Facebook’s mission is to give people the power to share and make the world more open and connected. People use Facebook to stay connected with friends and family, to discover what’s going on in the world, and to share and express what matters to them. With more than 1.0 Billion Daily Active People and 1.5 Billion Monthly Active People, it is crucial to provide a best personalized experience in a scalable way. Machine Learning techniques are our best friends on optimizing content allocation and entity recommendation when large amount of data are available.
Talk: "Machine Learning at Scaling Facebook, Challenges and Lessons Learned" - Junfeng Pan
In this tech talk, Junfeng Pan will talk about machine learning models, data parameters, the supporting infrastructure, storage and various applications in friend recommendation, news feed ranking and ads optimization. Junfeng is a founding member and leader for Online Machine Learning in Facebook. He is going to share practical challenges and lessons learned in developing real time prediction systems at large scale.
Talk: "A Trillion documents for a Billion search engines” - Hetu K
With over a trillion posts, photos and videos, the Facebook Search Index is one of the world’s largest repositories of information. The goal of Content Search at Facebook is to draw on this collective wisdom and serve the needs of the 1Billion+ users on Facebook. In this tech talk, Hetu Kamisetty will describe some of the challenges in Machine Learning and Natural Language Processing that we have addressed towards this goal.
As an engineering leader at Facebook, Junfeng leads the company's ads ranking and later on, user ranking. He is proud to have designed, built, and spearheaded the growth of large-scale machine learning algorithms and systems for ads ranking, user engagement and growth optimization at Facebook. Prior to joining Facebook, Junfeng led ads quality projects in Google where he received the company-wide Executive and Management Group (a.k.a OC) award for the achievement. He was a visiting scholar in Massachusetts Institute of Technology (MIT). He received his Ph.D. from Hong Kong University of Science and Technology (HKUST).
Junfeng published many papers in top-tier conferences and journals in IEEE, ACM and AAAI societies. He is a senior member of IEEE. He is a Co-Chair, a (Senior) Program Committee for more than 40 conferences and a regular reviewer for over ten academic journals. In 2005, he was awarded the Precision, Performance and Creativity Awards at the ACM Knowledge Discovery and Data Mining (KDD) Cup. Most recently he was featured in an interview in the magazine American Scientist in 2013.