Chaturvedi, Iti, Cavallari, Sandro, Cambria, Erik, and Zheng, Vincent (2017) Learning word vectors in Deep Walk using convolution. In: Proceedings of the 30th International Florida Artificial Intelligence Research Society Conference. pp. 323-328. From: FLAIRS-30: 30th International Florida Artificial Intelligence Research Society Conference, 22-24 May 2017, Marco Island, FL, USA.

PDF (Published Version) - Published Version Restricted to Repository staff only

 

4

1

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.

Actions (Repository Staff Only)

Item Control Page