Transfer Learning for Node Regression Applied to Spreading Prediction

TL;DR

This paper investigates the use of transfer learning with node representation models to predict spreading phenomena in complex networks, demonstrating promising transferability and zero-shot capabilities across similar network structures.

Contribution

It is among the first to evaluate transferability of node representations for regression tasks in network spreading prediction, including zero-shot transfer between similar networks.

Findings

Models can transfer effectively between similar networks

Zero-shot transfer achieves competitive performance

Transfer learning enhances spreading prediction accuracy

Abstract

Understanding how information propagates in real-life complex networks yields a better understanding of dynamic processes such as misinformation or epidemic spreading. The recently introduced branch of machine learning methods for learning node representations offers many novel applications, one of them being the task of spreading prediction addressed in this paper. We explore the utility of the state-of-the-art node representation learners when used to assess the effects of spreading from a given node, estimated via extensive simulations. Further, as many real-life networks are topologically similar, we systematically investigate whether the learned models generalize to previously unseen networks, showing that in some cases very good model transfer can be obtained. This work is one of the first to explore transferability of the learned representations for the task of node regression; we show there exist pairs of networks with similar structure between which the trained models can be transferred (zero-shot), and demonstrate their competitive performance. To our knowledge, this is one of the first attempts to evaluate the utility of zero-shot transfer for the task of node regression.