Skip to Content

383 Results Found

  • Article
  • Open Access
1 Citations
900 Views
42 Pages

Subdiffusion on graphs is often modeled by time-fractional diffusion equations; yet, its structural and dynamical consequences remain unclear. We show that subdiffusive transport on graphs is a memory-driven process generated by a random time change...

(This article belongs to the Special Issue Fractal Analysis and Data-Driven Complex Systems)
  • Article
  • Open Access
427 Views
13 Pages

Graph Attention Diffusion Method Combining Diffusion Mechanism and Graph Attention Mechanism

  • Xing Li,
  • Jiaxin Li,
  • Huijun Wang,
  • Yue Xie and ,
  • Shujuan Jia,
  • Zhijie Dong,
  • Zitong Yue and
  • Baoquan Ma
  • + 3 authors+ 0 author

15 June 2026

Graph neural networks have attracted much attention and performed well in many downstream tasks. However, due to issues such as oversmoothing, existing graph neural networks are limited in their ability to quantitatively exploit higher-order neighbor...

(This article belongs to the Special Issue Scalable Algorithms for Large-Scale Graph Neural Networks)
  • Feature Paper
  • Article
  • Open Access
1 Citations
2,697 Views
13 Pages

24 July 2025

The resistance distance is a squared Euclidean metric on the vertices of a graph derived from the consideration of a graph as an electrical circuit. Its connection with the commute time of a random walker on the graph has made it particularly appeali...

(This article belongs to the Special Issue Advances in Combinatorics, Discrete Mathematics and Graph Theory)
  • Article
  • Open Access
3,254 Views
13 Pages

19 November 2025

Graph Convolutional Networks (GCNs) have become a widely used framework for learning from graph-structured data due to their efficiency and performance in tasks such as node classification and link prediction. However, conventional GCNs are limited b...

(This article belongs to the Special Issue Data-Driven Analysis of Industrial Systems Using AI)
  • Article
  • Open Access
4 Citations
4,340 Views
16 Pages

Out-of-Distribution Node Detection Based on Graph Heat Kernel Diffusion

  • Fangfang Li,
  • Yangshuai Wang,
  • Xinyu Du,
  • Xiaohua Li and
  • Ge Yu

21 September 2024

Over the past few years, there has been a surge in research attention towards tasks involving graph data, largely due to the impressive performance demonstrated by graph neural networks (GNNs) in handling such information. Currently, out-of-distribut...

(This article belongs to the Special Issue Graph Theory and Applications, 2nd Edition)
  • Feature Paper
  • Article
  • Open Access
1 Citations
2,610 Views
21 Pages

2 November 2022

A diffusion-taking value in probability-measures on a graph with vertex set V, ∑i∈Vxiδi is studied. The masses on each vertex satisfy the stochastic differential equation of the form dxi=∑j∈N(i)xixjdBij on the simplex, where {...

(This article belongs to the Special Issue Random Combinatorial Structures)
  • Article
  • Open Access
1 Citations
3,596 Views
27 Pages

Lane Graph Extraction from Aerial Imagery via Lane Segmentation Refinement with Diffusion Models

  • Antonio Ruiz,
  • Andrew Melnik,
  • Nicolo Savioli,
  • Dong Wang and ,
  • Yanfeng Zhang and
  • Helge Ritter
  • + 1 author+ 0 author

15 August 2025

The lane graph is critical for applications such as autonomous driving and lane-level route planning. While previous research has focused on extracting lane-level graphs from aerial imagery using convolutional neural networks (CNNs) followed by post-...

(This article belongs to the Special Issue AI-Driven Mapping Using Remote Sensing Data)
  • Article
  • Open Access
1,105 Views
16 Pages

Early and accurate analysis of breast cancer is critical for improving patient outcomes. Ultrasound imaging is widely used for breast tumor screening due to its safety, accessibility, and low cost. We propose DGTN (Diffused Graph-Transformer Network)...

(This article belongs to the Special Issue AI-Driven Advances in Biomedical Diagnosis and Prognosis: Innovations, Applications, and Emerging Trends)
  • Article
  • Open Access
1 Citations
4,939 Views
18 Pages

Localization with Graph Diffusion Property

  • Pengpeng Chen,
  • Yuqing Yin,
  • Shouwan Gao,
  • Qiang Niu and
  • Jun Gu

15 July 2017

Node localization is an essential issue in wireless sensor networks (WSNs). Many range-free localization methods have been proposed to satisfy the requirement of low-system cost. However, some range-free methods only depend on network connectivity, a...

(This article belongs to the Special Issue Mobile Sensing Applications)
  • Article
  • Open Access
13 Citations
4,025 Views
15 Pages

The COVID-19 Infection Diffusion in the US and Japan: A Graph-Theoretical Approach

  • Mohammad Reza Davahli,
  • Waldemar Karwowski,
  • Krzysztof Fiok,
  • Atsuo Murata and ,
  • Nabin Sapkota,
  • Farzad V. Farahani,
  • Awad Al-Juaid,
  • Tadeusz Marek and
  • Redha Taiar
  • + 4 authors+ 0 author

13 January 2022

Coronavirus disease 2019 (COVID-19) was first discovered in China; within several months, it spread worldwide and became a pandemic. Although the virus has spread throughout the globe, its effects have differed. The pandemic diffusion network dynamic...

(This article belongs to the Special Issue Human Bodywork: Applications in Health, Disease, and Rehabilitation)
  • Article
  • Open Access
313 Views
26 Pages

Graph-Constrained Diffusion with Progressive Distillation for Traveling Salesman Problem

  • Chulei Zhang,
  • Yunshuo Li,
  • Fushuo Li,
  • Xuan Wu and ,
  • Yuanshu Li,
  • Yubin Xiao and
  • You Zhou
  • + 2 authors+ 0 author

Diffusion models have shown strong promise for neural combinatorial optimization, yet existing approaches define the forward noising process over a fully connected graph, discarding the sparse topological structure inherent to the Traveling Salesman...

(This article belongs to the Section Artificial Intelligence and Multi-Agent Systems)
  • Article
  • Open Access
4 Citations
2,252 Views
18 Pages

2 December 2023

Inlight of the extensive utilization of automated machining centers, the operation and maintenance level and efficiency of machining centers require further enhancement. In our work, an anomaly detection model is proposed to detect the operation exec...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
458 Views
21 Pages

Global-Local Complementary Fusion: Unsupervised Graph Anomaly Detection via Diffusion Reconstruction and Contrastive Learning

  • Ruibin Hu,
  • Qian Chen,
  • Huiying Xu,
  • Ruidong Wang and ,
  • Huazhen Jin,
  • Xiao Huang and
  • Xinzhong Zhu
  • + 2 authors+ 0 author

3 June 2026

Anomaly detection on attributed graphs is essential for scientific integrity, cybersecurity, and financial oversight, where abnormal patterns often manifest as breaks in structure or attributes. However, existing unsupervised methods are difficult to...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
6 Citations
2,774 Views
22 Pages

Spatiotemporal Anomaly Detection in Distributed Acoustic Sensing Using a GraphDiffusion Model

  • Seunghun Jeong,
  • Huioon Kim,
  • Young Ho Kim,
  • Chang-Soo Park and ,
  • Hyoyoung Jung and
  • Hong Kook Kim
  • + 1 author+ 0 author

19 August 2025

Distributed acoustic sensing (DAS), which can provide dense spatial and temporal measurements using optical fibers, is quickly becoming critical for large-scale infrastructure monitoring. However, anomaly detection in DAS data is still challenging ow...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
24 Citations
5,314 Views
22 Pages

Accurate traffic flow forecasting is a crucial component of intelligent transportation systems, playing a pivotal role in enhancing transportation intelligence. The integration of Graph Neural Networks (GNNs) and Transformers in traffic flow forecast...

  • Article
  • Open Access
3 Citations
1,506 Views
21 Pages

Enhancing MOOC Recommendation Through Preference-Aware Knowledge Graph Diffusion and Temporal Sequence Modeling

  • Chao Duan,
  • Wenlong Zhang,
  • Qiaoling Cui,
  • Yu Pei and ,
  • Bin He and
  • Qionghao Huang
  • + 1 author+ 0 author

3 December 2025

Course recommendation is a critical service in Intelligent Tutoring Systems (ITS) that helps learners discover relevant courses from massive online educational platforms. Despite substantial progress in this field, two key challenges remain unresolve...

(This article belongs to the Special Issue Graph Neural Networks and Transformers for Intelligent Data-Driven Systems)
  • Article
  • Open Access
197 Views
29 Pages

A Multi-Graph Diffusion Mamba Framework for Ultra-Short-Term Wind Power Forecasting

  • Ruizhe Hu,
  • Xiaoli Zhou,
  • Yunlong Xiang,
  • Subin Gao and ,
  • Yong Qian and
  • Gehao Sheng
  • + 1 author+ 0 author

11 November 2026

Accurate ultra-short-term wind power forecasting is critical to grid security and economic dispatch. However, existing methodologies are constrained by two fundamental gaps: rigid topologies that fail to balance physical and data-driven information,...

(This article belongs to the Topic Advanced Forecasting Methods for Sustainable Power Systems)
  • Article
  • Open Access
7 Citations
2,689 Views
17 Pages

9 March 2023

The clustering ensemble method has attracted much attention because it can improve the stability and robustness of single clustering methods. Among them, similarity-matrix-based methods or graph-based methods have had a wide range of applications in...

(This article belongs to the Special Issue Trustworthy Graph Neural Networks: Models and Applications)
  • Article
  • Open Access
1,537 Views
29 Pages

RNAFoldDiff-Based Sequence-Aware Graph Diffusion for Accurate RNA 3D Structure Prediction

  • Abdullah Al-Refai,
  • Mohammad F. Al-Hammouri,
  • Bandi Vamsi and
  • Ali Al Bataineh

11 May 2026

The prediction accuracy of RNA’s tertiary structure remains a core challenge in the field of computational biology. Existing models frequently encounter significant challenges due to the complexities of diverse topologies and the intricate natu...

  • Article
  • Open Access
6 Citations
2,683 Views
15 Pages

30 March 2024

The complex environmental impact makes it difficult to predict wind speed with high precision for multiple wind turbines. Most existing research methods model the temporal dependence of wind speeds, ignoring the spatial correlation between wind turbi...

(This article belongs to the Topic Solar and Wind Power and Energy Forecasting)
  • Article
  • Open Access
5 Citations
3,276 Views
12 Pages

23 May 2021

A novel unsupervised texture classification technique is proposed in this research work. The proposed method clusters automatically the textures of an image collection in similarity classes whose number is not a priori known. A nonlinear diffusion-ba...

(This article belongs to the Special Issue Graph Algorithms and Graph Theory)
  • Article
  • Open Access
2 Citations
1,365 Views
19 Pages

Enhanced Graph Diffusion Learning with Transformable Patching via Curriculum Contrastive Learning for Session Recommendation

  • Jin Li,
  • Rong Gao,
  • Lingyu Yan,
  • Quanfeng Yao and ,
  • Xianjun Peng and
  • Jiwei Hu
  • + 1 author+ 0 author

The fusion modeling of intra-session item information representation and inter-session item transition pattern for session recommendation has shown performance advantages. However, existing research still suffers from the following challenges: (1) th...

  • Article
  • Open Access
377 Views
23 Pages

4 June 2026

Graph representation learning models inherently capture structural and attribute correlations, which may lead to significant privacy risks under attribute inference attacks. Existing privacy-preserving methods mainly focus on post hoc suppression of...

  • Article
  • Open Access
17 Citations
4,103 Views
23 Pages

Integration of Diffusion Transformer and Knowledge Graph for Efficient Cucumber Disease Detection in Agriculture

  • Ruiheng Li,
  • Xiaotong Su,
  • Hang Zhang,
  • Xiyan Zhang and ,
  • Yifan Yao,
  • Shutian Zhou,
  • Bohan Zhang,
  • Muyang Ye and
  • Chunli Lv
  • + 4 authors+ 0 author

31 August 2024

In this study, a deep learning method combining knowledge graph and diffusion Transformer has been proposed for cucumber disease detection. By incorporating the diffusion attention mechanism and diffusion loss function, the research aims to enhance t...

(This article belongs to the Special Issue The Future of Artificial Intelligence and Sensor Systems in Agriculture)
  • Article
  • Open Access
1,169 Views
31 Pages

Research on a Method for Generating 3D Topologies of Combat Networks Based on Conditional Graph Diffusion Models

  • Xiaofei Yang,
  • Wenjing Yang,
  • Mei Gao,
  • Bo He and ,
  • Xiaoshuang Wang and
  • Zhiqiang Lin
  • + 1 author+ 0 author

19 January 2026

This paper addresses the pressing need for the intelligent design of three-dimensional topological structures in combat networks within modern joint operations. Conventional graph generation approaches struggle to simultaneously fulfill requirements...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
14 Citations
8,217 Views
25 Pages

Stock price forecasting remains a persistent challenge in time series analysis due to complex inter-stock relationships and dynamic textual signals such as financial news. While Graph Neural Networks (GNNs) can model relational structures, they often...

(This article belongs to the Special Issue Machine Learning Applications in Finance, 2nd Edition)
  • Article
  • Open Access
5 Citations
2,595 Views
41 Pages

TGDHTL: Hyperspectral Image Classification via Transformer–Graph Convolutional Network–Diffusion with Hybrid Domain Adaptation

  • Zarrin Mahdavipour,
  • Nashwan Alromema,
  • Abdolraheem Khader,
  • Ghulam Farooque and ,
  • Ali Ahmed and
  • Mohamed A. Damos
  • + 1 author+ 0 author

6 January 2026

Hyperspectral image (HSI) classification is pivotal for remote sensing applications, including environmental monitoring, precision agriculture, and urban land-use analysis. However, its accuracy is often limited by scarce labeled data, class imbalanc...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
2 Citations
4,727 Views
18 Pages

24 March 2025

With the rapid development of remote sensing technology, the question of how to leverage large amounts of unlabeled remote sensing data to detect changes in multi-temporal images has become a significant challenge. Self-supervised methods (SSL) for r...

  • Article
  • Open Access
127 Views
27 Pages

E-STG-DiffNet: Multimodal Spatio-Temporal Graph Diffusion for Edge–Cloud Anomaly Detection

  • Jiaqian Ji,
  • Jiake Li,
  • Huixiao Zhou,
  • Lifeng Yang and
  • Shaopeng Zhou

5 November 2026

Video anomaly detection is critical for information security in IoT-based intelligent surveillance, where heterogeneous sensors continuously measure the physical environment and anomalies manifest as deviations from learned normal behavior. Existing...

(This article belongs to the Special Issue Symmetry and Asymmetry in Network Measurement, Cryptography, and Information Security)
  • Article
  • Open Access
836 Views
28 Pages

12 August 2026

Recommendation systems have become crucial tools for mitigating information overload and enhancing user experience. Among them, LightGCN has achieved remarkable results in both efficiency and performance by simplifying graph convolution operations. H...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
5 Citations
2,299 Views
15 Pages

Entity Alignment with Global Information Aggregation

  • Liguo Zhang,
  • Zhao Li,
  • Ye Li,
  • Shiwei Wu and
  • Tong Chen

Entity alignment (EA) is a critical task in knowledge graph fusion, aiming to associate equivalent entities across disparate knowledge graphs (KGs). Current methods typically leverage entity representations derived from triples or neighboring entitie...

  • Article
  • Open Access
5 Citations
4,670 Views
45 Pages

In a peer-to-peer complex environment, information is permanently diffused. Such an environment can be modeled as a graph, where there are flows of information. The interest of such modeling is that (1) one can describe the exchanges through time fro...

(This article belongs to the Section Financial Technology and Innovation)
  • Article
  • Open Access
3 Citations
2,417 Views
19 Pages

29 September 2023

Although the existing cardiac diffusion tensor imaging (DTI) denoising methods have achieved promising results, most of them are dependent on the number of diffusion gradient directions, noise distributions, and noise levels. To address these issues,...

(This article belongs to the Special Issue Advances in Medical Image Analysis and Computer-Aided Diagnosis)
  • Article
  • Open Access
5 Citations
1,517 Views
18 Pages

CasDacGCN: A Dynamic Attention-Calibrated Graph Convolutional Network for Information Popularity Prediction

  • Bofeng Zhang,
  • Yanlin Zhu,
  • Zhirong Zhang,
  • Kaili Liao and ,
  • Sen Niu,
  • Bingchun Li and
  • Haiyan Li
  • + 2 authors+ 0 author

14 October 2025

Information popularity prediction is a critical problem in social network analysis. With the increasing prevalence of social platforms, accurate prediction of the diffusion process has become increasingly important. Existing methods mainly rely on gr...

(This article belongs to the Section Multidisciplinary Applications)
  • Article
  • Open Access
639 Views
25 Pages

9 June 2026

In complex socio-technical systems, human–AI collaboration is becoming fundamental to the processes of knowledge creation, content generation, and innovation. The existing innovation models typically consider only a single actor, the sole AI sy...

(This article belongs to the Special Issue Modeling and Data Analysis of Complex Networks)
  • Article
  • Open Access
1 Citations
1,437 Views
21 Pages

Reliable air-quality monitoring is essential for urban exposure assessment and environmental policy, yet many downstream applications are hindered by sparse regulatory stations and noisy real-world measurements. While diffusion models have shown prom...

(This article belongs to the Topic Advances in Sensor Data Fusion and AI for Environmental Monitoring)
  • Article
  • Open Access
273 Views
33 Pages

19 October 2026

Image encryption requires effective local transformation together with reliable propagation across image blocks. This study proposes a block-based encryption scheme that transforms a symmetric circulant graph into a key-dependent asymmetric directed...

(This article belongs to the Special Issue Symmetry and Asymmetry Study in Graph Theory II: Graph Intelligence, Distributed Systems, and Embodied AI)
  • Article
  • Open Access
2 Citations
3,540 Views
23 Pages

Diffusion Parameters Analysis in a Content-Based Image Retrieval Task for Mobile Vision

  • Federico Magliani,
  • Laura Sani,
  • Stefano Cagnoni and
  • Andrea Prati

9 August 2020

Most recent computer vision tasks take into account the distribution of image features to obtain more powerful models and better performance. One of the most commonly used techniques to this purpose is the diffusion algorithm, which fuses manifold da...

(This article belongs to the Section Physical Sensors)
  • Article
  • Open Access
4 Citations
2,227 Views
15 Pages

15 November 2023

Social media significantly influences business, politics, and society. Easy access and interaction among users allow information to spread rapidly across social networks. Understanding how information is disseminated through these new publishing meth...

  • Review
  • Open Access
6 Citations
8,058 Views
41 Pages

Advancements, Challenges, and Future Directions in Scene-Graph-Based Image Generation: A Comprehensive Review

  • Chikwendu Ijeoma Amuche,
  • Xiaoling Zhang,
  • Happy Nkanta Monday,
  • Grace Ugochi Nneji and ,
  • Chiagoziem C. Ukwuoma,
  • Okechukwu Chinedum Chikwendu,
  • Yeong Hyeon Gu and
  • Mugahed A. Al-antari
  • + 3 authors+ 0 author

The generation of images from scene graphs is an important area in computer vision, where structured object relationships are used to create detailed visual representations. While recent methods, such as generative adversarial networks (GANs), transf...

  • Article
  • Open Access
543 Views
37 Pages

Graph-Conditioned Stochastic Modeling of Twitter Information Cascades with Dual-Head Transformers for Early Virality Prediction

  • Bowen Dong,
  • Xinyu Zhang,
  • Chaoya Yan,
  • Weiyan Zhu and ,
  • Lingmin Hou and
  • Yifan Feng
  • + 1 author+ 0 author

27 June 2026

Information cascades in online social networks arise from stochastic interactions among user behavior, temporal activation, and graph-structured exposure. Early prediction of cascade outcomes remains difficult because only a short diffusion prefix is...

(This article belongs to the Special Issue Advanced Modeling and Computation in Big Data and Social Networks)
  • Article
  • Open Access
4 Citations
922 Views
26 Pages

14 December 2025

Market power remains a persistent challenge in liberalized electricity spot markets, where generators can manipulate bids to distort prices and extract rents. Traditional monitoring approaches—such as structural indices or simulation-based mode...

(This article belongs to the Topic Advanced Operation, Control, and Planning of Intelligent Energy Systems)
  • Article
  • Open Access
271 Views
18 Pages

8 October 2026

Multimodal hyperspectral point-cloud mineral mapping is complicated by spectral ambiguity and uneven class distributions. Graph encoders integrate complementary observations, but feature aggregation does not necessarily yield spatially consistent cla...

  • Article
  • Open Access
6 Citations
4,293 Views
18 Pages

29 March 2021

Associative knowledge networks are often explored by using the so-called spreading activation model to find their key items and their rankings. The spreading activation model is based on the idea of diffusion- or random walk -like spreading of activa...

  • Article
  • Open Access
4 Citations
3,893 Views
18 Pages

Exploring Spillover Effects for COVID-19 Cascade Prediction

  • Ninghan Chen,
  • Xihui Chen,
  • Zhiqiang Zhong and
  • Jun Pang

31 January 2022

An information outbreak occurs on social media along with the COVID-19 pandemic and leads to an infodemic. Predicting the popularity of online content, known as cascade prediction, allows for not only catching in advance information that deserves att...

(This article belongs to the Special Issue Analysis and Applications of Complex Social Networks)
  • Review
  • Open Access
150 Views
34 Pages

5 November 2026

Image retrieval re-ranking improves an initial retrieval result by incorporating local image features, neighborhood relationships, or learned similarity functions. This selective narrative review examines re-ranking methods for instance and landmark...

(This article belongs to the Special Issue Application of Machine Learning and Mathematical Methods in Image Analysis and Computer Vision)
  • Article
  • Open Access
303 Views
27 Pages

23 September 2026

A black-box optimizer must decide how to spend a fixed evaluation budget as the search population changes: whether to refine promising solutions, explore new directions, or recover from stagnation. Stress–Diffusion Proteostasis Optimization (SD...

(This article belongs to the Special Issue Advanced Algorithms and Intelligent Computational Methods)
  • Article
  • Open Access
139 Views
23 Pages

Variable-order fractional partial differential equations describe heterogeneous anomalous diffusion but can be costly to solve repeatedly at scale because of nonlocal memory and irregular geometry. We propose a physics-informed variable-order graph n...

(This article belongs to the Special Issue Fractional-Order Modeling in Data-Driven Intelligent Systems: From Optimization to AI/ML Applications)
  • Article
  • Open Access
77 Citations
8,315 Views
17 Pages

ST-TrafficNet: A Spatial-Temporal Deep Learning Network for Traffic Forecasting

  • Huakang Lu,
  • Dongmin Huang,
  • Youyi Song,
  • Dazhi Jiang and ,
  • Teng Zhou and
  • Jing Qin
  • + 1 author+ 0 author

9 September 2020

This paper presents a spatial-temporal deep learning network, termed ST-TrafficNet, for traffic flow forecasting. Recent deep learning methods highly relate accurate predetermined graph structure for the complex spatial dependencies of traffic flow,...

(This article belongs to the Special Issue Advances in Machine Learning)
  • Article
  • Open Access
14 Citations
4,098 Views
15 Pages

White Matter Brain Network Research in Alzheimer’s Disease Using Persistent Features

  • Liqun Kuang,
  • Yan Gao,
  • Zhongyu Chen,
  • Jiacheng Xing and ,
  • Fengguang Xiong and
  • Xie Han
  • + 1 author+ 0 author

Despite the severe social burden caused by Alzheimer’s disease (AD), no drug than can change the disease progression has been identified yet. The structural brain network research provides an opportunity to understand physiological deterioratio...

(This article belongs to the Section Medicinal Chemistry)

of 8