Effective Graph Neural Representation of Chain Architectures of Block Copolymers Tested by Predicting RPA Instability Limits
Abstract
Advances in polymer synthesis and computational modeling are expanding the block-copolymer architecture space accessible for phase-behavior design. Machine learning can accelerate this exploration, yet a common representation capable of learning across diverse chain topologies remains lacking. Here, we present a graph neural network (GNN) representation of acyclic AB multiblock architectures, tested by random-phase approximation (RPA) instability prediction. Each chain is represented as a graph, enabling a common model to learn across diverse topologies. This representation, which organizes RPA-related information, retains predictive capability when extrapolated to architectures with more blocks and demonstrates its potential for reuse across tasks through transfer to instability-wavenumber prediction. By effectively linking block-copolymer chain architecture to field-theoretic response, this graph representation not only reconstructs stability-limit curves but also provides a practical route for future self-consistent field theory exploration of ordered phase space across complex topologies.
Related
- Exploring Joint-Embedding Predictive Architectures for Self-Supervised Representation Learning of Powder X-ray Diffraction Patterns
- Vector Superradiance without Separability: Instability Rates from the Worldline Effective Theory
- Complex chromoelectric polarizability of a heavy-quarkonium resonance: pole response and channel-resolved effective-theory representation
- The effect of homopolymer adding on aggregation behavior in amphiphilic triblock copolymers containing rigid blocks
- Associative amphiphilic copolymers enabling emulsion stabilization via host-guest anchoring at the interface: A proof-of-concept
BibTeX
@misc{zhang2026effective,
title = {{Effective Graph Neural Representation of Chain Architectures of Block Copolymers Tested by Predicting RPA Instability Limits}},
author = {Xiyue Zhang and Yutong Wu and Yi-Xin Liu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.20374},
eprint = {2610.20374},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.20374},
}
RIS
TY - UNPB
TI - Effective Graph Neural Representation of Chain Architectures of Block Copolymers Tested by Predicting RPA Instability Limits
AU - Xiyue Zhang
AU - Yutong Wu
AU - Yi-Xin Liu
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.20374
UR - https://arxiv.org/abs/2610.20374
AB - Advances in polymer synthesis and computational modeling are expanding the block-copolymer architecture space accessible for phase-behavior design. Machine learning can accelerate this exploration, yet a common representation capable of learning across diverse chain topologies remains lacking. Here, we present a graph neural network (GNN) representation of acyclic AB multiblock architectures, tested by random-phase approximation (RPA) instability prediction. Each chain is represented as a graph, enabling a common model to learn across diverse topologies. This representation, which organizes RPA-related information, retains predictive capability when extrapolated to architectures with more blocks and demonstrates its potential for reuse across tasks through transfer to instability-wavenumber prediction. By effectively linking block-copolymer chain architecture to field-theoretic response, this graph representation not only reconstructs stability-limit curves but also provides a practical route for future self-consistent field theory exploration of ordered phase space across complex topologies.
ER -