Metraipolis › archive › dc_d52aaae5aadb
Atom-Wise Allocation of Message-Passing Scale for Molecular Property Prediction — arXiv:2611.02277
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02277
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:37:16.179Z
- SHA-256 of the archived text
33a62d9f32885d0f6633325e34ab46daf2d60bc210f1cd70a87ca7da768e4370- Stable URL of this page
https://metraipolis.com/documento/dc_d52aaae5aadb
How to cite
Atom-Wise Allocation of Message-Passing Scale for Molecular Property Prediction — arXiv:2611.02277 — arXiv (en), https://arxiv.org/abs/2611.02277 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d52aaae5aadb (Metraipolis archive dc_d52aaae5aadb, sha256 33a62d9f32885d0f6633325e34ab46daf2d60bc210f1cd70a87ca7da768e4370)
BibTeX
@misc{dcd52aaae5aadb,
title = {Atom-Wise Allocation of Message-Passing Scale for Molecular Property Prediction — arXiv:2611.02277},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02277},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d52aaae5aadb; sha256 33a62d9f32885d0f6633325e34ab46daf2d60bc210f1cd70a87ca7da768e4370},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02277. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Molecular properties depend on chemical structure at different ranges, from local polar groups governing solvation to extended substructures shaping bioactivity, yet graph neural networks usually fix one propagation scale for every atom. We present PRISM (Per-atom Routing over Intermediate States of Message Passing), in which each atom's encoded features produce a bounded scalar that positions a unimodal distribution over retained message-passing states and matching circular-fingerprint radii. Because one coordinate translates the whole profile, allocated depth responds to the routing scalar in closed form: at fixed temperature it is nondecreasing, its sensitivity scales with the profile variance, and it saturates in the clipped regions. Beyond providing closed-form analyzability, this constrained one-parameter profile matches or significantly outperforms parameter-matched, unconstrained node-wise gates and Jumping Knowledge attention. Under scaffold partitions with equal tuning budgets against eight graph, fingerprint, and geometric baselines, PRISM trained from scratch without three-dimensional coordinates achieves the lowest mean error on aqueous solubility and hydration free energy and strong accuracy on BACE and BBBP. As a general layer-combination rule, PRISM transfers directly to GCN, GIN, and GAT backbones, reducing hydration free energy error by up to 29% relative to last-layer readout. Applied to a pre-trained GIN, it improves on last-layer readout on four of six endpoints and gives the lowest lipophilicity error overall. In trained models, allocated depth differs systematically between atom types in a task-dependent way, and permuting profiles among a molecule's atoms raises prediction error on several endpoints, so the rule acts as a learned counterpart of atom typing. 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/2611.02277 — 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 2026-11-03T18:12:54.557Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).