Learning word vectors in Deep Walk using convolution

Conference Publication ResearchOnline@JCU
Chaturvedi, Iti;Cavallari, Sandro;Cambria, Erik;Zheng, Vincent
Abstract

Textual queries in networks such as Twitter can have more than one label, resulting in a multi-label classification problem. To reduce computational costs, a low-dimensional representation of a large network is learned that preserves proximity among nodes in the same community. Similar to sequences of words in a sentence, DeepWalk considers sequences of nodes in a shallow graph and clustering is done using hierarchical softmax in an unsupervised manner. In this paper, we generate network abstractions at different levels using deep convolutional neural networks. Since class labels of connected nodes in a network keep changing, we consider a fuzzy recurrent feedback controller to ensure robustness to noise.

Journal

N/A

Publication Name

FLAIRS 2017 - Proceedings of the 30th International Florida Artificial Intelligence Research Society Conference

Volume

N/A

ISBN/ISSN

978-1-57735-787-2

Edition

N/A

Issue

N/A

Pages Count

6

Location

Marco Island, FL, USA

Publisher

AAAI

Publisher Url

N/A

Publisher Location

Marco Island, FL, USA

Publish Date

N/A

Url

N/A

Date

N/A

EISSN

N/A

DOI

N/A