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

• URL: http://arxiv.org/abs/2604.15273v1
• Date: Thu, 16 Apr 2026 17:45:24 GMT
• Title: How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations
• Abstract summary: Node embeddings act as the information interface for graph neural networks, yet their impact is often reported under mismatched backbones, splits, and training budgets.<n>This paper provides a controlled benchmark of embedding choices for graph classification.<n>We evaluate two classical baselines alongside quantum-oriented alternatives, including a circuit-defined variational embedding and quantum-inspired embeddings.
• Score: 2.9583391652768314
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• On the Expressive Power of the Transverse-Field Ising Model for Graph Learning [1.4323566945483497]
  We study the quantum evolution induced by graph-indexed Ising Hamiltonians as a source of structural signal for graph learning.<n>We introduce QDAGer, a quantum-inspired graph-pair Transformer that injects quantum-dynamical features from time series of node occupations.
  arXiv  Detail & Related papers  (2026-08-18T13:12:50Z)
• Parameterized Quantum Circuits as Feature Maps: Representation Quality and Readout Effects in Multispectral Land-Cover Classification [0.0]
  We investigate variational quantum classifiers (VQCs) for land-cover classification from multispectral satellite imagery.<n>Our results show that, while VQCs with linear readout do not outperform strong classical baselines such as RBF-SVM, the same trained quantum feature map can significantly improve performance.
  arXiv  Detail & Related papers  (2026-04-29T13:47:18Z)
• Quantum Machine Learning Applied to the Sinking of the Titanic [0.0]
  Quantum models were constructed using Pauli entangling and non-entangling expansion-based feature maps and the RealAmplitudes ansatz with up to 50 variational parameters.<n>Model training employed the COBYLA gradient-free framework to minimize the cross-entropy loss.
  arXiv  Detail & Related papers  (2025-08-31T16:00:52Z)
• On the Importance of Fundamental Properties in Quantum-Classical Machine Learning Models [0.0]
  We present a systematic study of how quantum circuit design affects the performance of hybrid quantum-classical neural networks on a causal classification task.<n>The architecture combines a convolutional neural network for classical feature extraction with a parameterized quantum circuit acting as the quantum layer.<n>Results show that increasing the number of ansatz repetitions improves generalization and training stability, though benefits tend to plateau beyond a certain depth.<n>The choice of feature mapping is even more critical: only encodings with multi-axis Pauli rotations enable successful learning, while simpler maps lead to underfitting or loss of class separability.
  arXiv  Detail & Related papers  (2025-07-14T11:18:53Z)
• Analysis of quantum neural network performance via edge cases [4.180897432770239]
  We evaluate the particular performance of different quantum machine learning networks on a graph classification task.<n>Quantum circuits with varying internal symmetry that completely, partially and not at all confer to the symmetry of the graph show different performance on the data set.
  arXiv  Detail & Related papers  (2025-06-14T09:56:01Z)
• Scalable Graph Compressed Convolutions [68.85227170390864]
  We propose a differentiable method that applies permutations to calibrate input graphs for Euclidean convolution. Based on the graph calibration, we propose the Compressed Convolution Network (CoCN) for hierarchical graph representation learning.
  arXiv  Detail & Related papers  (2024-07-26T03:14:13Z)
• What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding [67.59552859593985]
  Graph Transformers, which incorporate self-attention and positional encoding, have emerged as a powerful architecture for various graph learning tasks. This paper introduces first theoretical investigation of a shallow Graph Transformer for semi-supervised classification.
  arXiv  Detail & Related papers  (2024-06-04T05:30:16Z)
• Topology-Aware Dynamic Reweighting for Distribution Shifts on Graph [24.44321658238713]
  Graph Neural Networks (GNNs) are widely used for node classification tasks but often fail to generalize when training and test nodes come from different distributions. We introduce the Topology-Aware Dynamic Reweighting (TAR) framework, which dynamically adjusts sample weights through gradient flow in the Wasserstein space during training. Our framework's superiority is demonstrated through standard testing on four graph OOD datasets and three class-imbalanced node classification datasets.
  arXiv  Detail & Related papers  (2024-06-03T07:32:05Z)
• On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions [49.8110352174327]
  We assess attribution methods from a perspective not previously explored in the graph domain: retraining. The core idea is to retrain the network on important (or not important) relationships as identified by the attributions. We run our analysis on four state-of-the-art GNN attribution methods and five synthetic and real-world graph classification datasets.
  arXiv  Detail & Related papers  (2024-01-01T02:03:35Z)
• The role of data embedding in equivariant quantum convolutional neural networks [2.255961793913651]
  We investigate the role of classical-to-quantum embedding on the performance of equivariant quantum neural networks (EQNNs) We numerically compare the classification accuracy of EQCNNs with three different basis-permuted amplitude embeddings to the one obtained from a non-equivariant quantum convolutional neural network (QCNN)
  arXiv  Detail & Related papers  (2023-12-20T18:25:15Z)
• Neural Tangent Kernels Motivate Graph Neural Networks with Cross-Covariance Graphs [94.44374472696272]
  We investigate NTKs and alignment in the context of graph neural networks (GNNs) Our results establish the theoretical guarantees on the optimality of the alignment for a two-layer GNN. These guarantees are characterized by the graph shift operator being a function of the cross-covariance between the input and the output data.
  arXiv  Detail & Related papers  (2023-10-16T19:54:21Z)
• Data-heterogeneity-aware Mixing for Decentralized Learning [63.83913592085953]
  We characterize the dependence of convergence on the relationship between the mixing weights of the graph and the data heterogeneity across nodes. We propose a metric that quantifies the ability of a graph to mix the current gradients. Motivated by our analysis, we propose an approach that periodically and efficiently optimize the metric.
  arXiv  Detail & Related papers  (2022-04-13T15:54:35Z)
• Building powerful and equivariant graph neural networks with structural message-passing [74.93169425144755]
  We propose a powerful and equivariant message-passing framework based on two ideas. First, we propagate a one-hot encoding of the nodes, in addition to the features, in order to learn a local context matrix around each node. Second, we propose methods for the parametrization of the message and update functions that ensure permutation equivariance.
  arXiv  Detail & Related papers  (2020-06-26T17:15:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.