Graph convolutional networks: a comprehensive review
Reads0
Chats0
TLDR
A comprehensive review specifically on the emerging field of graph convolutional networks, which is one of the most prominent graph deep learning models, is conducted and several open challenges are presented and potential directions for future research are discussed.Abstract:
Graphs naturally appear in numerous application domains, ranging from social analysis, bioinformatics to computer vision. The unique capability of graphs enables capturing the structural relations among data, and thus allows to harvest more insights compared to analyzing data in isolation. However, it is often very challenging to solve the learning problems on graphs, because (1) many types of data are not originally structured as graphs, such as images and text data, and (2) for graph-structured data, the underlying connectivity patterns are often complex and diverse. On the other hand, the representation learning has achieved great successes in many areas. Thereby, a potential solution is to learn the representation of graphs in a low-dimensional Euclidean space, such that the graph properties can be preserved. Although tremendous efforts have been made to address the graph representation learning problem, many of them still suffer from their shallow learning mechanisms. Deep learning models on graphs (e.g., graph neural networks) have recently emerged in machine learning and other related areas, and demonstrated the superior performance in various problems. In this survey, despite numerous types of graph neural networks, we conduct a comprehensive review specifically on the emerging field of graph convolutional networks, which is one of the most prominent graph deep learning models. First, we group the existing graph convolutional network models into two categories based on the types of convolutions and highlight some graph convolutional network models in details. Then, we categorize different graph convolutional networks according to the areas of their applications. Finally, we present several open challenges in this area and discuss potential directions for future research.read more
Citations
More filters
Journal ArticleDOI
A review on multimodal zero‐shot learning
TL;DR: Multimodal zero-shot learning (MZSL) as mentioned in this paper is a general solution for incorporating prior knowledge into data-driven models and achieving accurate class identification, which can fully exploit the advantages of both technologies and is expected to produce models with greater generalization ability.
Journal ArticleDOI
A Physics-Guided Neural Network for Predicting Protein–Ligand Binding Free Energy: From Host–Guest Systems to the PDBbind Database
TL;DR: This research explores the application of Theory-Guided Data Science in studying protein–ligand binding with a hybrid model introduced by integrating Graph Convolutional Network with the GBNSR6 implicit solvent (physics-based model) and results demonstrate that the proposed Physics- Guided Neural Network can successfully improve the “accuracy” of the pure data-driven model.
Journal ArticleDOI
Evaluation of Molecular Fingerprints for Determining Dye Aggregation on Semiconductor Surfaces.
TL;DR: It is shown that molecular fingerprint‐based methods provide a fast and efficient way to discriminate between H‐ and J‐aggregating dyes and achieves classification accuracies that are comparable with models based on a combination of fragment counts and topological indices.
Proceedings ArticleDOI
Dual-branch Density Ratio Estimation for Signed Network Embedding
TL;DR: Extensive empirical results demonstrate that DDRE not only significantly outperforms the methods based on density ratio estimation but also achieves competitive performance compared with other types of methods such as graph likelihood, generative adversarial networks, and graph convolutional networks.
Journal ArticleDOI
Deep learning in cortical surface-based neuroimage analysis: a systematic review
TL;DR: Deep learning approaches, especially convolutional neural networks, have become the method of choice in the field of medical image analysis over the last few years as mentioned in this paper , which is attributed to their excellent abilities of learning features in a more effective and efficient manner, not only for 2D/3D images in the Euclidean space, but also for meshes and graphs in non-Euclidean spaces, such as the cortical surfaces in neuroimaging analysis field.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.