The terms graph embeddings and graph representation learning can be seen as synonyms to each other where the key idea is to learn a mapping function that embeds nodes, or entire (sub)graphs (from non-euclidean), as points in low-dimensional vector space (to embedding space).
In this session, Sachin Sharma will put more light on this rapidly growing area and its industrial applications. In addition to this, Sachin will also demonstrate node embeddings generated from Amazon product co-purchasing network which can be used to predict shopping preferences.
About the Presenter:
Sachin is a Machine Learning Research Engineer at ArangoDB whose aim is to build Intelligent products using thorough research and engineering in the area of Graph Machine Learning. He completed his Masters’s degree in Computer Science with a specialization in Intelligent Systems. He is an AI Enthusiast who has conducted research in the areas of Computer Vision, NLP, and Graph Neural Networks at DFKI (German Research Centre for AI) during his academic career. Sachin also worked on building Machine Learning pipelines at Define Media Gmbh where he worked as a Machine Learning Engineer and Scientist.