Description
Title: REPRESENTATION LEARNING ON NETWORKS: EXPLORING CONVOLUTIONAL AUTO-ENCODERS
Abstract: Many significant synthetic or real-world systems have network structures. Machine learning research should focus on expanding learning methods like neural networks to process such non-Euclidean data. However, until recently, this domain had only received a small amount of attention. Since machine learning tools are made for i:i:d data, simple Euclidean data, or grids, there is no straightforward way to apply them to network data. The technical focus of this dissertation is on using graph neural networks for network representation learning (NRL), which entails learning the vector representations of network nodes, in order to address this challenge. Learning complex data’s vector embeddings into low-dimensional geometries is similar to embedding complex data into graphs. The disadvantages of graph-structured data are eliminated following the embedding procedure. Two deep learning auto-encoder-based methods for creating node embeddings are suggested by the current research. The proposed architectures use fully convolutional layers to address the shortcomings of existing auto-encoder methods, such as shallow architectures and excessive parameters. To demonstrate the viability of this strategy, numerous experiments are run on benchmark network datasets that are openly accessible.
Keywords: network representation learning, deep learning, graph convolutional neural networks
Paper Quality: SCOPUS / Web of Science Level Research Paper
Paper type: Analysis Based Research Paper
Subject: Computer Science
Writer Experience: 20+ Years
Plagiarism Report: Turnitin Plagiarism Report will be less than 10%
Restriction: Only one author may purchase a single paper. The paper will then indicate that it is out of stock.
What will I get after the purchase?
A turnitin plagiarism report of less than 10% in a pdf file and a full research paper in a word document.
In case you have any questions related to this research paper, please feel free to call/ WhatsApp on +919726999915
Reviews
There are no reviews yet.