Similarity-Based Classification in Partially Labeled Networks

TL;DR

This paper introduces a similarity-based classification method for partially labeled networks, demonstrating high accuracy with sparse labels and analyzing the effectiveness of local versus global similarity indices.

Contribution

It presents ten new similarity indices and evaluates their performance, highlighting their effectiveness in different labeling scenarios.

Findings

Global indices outperform local ones in sparse data conditions.

Similarity-based method achieves high accuracy with few labeled nodes.

Method helps mitigate the unconsistency problem in classification.

Abstract

We propose a similarity-based method, using the similarity between nodes, to address the problem of classification in partially labeled networks. The basic assumption is that two nodes are more likely to be categorized into the same class if they are more similar. In this paper, we introduce ten similarity indices, including five local ones and five global ones. Empirical results on the co-purchase network of political books show that the similarity-based method can give high accurate classification even when the labeled nodes are sparse which is one of the difficulties in classification. Furthermore, we find that when the target network has many labeled nodes, the local indices can perform as good as those global indices do, while when the data is sparce the global indices perform better. Besides, the similarity-based method can to some extent overcome the unconsistency problem which is another difficulty in classification.