Graph convolutional networks: a comprehensive review

Zhang, Si; Tong, Hanghang; Xu, Jin; Maciejewski, Ross

doi:10.1186/s40649-019-0069-y

Cited by 1,014 publications

(413 citation statements)

References 83 publications

Supporting

Mentioning

404

Contrasting

Unclassified

Order By: Relevance

“…The spatiotemporal graph contains vertices (individual pixels or regions on sequential video frames) and edges (relationships between vertices). The extension of CNN architecture that implements a convolution on a graph structure is named graph-based convolutional ANN (GCNN) and began emerging in 2019 [22]. Several GCNN architectures were proposed for video prediction: Bhattacharjee and Das [23] suggested an architecture with spatiotemporal graph convolution and the direction attention mechanism; Li et al [24] developed a GCNN architecture with separate temporal and spatial routing; Shi et al [25] proposed a two-stream GCNN architecture for skeleton-based motion on video.…”

Section: Video Prediction Methodologymentioning

confidence: 99%

Transfer Learning: Video Prediction and Spatiotemporal Urban Traffic Forecasting

Pavlyuk

2020

Algorithms

View full text Add to dashboard Cite

Transfer learning is a modern concept that focuses on the application of ideas, models, and algorithms, developed in one applied area, for solving a similar problem in another area. In this paper, we identify links between methodologies in two fields: video prediction and spatiotemporal traffic forecasting. The similarities of the video stream and citywide traffic data structures are discovered and analogues between historical development and modern states of the methodologies are presented and discussed. The idea of transferring video prediction models to the urban traffic forecasting domain is validated using a large real-world traffic data set. The list of transferred techniques includes spatial filtering by predefined kernels in combination with time series models and spectral graph convolutional artificial neural networks. The obtained models’ forecasting performance is compared to the baseline traffic forecasting models: non-spatial time series models and spatially regularized vector autoregression models. We conclude that the application of video prediction models and algorithms for urban traffic forecasting is effective both in terms of observed forecasting accuracy and development, and training efforts. Finally, we discuss problems and obstacles of transferring methodologies and present potential directions for further research.

show abstract

Section: Video Prediction Methodologymentioning

confidence: 99%

Transfer Learning: Video Prediction and Spatiotemporal Urban Traffic Forecasting

Pavlyuk

2020

Algorithms

View full text Add to dashboard Cite

show abstract

“…However, some problems about this have been pointed out. The complex and diverse connectivity patterns for the graph-structured data, such as non-Euclidean nature often are difficult to gain proper features (Zhang S. et al, 2019). A low-dimensional representation by embedding in a low-dimensional Euclidean space for handling such complex structures (Reutlinger and Schneider, 2012;Li B. et al, 2019).…”

Section: Comparison Of the Predictionmentioning

confidence: 99%

“…Whereas, some drawbacks for this GCN have also been shown (Kipf and Welling, 2017;Zhou et al, 2018;Wu Z. et al, 2019). First, if the graph convolution operation was repeated by increase of the number of layers, the representation at all nodes would converge to same values, so that the performance of the GCN was decreased Zhang S. et al, 2019). Second, most spectral-based approaches by transforming the graph into the spectral domain through the eigenvectors of the Laplacian matrix cannot be performed on graphs with different size numbers of vertices and Fourier bases (Bail et al, 2019).…”

Section: Comparison Of the Predictionmentioning

confidence: 99%

DeepSnap-Deep Learning Approach Predicts Progesterone Receptor Antagonist Activity With High Performance

Matsuzaka

Uesawa

2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

The progesterone receptor (PR) is important therapeutic target for many malignancies and endocrine disorders due to its role in controlling ovulation and pregnancy via the reproductive cycle. Therefore, the modulation of PR activity using its agonists and antagonists is receiving increasing interest as novel treatment strategy. However, clinical trials using the PR modulators have not yet been found conclusive evidences. Recently, increasing evidence from several fields shows that the classification of chemical compounds, including agonists and antagonists, can be done with recent improvements in deep learning (DL) using deep neural network. Therefore, we recently proposed a novel DL-based quantitative structure-activity relationship (QSAR) strategy using transfer learning to build prediction models for agonists and antagonists. By employing this novel approach, referred as DeepSnap-DL method, which uses images captured from 3-dimension (3D) chemical structure with multiple angles as input data into the DL classification, we constructed prediction models of the PR antagonists in this study. Here, the DeepSnap-DL method showed a high performance prediction of the PR antagonists by optimization of some parameters and image adjustment from 3Dstructures. Furthermore, comparison of the prediction models from this approach with conventional machine learnings (MLs) indicated the DeepSnap-DL method outperformed these MLs. Therefore, the models predicted by DeepSnap-DL would be powerful tool for not only QSAR field in predicting physiological and agonist/antagonist activities, toxicity, and molecular bindings; but also for identifying biological or pathological phenomena.

show abstract

“…Detecting relationships over biomedical data is one of the main study areas of GCN (Zhang et al, 2019).…”

Section: B Ddi With Graph Convolutional Network (Gcn)mentioning

confidence: 99%

Identifying Side Effects of Some Drugs Used in Covid-19 Treatment

Aygün

Kaya

Alhajj

2020

Preprint

View full text Add to dashboard Cite

To increase the success in Covid 19 treatment, many drug suggestions are presented, and some clinical studies are shared in the literature. There have been some attempts to use some of these drugs in combination. However, using more than one drug together may cause serious side effects on patients. Therefore, detecting drug-drug interactions of the drugs used will be of great importance in the treatment of Covid 19. In this study, the interactions of 8 drugs used for Covid 19 treatment with 645 different drugs and possible side effects estimates have been produced using Graph Convolutional Networks. Organ systems and diseases in which these 8 drugs cause the most negative effects have been identified. In addition, as it is known that some of these 8 drugs are used together in Covid-19 treatment, the side effects caused by using these drugs together are shared. With the experimental results obtained, it is aimed to facilitate the selection of the drugs and increase the success of Covid 19 treatment according to the targeted patient.

show abstract

Graph convolutional networks: a comprehensive review

Cited by 1,014 publications

References 83 publications

Transfer Learning: Video Prediction and Spatiotemporal Urban Traffic Forecasting

Transfer Learning: Video Prediction and Spatiotemporal Urban Traffic Forecasting

DeepSnap-Deep Learning Approach Predicts Progesterone Receptor Antagonist Activity With High Performance

Identifying Side Effects of Some Drugs Used in Covid-19 Treatment

Contact Info

Product

Resources

About