Exploring the potential of Quantum Graph Neural Networks in analyzing Large-Scale Structure of Universe

In this work, we studied the use of Quantum Machine Learning (QML) algorithms for binary classification and compared their performance with classical Machine Learning (ML) methods. QML merges principles of Quantum Computing (QC) and ML, offering improved efficiency and potential quantum advantage in data-driven tasks and when solving complex problems. In binary classification, where the goal is to assign data to one of two categories, QML uses quantum algorithms to process large datasets efficiently. Quantum algorithms like Quantum Support Vector Machines (QSVM) and Quantum Neural Networks (QNN) exploit quantum parallelism and entanglement to enhance performance over classical methods. This study focuses on two common QML algorithms, Quantum Support Vector Classifier (QSVC) and QNN. We used the Qiskit software and conducted the experiments with three different datasets. Data preprocessing included dimensionality reduction using Principal Component Analysis (PCA) and standardization using scalers. The results showed that quantum algorithms demonstrated competitive performance against their classical counterparts in terms of accuracy, while QSVC performed better than QNN. These findings suggest that QML holds potential for improving computational efficiency in binary classification tasks. This opens the way for more efficient and scalable solutions in complex classification challenges and shows the complementary role of quantum computing.

Machine learned potentials based on artificial neural networks are becoming a popular tool to define an effective energy model for complex systems, either incorporating electronic structure effects at the atomistic resolution, or effectively renormalizing part of the atomistic degrees of freedom at a coarse-grained resolution. One main criticism regarding neural network potentials is that their inferred energy is less interpretable than in traditional approaches, which use simpler and more transparent functional forms. Here we address this problem by extending tools recently proposed in the nascent field of explainable artificial intelligence to coarse-grained potentials based on graph neural networks. With these tools, neural network potentials can be practically decomposed into n-body interactions, providing a human understandable interpretation without compromising predictive power. We demonstrate the approach on three different coarse-grained systems including two fluids (methane and water) and the protein NTL9. The obtained interpretations suggest that well-trained neural network potentials learn physical interactions, which are consistent with fundamental principles.

StructuredLight-GNN: A graph neural network for end-to-end structured light 3D point cloud processing

At present, the urban traffic system is faced with the problems of congestion and low efficiency, and the traditional methods have certain limitations when dealing with the complex urban road network. This paper aims to explore a new method of capacity Optimization of Road Networks in a Smart City environment and proposes a method based on a Graph Neural network, named “Smart City Road optimization Graph Neural Network” (SCRO-GNN). SCRO-GNN first collects and preprocesses multi-source data, including road network data, traffic flow, accident records, environmental factors, etc. The key node and edge features, including the number of lanes at the intersection, the traffic flow of the section, and the adjacency matrix of the road network are defined to characterize the structure of the road network. Then, the graph neural network model is constructed and trained to predict the traffic flow of different sections and evaluate the road capacity by using the graph structure of the road network. This paper tests the performance of SCRO-GNN on real road networks in multiple cities. The results show that, compared with the traditional traffic flow prediction model, SCRO-GNN can significantly improve the prediction accuracy, especially when dealing with the highly complex urban road network structure. Based on these predictions, the proposed optimization strategy performed well in reducing traffic congestion and improving the efficiency of road use. The research in this paper not only demonstrates the potential of graph neural networks in smart city road network optimization, but also provides a new direction for future traffic system research. The successful implementation of the SCRO-GNN approach is expected to provide more efficient and intelligent solutions for urban traffic management and planning.

This article introduces the Missingness-aware Self-Supervised Graph Neural Network (MissGNN), a novel model for tabular data predictions in scenarios with missing values. Addressing a significant challenge in fields like finance, healthcare, and environmental studies, MissGNN innovatively integrates feature imputation and label prediction within a unified framework. Utilizing a Tabular Bipartite Graph, it distinctively represents data points and features, enabling intricate modeling of their relationships. This approach is pivotal in contexts where missing data can significantly skew model training and predictions. MissGNN employs a Graph Neural Network to generate embeddings, capturing interactions between data points and features for accurate missing value imputation and label prediction. It features a dual-focus mechanism, comprising edge-wise feature imputation and node-wise label prediction. A pre-training phase for feature imputation enhances the model’s predictive ability for both features and labels. Additionally, MissGNN incorporates a multi-view learning strategy through feature subsetting, further enriching its representation learning. Experiments on 14 tabular datasets demonstrate MissGNN’s superiority over existing models in managing missing values across both regression and classification tasks. The results underscore its robustness and practical applicability, establishing it as a versatile tool for tackling tabular data prediction challenges with missing values. MissGNN’s contributions significantly redefine the approach to missing value imputation, aligning feature imputation and label prediction in a cohesive manner and underscoring the potential of Graph Neural Networks in processing tabular data.

Efficient graph representation in graph neural networks for stress predictions in stiffened panels

Recent advances in Earth observation and data collection technologies have made high-resolution hydrological datasets increasingly accessible, enhancing our capabilities for monitoring and predicting hydrological processes. While a variety of artificial intelligence (AI) models can be employed to leverage these datasets, the challenges and opportunities of different AI approaches in the context of high-resolution data availability remain only partially explored. For instance, although Long Short-Term Memory (LSTM) networks are widely used for discharge prediction, the potential of Graph Neural Networks (GNNs)—which naturally represent river networks as graphs and capture spatial dependencies—has yet to be fully investigated.In this study, we conduct a comprehensive analysis of GNN-based models for river discharge prediction in the Danube River Basin. Leveraging the LamaH-CE (Large-Sample Data for Hydrology and Environmental Sciences for Central Europe) dataset, we incorporate both dynamic features (e.g., daily precipitation, temperature, soil moisture) and static variables (e.g., digital elevation model, river density, basin area). Three architectures—GNN, a hybrid LSTM-GNN, and a standalone LSTM—are trained, validated, and tested at daily time steps from 2000 to 2017.We further investigate the impact of network density and high-resolution (1km) soil moisture and precipitation data on discharge prediction accuracy. Our analysis reveals the potential advantages and limitations of these architectural approaches in river discharge prediction under high-resolution data availability and underscores the growing importance of harnessing graph-based deep learning methods for hydrological applications.

Network modeling is a critical component for building self-driving Software-Defined Networks, particularly to find optimal routing schemes that meet the goals set by administrators. However, existing modeling techniques do not meet the requirements to provide accurate estimations of relevant performance metrics such as delay and jitter. In this paper we propose a novel Graph Neural Network (GNN) model able to understand the complex relationship between topology, routing and input traffic to produce accurate estimates of the per-source/destination pair mean delay and jitter. GNN are tailored to learn and model information structured as graphs and as a result, our model is able to generalize over arbitrary topologies, routing schemes and variable traffic intensity. In the paper we show that our model provides accurate estimates of delay and jitter (worst case R2 = 0.86) when testing against topologies, routing and traffic not seen during training. In addition, we present the potential of the model for network operation by presenting several use-cases that show its effective use in per-source/destination pair delay/jitter routing optimization and its generalization capabilities by reasoning in topologies and routing schemes not seen during training.

This rapid growth in data and the increased complexity of machine learning models have made it almost impossible to continue pushing forward with classical computing, thereby creating a pressing need for new computational paradigms. The following paper will examine how quantum machine learning answers the above questions by applying the principles of quantum mechanics to the art of artificial intelligence (AI) and big data analytics. We examine some of the current Quantum Machine Learning (QML) algorithms and their applications based on a framework that employs quantum-enhanced feature spaces, variational quantum circuits, and quantum-inspired classical algorithms. Our methodology combines theoretical analysis with empirical evaluation of these methods over standard benchmark datasets, using both quantum simulators and real quantum hardware. Key findings include a set of advantages carried by QML in specific fields, such as dimensionality reduction, optimization problems, and some clustering tasks. These are the quadratic speedup for support vector machines and the exponential advantage for principal component analysis. Our results also show that quantum error correction isn’t perfect and that loading classical data into a quantum system can be hard. We conclude that, while QML holds much promise, it is, by all means, clearly still a way off from being considered a panacea. It is awaiting further breakthroughs in quantum hardware, error mitigation techniques, and algorithm design in order to fully realize its potential. This work thus presents a roadmap for future research and highlights where QML is best placed to make major impactful differences in artificial intelligence and big data analytics.

Quantum machine learning (QML) promises computational advantages for complex learning tasks, but identifying which datasets stand to benefit remains an open question. The recently proposed bit-bit encoding scheme encodes both inputs and outputs as bitstrings, which leads to quantum models that are universal approximators. Under bit-bit encoding, the number of input and output pairs increases exponentially with the number of qubits, which allows the calculation of the number of qubits required to fully represent a dataset. Datasets that can be covered with fewer than 50 qubits are unlikely to benefit from quantum advantage, as they are classically simulable. We use bit-bit encoding to perform a resource estimation study on both synthetic and real-world classification datasets. On synthetic data, we analyze how qubit requirements scale with the number of features and samples. On real datasets, we compare qubit requirements across different classical dimensionality reduction schemes. We find that all tested datasets require 49 qubits or fewer for full coverage, regardless of dimensionality reduction method. This suggests that standard, medium-sized, single-label classification datasets are unlikely to see performance gains from QML. In future work, we will explore more complex data types, such as multi-label, sequential, and regression, that may require more than 50 qubits for coverage and could therefore be promising candidates for quantum advantage.

We study anisotropic (patchy) screening induced by the resonant conversion of cosmic microwave background (CMB) photons into dark-sector massive vector bosons (dark photons) as they cross non-linear large scale structure (LSS). Resonant conversion takes place through the kinetic mixing of the photon with the dark photon, one of the simplest low energy extensions to the Standard Model. In the early Universe, resonant conversion can occur when the photon plasma mass, obtained as the photon propagates through the ionized interstellar and intergalactic media, matches the dark photon mass. After the epoch of reionization, resonant conversion occurs mainly in the ionized gas that occupies virialized dark matter halos, for a range of dark photon masses between 10-13 eV ≲ m A' ≲ 10-11 eV. This leads to new CMB anisotropies that are correlated with LSS, which we refer to as patchy dark screening, in analogy with anisotropies from Thomson screening. Its unique frequency dependence allows it to be distinguished from the blackbody CMB. In this paper, we use a halo model approach to predict the imprint of dark screening on the CMB temperature and polarization anisotropies, as well as their correlation with LSS. We then examine the two- and three-point correlation functions of the dark-screened CMB, as well as correlation functions between CMB and LSS observables, to project the sensitivity of future measurements to the kinetic mixing parameter and dark photon mass. We demonstrate that an analysis with existing CMB data can improve upon current constraints on the kinetic mixing parameter by two orders of magnitude with the two-point correlation functions, while data from upcoming CMB experiments and LSS surveys can further improve the reach by another order of magnitude with two- and three-point correlation functions.

Abstract. On 20 April 2013, Lushan experienced an earthquake with a magnitude of 7.0. In seismic assessments, borehole strainmeters, recognized for their remarkable sensitivity and inherent reliability in tracking crustal deformation, are extensively employed. However, traditional data-processing methods encounter challenges when handling massive dataset-s. This study proposes using a Graph WaveNet graph neural network to analyze borehole strain data from multiple stations near the earthquake epicenter and establishes a node graph structure using data from four stations near the Lushan epicenter, covering the years 2010–2013. After excluding the potential effects of pressure, temperature, and rainfall, we statistically analyzed the pre-earthquake anomalies. Focusing on the Guza, Xiaomiao, and Luzhou stations, which are the closest to the epicenter, the fitting results revealed two acceleration events of anomalous accumulation that occurred before the earthquake. Occurring approximately 4 months before the earthquake event, the first acceleration event indicated the pre-release of energy from a weak fault section. Conversely, the acceleration event observed a few days before the earthquake indicated a strong fault section that reached an unstable state with accumulating strain. We tentatively infer that these two anomalous cumulative accelerations may be related to the preparation phase for a large earthquake. This study highlights the considerable potential of graph neural networks in conducting multistation studies of pre-earthquake anomalies.

In today’s digital economy, organisations must manage an excessive volume of unstructured data. Traditional data warehouses are frequently underutilised due to inconsistencies in how to successfully evaluate such massive amounts of information. Knowledge graphs have developed as an effective solution, giving a structured representation of interrelated facts to improve data organisation, retrieval, and inference across several disciplines. Knowledge graphs, which capture interactions between elements such as people, locations, and concepts, provide a complete framework for interpreting and identifying hidden patterns in data. This study investigates the evolution of knowledge graphs, from simple data integration tools to complex systems that support semantic searches. These searches go beyond standard keyword searches, providing context-aware results that increase the relevance and accuracy of information retrieval. In addition, the study investigates the use of knowledge graphs in recommendation systems, emphasising their capacity to personalise user experiences through personalised suggestions. This research highlights the potential of knowledge graph technology to improve data management and utilisation, promoting innovation and efficiency across a variety of sectors.

Cicada species recognition based on acoustic signals using dynamic time warping-graph based GraphMix, graph convolution network

This study investigates the potential of graph neural networks (GNNs) for estimating system-level integrated information and major complex in integrated information theory (IIT) 3.0. Owing to the hierarchical complexity of IIT 3.0, calculating the integrated information and identifying the major complex are computationally prohibitive for large systems. To overcome this difficulty, we propose a GNN model with transformer convolutions characterized by multi-head attention mechanisms for estimating the major complex and its integrated information. For evaluation, we begin by obtaining exact solutions for integrated information and major complexes in systems with 5, 6, and 7 nodes, and conduct two experiments: (1) a non-extrapolative setting in which the model is trained and tested on a mixture of systems with 5, 6, and 7 nodes, and (2) an extrapolative setting in which systems with 5 and 6 nodes are used for training and systems with 7 nodes are used for testing. We then examine the scaling behavior for tree-like, fully connected, and loop-containing graph topologies in larger systems. Although accurate estimation is difficult, our approximate estimates for larger systems generally preserve the qualitative patterns of integrated information and major complex size that are observed in small systems. Finally, based on this observation, we qualitatively analyze a split-brain–like system of 100 nodes. The system consists of two weakly coupled subsystems of 50 nodes each, representing a structurally meaningful, brain-inspired configuration. When the connectivity between the subsystems is low, “local integration” emerges, and a single subsystem forms a major complex. As the connectivity increases, local integration rapidly disappears, and the integrated information gradually rises toward “global integration,” in which a large portion of the entire system forms a major complex. Our analysis suggests that the proposed GNN-based framework provides a practical approach to qualitative analysis of integrated information and major complexes in large systems.