Author: Dániel Unyi

Link prediction is to predict whether two components in a network are likely to interact with each other. It’s a fundamental task in network science, with a wide variety of real-world applications. Examples include predicting friendship links on social media, identifying hidden communities, or discovering drug-drug interactions in pharmacology. However, current state-of-the-art algorithms are unable to scale efficiently for large graphs. My goal was to work out a scalable, accurate link prediction method by exploiting the modeling power of deep neural networks.


Graph-based deep learning generalizes traditional methods by allowing connectivity between data points [1]. Accordingly…

Daniel Unyi