Probabilistic Salary Prediction with Graph Attention Networks and a Mixture Density Network
Researchers have developed a new framework called GAT-MDN for more accurate salary prediction by considering the inherent uncertainty and multi-modal nature of compensation data. This approach utilizes Graph Attention Networks (GATs) to learn representations from job attributes like location and occupation, incorporating hierarchical and semantic relationships. The model then employs a Mixture Density Network (MDN) to output a full conditional salary distribution, outperforming traditional methods in experiments on a large Dutch job dataset. AI
IMPACT This research offers a more nuanced approach to salary prediction by modeling uncertainty and relationships between job attributes, potentially benefiting job seekers and employers.