Graph Neural Networks in TensorFlow and Keras with Spektral [Application Notes]

Grattarola, Daniele; Alippi, Cesare

doi:10.1109/mci.2020.3039072

Cited by 188 publications

(103 citation statements)

References 42 publications

Supporting

Mentioning

103

Contrasting

Order By: Relevance

“…We used the Python package Spektral 32 to implement our model. There are many types of graph neural networks that can be used as the encoder or decoder.…”

Section: Methodsmentioning

confidence: 99%

A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder

Luo

Zhang

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Dimensionality reduction is crucial for the visualization and interpretation of the high-dimensional single-cell RNA sequencing (scRNA-seq) data. However, preserving topological structure among cells to low dimensional space remains a challenge. Here, we present the single-cell graph autoencoder (scGAE), a dimensionality reduction method that preserves topological structure in scRNA-seq data. scGAE builds a cell graph and uses a multitask-oriented graph autoencoder to preserve topological structure information and feature information in scRNA-seq data simultaneously. We further extended scGAE for scRNA-seq data visualization, clustering, and trajectory inference. Analyses of simulated data showed that scGAE accurately reconstructs developmental trajectory and separates discrete cell clusters under different scenarios, outperforming recently developed deep learning methods. Furthermore, implementation of scGAE on empirical data showed scGAE provided novel insights into cell developmental lineages and preserved inter-cluster distances.

show abstract

“…We used the Python package Spektral 32 to implement our model. There are many types of graph neural networks that can be used as the encoder or decoder.…”

Section: Methodsmentioning

confidence: 99%

A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder

Luo

Zhang

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…It is a high-level application programming interface (API) that runs on top of Tensorflow, Theano, and CNTK and wraps up extensive complex numerical computation. Keras provides a convenient solution to deep learning problems and removes the effort of building a complex network [29]. Keras overcome the process of complex neural networks into a much simplified solution that has been supported tf [29].…”

Section: Kerasmentioning

confidence: 99%

“…Keras provides a convenient solution to deep learning problems and removes the effort of building a complex network [29]. Keras overcome the process of complex neural networks into a much simplified solution that has been supported tf [29]. Keras module is the official frontend of Tensorflow, which is the most popular API among other deep learning libraries [30].…”

Section: Kerasmentioning

confidence: 99%

Hybrid deep learning model using recurrent neural network and gated recurrent unit for heart disease prediction

Krishnan

Magalingam

Ibrahim

2021

IJECE

View full text Add to dashboard Cite

<span>This paper proposes a new hybrid deep learning model for heart disease prediction using recurrent neural network (RNN) with the combination of multiple gated recurrent units (GRU), long short-term memory (LSTM) and Adam optimizer. This proposed model resulted in an outstanding accuracy of 98.6876% which is the highest in the existing model of RNN. The model was developed in Python 3.7 by integrating RNN in multiple GRU that operates in Keras and Tensorflow as the backend for deep learning process, supported by various Python libraries. The recent existing models using RNN have reached an accuracy of 98.23% and deep neural network (DNN) has reached 98.5%. The common drawbacks of the existing models are low accuracy due to the complex build-up of the neural network, high number of neurons with redundancy in the neural network model and imbalance datasets of Cleveland. Experiments were conducted with various customized model, where results showed that the proposed model using RNN and multiple GRU with synthetic minority oversampling technique (SMOTe) has reached the best performance level. This is the highest accuracy result for RNN using Cleveland datasets and much promising for making an early heart disease prediction for the patients.</span>

show abstract

“…This chapter defines the architecture of model that we created, and then we apply this model on images from our dataset. Thus, we work with python language for data science (Jarolímek et al, 2019), the Tensorflow and Keras libraries for learning and classification (Grattarola and Alippi, 2020). To improve the model's performance, we use some simple and effective techniques such as data augmentation and Tensorboard.…”

Section: Implementation Of Cnnmentioning

confidence: 99%

A Strategic Analytics Using Convolutional Neural Networks for Weed Identification in Sugar Beet Fields

Jabir

Falih

Sarih

et al. 2021

AOL

View full text Add to dashboard Cite

Researchers in precision agriculture regularly use deep learning that will help growers and farmers control and monitor crops during the growing season; these tools help to extract meaningful information from large-scale aerial images received from the field using several techniques in order to create a strategic analytics for making a decision. The information result of the operation could be exploited for many reasons, such as sub-plot specific weed control. Our focus in this paper is on weed identification and control in sugar beet fields, particularly the creation and optimization of a Convolutional Neural Networks model and train it according to our data set to predict and identify the most popular weed strains in the region of Beni Mellal, Morocco. All that could help select herbicides that work on the identified weeds, we explore the way of transfer learning approach to design the networks, and the famous library Tensorflow for deep learning models, and Keras which is a high-level API built on Tensorflow.

show abstract

Graph Neural Networks in TensorFlow and Keras with Spektral [Application Notes]

Cited by 188 publications

References 42 publications

A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder

A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder

Hybrid deep learning model using recurrent neural network and gated recurrent unit for heart disease prediction

A Strategic Analytics Using Convolutional Neural Networks for Weed Identification in Sugar Beet Fields

Contact Info

Product

Resources

About