Graph Neural Networks with Ankit Jain

Ankit is an experienced AI Researcher/Machine Learning Engineer who is passionate about using AI to build scalable machine learning products. In his 10 years of AI career, he has researched and deployed several state-of-the-art machine learning models which have impacted 100s of millions of users.    Currently, He works as a senior research scientist at Facebook where he works on a variety of machine learning problems across different verticals. Previously, he was a  researcher at Uber AI  where he worked on application of deep learning methods to different problems ranging from food delivery, fraud detection to self-driving cars.   He has been a featured speaker in many of the top AI conferences and universities like UC Berkeley, IIT Bombay and has published papers in several top conferences like Neurips, ICLR. Additionally, he has co-authored a book on machine learning titled TensorFlow Machine Learning Projects.  He has undergraduate and graduate degrees from IIT Bombay (India) and UC Berkeley respectively. Outside of work, he enjoys running and has run several marathons. 00:00 Intro 00:17  IIT vs FAANG companies, Competition Anxiety 05:40  Work Load between India and US, Educational Culture   07:50. Uber Eats, Food Recommendation Systems and Graph Networks  11:00 Accuracy Matrices for Recommendation Systems   12:42 Weather as a predictor of Food Orders and Pizza Fad 15:48 Raquel Urtusun and Zoubin Gharamani, Autonomous Driving and Google Brain 17:30 Graph Learning in Computer Vision & Beating the Benchmarks 19:15 Latent Space Representations and Fraud Detection 21:30 Multimodal Data & Prediction Accuracy  23:20 Multimodal Graph Recommendation at Uber Eats 23:50 Post-Order Data Analysis for Uber Eats 27:30  Plugging out of Matrix and Marathon Running 31:44  Finding Collusion between Riders and Drivers with Graph Learning  35:40  Reward Sensitivity Analysis for Drivers in Uber through LSTM Networks  42:00 PyG 2.0, Jure Leskovec, and DeepGraph, Tensorflow Support   46:46 Pytorch vs Tensorflow, Scalability and ease of use. 52:10 Work at Facebook, End to End Experiments 55:19 Optimisation of Cross-functional Solutions for Multiple Teams   57:30  Content Understanding teams and Behaviour Prediction 59:50 Cold Start Problem and Representation Mapping  01:03:30 NeurIPS paper on Meta-Learning and Global Few-Shot Model 01:07:00 Experimentation Ambience at Facebook, Privacy and Data Mine  01:09:03 Cons of working at FAANG  01:10:20 High School Math Teacher as Inspiration and Mentoring Others  01:18:25 TensorFlow Book and Upcoming Blog 01:16:40 Working at Oil Rig in the Ocean Straight Out of College  01:20:08 Promises of AI and Benefits to Society at Large 01:25:50 Facebook accused of Polarisation, Manipulation and Racism  01:28:10 Revenue Models - Product vs Advertising 01:31:15 Metaverse and Long-term Goals  01:33:10 Facebook Ray-Ban Stories and Market for Smart Glasses 01:36:40 Possibility of Facebook OS for Facebook Hardware 01:38:00 LibraCoin & Moving Fast - Breaking Things at Facebook  01:39:09 Orkut vs Facebook - A case study on Superior Tech Stack 01:42:00 Careers in Data Science & How to Get into It 01:45:00 Irrelevance of College Degrees and Prestigious Universities as Pre-requisites 01:49:50 Decreasing Attention Span & Lack of Curiosity  01:54:40 Arranged Marriages & Shifting Relationship Trends