SigGAN : Adversarial Model for Learning Signed Relationships in Networks
This addresses signed link prediction for applications in diverse domains, but it is incremental as it adapts existing GAN methods to signed networks.
The paper tackles the problem of signed link prediction in networks, which predicts whether edges are positive or negative, by proposing SigGAN, a Generative Adversarial Network-based model that incorporates structural balance theory and handles data imbalances, and it shows effectiveness compared to state-of-the-art techniques on real-world datasets.
Signed link prediction in graphs is an important problem that has applications in diverse domains. It is a binary classification problem that predicts whether an edge between a pair of nodes is positive or negative. Existing approaches for link prediction in unsigned networks cannot be directly applied for signed link prediction due to their inherent differences. Further, additional structural constraints, like, the structural balance property of the signed networks must be considered for signed link prediction. Recent signed link prediction approaches generate node representations using either generative models or discriminative models. Inspired by the recent success of Generative Adversarial Network (GAN) based models which comprises of a discriminator and generator in several applications, we propose a Generative Adversarial Network (GAN) based model for signed networks, SigGAN. It considers the requirements of signed networks, such as, integration of information from negative edges, high imbalance in number of positive and negative edges and structural balance theory. Comparing the performance with state of the art techniques on several real-world datasets validates the effectiveness of SigGAN.