Applied Machine Learning and AI @ FaceBook

“Facebook today cannot exist without AI. Every time you use Facebook or Instagram or Messenger, you may not realize it, but your experiences are being powered by AI.”  —  Joaquin Candela, Facebook’s Applied ML team leader

———————

“Machine learning is a core transformative way by which we are rethinking everything we are doing. Google Brain is the way we are embedding this in everything we do.”                                               Sundar Pichai (CEO Google)

———————

Salesforce CEO Marc Benioff said at a recent conference: “This [AI, ML] is a huge shift going forward, which is that everybody wants systems that are smarter, everybody wants systems that are more predictive, everybody wants everything scored, everybody wants to understand what’s the next best offer, next best opportunity, how to make things a little bit more efficient.”

Machine Learning (ML), Deep Learning and AI powering “Systems that Learn at scale” are at the bleeding edge of data science, deep learning and predictive search today.

Every market leader is jumping on this AI enabled engagement trend in retail, banking and healthcare.

Machine learning is central to Facebook’s future. Creating the extreme personalized experience (“individual equation based on 1000s of attributes – your preferences, predilections, conversations and transactions “) is the killer app.

FaceBook – AI/ML Case Study

Facebook is a bleeding edge case study of where AI/ML are being used to augment user engagement and experiences. I am starting to see many leading firms investing in ML Accelerators and Platforms as part of their data science strategy.

According to Facebook software engineer Jeffrey Dunn, “Many of the experiences and interactions people have on Facebook today are made possible with AI. When you log in to Facebook, we use the power of ML to provide you with unique, personalized experiences. ML models are part of ranking and personalizing News Feed stories, filtering out offensive content, highlighting trending topics, ranking search results, and much more. ”

Take for instance photo display. Collectively, people will take 1 trillion photos this year. Most of these are on Facebook which has become the new album for everyday life. For its 1.8+ billion monthly active users, FB is data mining to surface the right photo at the right moment (birthday, anniversary, vacation anniversary etc.). Advances in deep learning have enabled big improvements in image classification — questions like “Who is in the image?” and “Where are the objects?” are being auto-classified more accurately than ever.

Talk about a scalable data driven digital engagement platform.  Only Apple, Amazon.com or Google can match this scale.

To ensure that other experiences on Facebook that could benefit from ML models, Facebook in late 2014 set out to redefine ML/AI platforms at Facebook from the ground up, and to put state-of-the-art algorithms at the fingertips of every Facebook engineer.  Until then it was a chore for engineers without a strong ML/AI background to take advantage of the data and algorithms.

FBLearner Flow, as the software is known, is filled with algorithms (e.g., sparse matrix, neural networks, deep learning, metric learning, kernel learning, compositional models, non-linear structured prediction) developed by Facebook’s AI/ML experts that can be accessed by more general engineers across the company to build different products.

CoreML group is a dedicated Facebook team established to work on state of the art infrastructure and applied research to bridge the gap between research and product.  CoreML has been working on FBLearner Flow since late 2014 to enable things like improved search ranking, text/sentiment classification, collaborative filtering/recommendation, payment fraud, click-through rate prediction, click-fraud detection, or spam detection.

Today, >25% of Facebook engineers are using APIs to help them leverage artificial intelligence (AI) and machine learning (ML).

“FBLearner Flow [is] capable of easily reusing algorithms in different products, scaling to run thousands of simultaneous custom experiments, and managing experiments with ease,” wrote Facebook software engineer Jeffrey Dunn, in a blog post titled “Introducing FBLearner Flow: Facebook’s AI backbone.”

“FBLearner Flow is used by more than 25% of Facebook’s engineering team,” wrote Dunn. “Since its inception, more than a million models have been trained, and our prediction service has grown to make more than 6 million predictions per second.”

The FBLearner Flow platform is similar to Microsoft’s Azure Machine Learning service and Airbnb’s open source Airflow platform, according to VentureBeat. Google leverage ML extensively already. Take for instance, Google Maps. When you ask about a location, you don’t just want to know how to get from point A to point B. Depending on the context, you may want to know what time is best to avoid the crowds, whether the store you’re looking for is open right now, or what the best things to do are in a destination you’re visiting for the first time.

Contextual AI is the most important technology anyone in the world is working on today, according to Dave Coplin, Microsoft’s chief envisioning officer, so it’s not all that surprising Facebook wants to put the technology into the hands of developers.

Making an instant (and accurate!) prediction of how many people will click on a given ad or offer…. is the equivalent of the holy grail 🙂  Robots will be replacing marketing talent soon. End of marketing as we know it.

Other Relevant References

• Building scalable systems to understand content
• Google AI Mega Chatbot
• Dunn’s full post can be read in full here.
• FBLearner Flow screen shot below is from VentureBeat.
• Bernard Marr’s article on Forbes
• An-exclusive-look-at-how-AI-and-machine-learning-work-at-Apple