Graph Representation Ensemble Learning

TL;DR

This paper introduces a novel ensemble learning framework for graph representations, combining multiple embedding methods to better capture complex graph properties and improve node classification performance.

Contribution

It presents the first framework for aggregating multiple graph embedding methods, with theoretical and empirical analysis demonstrating improved classification results.

Findings

Ensemble methods outperform state-of-the-art by up to 8% on macro-F1.

Significant improvements for underrepresented classes, up to 12%.

Framework effectively captures multiple graph properties.

Abstract

Representation learning on graphs has been gaining attention due to its wide applicability in predicting missing links, and classifying and recommending nodes. Most embedding methods aim to preserve certain properties of the original graph in the low dimensional space. However, real world graphs have a combination of several properties which are difficult to characterize and capture by a single approach. In this work, we introduce the problem of graph representation ensemble learning and provide a first of its kind framework to aggregate multiple graph embedding methods efficiently. We provide analysis of our framework and analyze -- theoretically and empirically -- the dependence between state-of-the-art embedding methods. We test our models on the node classification task on four real world graphs and show that proposed ensemble approaches can outperform the state-of-the-art methods by up to 8% on macro-F1. We further show that the approach is even more beneficial for underrepresented classes providing an improvement of up to 12%.