Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Neural Networks

Rotation equivariant quantum graph neural networks with trainable compression encoder and entanglement-enhanced aggregation

Wenjie Liu, Bohan Du, Weiwei Liu, Yifan Zhu

Published Jan 20, 2026• 1 citation
Publisher

Abstract

The integration of symmetry, such as permutation equivariance, into Quantum Graph Neural Networks (QGNNs), referred to as Equivariant Quantum Graph Neural Networks (EQGNNs), markedly improves the model's generalization performance on graph-structured data. Despite this advancement, current research has not yet extended rotational equivariance to QGNN frameworks. Furthermore, processing large-scale graph data increases computational complexity due to numerous inter-node connections, significantly raising the required number of qubits. To address these challenges, a novel Rotationally Equivariant Quantum Graph Neural Network (REQGNN) with trainable compression encoder and entanglement-enhanced aggregation mechanism is proposed. By adopting quantum fidelity as the evaluation metric, we design a quantum autoencoder to effectively compress feature dimensionality, substantially lowering the qubit requirements of the model while preserving essential global structural details. To achieve rotational equivariance in the model, we propose an entanglement-enhanced layer that incorporates distance and angle information between nodes. This layer performs entanglement by extracting diverse edge information, thereby further refining edge feature extraction. Additionally, an auxiliary entanglement layer is introduced to mitigate the over-smoothing issue. Experiment results demonstrate REQGNN is significantly better for graph classification tasks than GIN, Gra+QSVM, and Gra+QCNN on four datasets in all metrics and achieves better results than egoGQNN in accuracy on PTC dataset, and it also has advantage for graph regression tasks over the classical models, including EGNN and EquiformerV2, and reduces the MAE of $C_v$ task unit by 20\% on average compared with a previous quantum model QGCNN. Our approach offers an effective solution for achieving rotational equivariance while providing a novel perspective for exploring symmetry in graph neural networks (GNNs).

DOI
10.1016/j.neunet.2026.108625

Related papers

Rotation- and Permutation-Equivariant Quantum Graph Neural Network for 3D Graph Data

Wenjie Liu, Yifan Zhu, Ying Zha +3 more

Equivariant quantum graph neural networks (EQGNNs) offer a potentially powerful method to process graph data. However, existing EQGNN models only consider the permutation symmetry of graphs, and failing to fully exploit the geometric and non-geometric information in graphs, resulting in suboptimal performance when processing 3D graph data. To address these limitations, we derive constraints of rotation and permutation equivariance, and then propose a novel rotation- and permutation-equivariant quantum graph neural network (RP-EQGNN). An equivariant module is designed to extract the geometric information. Then, a convolution and entanglement module is constructed to extract non-geometric information. To improve performance of our model, an edge entanglement strategy is designed to perform distinguishable entanglement operations based on edge heterogeneity. The experiment results demonstrate that RP-EQGNN is significantly better for graph regression on the QM9 dataset and the OC20 dataset than Q3DGL and EQC in MAE and achieves results comparable to those of EquiformerV2, Geoformer, SO3KRATES and HEGNN. It also has advantage for point cloud classification on the ModelNet40 dataset over quantum models, including sQCNN-3D and PI-QSVM. RP-EQGNN introduces an innovative approach for processing 3D graph data, establishing a basis for future investigations into symmetries within graph neural networks.

IEEE Transactions on Pattern Analysis and Machine Intelligence•Jul 28, 2025•7 citations

一种针对三维图分类问题的量子群等变图神经网络

Wenjie Liu, Yifan Zhu, Qingshan Wu

Equivariance is a crucial property of 3D graph data that has gathered significant attention from researchers in recent years. By designing quantum gate sets tailored to specific types of equivariance, researchers have successfully developed equivariant quantum graph neural networks, significantly improving the performance of graph learning models. However, 3D graph data exhibit various types of equivariances, such as rotation, translation, reflection, and permutation equivariances, which complicates the construction of a quantum graph neural network that can accommodate all these equivariances To overcome this challenge, this study introduces a method for calculating relative coordinates of 3D graph nodes and proposes a novel quantum group-equivariant graph neural network. This network incorporates a group-equivariant encoding module to encode relative coordinates, a permutation-equivariant convolution module to extract geometric information, and an entanglement module to aggregate global features. Classification experiments conducted on the ModelNet40 and ShapeNet datasets reveal that the proposed model outperforms existing approaches, including QGCNN, sQCNN-3D, and PI-QSVM. Furthermore, it achieves accuracy comparable to Q3DGL while requiring fewer training parameters.

Zhongguo kexue. Wulixue Lixue Tianwenxue•Oct 1, 2024•0 citations

Permutation-Invariant Quantum Graph Neural Network Based on Variational Quantum Algorithms

M Li, Wen Liu, Lei Shi +2 more

Graph neural networks (GNNs) have demonstrated strong capabilities in graph representation learning but still face limitations in efficiency and scalability. Quantum GNNs (QGNNs) offer a promising alternative. However, existing approaches often fail to fully exploit edge information, require substantial quantum resources, and insufficiently account for permutation invariance in graph learning. To address these challenges, this article proposes a permutation-invariant quantum GNN (PIQGNN). The proposed model introduces a low-qubit-cost quantum encoding strategy that jointly embeds node features, edge features, and graph topology into entangled quantum states using only $n$ qubits, where $n$ denotes the number of nodes, while explicitly enforcing permutation invariance. Furthermore, a symmetry-aware variational quantum neural network (QNN) is designed to enable end-to-end permutation-invariant learning. Its hyperparameters are optimized via Bayesian optimization to alleviate barren plateau (BP) effects and enhance training stability. Experimental results on multiple graph binary classification benchmark datasets demonstrate that, compared with classical GNNs, PIQGNN achieves competitive performance with a significantly reduced number of trainable parameters. Compared with existing QGNNs, PIQGNN attains higher accuracy with lower quantum resource requirements and exhibits stronger robustness under noisy conditions. These results indicate that PIQGNN provides an efficient, scalable, and noise-resilient quantum framework for graph learning, highlighting its practical potential in the noisy intermediate-scale quantum (NISQ) era.

IEEE Transactions on Neural Networks and Learning Systems•Jan 1, 2026•0 citations

Quantum-enhanced learning: Leveraging von Neumann entropy for enhanced graph neural network performance

Muhammad Awais, Octavian Adrian Postolache, Sancho Moura Oliveira

Graph Neural Networks (GNNs) have established themselves as powerful tools for learning from graph-structured data. However, their reliance on local message-passing mechanisms leads to over-squashing-the compression of exponentially growing neighborhood information into fixed-size vectors-which severely limits long-range dependency modeling. We introduce the Quantum-Inspired Graph Neural Network (QGNN) with a novel Quantum Entanglement Loss (QEL) function that addresses this challenge through a fundamentally different mechanism than existing approaches. Unlike spectral regularization (which enforces smoothness) or maximum entropy methods (which encourage representation diversity), QEL minimizes the von Neumann entropy of the node embedding correlation matrix, thereby concentrating eigenvalues in dominant eigenmodes that preserve global structural patterns. This entropy minimization creates direct information pathways between distant but functionally related nodes, effectively bypassing multi-hop bottlenecks. We evaluate QGNN on both standard benchmarks (Cora, Citeseer, PPI, Electronic Circuits) and the Long Range Graph Benchmark (LRGB) suite, which features graphs with average diameters up to 56.99 (Peptides). On LRGB datasets, QGNN achieves substantial improvements: 37.6% relative MAE reduction on Peptides-struct compared to GCN, 4.0% improvement over Graph Transformers (GraphGPS), and notably, 97% better performance than GCN on node pairs separated by 7+ hops. Despite these gains, QGNN requires only 20-30% additional computational overhead compared to standard GCN, while being 5-6 × faster than Graph Transformer approaches. Our results establish entropy-based regularization as a principled and efficient approach for long-range dependency modeling in graphs.

Neural Networks•Apr 9, 2026•0 citations

Guided graph compression for quantum graph neural networks

Mikel Casals, Vasilis Belis, Elías F. Combarro +3 more

Abstract Graph neural networks (GNNs) are effective for processing graph-structured data but face challenges with large graphs due to high memory requirements and inefficient sparse matrix operations on GPUs. Quantum computing offers a promising avenue to address these issues and inspires new algorithmic approaches. In particular, quantum GNNs (QGNNs) have been explored in recent literature. However, current quantum hardware limits the dimension of the data that can be effectively encoded. Existing approaches either simplify datasets manually or use artificial graph datasets. This work introduces the guided graph compression (GGC) framework, which uses a graph autoencoder to reduce both the number of nodes and the dimensionality of node features. The compression is guided to enhance the performance of a downstream classification task, which can be applied either with a quantum or a classical classifier. The framework is evaluated on the Jet Tagging task, a classification problem of fundamental importance in high energy physics that involves distinguishing particle jets initiated by quarks from those by gluons. We compare GGC to a model that uses the autoencoder as a preprocessing step and to a baseline classical GNN classifier. Our numerical results demonstrate that GGC outperforms both alternatives, while also facilitating the testing of novel QGNN ansatzes on realistic datasets.

arXiv:2506.09862•Machine Learning Science and Technology•Aug 27, 2025•1 citation

Inductive Graph Representation Learning with Quantum Graph Neural Networks

Arthur Mendonça Faria, Ignacio Fernández Graña, Savvas Varsamopoulos

Graph Neural Networks (QGNNs) offer a promising approach to combining quantum computing with graph-structured data processing. While classical Graph Neural Networks (GNNs) are scalable and robust, existing QGNNs often lack flexibility due to graph-specific quantum circuit designs, limiting their applicability to diverse real-world problems. To address this, we propose a versatile QGNN framework inspired by GraphSAGE, using quantum models as aggregators to generate quantum-native node embeddings. We integrate inductive representation learning techniques with parameterized quantum convolutional and pooling layers, bridging classical and quantum paradigms. The convolutional layer is flexible, allowing tailored designs for specific tasks. Benchmarked on a node regression task with the QM9 dataset, our framework, using a single minimal circuit for all aggregation steps, handles molecules with varying numbers of atoms without changing qubits or circuit architecture. While classical GNNs achieve higher training performance, our quantum approach remains competitive and often shows enhanced generalization as molecular complexity increases. We also observe faster learning in early training epochs. To mitigate trainability limitations of a single-circuit setup, we extend the framework with multiple quantum aggregators on QM9. Assigning distinct circuits to each hop substantially improves training performance across all cases. Additionally, we numerically demonstrate the absence of barren plateaus as qubit numbers increase, suggesting that the proposed model remains trainable to larger, more complex graph-based problems.

arXiv:2503.24111•Mar 31, 2025•0 citations
The integration of symmetry, such as permutation equivariance, into Quantum Graph Neural Networks (QGNNs), referred to as Equivariant Quantum Graph Neural Networks (EQGNNs), markedly improves the model's generalization performance on graph-structured data. Despite this advancement, current research has not yet extended rotational equivariance to QGNN frameworks. Furthermore, processing large-scale graph data increases computational complexity due to numerous inter-node connections, significantly raising the required number of qubits. To address these challenges, a novel Rotationally Equivariant Quantum Graph Neural Network (REQGNN) with trainable compression encoder and entanglement-enhanced aggregation mechanism is proposed. By adopting quantum fidelity as the evaluation metric, we design a quantum autoencoder to effectively compress feature dimensionality, substantially lowering the qubit requirements of the model while preserving essential global structural details. To achieve rotational equivariance in the model, we propose an entanglement-enhanced layer that incorporates distance and angle information between nodes. This layer performs entanglement by extracting diverse edge information, thereby further refining edge feature extraction. Additionally, an auxiliary entanglement layer is introduced to mitigate the over-smoothing issue. Experiment results demonstrate REQGNN is significantly better for graph classification tasks than GIN, Gra+QSVM, and Gra+QCNN on four datasets in all metrics and achieves better results than egoGQNN in accuracy on PTC dataset, and it also has advantage for graph regression tasks over the classical models, including EGNN and EquiformerV2, and reduces the MAE of CvC_vCv​ task unit by 20% on average compared with a previous quantum model QGCNN. Our approach offers an effective solution for achieving rotational equivariance while providing a novel perspective for exploring symmetry in graph neural networks (GNNs).
Equivariant quantum graph neural networks (EQGNNs) offer a potentially powerful method to process graph data. However, existing EQGNN models only consider the permutation symmetry of graphs, and failing to fully exploit the geometric and non-geometric information in graphs, resulting in suboptimal performance when processing 3D graph data. To address these limitations, we derive constraints of rotation and permutation equivariance, and then propose a novel rotation- and permutation-equivariant quantum graph neural network (RP-EQGNN). An equivariant module is designed to extract the geometric information. Then, a convolution and entanglement module is constructed to extract non-geometric information. To improve performance of our model, an edge entanglement strategy is designed to perform distinguishable entanglement operations based on edge heterogeneity. The experiment results demonstrate that RP-EQGNN is significantly better for graph regression on the QM9 dataset and the OC20 dataset than Q3DGL and EQC in MAE and achieves results comparable to those of EquiformerV2, Geoformer, SO3KRATES and HEGNN. It also has advantage for point cloud classification on the ModelNet40 dataset over quantum models, including sQCNN-3D and PI-QSVM. RP-EQGNN introduces an innovative approach for processing 3D graph data, establishing a basis for future investigations into symmetries within graph neural networks.
Equivariance is a crucial property of 3D graph data that has gathered significant attention from researchers in recent years. By designing quantum gate sets tailored to specific types of equivariance, researchers have successfully developed equivariant quantum graph neural networks, significantly improving the performance of graph learning models. However, 3D graph data exhibit various types of equivariances, such as rotation, translation, reflection, and permutation equivariances, which complicates the construction of a quantum graph neural network that can accommodate all these equivariances To overcome this challenge, this study introduces a method for calculating relative coordinates of 3D graph nodes and proposes a novel quantum group-equivariant graph neural network. This network incorporates a group-equivariant encoding module to encode relative coordinates, a permutation-equivariant convolution module to extract geometric information, and an entanglement module to aggregate global features. Classification experiments conducted on the ModelNet40 and ShapeNet datasets reveal that the proposed model outperforms existing approaches, including QGCNN, sQCNN-3D, and PI-QSVM. Furthermore, it achieves accuracy comparable to Q3DGL while requiring fewer training parameters.
Graph neural networks (GNNs) have demonstrated strong capabilities in graph representation learning but still face limitations in efficiency and scalability. Quantum GNNs (QGNNs) offer a promising alternative. However, existing approaches often fail to fully exploit edge information, require substantial quantum resources, and insufficiently account for permutation invariance in graph learning. To address these challenges, this article proposes a permutation-invariant quantum GNN (PIQGNN). The proposed model introduces a low-qubit-cost quantum encoding strategy that jointly embeds node features, edge features, and graph topology into entangled quantum states using only nnn qubits, where nnn denotes the number of nodes, while explicitly enforcing permutation invariance. Furthermore, a symmetry-aware variational quantum neural network (QNN) is designed to enable end-to-end permutation-invariant learning. Its hyperparameters are optimized via Bayesian optimization to alleviate barren plateau (BP) effects and enhance training stability. Experimental results on multiple graph binary classification benchmark datasets demonstrate that, compared with classical GNNs, PIQGNN achieves competitive performance with a significantly reduced number of trainable parameters. Compared with existing QGNNs, PIQGNN attains higher accuracy with lower quantum resource requirements and exhibits stronger robustness under noisy conditions. These results indicate that PIQGNN provides an efficient, scalable, and noise-resilient quantum framework for graph learning, highlighting its practical potential in the noisy intermediate-scale quantum (NISQ) era.
Graph Neural Networks (GNNs) have established themselves as powerful tools for learning from graph-structured data. However, their reliance on local message-passing mechanisms leads to over-squashing-the compression of exponentially growing neighborhood information into fixed-size vectors-which severely limits long-range dependency modeling. We introduce the Quantum-Inspired Graph Neural Network (QGNN) with a novel Quantum Entanglement Loss (QEL) function that addresses this challenge through a fundamentally different mechanism than existing approaches. Unlike spectral regularization (which enforces smoothness) or maximum entropy methods (which encourage representation diversity), QEL minimizes the von Neumann entropy of the node embedding correlation matrix, thereby concentrating eigenvalues in dominant eigenmodes that preserve global structural patterns. This entropy minimization creates direct information pathways between distant but functionally related nodes, effectively bypassing multi-hop bottlenecks. We evaluate QGNN on both standard benchmarks (Cora, Citeseer, PPI, Electronic Circuits) and the Long Range Graph Benchmark (LRGB) suite, which features graphs with average diameters up to 56.99 (Peptides). On LRGB datasets, QGNN achieves substantial improvements: 37.6% relative MAE reduction on Peptides-struct compared to GCN, 4.0% improvement over Graph Transformers (GraphGPS), and notably, 97% better performance than GCN on node pairs separated by 7+ hops. Despite these gains, QGNN requires only 20-30% additional computational overhead compared to standard GCN, while being 5-6 × faster than Graph Transformer approaches. Our results establish entropy-based regularization as a principled and efficient approach for long-range dependency modeling in graphs.
Abstract Graph neural networks (GNNs) are effective for processing graph-structured data but face challenges with large graphs due to high memory requirements and inefficient sparse matrix operations on GPUs. Quantum computing offers a promising avenue to address these issues and inspires new algorithmic approaches. In particular, quantum GNNs (QGNNs) have been explored in recent literature. However, current quantum hardware limits the dimension of the data that can be effectively encoded. Existing approaches either simplify datasets manually or use artificial graph datasets. This work introduces the guided graph compression (GGC) framework, which uses a graph autoencoder to reduce both the number of nodes and the dimensionality of node features. The compression is guided to enhance the performance of a downstream classification task, which can be applied either with a quantum or a classical classifier. The framework is evaluated on the Jet Tagging task, a classification problem of fundamental importance in high energy physics that involves distinguishing particle jets initiated by quarks from those by gluons. We compare GGC to a model that uses the autoencoder as a preprocessing step and to a baseline classical GNN classifier. Our numerical results demonstrate that GGC outperforms both alternatives, while also facilitating the testing of novel QGNN ansatzes on realistic datasets.
Graph Neural Networks (QGNNs) offer a promising approach to combining quantum computing with graph-structured data processing. While classical Graph Neural Networks (GNNs) are scalable and robust, existing QGNNs often lack flexibility due to graph-specific quantum circuit designs, limiting their applicability to diverse real-world problems. To address this, we propose a versatile QGNN framework inspired by GraphSAGE, using quantum models as aggregators to generate quantum-native node embeddings. We integrate inductive representation learning techniques with parameterized quantum convolutional and pooling layers, bridging classical and quantum paradigms. The convolutional layer is flexible, allowing tailored designs for specific tasks. Benchmarked on a node regression task with the QM9 dataset, our framework, using a single minimal circuit for all aggregation steps, handles molecules with varying numbers of atoms without changing qubits or circuit architecture. While classical GNNs achieve higher training performance, our quantum approach remains competitive and often shows enhanced generalization as molecular complexity increases. We also observe faster learning in early training epochs. To mitigate trainability limitations of a single-circuit setup, we extend the framework with multiple quantum aggregators on QM9. Assigning distinct circuits to each hop substantially improves training performance across all cases. Additionally, we numerically demonstrate the absence of barren plateaus as qubit numbers increase, suggesting that the proposed model remains trainable to larger, more complex graph-based problems.