English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automatic feature learning algorithms are at the forefront of modern daymachine learning research. We present a novel algorithm, supervised Q-walk,which applies Q-learning to generate random walks on graphs such that the walksprove to be useful for learning node features suitable for tackling with thenode classification problem. We present another novel algorithm, k-hopsneighborhood based confidence values learner, which learns confidence values oflabels for unlabelled nodes in the network without first learning the nodeembedding. These confidence values aid in learning an apt reward function forQ-learning.  We demonstrate the efficacy of supervised Q-walk approach over existingstate-of-the-art random walk based node embedding learners in solving thesingle / multi-label multi-class node classification problem using several realworld datasets.  Summarising, our approach represents a novel state-of-the-art technique tolearn features, for nodes in networks, tailor-made for dealing with the nodeclassification problem.

Supervised Q-walk for Learning Vector Representation of Nodes in Networks