36,651 Hits in 1.9 sec

Simple and Deep Graph Convolutional Networks [article]

Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, Yaliang Li
2020 arXiv   pre-print
In this paper, we study the problem of designing and analyzing deep graph convolutional networks.  ...  Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data.  ...  Acknowledgements This research was supported in part by National Natural Science Foundation of China (No. 61832017, No. 61932001 and No. 61972401  ... 
arXiv:2007.02133v1 fatcat:euxtywpbm5cb7jwwnolew6qtu4

Graph neural networks in TensorFlow-Keras with RaggedTensor representation (kgcnn)

Patrick Reiser, Andre Eberhard, Pascal Friederich
2021 Software Impacts  
Hinton, Imagenet classification with deep convolutional neural networks, Commun.  ...  We developed the Keras Graph Convolutional Neural Network Python package kgcnn based on TensorFlow-Keras which focus on a transparent tensor structure passed between layers and an ease-of-use mindset.  ...  Graph Libraries Since graph neural networks require modified convolution and pooling operators, many Python packages for deep learning have emerged for either TensorFlow [44, 45] or PyTorch [48] to  ... 
doi:10.1016/j.simpa.2021.100095 fatcat:3bktiwnhqzee3dxbnrez2krjca

Exploiting Relational Information in Social Networks using Geometric Deep Learning on Hypergraphs

Devanshu Arya, Marcel Worring
2018 Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval - ICMR '18  
In these communities, some relations are much more complicated than pairwise relations, thus cannot be simply modeled by a graph; (b) there are different types of entities and relations in a social network  ...  Online social networks are constituted by a diverse set of entities including users, images and posts which makes the task of predicting interdependencies between entities challenging.  ...  ACKNOWLEDGMENTS This research has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement 700381.  ... 
doi:10.1145/3206025.3206062 dblp:conf/mir/AryaW18 fatcat:efr5s4otpvc3hdcdgmxv6gu7my

Exploring convolutional auto-encoders for representation learning on networks

Pranav Nerurkar, Madhav Chandane, Sunil Bhirud
2019 Computer Science  
The drawbacks in such existing auto-encoder approaches as shallow architectures and excessive parameters are tackled in the proposed architectures by using fully convolutional layers.  ...  There is no straight-forward application of machine learning to network data, as machine learning tools are designed for i.i.d data, simple Euclidean data, or grids.  ...  In the literature, deep-learning architectures are based on graph convolutional neural (GCN) networks or graph auto-encoder (GAE) networks.  ... 
doi:10.7494/csci.2019.20.3.3167 fatcat:lgwnh6nqbvdpxj22kyqfwapiwa

Hypergraph Convolution and Hypergraph Attention [article]

Song Bai, Feihu Zhang, Philip H.S. Torr
2020 arXiv   pre-print
To efficiently learn deep embeddings on the high-order graph-structured data, we introduce two end-to-end trainable operators to the family of graph neural networks, i.e., hypergraph convolution and hypergraph  ...  Recently, graph neural networks have attracted great attention and achieved prominent performance in various research fields.  ...  Acknowledgment This work was supported by EPSRC grant Seebibyte EP/M013774/1 and EPSRC/MURI grant EP/N019474/1.  ... 
arXiv:1901.08150v2 fatcat:gqanvg6tqrhchlx2dlub5iosgu

Pushing the AI Envelope: Merging Deep Networks to Accelerate Edge Artificial Intelligence in Consumer Electronics Devices and Systems

Shabab Bazrafkan, Peter M. Corcoran
2018 IEEE Consumer Electronics Magazine  
Project ID: 13/SPP/I2868 on Next Generation Imaging for Smartphone and Embedded Platforms.  ...  Acknowledgment This research is funded under the SFI Strategic Partnership Program by Science Foundation Ireland (SFI) and FotoNation Ltd.  ...  a simple combination of the original networks.  ... 
doi:10.1109/mce.2017.2775245 fatcat:q7nwvsz7ijabvegeeerc4rnava

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).  ...  The proposed method utilize the characteristics of the hierarchical structure of the video, and performed multi-level feature extraction on the video frame sequence through the graph network, obtained  ...  We model the video frame sequence, shot, and event hierarchically by a deep convolution graph Network (DCGN).  ... 
doi:10.1007/978-3-030-11018-5_24 fatcat:3llknh5yvjf2jiriaorcs4vgiy

Low Data Drug Discovery with One-shot Learning [article]

Han Altae-Tran, Bharath Ramsundar, Aneesh S. Pappu, Vijay Pande
2016 arXiv   pre-print
Deep neural networks in particular have been demonstrated to provide significant boosts in predictive power when inferring the properties and activities of small-molecule compounds.  ...  We introduce a new architecture, the residual LSTM embedding, that, when combined with graph convolutional neural networks, significantly improves the ability to learn meaningful distance metrics over  ...  B.R. was supported by the Fannie and John Hertz Foundation.  ... 
arXiv:1611.03199v1 fatcat:hzeuiulzlfaoxa75qiiwo7osie

Link Prediction in Facebook using Web Scrapping and Deep Learning Techniques

2021 International Journal of Advanced Trends in Computer Science and Engineering  
Dataset is obtained by scraping the profile of Facebook users and they are used along with the random forest and graph convolution neural network to measure the performance of link prediction in social  ...  Machine learning techniques are used to analyze the link between the nodes of the network and also create a better link prediction model through deep learning.  ...  The graph convolutional network is used to analyze different datasets using deep learning.  ... 
doi:10.30534/ijatcse/2021/271012021 fatcat:5d7h3ps27fdopk254rtnttgoyq

Implementing graph neural networks with TensorFlow-Keras [article]

Patrick Reiser, Andre Eberhard, Pascal Friederich
2021 arXiv   pre-print
We developed the Keras Graph Convolutional Neural Network Python package kgcnn based on TensorFlow-Keras that provides a set of Keras layers for graph networks which focus on a transparent tensor structure  ...  In this technical report, we present an implementation of convolution and pooling layers for TensorFlow-Keras models, which allows a seamless and flexible integration into standard Keras layers to set  ...  . 14, 15 Graph convolutional neural networks (GCN) stack multiple convolutional and pooling layers for deep learning to generate a high-level node representation from which both a local node and global  ... 
arXiv:2103.04318v1 fatcat:qin3mmux2ffn7jctegd2ykxvku

Predicting Impact of COVID-19 on Crude Oil Price Image with Directed Acyclic Graph Deep Convolution Neural Network

David O. Oyewola, Akomolafe Femi Augustine
2021 Journal of Robotics and Control (JRC)  
In this study, we propose image transformation of time series crude oil price by incorporating Directed Acyclic Graph to Convolutional Neural Network (DAG) based on image processing characteristics.  ...  In sequential data, prediction and image classification, deep learning methods have obtained outstanding results.  ...  Structure of Classification Directed Acyclic Graph Convolution Oyewola, Predicting Impact of COVID-19 on Crude Oil Price Image with Directed Acyclic Graph Deep Convolutional Neural Network III.  ... 
doi:10.18196/jrc.2261 fatcat:xesnmo6tcbedjhwfbvn72mxxym

DAGCN: Dual Attention Graph Convolutional Networks [article]

Fengwen Chen, Shirui Pan, Jing Jiang, Huan Huo, Guodong Long
2019 arXiv   pre-print
Graph convolutional networks (GCNs) have recently become one of the most powerful tools for graph analytics tasks in numerous applications, ranging from social networks and natural language processing  ...  The dual attention network is trained in an end-to-end manner for the graph classification task. We compare our model with state-of-the-art graph kernels and other deep learning methods.  ...  2) LP150100671 partnership with Australia Research Alliance for Children and Youth (ARACY) and Global Business College Australia (GBCA).  ... 
arXiv:1904.02278v1 fatcat:oojmlakxonahja75gyqu6ebgdm

Compact Graph Architecture for Speech Emotion Recognition [article]

A. Shirian, T. Guha
2021 arXiv   pre-print
Such graph structure enables us to construct a Graph Convolution Network (GCN)-based architecture that can perform an accurate graph convolution in contrast to the approximate convolution used in standard  ...  We propose a deep graph approach to address the task of speech emotion recognition. A compact, efficient and scalable way to represent data is in the form of graphs.  ...  Such GCN models are simple to implement, and have been successfully used for various node classification tasks in social media networks and citation networks [9] .  ... 
arXiv:2008.02063v4 fatcat:qjfyt7uqbvc3xl5kjmpwuqrpha

Molecular graph convolutions: moving beyond fingerprints

Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, Patrick Riley
2016 Journal of Computer-Aided Molecular Design  
Graph convolutions use a simple encoding of the molecular graph---atoms, bonds, distances, etc.---which allows the model to take greater advantage of information in the graph structure.  ...  We describe molecular "graph convolutions", a machine learning architecture for learning from undirected graphs, specifically small molecules.  ...  S.K. and V.P. also acknowledge support from from NIH 5U19AI109662-02.  ... 
doi:10.1007/s10822-016-9938-8 pmid:27558503 pmcid:PMC5028207 fatcat:lgtpvq6z2baf3jz5gwliqlrqwy

Dynamic Graph Filters Networks: A Gray-box Model for Multistep Traffic Forecasting

Guopeng LI, Victor L. Knoop, Hans van Lint
2020 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)  
DGFN has a simple recurrent cell structure where local area-wide graph convolutional kernels are dynamically computed from varying inputs.  ...  To overcome this difficulty, we proposed a novel multistep speed forecasting model, Dynamic Graph Filters Networks (DGFN).  ...  Many deep learning models use stacked convolutional layers (regular convolution for route-level forecasting or graph convolution for network-level forecasting) [9] - [12] to capture spatial features  ... 
doi:10.1109/itsc45102.2020.9294627 fatcat:w4uht6io4zgqpflwao6hr4k55u
« Previous Showing results 1 — 15 out of 36,651 results