Graph Representation Ensemble Learning
This work addresses the problem of improving graph representation learning for applications like node classification, offering a novel ensemble approach that is particularly beneficial for underrepresented classes, though it is incremental in building upon existing embedding methods.
The paper tackles the challenge of capturing diverse properties in real-world graphs by introducing a graph representation ensemble learning framework that aggregates multiple embedding methods, achieving up to 8% improvement in macro-F1 on node classification tasks and up to 12% for underrepresented classes.
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%.