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

TL;DR

This paper introduces supervised Q-walk, a novel Q-learning based algorithm for generating random walks on graphs to learn node features, improving node classification performance on real-world datasets.

Contribution

The paper proposes supervised Q-walk and a confidence value learner, advancing node embedding techniques specifically for node classification tasks.

Findings

Supervised Q-walk outperforms existing random walk methods in node classification.

The confidence value learner improves label estimation for unlabelled nodes.

The approach achieves state-of-the-art results on multiple datasets.

Abstract

Automatic feature learning algorithms are at the forefront of modern day machine learning research. We present a novel algorithm, supervised Q-walk, which applies Q-learning to generate random walks on graphs such that the walks prove to be useful for learning node features suitable for tackling with the node classification problem. We present another novel algorithm, k-hops neighborhood based confidence values learner, which learns confidence values of labels for unlabelled nodes in the network without first learning the node embedding. These confidence values aid in learning an apt reward function for Q-learning. We demonstrate the efficacy of supervised Q-walk approach over existing state-of-the-art random walk based node embedding learners in solving the single / multi-label multi-class node classification problem using several real world datasets. Summarising, our approach represents a novel state-of-the-art technique to learn features, for nodes in networks, tailor-made for dealing with the node classification problem.