Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “Advanced Graph Neural Networks”

Advanced Applications in Graph Neural Networks

Yao Ma, Jiliang Tang · Cambridge University Press eBooks · 2021

A summary is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.

Cited by 0

Lung cancer prediction with advanced graph neural networks

Bineesh Moozhippurath, N. Jayapandian · Indonesian Journal of Electrical Engineering and Computer Science · 2024

This research aims to enhance lung cancer prediction using advanced machine learning techniques. The major finding is that integrating graph convolutional networks (GCNs) with graph attention networks (GATs) significantly improves predictive accuracy. The problem addressed is the need for early and accurate detection of lung cancer, leveraging a dataset from Kaggle's "Lung Cancer Prediction Dataset," which includes 309 instances and 16 attributes. The proposed A-GCN with GAT model is meticulously engineered with multiple layers and hidden units, optimized through hyperparameter adjustments, early stopping mechanisms, and Adam optimization techniques. Experimental results demonstrate the model's superior performance, achieving an accuracy of 0.9454, precision of 0.9213, recall of 0.9743, and an F1 score of 0.9482. These findings highlight the model's efficacy in capturing intricate patterns within patient data, facilitating early interventions and personalized treatment plans. This research underscores the potential of graph-based methodologies in medical research, particularly for lung cancer prediction, ultimately aiming to improve patient outcomes and survival rates through proactive healthcare interventions.

Cited by 1Open access

Graph Neural Networks for Advanced Molecular Data Analysis

Niccolò Pancino · Florence Research (University of Florence) · 2023

Niccolò Pancino's Ph.D. Thesis, Ph.D. program in Smart Computing, Cycle XXXV, discussed on 29/5/2023. 
\n
\nGraphs are data structures composed of collections of nodes and edges, which can be used to represent objects, or patterns, along with their relationships.
\nDeep Learning techniques, and in particular Deep Neural Networks, have recently known a great development and have been employed in solving tasks of increasing complexity and variety. In particular, Graph Neural Networks (GNNs) have been extensively studied in the last decade, with many theoretical and practical innovations. Indeed, their main feature is the capability of processing graphs with minimal loss of structural information, which has caused GNNs to be applied to an increasing number of problems of different nature, leading to the development of new theories, models, and techniques.
\nIn particular, biological data proved to be a very suitable application field for GNNs, with metabolic networks, molecules, and proteins representing just few examples of data that are naturally encoded as graphs.
\nIn this thesis, a software framework for implementing GNN models was developed and discussed. Furthermore, some applications of GNNs to molecular data, relevant both from the point of view of Deep Learning and Bioinformatics, are discussed. The main focus of the work is on the drug side–effect prediction problem. This is a challenging task, since predictions can be based on homogeneous as well as heterogeneous and complex data, with graphs collecting nodes and edges representing different entities and relationships.
\nOn the other side, protein–protein interfaces can be detected by identifying the maximum clique in a correspondence graph of protein secondary structures, a problem which can be solved with Layered Graph Neural Networks (LGNNs). Promising experimental outcomes offer valuable insights and permit drawing interesting conclusions about the abilities of GNNs in analyzing molecular data. Given the growing interest of the AI research community on graph–based models, these applications, inspired by real–world problems, constitute a very good testing ground for evaluating GNN computational capabilities, in order to improve and evolve the actual models and extend them
\nto more complex tasks, particularly in the biological field.

Cited by 1Open access

Graph Neural Networks for Timing Optimization in Advanced Node Placement

Jiahao Liu, Pengfei Wu, Robert A. Klein · Frontiers in Artificial Intelligence Research · 2026

The escalating complexity of modern integrated circuit design demands innovative approaches to address timing optimization challenges in advanced technology nodes. Graph Neural Networks (GNNs) have emerged as a transformative paradigm for modeling circuit representations and optimizing placement decisions. This paper presents a comprehensive investigation of GNN applications in timing-driven placement optimization for sub-10nm process technologies. We propose a novel framework that leverages GNN architectures to encode circuit connectivity patterns, predict timing metrics, and guide placement algorithms toward solutions that minimize critical path delays while maintaining acceptable wirelength overhead. Our methodology employs a two-stage GNN model integrating global placement refinement with local timing optimization subroutines. The framework captures spatial dependencies between circuit components through message passing mechanisms while incorporating timing constraints directly into the optimization objective. Experimental evaluations on industry benchmark circuits demonstrate that GNN-based timing optimization achieves 18-24% reduction in worst negative slack compared to conventional analytical placement methods, with runtime improvements of 3-5x over traditional static timing analysis iterations. The proposed approach maintains placement quality metrics including wirelength increase below 7% and demonstrates robust convergence across diverse circuit topologies ranging from processor cores to memory controllers. This research establishes GNNs as viable alternatives to conventional timing-driven placement algorithms and opens new directions for machine learning integration in electronic design automation workflows.

Cited by 0Open access

Advanced state estimation in distribution networks using graph and physics-informed neural networks

Milos Saric · QRU Quaderns de Recerca en Urbanisme · 2026

This document presents a study on state estimation in electrical distribution networks using Graph Neural Networks and graph-based Physics-Informed Neural Networks. Accurate state estimation is crucial for reliable operation, monitoring, and control of modern distribution systems, especially with high penetration of Distributed Energy Resources. Graph-based PhysicsInformed Neural Networks leverage the network’s topology and physical laws to provide scalable and physically consistent estimation. A central focus of this work is the integration of Graph Neural Networks with power flow physics. The proposed approach embeds Kirchhoff’s laws and nodal voltage-current relationships into the neural network’s loss function, ensuring that predictions respect the underlying physics. The network architecture considers node and edge features, such as bus voltages, branchcurrents, loads, and line parameters, enabling themodeltocapturebothtopologicaland electrical dependencies. The study includes detailed modeling of the distribution network and the formulation of the state estimation problem as a physics-informed learning task. Simulations are carried out in Python using PyTorch Geometric to validate the proposed framework.

Cited by 0Open access

Graph Neural Networks for Advanced Financial Risk Modeling in Volatile Markets

Krishnam Raju Narsepalle, Sreepal Reddy Bolla · 2025

The complex and nonlinear relationships between assets, firms, and economic indicators are not thoroughly captured by conventional risk modeling methods in the constantly changing landscape of volatile financial markets. This research introduces a new model based on Graph Neural Network (GNN) that utilizes the graph-based structure of financial systems to offer improvements in financial risk modelling using graph-based constructs. Graph Neural Networks (GNNs) [5] are leveraged to represent market entities as nodes and their complex interrelations as edges across both temporal and relational dimensions to allow deep representation learning. This work uses a combined estimate of systemic risk and probability of contagion pathways through historical market data, macroeconomic signals, and sector dependence. Experimental results on real-world financial datasets show that the proposed model achieves superior performance in volatility forecasting, stress testing and anomaly detection tasks compared to conventional machine learning methods. The GNN-driven framework provides such a forward-looking, adaptive tool set for robust financial decision making under high uncertainty.

Cited by 2

Advanced 3D Face Reconstruction from Single 2D Images Using Enhanced Adversarial Neural Networks and Graph Neural Networks

Mohamed Fathallah, Sherif El-etriby, Maazen Alsabaan et al. · Sensors · 2024

This paper presents a novel framework for 3D face reconstruction from single 2D images and addresses critical limitations in existing methods. Our approach integrates modified adversarial neural networks with graph neural networks to achieve state-of-the-art performance. Key innovations include (1) a generator architecture based on Graph Convolutional Networks (GCNs) with a novel loss function and identity blocks, mitigating mode collapse and instability; (2) the integration of facial landmarks and a non-parametric efficient-net decoder for enhanced feature capture; and (3) a lightweight GCN-based discriminator for improved accuracy and stability. Evaluated on the 300W-LP and AFLW2000-3D datasets, our method outperforms existing approaches, reducing Chamfer Distance by 62.7% and Earth Mover's Distance by 57.1% on 300W-LP. Moreover, our framework demonstrates superior robustness to variations in head positioning, occlusion, noise, and lighting conditions while achieving significantly faster processing times.

Cited by 7Open access

Advanced Apple Sorting and Quality Grading Application Using Graph Neural Networks, Vision Transformers, and Convolutional Neural Networks

Arafat Ali Mondal, Nabarun Bhattacharyya, Shatadal Ghosh · 2025

In the agriculture sector, assessing apples for quality is crucial for both market sales and international commerce. Traditional procedures, including human grading, need experienced employees and take a long time. Grading in a lab is also very costly. Farmers on a limited budget require a quick and precise means to pick along with grade apples, and there is a need for them. Our work addresses these limitations by building a smart and automated approach for quality grading of the Advanced Apple Sorting Application. The primary goal is to integrate 3 types of models, Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Graph Neural Networks (GNNs) to create a smart, automated software for grading apples. We are using a CNN model to extract important features such as surface texture coloration patterns and defects which are critical for our quality evaluation. The CNNs are primarily interested in localized features and find it difficult to observe the entire context of an image. But CNNs individually concentrate on local features but lack global structural relationships. For this we are utilizing ViTs self-attention mechanisms to examine the whole apple image simultaneously, enabling them to pick up on slight differences in shape size and color. While ViTs take a global view they might miss finer details. Finally, we use GNNs to improve classification accuracy by detecting important attributes such as weight diameter and ripeness. This guarantees a more consistent grading process that is not limited to simple pixel based analysis. GNNs bridge this gap by learning physical relationships and enhancing classification stability. By integrating these three modules, the system can extract fine-grained features and comprehend the global structure of the image. This results in a more accurate grading process. We have also developed an easy to use web and Android Application that farmers can grade apples promptly and efficiently. Our model has been tested and trained using various kinds of Apple datasets.

Cited by 0

Three Essays in Advanced Graph Neural Networks: From Multivariate Temporal Forecasting to Heterophilous Graph Learning

Ruikun Li · The Sydney eScholarship Repository (The University of Sydney) · 2025

In recent decades, the rapid advancement of computing power and data collection techniques has led to an unprecedented surge in structured and semi-structured data, necessitating the development of deep learning techniques to extract meaningful insights. While traditional deep learning methods have demonstrated remarkable power across various domains, they struggle to model the complex inter-relational structures inherent in real-world data, such as graphs. Graph Neural Networks (GNNs) have emerged as a powerful framework to address this limitation, enabling the effective representation of interdependent entities and achieving success in numerous real-world applications. However, several challenges remain for GNNs, particularly in areas such as multivariate time series forecasting and heterophilous graph learning. For instance, while GNNs have been widely applied to multivariate time series forecasting, their potential in probabilistic forecasting remains under-explored. Most existing GNN-based forecasting models focus on deterministic predictions, failing to quantify predictive uncertainty, which is crucial for decision-making. Developing a GNN-based framework that effectively integrates probabilistic modelling into temporal forecasting remains an open challenge. Additionally, GNNs are often incorporated into time series models to capture inter-series dependencies, while intra-series temporal dependencies are typically modelled separately using temporal models. However, in real-world systems, intra- and inter-temporal dependencies are inherently intertwined, making it challenging to fully exploit complex entangled relationships using existing methods. This raises the question of whether time series data can be transformed into a pure graph representation to unify these dependencies under a pure graph paradigm...

Cited by 0

Advanced risk prediction in healthcare: Neutrosophic Graph Neural Networks for disease transmission

A. Meenakshi, Janmejaya Mishra, Jeong-Gon Lee et al. · Complex & Intelligent Systems · 2025

This research investigates the integration of neutrosophic logic with Graph Neural Networks (GNNs) for disease transmission risk prediction. Neutrosophic Graph Neural Networks (NGNNs) extend the capabilities of Fuzzy Graph Neural Networks (F-GNNs) as utilized in this paper to process structured information. By merging neutrosophic logic with GNNs, the technique significantly improved the handling of uncertainty while monitoring contagious diseases. The standard GNN model fails to process unreliable and unspecific information commonly found in epidemiological data collections. The neutrosophic triplets $$(\mathcal {T, I, F})$$ within NGNNs represent uncertain components found in disease outbreak conditions. Improved message passage through the NGNN works best while processing complex and extended datasets that programmers structure with Python. The risk evaluation and transmission uncertainty of diseases appear in visual heat maps to assist in the analysis of network dynamics. Through visual output, the health sector receives essential information related to outbreak development for making better decisions. By uniting state-of-the-art computing solutions with health-related implementation, this approach establishes superior standards for medical risk evaluation and produces foundational capabilities for future research. The authors established a firm foundation for advanced epidemic simulation and risk assessment through their work, which integrates theoretical graph theory advances into practical public health scenarios.

Cited by 3Open access

FedHE-Graph: Federated Learning with Hybrid Encryption on Graph Neural Networks for Advanced Persistent Threat Detection

Atmane Ayoub Mansour Bahar, Kamel Soaïd Ferrahi, Mohamed‐Lamine Messai et al. · 2024

Intrusion Detection Systems (IDS) play a crucial role in safeguarding systems and networks from different types of attacks. However, IDSes face significant hurdles in detecting Advanced Persistent Threats (APTs), which are sophisticated cyber-attacks characterised by their stealth, duration, and advanced techniques. Recent research has explored the effectiveness of Graph Neural Networks (GNNs) in APT detection, leveraging their ability to analyse intricate-relationships within graph data. However, existing approaches often rely on local models, limiting their adaptability to evolving APT-tactics and raising privacy-concerns. In response to these challenges, this paper proposes integrating Federated-Learning (FL) into the architectures of GNN-based Intrusion Detection Systems. Moreover, our solution includes an enhanced encryption-system of the clients’ weights to safely send them to the server through the system’s network. This solution prevents man-in-the-middle (MitM) attacks from intercepting the weights and reconstructing clients data using reverse engineering. We evaluate our approach on several datasets, demonstrating promising results in reducing false-positive rates compared to state-of-the-art Provenance-based IDSes (PIDS).

Cited by 5

Advanced Threat Detection Using Structural Features and Graph Neural Networks for Malware Analysis

Nasser Al-Sharif · 2025

Malware enriched with polymorphism, and obfuscation, has surpassed traditional signature and heuristic-based detection approaches. Machine learning and deep learning methods such as Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs) have enhanced malware classification performance by utilizing static and sequential input as features. Nevertheless, the effectiveness of these approaches is limited due to their inability to model structural dependencies, which are crucial for identifying threats. This study, we propose a malware detection framework utilizing Graph Neural Networks (GNNs) to identify structural relationships within malware samples. The structural elements among the malware samples are incorporated within nodes/ and edges that apply to nodes, thereby allowing us to extract behavioral semantics that were not captured in previous models. The framework is evaluated using the EMBER dataset, which has 2,381 static and dynamic malware features; features are selected using Chi-square tests. We analyse advanced GNNs: Graph Convolutional Networks (GCNs); and Graph Attention Networks (GATs). Our findings demonstrate that the GNN-based malware detection framework outperforms classical detection methods (e.g., SVM, Random Forest, CNN, and RNN) consistently across multiple instances. This study establishes GNNs as a scalable, interpretable, and accurate approach for next-generation malware detection, and as a method that is resilient to adversarial evasion and structurally aware of malware behaviors.

Cited by 0