Representation Learning in Continuous-Time Dynamic Signed Networks

TL;DR

This paper introduces SEMBA, a novel GNN-based model for dynamic signed networks that effectively captures temporal and sign information, significantly improving future link sign prediction over existing methods.

Contribution

The work presents SEMBA, a new approach combining memory modules and balanced aggregation to model the evolution of signed links in dynamic networks, addressing a gap in existing static or unsigned models.

Findings

SEMBA outperforms baselines by up to 80% in sign prediction.

SEMBA matches state-of-the-art in link existence prediction.

Superior performance on negative class links.

Abstract

Signed networks allow us to model conflicting relationships and interactions, such as friend/enemy and support/oppose. These signed interactions happen in real-time. Modeling such dynamics of signed networks is crucial to understanding the evolution of polarization in the network and enabling effective prediction of the signed structure (i.e., link signs and signed weights) in the future. However, existing works have modeled either (static) signed networks or dynamic (unsigned) networks but not dynamic signed networks. Since both sign and dynamics inform the graph structure in different ways, it is non-trivial to model how to combine the two features. In this work, we propose a new Graph Neural Network (GNN)-based approach to model dynamic signed networks, named SEMBA: Signed link's Evolution using Memory modules and Balanced Aggregation. Here, the idea is to incorporate the signs of temporal interactions using separate modules guided by balance theory and to evolve the embeddings from a higher-order neighborhood. Experiments on 4 real-world datasets and 4 different tasks demonstrate that SEMBA consistently and significantly outperforms the baselines by up to $80\%$ on the tasks of predicting signs of future links while matching the state-of-the-art performance on predicting the existence of these links in the future. We find that this improvement is due specifically to the superior performance of SEMBA on the minority negative class.