Filters








38,491 Hits in 3.0 sec

Understanding Pooling in Graph Neural Networks [article]

Daniele Grattarola, Daniele Zambon, Filippo Maria Bianchi, Cesare Alippi
2021 arXiv   pre-print
Inspired by the conventional pooling layers in convolutional neural networks, many recent works in the field of graph machine learning have introduced pooling operators to reduce the size of graphs.  ...  In this paper we propose a formal characterization of graph pooling based on three main operations, called selection, reduction, and connection, with the goal of unifying the literature under a common  ...  The UPSCALE layer lifts the reduced node features X of the coarsened graph G back to the original data dimensionality of X in .  ... 
arXiv:2110.05292v1 fatcat:dgbtrxwndzh4pcvbyrpaamqmhu

Graph Convolutional Networks with EigenPooling [article]

Yao Ma, Suhang Wang, Charu C. Aggarwal, Jiliang Tang
2019 arXiv   pre-print
Graph neural networks, which generalize deep neural network models to graph structured data, have attracted increasing attention in recent years.  ...  There are some recent works on hierarchically learning graph representation analogous to the pooling step in conventional convolutional neural (CNN) networks.  ...  Comprehensive surveys on graph neural networks can be found in [2, 46, 50, 51] .  ... 
arXiv:1904.13107v2 fatcat:rq2wdahorjb43ivivxh46ggs2i

GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions [article]

Hanchen Wang, Defu Lian, Ying Zhang, Lu Qin, Xuemin Lin
2020 arXiv   pre-print
In this paper, we propose a Graph of Graphs Neural Network, namely GoGNN, which extracts the features in both structured entity graphs and the entity interaction graph in a hierarchical way.  ...  We also propose the dual-attention mechanism that enables the model to preserve the neighbor importance in both levels of graphs.  ...  Graph of Graphs Neural Network In this section, we introduce our Graph of Graphs Neural Network model. Framework of GoGNN The framework of GoGNN is illustrated in Figure 2 .  ... 
arXiv:2005.05537v1 fatcat:ipqoahg5wzcohbj3k7dedsygbm

GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions

Hanchen Wang, Defu Lian, Ying Zhang, Lu Qin, Xuemin Lin
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
In this paper, we propose a Graph of Graphs Neural Network, namely GoGNN, which extracts the features in both structured entity graphs and the entity interaction graph in a hierarchical way.  ...  We also propose the dual-attention mechanism that enables the model to preserve the neighbor importance in both levels of graphs.  ...  Graph of Graphs Neural Network In this section, we introduce our Graph of Graphs Neural Network model. Framework of GoGNN The framework of GoGNN is illustrated in Figure 2 .  ... 
doi:10.24963/ijcai.2020/183 dblp:conf/ijcai/WangL0Q020 fatcat:gj6tkazrfbceflyuyxtbmn4kxq

Fine-Grained Emotion Classification of Chinese Microblogs Based on Graph Convolution Networks [article]

Yuni Lai, Linfeng Zhang, Donghong Han, Rui Zhou, Guoren Wang
2019 arXiv   pre-print
In this paper, we propose a syntax-based graph convolution network (GCN) model to enhance the understanding of diverse grammatical structures of Chinese microblogs.  ...  In addition, a pooling method based on percentile is proposed to improve the accuracy of the model.  ...  In this paper, we focus on this issue and adopt Bi-LSTM model and graph convolution neural network to enhance emotion understanding of microblogs.  ... 
arXiv:1912.02545v1 fatcat:r5pihl2zsrf3fe4pblg53njy2i

Graph Based Convolutional Neural Network [article]

Michael Edwards, Xianghua Xie
2016 arXiv   pre-print
Algebraic Multigrid is presented as a graph pooling method, reducing the resolution of the graph through agglomeration of nodes between layers of the network.  ...  The benefit of localized features within the regular domain has given rise to the use of Convolutional Neural Networks (CNNs) in machine learning, with great proficiency in the image classification.  ...  Introduction In recent years, the machine learning and pattern recognition community has seen a resurgence in the use of neural network and deep learning architecture for the understanding of classification  ... 
arXiv:1609.08965v1 fatcat:o5tug7yifvduthfeuasjiejdpm

Efficient Colon Cancer Grading with Graph Neural Networks [article]

Franziska Lippoldt
2020 arXiv   pre-print
The graph neural network itself consists of three convolutional blocks and linear layers, which is a rather simple design compared to other networks for this application.  ...  Further, the graph size in terms of nodes becomes stable with respect to the model's prediction and accuracy for sufficiently large models.  ...  (2019) : A i,j = 1 − p if i = j p i,i =j A i,j if i = j (1) GNN pooling operations The graph neural network leverages differential graph pooling Diffpool as originally described in Ying et al.  ... 
arXiv:2010.01091v1 fatcat:hq72sxdh7ravpmzby7777cqvbq

Hierarchical Video Frame Sequence Representation with Deep Convolutional Graph Network [chapter]

Feng Mao, Xiang Wu, Hui Xue, Rong Zhang
2019 Lecture Notes in Computer Science  
In this paper, we proposes a novel video classification method based on a deep convolutional graph neural network(DCGN).  ...  These data could be frame feature sequences extracted by a pre-trained convolutional-neural-network, which promote the efficiency for creating models.  ...  One layer in DCGN is composed of graph pooling, nodes convolution and nodes feature propagation.  ... 
doi:10.1007/978-3-030-11018-5_24 fatcat:3llknh5yvjf2jiriaorcs4vgiy

BrainGB: A Benchmark for Brain Network Analysis with Graph Neural Networks [article]

Hejie Cui and Wei Dai and Yanqiao Zhu and Xuan Kan and Antonio Aodong Chen Gu and Joshua Lukemire, Liang Zhan, Lifang He, Ying Guo, Carl Yang
2022 arXiv   pre-print
Recently, Graph Neural Networks (GNNs) motivated from geometric deep learning have attracted broad interest due to their established power for modeling complex networked data.  ...  Despite their established performance in other fields, there has not yet been a systematic study of how to design effective GNNs for brain network analysis.  ...  Graph Neural Networks Graph Neural Networks (GNNs) have revolutionized the field of graph modeling and analysis for real-world networked data such as social networks [8] , knowledge graphs [29] , protein  ... 
arXiv:2204.07054v1 fatcat:wuynk4z6wza4rg7n3yoa5gwzua

Compendious Comparison of Capsule Network and Convolutional Neural Network through end-to-end Digit Classification Application

2021 International Journal of Intelligent Communication Computing and Networks  
Convolutional Neural Networks have proven to be the state of the art approach for doing image processing in the field of Deep Learning.  ...  CNN has proven to be particularly successful in classification of objects. CNNs have certain fundamental drawbacks that have been addressed in Capsule Networks.  ...  Max Pooling Layer : important features in an image and reduction in feature size is done using Pooling Layers. Max Pooling and Average Pooling [6] are commonly considered forms of Pooling.  ... 
doi:10.51735/ijiccn/001/27 fatcat:3m3j6nimyre55da2slssainfbu

Hierarchical Graph Pooling with Structure Learning [article]

Zhen Zhang, Jiajun Bu, Martin Ester, Jianfeng Zhang, Chengwei Yao, Zhi Yu, Can Wang
2019 arXiv   pre-print
Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks  ...  In this paper, we propose a novel graph pooling operator, called Hierarchical Graph Pooling with Structure Learning (HGP-SL), which can be integrated into various graph neural network architectures.  ...  Introduction Deep neural networks with convolution and pooling layers have achieved great success in various challenging tasks, ranging from computer vision (He et al. 2016) , natural language understanding  ... 
arXiv:1911.05954v3 fatcat:mpqv3673izbllpv7esuivzuuey

HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation [article]

Bardia Doosti, Shujon Naha, Majid Mirbagheri, David Crandall
2020 arXiv   pre-print
Our network uses a cascade of two adaptive graph convolutional neural networks, one to estimate 2D coordinates of the hand joints and object corners, followed by another to convert 2D coordinates to 3D  ...  In this paper, we propose a lightweight model called HOPE-Net which jointly estimates hand and object pose in 2D and 3D in real-time.  ...  Acknowledgment The work in this paper was supported in part by the National Science Foundation (CAREER IIS-1253549), and by the IU Office of the Vice Provost for Research, the College of Arts and Sciences  ... 
arXiv:2004.00060v1 fatcat:63qxmkoyrbcrpdn72c4hfwxtmu

Understanding Attention and Generalization in Graph Neural Networks [article]

Boris Knyazev, Graham W. Taylor, Mohamed R. Amer
2019 arXiv   pre-print
We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness.  ...  Motivated by insights from the work on Graph Isomorphism Networks, we design simple graph reasoning tasks that allow us to study attention in a controlled environment.  ...  In graph neural networks (GNNs), attention can be defined over edges [4, 5] or over nodes [6] .  ... 
arXiv:1905.02850v3 fatcat:rs6cru2yhrehzapyjqhj74vn7a

Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data [article]

Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo, Byoung-Tak Zhang
2020 arXiv   pre-print
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency.  ...  The CB-GLNs find compositional dependencies of the data in multilevel graph forms via a parameterized kernel with graph-cut and a message passing framework.  ...  This has led to various graph-based neural networks being proposed over the years.  ... 
arXiv:2001.07613v1 fatcat:ytasc3bvube3zok66pfdhaaw44

Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data

Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo, Byoung-Tak Zhang
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Conventional sequential learning methods such as Recurrent Neural Networks (RNNs) focus on interactions between consecutive inputs, i.e. first-order Markovian dependency.  ...  The CB-GLNs find compositional dependencies of the data in multilevel graph forms via a parameterized kernel with graph-cut and a message passing framework.  ...  This has led to various graph-based neural networks being proposed over the years.  ... 
doi:10.1609/aaai.v34i04.5978 fatcat:fafwr2admzejlp3rjgf2pq5uiq
« Previous Showing results 1 — 15 out of 38,491 results