Customized Graph Embedding: Tailoring Embedding Vectors to different Applications

TL;DR

This paper introduces Customized Graph Embedding (CGE), a method that tailors node vector representations to specific applications by automatically weighting graph paths, improving performance across various tasks.

Contribution

The paper presents a novel CGE approach that aligns graph embedding optimization with target applications, addressing a key limitation of existing methods.

Findings

CGE outperforms traditional embedding methods on node classification tasks.

CGE automatically differentiates the importance of graph paths for specific applications.

Experiments provide insights into how path importance impacts embedding quality.

Abstract

Graph is a natural representation of data for a variety of real-word applications, such as knowledge graph mining, social network analysis and biological network comparison. For these applications, graph embedding is crucial as it provides vector representations of the graph. One limitation of existing graph embedding methods is that their embedding optimization procedures are disconnected from the target application. In this paper, we propose a novel approach, namely Customized Graph Embedding (CGE) to tackle this problem. The CGE algorithm learns customized vector representations of graph nodes by differentiating the importance of distinct graph paths automatically for a specific application. Extensive experiments were carried out on a diverse set of node classification datasets, which demonstrate strong performances of CGE and provide deep insights into the model.