
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:42.633Z
- SHA-256 of the archived text
ef71bd49884fc48a4cab629a73cf9d23f589fefa5675802a1b4dc7bfccc73185- Stable URL of this page
https://metraipolis.com/documento/dc_f27bb96b4df7
How to cite
Latent Flow Matching for Molecular Graph Generation — arXiv:2610.06468 — arXiv, https://arxiv.org/abs/2610.06468 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f27bb96b4df7 (Metraipolis archive dc_f27bb96b4df7, sha256 ef71bd49884fc48a4cab629a73cf9d23f589fefa5675802a1b4dc7bfccc73185)
BibTeX
@misc{dcf27bb96b4df7,
title = {Latent Flow Matching for Molecular Graph Generation — arXiv:2610.06468},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06468},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f27bb96b4df7; sha256 ef71bd49884fc48a4cab629a73cf9d23f589fefa5675802a1b4dc7bfccc73185},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06468. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern graph generative models typically operate directly in the discrete graph space, explicitly generating node and edge variables, which can become costly as graphs grow. In this paper, we perform generation explicitly on latent representations of entire graphs obtained from a pretrained Variational Autoencoder with high reconstruction fidelity. The generated representations, obtained through flow matching, are then decoded only at the final step. Across molecular benchmarks of increasing size, our approach achieves strong validity and FCD while offering a favorable quality-efficiency trade-off compared with state-of-the-art explicit graph generative models. One of the main advantages of this formulation is that the graph representation only needs to be learned once, after which the same one can be reused across multiple generative objectives without retraining. We demonstrate generation guided by molecular properties and further introduce validity-aware generation though a classifier learned directly in latent space. All code will be made available upon acceptance. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.06468 — 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 2026-10-06T05:24:06.163Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).