Bandit Sampling for Multiplex Networks

TL;DR

This paper introduces a scalable online layer sampling algorithm for multiplex graph neural networks, significantly improving efficiency in learning from multiple connection types while maintaining strong predictive performance.

Contribution

It proposes a novel layer sampling method for multiplex networks that reduces computational complexity compared to existing approaches, enabling scalable training on large, multi-layer graphs.

Findings

Efficient layer sampling improves training speed on large multiplex networks.

The method maintains or improves prediction accuracy compared to full-layer aggregation.

Experimental results validate the approach on synthetic and real-world datasets.

Abstract

Graph neural networks have gained prominence due to their excellent performance in many classification and prediction tasks. In particular, they are used for node classification and link prediction which have a wide range of applications in social networks, biomedical data sets, and financial transaction graphs. Most of the existing work focuses primarily on the monoplex setting where we have access to a network with only a single type of connection between entities. However, in the multiplex setting, where there are multiple types of connections, or \emph{layers}, between entities, performance on tasks such as link prediction has been shown to be stronger when information from other connection types is taken into account. We propose an algorithm for scalable learning on multiplex networks with a large number of layers. The efficiency of our method is enabled by an online learning algorithm that learns how to sample relevant neighboring layers so that only the layers with relevant information are aggregated during training. This sampling differs from prior work, such as MNE, which aggregates information across \emph{all} layers and consequently leads to computational intractability on large networks. Our approach also improves on the recent layer sampling method of \textsc{DeePlex} in that the unsampled layers do not need to be trained, enabling further increases in efficiency.We present experimental results on both synthetic and real-world scenarios that demonstrate the practical effectiveness of our proposed approach.