• REQGNN with rotational and permutation equivariance are considered. • An optimized method for constructing equivariant quantum gatesets with reduced computational complexity is proposed. • The trainable quantum graph compression encoder effectively captures low-dimensional structural representations while preserving graph information. • The entanglement-enhanced aggregation strategy effectively captures edge information while preserving graph rotation symmetry. • An auxiliary entanglement layer mitigates the over-smoothing issue induced by multiple entanglement layers. • Experiments on standard graph classification and regression datasets validate the model’s effectiveness. 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. Experimental 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).

With the increasing scale of data and complexity of problems, some researchers have explored the integration of parameterized quantum circuits (PQCs) within convolutional neural networks (CNNs) as a means to enhance algorithmic performance. However, in most current quantum convolutional neural networks (QCNN) models, a single topological structure for quantum kernels (qkernels) is adopted and only one qubit of qkernels is measured, both of which may limit the model’s performance. To solve these problems, a novel multi-topology quantum convolutional neural networks with qubit-measurement attention for image classification is proposed. In order to enhance the capability of feature extraction, a multi-topology PQCs strategy is proposed, i.e., we adopt the different topology PQCs to construct quantum convolutional layers. In addition, a qubit-measurement attention mechanism is designed to mitigate the significant loss of entanglement information during the measurement phase. Specifically, each qubit in the qkernel is measured to generate a local feature map, and the weight of each local feature map is then calculated, resulting in the final feature map. Nine image classification experiments conducted on CIFAR-10 demonstrate that our model outperforms the state-of-the-art QCNN model, achieving an improvement of 11.7% on ten categories classification. Our model not only introduces a new approach for constructing QCNNs but also provides valuable reference for designing attention mechanisms tailored to quantum computing.

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.

Multimodal knowledge graph completion (MKGC) seeks to enrich knowledge graphs by integrating information from diverse modalities, facilitating more comprehensive knowledge representation and enhancing reasoning accuracy. However, existing models lack the flexibility to adapt to different tasks, and their performance still requires further improvement. To tackle these challenges, we propose an MKGC model based on Dynamic prompt learning and Multi-granularity cross-modal Aggregation, namely DM-MKGC. To be specific, a novel dynamic prompt template is proposed, which employs an adaptive task-guided mechanism to dynamically adjust the structure of entities, relations, and textual information. This approach enables the generation of prompts tailored to diverse tasks, ensuring both functional flexibility and structural consistency. Furthermore, a multi-granularity cross-modal aggregation method, which facilitates the aggregation of cross-modal information by facilitating the interaction between coarse-grained and fine-grained image features with textual features, is designed to enhance the model’s performance. Extensive experiments conducted on four datasets (FB15k-237-IMG, WN18-IMG, MNRE, and Twitter-2017) demonstrate our model outperforms other SOTA methods in knowledge completion, achieving an average improvement of 9.8%, 1.6%, and 1.23% in MR, Hits@n, and F1 respectively. Our model not only offers a novel method for multimodal knowledge graph completion but also contributes valuable insights for the advancement of knowledge graph technologies.

Abstract The proliferation of deep learning has driven research into deep learning‐based logo detection, which usually needs a large number of annotated data to train the model. However, due to the occasional appearance of new brands or the high cost of annotation, the number of training data is limited. Against this backdrop, the authors adapt the few‐shot object detection into logo detection, and thus present a cutting‐edge method called Double Classification Head (DCH) for Few‐Shot Logo Detection (DCH‐FSLogo), which aims at detecting the unseen logo classes using few annotated data. Unlike the traditional few‐shot detection, some logo objects are similar to their backgrounds and have diverse shapes as well. For this reason, the authors adopt balanced feature pyramid and deformable Region of Interest pooling in DCH‐FSLogo, this enhances the feature extraction capability and adapts to the different logo shapes. In addition, we introduce the DCH for few‐shot logo detection to detect logo objects using few annotated data. Specifically, we use an extra classification head for the base classes to ease the influence from the novel classes. The experimental results on four datasets, namely: FlickrLogos‐32, FoodLogoDet‐1500‐100, LogoDet‐3K‐100 and QMUL‐OpenLogo‐100, demonstrate that our method achieves better performance.

Secure two-party scalar product (S2SP) is a promising research area within secure multiparty computation (SMC), which can solve a range of SMC problems, such as intrusion detection, data analysis, and geometric computations. However, existing quantum S2SP protocols are not efficient enough, and the complexity is usually close to exponential level. In this paper, a novel secure two-party quantum scalar product (S2QSP) protocol based on Fourier entangled states is proposed to achieve higher efficiency. Firstly, the definition of unconditional security under malicious models is given. And then, an honesty verification method called Entanglement Bondage is proposed, which is used in conjunction with the modular summation gate to resist malicious attacks. The property of Fourierentangled states is used to calculate the scalar product with polynomial complexity. The unconditional security of our protocol is proved, which guarantees the privacy of all parties. In addition, we design a privacy-preserving quantum matrix multiplication protocol based on S2QSP protocol. By transforming matrix multiplication into a series of scalar product processes, the product of two private matrices is calculated without revealing any privacy. Finally, we show our protocol’s feasibility in IBM Qiskit simulator.

Cloud computing is a powerful and popular information technology paradigm that enables data service outsourcing and provides higher-level services with minimal management effort. However, it is still a key challenge to protect data privacy when a user accesses the sensitive cloud data. Privacy-preserving database query allows the user to retrieve a data item from the cloud database without revealing the information of the queried data item, meanwhile limiting user’s ability to access other ones. In this study, in order to achieve the privacy preservation and reduce the communication complexity, a quantum-based database query scheme for privacy preservation in cloud environment is developed. Specifically, all the data items of the database are firstly encrypted by different keys for protecting server’s privacy, and in order to guarantee the clients’ privacy, the server is required to transmit all these encrypted data items to the client with the oblivious transfer strategy. Besides, two oracle operations, a modified Grover iteration, and a special offset encryption mechanism are combined together to ensure that the client can correctly query the desirable data item. Finally, performance evaluation is conducted to validate the correctness, privacy, and efficiency of our proposed scheme.

Fog computing is emerging as a powerful and popular computing paradigm to perform IoT (Internet of Things) applications, which is an extension to the cloud computing paradigm to make it possible to execute the IoT applications in the network of edge. The IoT applications could choose fog or cloud computing nodes for responding to the resource requirements, and load balancing is one of the key factors to achieve resource efficiency and avoid bottlenecks, overload, and low load. However, it is still a challenge to realize the load balance for the computing nodes in the fog environment during the execution of IoT applications. In view of this challenge, a dynamic resource allocation method, named DRAM, for load balancing in fog environment is proposed in this paper. Technically, a system framework for fog computing and the load‐balance analysis for various types of computing nodes are presented first. Then, a corresponding resource allocation method in the fog environment is designed through static resource allocation and dynamic service migration to achieve the load balance for the fog computing systems. Experimental evaluation and comparison analysis are conducted to validate the efficiency and effectiveness of DRAM.

This article describes a study of the satellite module layout problem (SMLP), which is a three-dimensional (3D) layout optimization problem with performance constraints that has proved to be non-deterministic polynomial-time hard (NP-hard). To deal with this problem, we convert it into an unconstrained optimization problem using a quasi-physical strategy and the penalty function method. The energy landscape paving (ELP) method is a class of Monte-Carlo-based global optimization algorithm that has been successfully applied to solve many optimization problems. ELP can search for low-energy layouts via a random walk in complex energy landscapes. However, when ELP falls into the narrow and deep valleys of an energy landscape, it is difficult to escape. By putting forward a new update mechanism of the histogram function in ELP, we obtain an improved ELP method which can overcome this drawback. By incorporating the gradient method with local search into the improved ELP method, a new global search optimization method, nELP, is proposed for SMLP. Two representative instances from the literature are tested. Computational results show that the proposed nELP algorithm is an effective method for solving SMLP with performance constraints.

By reviewing the original INIQGA algorithm, an improved algorithm (IINIQGA) is put forward by revising the lookup table. In addition, By introducing the variable angle-distance rotation method into the update Q(t) procedure, a novel quantum-inspired evolutionary algorithm, QEA-VAR, was proposed. Compared with previous algorithms, our update Q(t) procedure is more simple and feasible. Finally, the corresponding experiments on the 0-1 knapsack problem were carried out, and the results show that our improvement is efficient, and comparing with IINIQGA, QEA, and CGA, QEA-VAR has a faster convergence and better profits than other algorithms.

We propose an efficient quantum secret sharing scheme with orthogonal product states in the 3×3 Hilbert space. Different from Hsu and Li's scheme [Phys. Rev. A 71, 022321 (2005)], this scheme utilizes a novel distribution strategy which sends the qutrits of basis states and superpositions to two separated observers respectively. The theoretical analysis shows that the intrinsic efficiency for qutrits in this scheme approaches 100% and the total efficiency of this scheme is higher than that of the aforementioned scheme. Furthermore, the security and some possible eavesdropping strategies are also examined in this paper.

Owing to the exponential nature of the memory or run-tune complexity, many existing methods can only synthesize 3-qubit circuits, however, (G.W. Yang et al., 2005) can achieve 12 steps for the CNP (controlled-Not gate, NOT gate and Peres gate) library in 4-qubit circuit synthesis with mini-length by using an enhanced bi-directional synthesis approach. We mainly absorb the ideas of our 3-qubit synthesis algorithms based on hash table and present a novel and efficient algorithm which can construct almost all optimal 4-qubit reversible logic circuits with various types of gates and mini-length cost based on constructing the shortest coding and the specific topological compression, whose lossless compression ratios of the space of n-qubit circuits is near 2timesn!. Our algorithm has created all 3120218828 optimal 4-qubit circuits whose length is less than 9 for the CNT (Toffoli gate) library, and it can quickly achieve 16 steps through cascading created circuits. To the best of our knowledge, there are no other algorithms to achieve the contribution.

Two protocols of quantum direct communication with authentication [Phys. Rev. A 73, 042305(2006)], proposed by Lee, Lim and Yang, recently were indicated to be insecure against the authenticator Trentpsilas attacks [Phys. Rev. A 75, 026301(2007)]. In this paper, two novel efficient protocols of quantum direct communication with authentication are presented by utilizing four kinds of Pauli operations (I, sigmax, isigmay, sigmaz). These new protocols can transmit two bits message every GHZ state, instead of one bit in the aforementioned protocols. Analysis shows that they are secure against the inner participantpsilas attacks (such as Trentpsilas attacks) as well as the outer Evepsilas attacks. Finally, we generalize them to multiparty quantum direction communication.

To ensure the validity and reliability of reversible circuits, fault detection is necessarily. Two methods to get complete test set with respect to missing-gate fault (MGF) in reversible circuits were introduced. They are the method that divided the circuit into subcircuit to get the complete test set which is not minimal and the set covering method to get the minimal complete test set. Comparing to DFT detection method, the methods introduced in this paper do not need additional gates; they do not change the structure of the circuits and do not depend on implement technologies. So, it can be widely applied.