Adaptive Relational Learning on Multi-instance Quantum Data with Photonic Processors
Abstract
Loading multiple quantum states in parallel into a quantum machine learning (QML) model can unlock learning tasks where key information resides in the \emph{relations} between states rather than in individual states. We introduce an adaptive relational learning framework for such multi-instance quantum data that accesses pairwise and higher-order relations. Our model combines global measurements via SWAP or CYCLE tests for evaluating an n-state Bargmann invariant with shallow trainable transformations applied locally to each input state. We demonstrate the approach for continuous-variable (CV) photonic systems, which naturally provide access to quantum data and necessary computing operations. We solve tasks involving hidden relationship detection, geometric phase classification, and sensing in the presence of an unknown shared nuisance interaction. We benchmark the adaptive model against a non-adaptive ``measure-first'' approach based on continuous-variable classical shadows, and show that the cost of shadow estimation grows rapidly with n, while our model avoids this dependence. Already for n=2, we achieve perfect test accuracy A=1.0 with $500$ inference shots, improving average test accuracy over the shadow-based method by ΔA=0.15 while using $100$ times fewer shots per data point. Our work opens routes to sensing and quantum-data applications where adaptive photonic QML can access relational features that are costly to recover with non-adaptive, measure-first models.
Related
- Phase-Drift Limits and Adaptive Quadrature Readout in Programmable Photonic Processors
- Floquet-driven light transport in programmable photonic processors via discretized evolution of synthetic magnetic fields
- Information capacity of quantum statistics: Fock-state tests of a discrete binary-sequence model on cloud photonic quantum processors
- Photonic-Based Adaptive Spectrum Analysis of RF Signals. Application to Signal Detection by Generalized Time-Frequency Filtering
- Engineered Learning Problems on Noisy Quantum Processors
BibTeX
@misc{jastrzebski2026adaptive,
title = {{Adaptive Relational Learning on Multi-instance Quantum Data with Photonic Processors}},
author = {Marcin Jastrzebski and Shang Yu and Raj B. Patel and Oleksandr Kyriienko},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.17352},
eprint = {2609.17352},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.17352},
}
RIS
TY - UNPB
TI - Adaptive Relational Learning on Multi-instance Quantum Data with Photonic Processors
AU - Marcin Jastrzebski
AU - Shang Yu
AU - Raj B. Patel
AU - Oleksandr Kyriienko
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2609.17352
UR - https://arxiv.org/abs/2609.17352
AB - Loading multiple quantum states in parallel into a quantum machine learning (QML) model can unlock learning tasks where key information resides in the \emph{relations} between states rather than in individual states. We introduce an adaptive relational learning framework for such multi-instance quantum data that accesses pairwise and higher-order relations. Our model combines global measurements via SWAP or CYCLE tests for evaluating an n-state Bargmann invariant with shallow trainable transformations applied locally to each input state. We demonstrate the approach for continuous-variable (CV) photonic systems, which naturally provide access to quantum data and necessary computing operations. We solve tasks involving hidden relationship detection, geometric phase classification, and sensing in the presence of an unknown shared nuisance interaction. We benchmark the adaptive model against a non-adaptive ``measure-first'' approach based on continuous-variable classical shadows, and show that the cost of shadow estimation grows rapidly with n, while our model avoids this dependence. Already for n=2, we achieve perfect test accuracy A=1.0 with $500$ inference shots, improving average test accuracy over the shadow-based method by ΔA=0.15 while using $100$ times fewer shots per data point. Our work opens routes to sensing and quantum-data applications where adaptive photonic QML can access relational features that are costly to recover with non-adaptive, measure-first models.
ER -