Figure - available via license: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
Content may be subject to copyright.
Summary of related works. L: the number of layers, |E|: the number of non-zeros in adjacency matrix, P: the number of neighbours per node, F: the number of features, b: represents the batch size, I: the iteration number, S: the singular value, R: the number of samples per node, N: the sample length, d: the embedding size, and K: the number of negative samples.
Source publication
Recently network embedding has gained increasing attention due to its advantages in facilitating network computation tasks such as link prediction, node classification and node clustering. The objective of network embedding is to represent network nodes in a low-dimensional vector space while retaining as much information as possible from the origi...
Context in source publication
Similar publications
Text classification is an important task in natural language processing. However, most of the existing models focus on long texts, and their performance in short texts is not satisfied due to the problem of data sparsity. To solve this problem, recent studies have introduced the concepts of words to enrich the representation of short texts. However...
In order to overcome the long time, high cost and low efficiency of traditional experimental methods in predicting the potential association between microorganisms and drugs, a new prediction model named GCNATMDA is proposed in this paper. The model combines two deep learning models, Graph Convolutional Network and Graph Attention Network, and aims...
Personalized exercise question recommendation is a crucial aspect of smart education used to customize educational exercises and questions to individual students' distinct abilities and learning progress. Integrating cognitive diagnosis with deep learning has shown promising results in personalized exercise recommendations. However, the black-box n...
