Z-ENG: Graph Representation Learning for Recommender Systems
The primary goal of recommender systems is to estimate user preferences on items, e.g., audio, video content. Such systems are applied by various online companies, e.g., Google, Bing, YouTube, Amazon, eBay, Booking. Graph based recommendation techniques deliver high quality recommendations, e.g., random walk, recommendation spreading. However, these calculation methods are eager on memory and CPU/GPU and suffer from performance issues. The goal of this project is to reduce the size of the knowledge graph while keeping the relevant information in order to improve the performance of calculation techniques. The student will apply representation learning techniques to the graph and evaluate various personalization algorithms.