Enhanced Network Embeddings via Exploiting Edge Labels

TL;DR

This paper introduces a network embedding method that incorporates edge labels to better capture the semantic relations between nodes, leading to improved performance on node classification tasks.

Contribution

It presents a novel approach that leverages edge labels in network embeddings, enhancing the preservation of semantic relations beyond traditional binary edge representations.

Findings

Outperforms state-of-the-art methods in multi-label node classification

Produces higher quality node embeddings by considering edge semantics

Demonstrates effectiveness on real-world networks

Abstract

Network embedding methods aim at learning low-dimensional latent representation of nodes in a network. While achieving competitive performance on a variety of network inference tasks such as node classification and link prediction, these methods treat the relations between nodes as a binary variable and ignore the rich semantics of edges. In this work, we attempt to learn network embeddings which simultaneously preserve network structure and relations between nodes. Experiments on several real-world networks illustrate that by considering different relations between different node pairs, our method is capable of producing node embeddings of higher quality than a number of state-of-the-art network embedding methods, as evaluated on a challenging multi-label node classification task.