How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations

2026-04-16 · Nouhaila Innan, Antonello Rosato, Alberto Marchisio, Muhammad Shafique arxiv

Node embeddings act as the information interface for graph neural networks, yet their empirical impact is often reported under mismatched backbones, splits, and training budgets. This paper provides a controlled benchmark of embedding choices for graph classification, comparing classical baselines with quantum-oriented node representations under a unified pipeline. We evaluate two classical baselines alongside quantum-oriented alternatives, including a circuit-defined variational embedding and quantum-inspired embeddings computed via graph operators and linear-algebraic constructions. All variants are trained and tested with the same backbone, stratified splits, identical optimization and early stopping, and consistent metrics. Experiments on five different TU datasets and on QM9 converted to classification via target binning show clear dataset dependence: quantum-oriented embeddings yield the most consistent gains on structure-driven benchmarks, while social graphs with limited node attributes remain well served by classical baselines. The study highlights practical trade-offs between inductive bias, trainability, and stability under a fixed training budget, and offers a reproducible reference point for selecting quantum-oriented embeddings in graph learning.

📄 PDF Abstract BibTeX arXiv:2604.15273

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Classification Graph Learning

MolPaQ: Modular Quantum-Classical Patch Learning for Interpretable Molecular Generation

2026-03-27 · Syed Rameez Naqvi, Lu Peng arxiv

Molecular generative models must jointly ensure validity, diversity, and property control, yet existing approaches typically trade off among these objectives. We present MOLPAQ, a modular quantum-classical generator that…

Variational Quantum Circuit Model for Knowledge Graphs Embedding

2019-02-19 · Yunpu Ma, Volker Tresp, Liming Zhao, Yuyi Wang

In this work, we propose the first quantum Ans\"atze for the statistical relational learning on knowledge graphs using parametric quantum circuits. We introduce two types of variational quantum circuits for knowledge gra…

Graph Embedding Knowledge Graph Embedding Knowledge Graphs model+2

D2D Power Allocation via Quantum Graph Neural Network

2025-11-19 · Tung Giang Le, Xuan Tung Nguyen, Won-Joo Hwang arxiv

Increasing wireless network complexity demands scalable resource management. Classical GNNs excel at graph learning but incur high computational costs in large-scale settings. We present a fully quantum Graph Neural Netw…

Graph Neural Network Graph Learning

Tailor Made Embeddings for Quantum Machine Learning

2026-06-24 · Aldo Lamarre, Dominik Šafránek arxiv

Autoencoders transformed classical machine learning by solving the curse of dimensionality, enabling principled weight initialization and learning compact, structured representations. In this work, we extend this paradig…

Quantum Machine Learning

SAFE Quantum Machine Learning with Variational Quantum Classifiers

2026-05-15 · Ying Chen, Paolo Giudici, Vasily Kolesnikov, Paolo Recchia arxiv

We propose a variational quantum classifier operating on high dimensional deep representations via amplitude encoding, stabilized by a learnable classical pre encoding layer.By combining normalized amplitude embeddings w…