Quantum Graph Neural Networks for HEP
Lorentz-equivariant and contrastive quantum GNNs for jet physics
Two related works applying quantum machine learning to high-energy physics jet classification:
Quantum Rationale-Aware Graph Contrastive Learning (TMLR 2026)
A quantum graph contrastive learning framework for jet discrimination, combining graph neural networks with variational quantum circuits for improved feature learning.
Lorentz-Equivariant Quantum Graph Neural Network (IEEE TAI 2025)
A Lorentz-equivariant QGNN that exploits relativistic symmetries via quantum circuits for jet tagging.
Why Quantum?
Both works explore whether quantum inductive biases (entanglement, superposition) can provide genuine advantages for structured physics data over classical GNN baselines.