Skip to content
DraconiticResearch
Search Sources API
186,541 studies31 sourcesUpdated 13 min ago
PreprintCC BY-NCChemRxiv

Two extrapolation axes for many-body systems: interaction without an interaction module, chemical mixtures as the main example

  • Xiao Yang1
  • Guanghao Song1
  • Feiyu Li1
  • Zihan Xu1
  • Yanan Yang1
  • Baojiang He1
  • Lingbo Ji1
  • Xiankuan Huo1
  • Jun Hu1
  • Zhan Qu1
  1. 1Zhengzhou, China, 450001
Open at sourcePDFDOICite

Abstract

We separate the extrapolation problem in many-body systems into two axes: toward combinations with more components, and toward components unseen. The prevailing pipeline—encode then interact—performs poorly when extrapolating in composition count. We propose a route that expresses interaction without an interaction module: a per-component encoder shaped by the task compresses interaction behaviour into each component’s encoding, and the encodings are combined and read out by a simple MLP. Where component identities are bounded while their combinations are not, this route performs better along the composition axis—a difference that follows from the underlying function form rather than from the data. Chemical mixtures are the main example, synthetic tasks isolate the two axes, and the same structure recurs in other fields.

Related

  1. Chemical potentials from structure factors: II. Charged multi-component mixtures
    Xiaoyu Wang, Roya Savoj, Musahid Ahmed +1
    arXivPreprintarXiv licenceFull textPhysical chemistryComputational physicsarXiv
  2. Chemical potentials from structure factors: I. Neutral multi-component mixtures
    Roya Savoj, Xiaoyu Wang, Musahid Ahmed +1
    arXivPreprintarXiv licenceFull textPhysical chemistryComputational physicsarXiv
  3. Density and excess molar enthalpy of 2-butanol + glyme liquid mixtures. Application of the DISQUAC, UNIFAC (Dortmund) and ERAS models to 2-alkanol + linear ether systems
    Fatemeh Pazoki, João Victor Alves-Laurentino, Susana Villa +4
    arXivPreprintCC BY-NC-ND 4.0Full textPhysical chemistryarXiv
  4. Comprehensive Quantum Chemical Interaction Analysis of Whole Protein–Ligand Structures in BindingDB Using the Fragment Molecular Orbital Method
    Shuhei Miyakawa, Naoko Konami, Ruri Mihata +10
    ChemRxivPreprintCC BYFull textGeneral chemistryChemRxiv
  5. Ultrastructural, Chemical, and Wettability Insights into the Interaction between Novel Natural Dentifrices and Nanohybrid Composites: A Multi-Technique Microscopy Approach
    Giovanna dos Santos S. Teixeira, Ilene Cristine R. Cesar, Luís Eduardo S. Soares
    ACS OmegaPeer-reviewedCC BY 4.0Full textGeneral chemistryCrossref

Cite

BibTeXRIS
BibTeX
@misc{yang2026extrapolation,
  title = {{Two extrapolation axes for many-body systems: interaction without an interaction module, chemical mixtures as the main example}},
  author = {Xiao Yang and Guanghao Song and Feiyu Li and Zihan Xu and Yanan Yang and Baojiang He and Lingbo Ji and Xiankuan Huo and Jun Hu and Zhan Qu},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15010330/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010330/v1},
  note = {CC BY-NC},
}
RIS
TY  - UNPB
TI  - Two extrapolation axes for many-body systems: interaction without an interaction module, chemical mixtures as the main example
AU  - Xiao Yang
AU  - Guanghao Song
AU  - Feiyu Li
AU  - Zihan Xu
AU  - Yanan Yang
AU  - Baojiang He
AU  - Lingbo Ji
AU  - Xiankuan Huo
AU  - Jun Hu
AU  - Zhan Qu
PY  - 2026
DA  - 2026/10/13
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15010330/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010330/v1
AB  - We separate the extrapolation problem in many-body systems into two axes: toward combinations with more components, and toward components unseen. The prevailing pipeline—encode then interact—performs poorly when extrapolating in composition count. We propose a route that expresses interaction without an interaction module: a per-component encoder shaped by the task compresses interaction behaviour into each component’s encoding, and the encodings are combined and read out by a simple MLP. Where component identities are bounded while their combinations are not, this route performs better along the composition axis—a difference that follows from the underlying function form rather than from the data. Chemical mixtures are the main example, synthetic tasks isolate the two axes, and the same structure recurs in other fields.
ER  -