Scalable Graph Learning for your Enterprise

​Relational databases like Snowflake house much of the world’s critical data, but building predictive models from this data can be slow and error-prone. Hours of feature engineering to join and aggregate data into a single table ends with suboptimal models. A new method, Relational Deep Learning (RDL), eliminates this bottleneck by treating the Snowflake database as temporal, heterogeneous graphs, where rows are nodes and primary-foreign key relationships form edges.

​Message Passing Graph Neural Networks, like those used by Kumo AI, learn directly from this structure, creating richer representations without manual feature engineering. This leads to faster, more accurate models and allows data scientists to define and solve node and link prediction tasks with ease. RDL streamlines recommendation systems, fraud detection, customer retention, and more. RDL scales to handle graphs with billions of entities, ensuring security, privacy, and explainability.

​

​You'll learn:

​1️⃣ How to quickly set up relational deep learning using Snowflake and Kumo AI
2️⃣ How to use AI for practical purposes like improving product recommendations or personalizing communications
3️⃣ How cutting-edge innovations are changing the way leaders use their data

Speaker:

​Hema Raghavan is Vice President of Engineering and Co-founder of Kumo AI where she is responsible for developing the AI technology to help Kumo users build better predictive models. Previously, Raghavan was Senior Director of Engineering at LinkedIn where she led a globally distributed diverse team that built AI and ML solutions for fueling LinkedIn’s growth, including People You May Know and the company’s Air Traffic Controller AI that governed member communications. She has also worked as a Research Staff Member at IBM and a Scientist at Yahoo!. Raghavan has a PhD in Computer Science from the University of Massachusetts Amherst, and a degree in Computer Engineering from the University of Mumbai.