Scaling Machine Learning on Graphs at LinkedIn with Hema Raghavan and Scott Meyer - TWiML Talk #236
Published:Mar 4, 2019 17:00
•1 min read
•Practical AI
Analysis
This article summarizes a discussion on the Practical AI podcast, focusing on LinkedIn's use of graph databases and machine learning. The guests, Hema Raghavan and Scott Meyer, discuss the systems behind features like "People You May Know" and second-degree connections. The conversation covers the motivations for using graph-based models at LinkedIn, the challenges of scaling these models, and the software used to support the company's large graph databases. The article highlights the practical application of graph-based machine learning in a real-world, large-scale environment.
Key Takeaways
- •LinkedIn leverages graph databases and machine learning for features like "People You May Know".
- •The discussion covers the motivations and challenges of using graph-based models at a large scale.
- •The article highlights the software infrastructure supporting LinkedIn's graph databases.
Reference
“Hema shares her insight into the motivations for LinkedIn’s use of graph-based models and some of the challenges surrounding using graphical models at LinkedIn’s scale, while Scott details his work on the software used at the company to support its biggest graph databases.”