36,903 Hits in 8.5 sec

Exploiting Edge Features in Graph Neural Networks [article]

Liyu Gong, Qiang Cheng
2019 arXiv   pre-print
Third, for the proposed new framework, edge features are adaptive across network layers. As a result, our proposed new framework and new models can exploit a rich source of graph information.  ...  approches used in current graph neural networks.  ...  Then, based on the proposed new attention mechanism, we propose a new graph neural network architecture that adapts edge features across neural network layers.  ... 
arXiv:1809.02709v2 fatcat:k64r3grrqvaknbmulbfti6e7w4

Customized Graph Neural Networks [article]

Yiqi Wang, Yao Ma, Wei Jin, Chaozhuo Li, Charu Aggarwal, Jiliang Tang
2021 arXiv   pre-print
Recently, Graph Neural Networks (GNNs) have greatly advanced the task of graph classification.  ...  Therefore, in this paper, we aim to develop customized graph neural networks for graph classification.  ...  Recently, graph neural networks (GNNs) have generalized deep neural networks to graph data.  ... 
arXiv:2005.12386v2 fatcat:5rk5nsdodrgzvmq37nx2xe47je

Multi-Hops Functional Connectivity Improves Individual Prediction of Fusiform Face Activation via a Graph Neural Network

Dongya Wu, Xin Li, Jun Feng
2021 Frontiers in Neuroscience  
To test this proposal, we used multi-hops functional connectivity to predict the individual face activation of the right fusiform face area (rFFA) via a multi-layer graph neural network and showed that  ...  Results also indicated that the two-layer graph neural network is the best in characterizing rFFA's face activation and revealed a hierarchical network for the face processing of rFFA.  ...  of the multi-layer graph neural network.  ... 
doi:10.3389/fnins.2020.596109 pmid:33519356 pmcid:PMC7840579 fatcat:3mu65ovgirbihbapxqayo7h3yq

Graph Attention Network based Pruning for Reconstructing 3D Liver Vessel Morphology from Contrasted CT Images [article]

Donghao Zhang, Siqi Liu, Shikha Chaganti, Eli Gibson, Zhoubing Xu, Sasa Grbic, Weidong Cai, Dorin Comaniciu
2020 arXiv   pre-print
In this paper, we propose a framework for liver vessel morphology reconstruction using both a fully convolutional neural network and a graph attention network.  ...  With the injection of contrast material into blood vessels, multi-phase contrasted CT images can enhance the visibility of vessel networks in the human body.  ...  To better model the vessel connectivity, the graph neural network (GNN) has been adapted into the image segmentation model [16] .  ... 
arXiv:2003.07999v1 fatcat:ucw2thsl5vgqhk5zowghc4wvwm

Capsule Graph Neural Network for Multi-Label Image Recognition (Student Abstract)

Xiangping Zheng, Xun Liang, Bo Wu
graph convolutional network module that leverages the popular graph convolutional networks with an adaptive label correlation graph to model label dependencies.  ...  This paper studies the problem of learning complex relationships between multi-labels for image recognition. Its challenges come from the rich and diverse semantic information in images.  ...  Methodology In this work, we present a capsule graph neural network for multi-label image recognition named CGML to address the above challenges.  ... 
doi:10.1609/aaai.v36i11.21695 fatcat:3czdtxmdgjev7pxhj27yx2pbda

Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks [article]

Yuanku Xu, Dong Huang, Chang-Dong Wang, Jian-Huang Lai
2022 arXiv   pre-print
convolutional neural network (CNN) and graph convolutional network (GCN) as well as the gap between contrastive learning and multi-scale neighborhood structure learning for the image clustering task.  ...  In view of this, this paper presents a new deep clustering approach termed Image clustering with contrastive learning and multi-scale Graph Convolutional Networks (IcicleGCN), which bridges the gap between  ...  Graph Convolutional Network The concept of graph neural network (GNN) was first proposed by Gori et al. [24] and further elaborated in GNN* [25] .  ... 
arXiv:2207.07173v1 fatcat:jrr3mxg525ekvnluq32dl2uo3q

Spatiotemporal Graph Convolutional Network for Multi-Scale Traffic Forecasting

Yi Wang, Changfeng Jing
2022 ISPRS International Journal of Geo-Information  
To address this multi-scale problem, we adopted the idea of Res2Net and designed a hierarchical temporal attention layer and hierarchical adaptive graph convolution layer.  ...  The spatiotemporal graph neural network has attracted attention from academic and business domains for its powerful spatiotemporal pattern capturing capability.  ...  As for the hierarchical attention layer and the hierarchical adaptive graph convolution layer, they implement the capture of multi-scale temporal and multi-scale spatial information on a layer-by-layer  ... 
doi:10.3390/ijgi11020102 fatcat:vfbjdc7t3bfyre3cbu5df3m4mm

Adaptive backstepping synchronization for networked Lagrangian systems

Yassine Bouteraa, Jawhar Ghommam, Gerard Poisson
2012 International Journal of Computer Applications  
Compared with all the cited references that deal with the standard adaptive 2 j=1 synchronization [28], [3] the proposed control law uses the adaptive neural network that essentially avoids the computation  ...  Then, in order to deal with the presence of parametric modeling uncertainties, the control law has been extended to adaptive controller based on neural network algorithm .  ...  Neural Network background Consider the multilayer neural network architecture presented in F ig.3.  ... 
doi:10.5120/5741-7608 fatcat:zc5d6gkdtvbyjpalk3snekoizy

Enhancement of Shadow Region in an Image using Artificial Neural Network

Proposed system uses multi layer feed forward artificial neural network. Error Back Propagation algorithm is used in training process. Desired data is obtained using log transformation method.  ...  Networks, Adaptive Interpolation Method, Contrast Stretching, Range Compression, Alpha Rooting and Spatially Adaptive Iterative Filtering and Multi-Frame Super Resolution [1] .  ...  We have selected back propagation neural network training algorithm to implement a multi layered neural network. Fig. 2.Error back-propagation training algorithm [2] B.  ... 
doi:10.35940/ijitee.c7942.019320 fatcat:ei2xa67wwbgphcuyr43hlzpcba

Contrastive Meta Learning with Behavior Multiplicity for Recommendation [article]

Wei Wei and Chao Huang and Lianghao Xia and Yong Xu and Jiashu Zhao and Dawei Yin
2022 arXiv   pre-print
In addition, to capture the diverse multi-behavior patterns, we design a contrastive meta network to encode the customized behavior heterogeneity for different users.  ...  In particular, we propose a multi-behavior contrastive learning framework to distill transferable knowledge across different types of behaviors via the constructed contrastive loss.  ...  In particular: i) In the first stage, we integrate the behavior-aware graph neural network (with cloned state) and contrastive meta network, to learn initial parameter space of our multi-behavior contrastive  ... 
arXiv:2202.08523v1 fatcat:mvx3u5hxkvh2hekxisptmupyp4

ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network [article]

Xingcheng Fu, Jianxin Li, Jia Wu, Qingyun Sun, Cheng Ji, Senzhang Wang, Jiajun Tan, Hao Peng, Philip S. Yu
2021 arXiv   pre-print
Graph Neural Networks (GNNs) have been widely studied in various graph data mining tasks.  ...  Hyperbolic Graph Neural Networks(HGNNs) extend GNNs to hyperbolic space and thus are more effective to capture the hierarchical structures of graphs in node representation learning.  ...  For neural network methods, we consider Multi-Layer Perceptron (MLP) in Euclidean space and HNN [16] in hyperbolic space.  ... 
arXiv:2110.07888v1 fatcat:2tqj2vqd2rgjbizrukiidzxbou

Instance-Adaptive Graph for EEG Emotion Recognition

Tengfei Song, Suyuan Liu, Wenming Zheng, Yuan Zong, Zhen Cui
To give a more precise graphic representation, we design the multi-level and multi-graph convolutional operation and the graph coarsening.  ...  To tackle the individual differences and characterize the dynamic relationships among different EEG regions for EEG emotion recognition, in this paper, we propose a novel instance-adaptive graph method  ...  EEG signals are processed by multi-level and multi-graph convolution, graph coarsening, region dependency modeling, full connection layer (FC) and softmax layer.  ... 
doi:10.1609/aaai.v34i03.5656 fatcat:xgvqsaroh5fmzjn46ma3asmwda

Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks [article]

Hao Peng, Ruitong Zhang, Yingtong Dou, Renyu Yang, Jingyi Zhang, Philip S. Yu
2021 arXiv   pre-print
In this paper, we propose RioGNN, a novel Reinforced, recursive and flexible neighborhood selection guided multi-relational Graph Neural Network architecture, to navigate complexity of neural network structures  ...  Graph Neural Networks (GNNs) have been widely used for the representation learning of various structured graph data.  ...  graph neural network model used to learn the adaptive receptive domain of neural networks defined on permutation invariant graph data.  ... 
arXiv:2104.07886v2 fatcat:5loufv5m6bcp5ny2rzd7aqnuju

Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval [article]

Yang Liu, Keze Wang, Haoyuan Lan, Liang Lin
2021 arXiv   pre-print
To model multi-scale temporal dependencies, our TCGL integrates the prior knowledge about the frame and snippet orders into graph structures, i.e., the intra-/inter- snippet temporal contrastive graphs  ...  In contrast to the existing methods that ignore modeling elaborate temporal dependencies, our TCGL roots in a hybrid graph contrastive learning strategy to jointly regard the inter-snippet and intra-snippet  ...  multi-layer perception.  ... 
arXiv:2101.00820v8 fatcat:377k53ms55gcfgxzl533xqt5vi

A Survey of Multi-Focus Image Fusion Methods

Youyong Zhou, Lingjie Yu, Chao Zhi, Chuwen Huang, Shuai Wang, Mengqiu Zhu, Zhenxia Ke, Zhongyuan Gao, Yuming Zhang, Sida Fu
2022 Applied Sciences  
At the end of this paper, some main limitations in current research are discussed, and the future development of multi-focus image fusion is prospected.  ...  As an important branch in the field of image fusion, the multi-focus image fusion technique can effectively solve the problem of optical lens depth of field, making two or more partially focused images  ...  This method proved that the decision graph obtained by a multi-scale convolutional neural network is reliable and can produce high-quality fusion images. Ma et al.  ... 
doi:10.3390/app12126281 fatcat:mzzmnt63ofcovg7w2ya6rdfoye
« Previous Showing results 1 — 15 out of 36,903 results