Advanced 3D Face Reconstruction from Single 2D Images Using Enhanced Adversarial Neural Networks and Graph Neural Networks by Mohamed Fathallah, Sherif Eletriby, Maazen Alsabaan, Mohamed I. Ibrahem, Gamal Farok

“…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. …”
Get full text

SiamAHG: adaptive hierarchical graph attention for lightweight siamese tracking by Na Li, Yaofu Fan, Xuhao Chen, Xinyu Liu, Jinglu He

“…It employs the lightweight network ShuffleNet V2 for feature extraction and a novel adaptive hierarchical graph attention for feature fusion. …”
Get full text

EGNAS: Efficient Graph Neural Architecture Search Through Evolutionary Algorithm by Younkyung Jwa, Chang Wook Ahn, Man-Je Kim

“…The primary objective of our research is to enhance the efficiency and effectiveness of Neural Architecture Search (NAS) with regard to Graph Neural Networks (GNNs). GNNs have emerged as powerful tools for learning from unstructured network data, compensating for several known limitations of Convolutional Neural Networks (CNNs). …”
Get full text

Research on the Automatic Multi-Label Classification of Flight Instructor Comments Based on Transformer and Graph Neural Networks by Zejian Liang, Yunxiang Zhao, Mengyuan Wang, Hong Huang, Haiwen Xu

“…To address this challenge, this study presents a novel multi-label classification model that seamlessly integrates RoBERTa, a robust language model, with Graph Convolutional Networks (GCNs). By simultaneously modeling text features and label interdependencies, this model enables the automated, multi-dimensional classification of instructor evaluations. …”
Get full text

Autoencoder-Augmented Graph Neural Networks for Accurate and Scalable Structure Recognition in Analog/Mixed-Signal Schematics by Mohamed Salem, Witesyavwirwa Vianney Kambale, Ali Deeb, Sergii Tkachov, Anjeza Karaj, Joachim Pichler, Manuel Ludwig Lexer, Kyandoghere Kyamakya

“…In this work, a novel framework has been proposed that combines the generative augmentation capabilities of convolutional Autoencoders with the structural analysis power of Graph Convolutional Networks (GCNs). …”
Get full text

A Multi-Task Spatiotemporal Graph Neural Network for Transient Stability and State Prediction in Power Systems by Shuaibo Wang, Xinyuan Xiang, Jie Zhang, Zhuohang Liang, Shufang Li, Peilin Zhong, Jie Zeng, Chenguang Wang

“…To address these challenges, this paper presents a multi-task learning framework based on spatiotemporal graph convolutional networks that efficiently performs both tasks. …”
Get full text

Calibrating calving parameterizations using graph neural network emulators: application to Helheim Glacier, East Greenland by Y. Koo, Y. Koo, Y. Koo, G. Cheng, M. Morlighem, M. Rahnemoonfar, M. Rahnemoonfar

“…In this study, we adopt three standard graph neural network (GNN) architectures, including graph convolutional network, graph attention network, and equivariant graph convolutional network (EGCN), to develop surrogate models for finite-element simulations from the Ice-sheet and Sea-level System Model. …”
Get full text

Infant cry classification using an efficient graph structure and attention-based model by Qiao X., Jiao S., Li H.

“…Additionally, in order to better classify the efficient graph structure, a local-to-global convolutional neural network (AlgNet) based on convolutional neural networks and attention mechanisms is proposed. …”
Get full text

FraudGNN-RL: A Graph Neural Network With Reinforcement Learning for Adaptive Financial Fraud Detection by Yiwen Cui, Xu Han, Jiaying Chen, Xinguang Zhang, Jingyun Yang, Xuguang Zhang

“…This article introduces FraudGNN-RL, an innovative framework that combines Graph Neural Networks (GNNs) with Reinforcement Learning (RL) for adaptive and context-aware financial fraud detection. …”
Get full text

Graph attention networks based multi-agent path finding via temporal-spatial information aggregation. by Qingling Zhang, Peng Wang, Cui Ni, Xianchang Liu

“…Initially, historical observations are fused by incorporating a Gated Recurrent Unit (GRU) with a Convolutional Neural Network (CNN), extracting local observations to form an encoder. …”
Get full text

PEGSGraph: A Graph Neural Network for Fast Earthquake Characterization Based on Prompt ElastoGravity Signals by Céline Hourcade, Kévin Juhel, Quentin Bletery

“…Accurate instantaneous tracking of large earthquake magnitude using PEGS has been proven possible through the use of a Convolutional Neural Network (CNN). However, the CNN architecture is sub‐optimal as it does not allow to capture the geometry of the problem. …”
Get full text

Learning Developmental Age From 3D Infant Kinetics Using Adaptive Graph Neural Networks by Daniel Holmberg, Manu Airaksinen, Viviana Marchi, Andrea Guzzetta, Anna Tuiskula, Leena Haataja, Sampsa Vanhatalo, Teemu Roos

“…These data are modeled using adaptive graph convolutional networks (AAGCNs), able to capture the spatio-temporal dependencies in infant movements. …”
Get full text

L2-GNN: Graph neural networks with fast spectral filters using twice linear parameterization by Siying Huang, Xin Yang, Zhengda Lu, Hongxing Qin, Huaiwen Zhang, Yiqun Wang

“…The parameterization allows for an enlarged receptive field of graph convolutions, which can simultaneously capture low-frequency and high-frequency information. …”
Get full text

Root Cause Analysis of Cast Product Defects with Two-Branch Reasoning Network Based on Continuous Casting Quality Knowledge Graph by Xiaojun Wu, Xinyi Wang, Yue She, Mengmeng Sun, Qi Gao

“…In order to improve the reasoning accuracy of C2Q-KGs, this paper proposes a model based on a two-branch reasoning network. Our model classifies the continuous casting triples according to the number distribution of the head and tail entities in the relation and connects a two-branch reasoning network consisting of one connection layer and one capsule layer behind the convolutional layer. …”
Get full text

Integrating deformable CNN and attention mechanism into multi-scale graph neural network for few-shot image classification by Yongmin Liu, Fengjiao Xiao, Xinying Zheng, Weihao Deng, Haizhi Ma, Xinyao Su, Lei Wu

“…The feature extraction module of graph neural networks has always been designed as a fixed convolutional neural network (CNN), but due to the intrinsic properties of convolution operations, its receiving domain is limited. …”
Get full text

A Lightweight Semantic- and Graph-Guided Network for Advanced Optical Remote Sensing Image Salient Object Detection by Jie Liu, Jinpeng He, Huaixin Chen, Ruoyu Yang, Ying Huang

“…To further efficiently aggregate multi-level features and preserve the integrity and complexity of overall object shape, we introduce a Graph-Based Region Awareness Module (GRAM). This module incorporates non-local operations under graph convolution domain to deeply explore high-order relationships between adjacent layers, while utilizing depth-wise separable convolution blocks to significantly reduce computational cost. …”
Get full text

SDDGRNets: Level–Level Semantically Decomposed Dynamic Graph Reasoning Network for Remote Sensing Semantic Change Detection by Zhuli Xie, Gang Wan, Yunxia Yin, Guangde Sun, Dongdong Bu

“…Therefore, a dynamic graph reasoning network with layer-by-layer semantic decomposition for semantic change detection in remote sensing data is developed in response to these limitations. …”
Get full text

A Multiscale Mixed-Graph Neural Network Based on Kinematic and Dynamic Joint Features for Human Motion Prediction by Rongyong Zhao, Bingyu Wei, Lingchen Han, Yuxin Cai, Yunlong Ma, Cuiling Li

“…The extraction of joint features at each scale is facilitated by a single-scale mixed-graph convolution module. And to effectively integrate the extracted kinematic and dynamic features, a KD-fused Graph-GRU (Kinematic and Dynamics Fused Graph Gate Recurrent Unit) predictor is designed to fuse them. …”
Get full text

SAR Target Depression Angle Invariant Recognition of Few-Shot Learning Via Dense Graph Prototype Network by Xiangyu Zhou, Yuhui Zhang, Qianru Wei

“…Specifically, by leveraging the information propagation mechanism of a densely connected graph convolutional network (GCN), potential features are iteratively learned while retaining previous features, thereby clustering samples of the same class with different elevation angles and eliminating feature deviations. …”
Get full text

Interpretable multi-instance heterogeneous graph network learning modelling CircRNA-drug sensitivity association prediction by Mengting Niu, Chunyu Wang, Yaojia Chen, Quan Zou, Ximei Luo

“…Results We first extracted similar features of circRNAs and drugs and the structural features of drugs to construct a heterogeneous network. To learn the deep embedding features of the heterogeneous network, we designed a heterogeneous graph convolutional network (GCN) architecture. …”
Get full text