Predicting Multipartite Entanglement in Quantum Circuits using Transformer
Abstract
Multipartite entanglement is a critical property of parameterized quantum circuits (PQCs), particularly for near-term hybrid quantum-classical algorithms, as it characterizes their ability to generate highly entangled states. However, measuring entanglement remains computationally expensive because conventional Monte Carlo sampling scales unfavorably with system size. To overcome this challenge, we introduce a graph-based transformer surrogate that predicts both the first-order Meyer-Wallach measure (Q1) and the second-order Scott measure (Q2), resolving entanglement structures indistinguishable under Q1 alone. Our central contribution is the qubit-interconnected graph (QIG) encoding for transformers, where each node represents a qubit and weighted adjacencies record entangling-gate multiplicities. Fused with a gate-level DAG encoder, this yields the QIG-Fusion model. Evaluated on 50,000 circuits spanning 4- to 8-qubit systems across a ten-seed protocol, QIG-Fusion achieves an RMSE as low as 0.037 (Q2) and 0.038 (Q1), with a Spearman rank correlation up to 0.95. This framework significantly reduces the computational cost of Quantum Architecture Search (QAS), enabling efficient entanglement estimation for large-scale PQCs.
Related
- Algorithmic Design of Heralded Linear Optical Circuits for Multipartite Entanglement
- Neural network-based multipartite entanglement classification with prior guidance from quantum uncertainty relations
- Quantum Fisher Information as the Speed Limit for Multipartite Entanglement
- Nonlocality without entanglement for multipartite quantum measurements
- Optimising multipartite entanglement manipulation in quantum networks
BibTeX
@misc{tarigan2026predicting,
title = {{Predicting Multipartite Entanglement in Quantum Circuits using Transformer}},
author = {Darell Timothy Tarigan and Fadhil Fatih Shiddiq and Hadyan Luthfan Prihadi and Donny Dwiputra and Jusak S. Kosasih and Yanoar P. Sarwono and Freddy Permana Zen and Rui-Qin Zhang},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.27993},
eprint = {2608.27993},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.27993},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Predicting Multipartite Entanglement in Quantum Circuits using Transformer
AU - Darell Timothy Tarigan
AU - Fadhil Fatih Shiddiq
AU - Hadyan Luthfan Prihadi
AU - Donny Dwiputra
AU - Jusak S. Kosasih
AU - Yanoar P. Sarwono
AU - Freddy Permana Zen
AU - Rui-Qin Zhang
PY - 2026
DA - 2026/08/28
PB - arXiv
DO - 10.48550/arxiv.2608.27993
UR - https://arxiv.org/abs/2608.27993
AB - Multipartite entanglement is a critical property of parameterized quantum circuits (PQCs), particularly for near-term hybrid quantum-classical algorithms, as it characterizes their ability to generate highly entangled states. However, measuring entanglement remains computationally expensive because conventional Monte Carlo sampling scales unfavorably with system size. To overcome this challenge, we introduce a graph-based transformer surrogate that predicts both the first-order Meyer-Wallach measure (Q_1) and the second-order Scott measure (Q_2), resolving entanglement structures indistinguishable under Q_1 alone. Our central contribution is the qubit-interconnected graph (QIG) encoding for transformers, where each node represents a qubit and weighted adjacencies record entangling-gate multiplicities. Fused with a gate-level DAG encoder, this yields the QIG-Fusion model. Evaluated on 50,000 circuits spanning 4- to 8-qubit systems across a ten-seed protocol, QIG-Fusion achieves an RMSE as low as 0.037 (Q_2) and 0.038 (Q_1), with a Spearman rank correlation up to 0.95. This framework significantly reduces the computational cost of Quantum Architecture Search (QAS), enabling efficient entanglement estimation for large-scale PQCs.
ER -