WHAT IS IT?
Graph Neural Networks (GNNs) have emerged as the most effective approach for machine learning on graphs. Graphs are useful for describing most real-world applications (including financial graphs, social networks, ecommerce, and online marketplaces), where phenomena can be broken down into entities, their relationships, and their dynamic interactions.
Link prediction is the task of predicting an edge between any pair of nodes - thus defining their relationships or interactions. Link prediction has a broad range applications including recommendations (predicting a user’s affinity to different products, content, ads, or other users which would lead to a user buying specific items, viewing specific content, or clicking on an ad in any ecommerce or online marketplace transaction networks), customer outreach (ranking top outreach strategies by channel, content, timing, and volume), drug discovery (predicting molecular interactions and activations while simultaneously predicting side effects based on biological structure), transportation (predicting traffic flows to optimize routes), and more.
This webinar will deep dive on techniques and best practices for building link prediction for production use cases, including recommendation and ranking systems. We’ll walk through the different approaches of link prediction using GNNs, walking through the typical flow of setting up the problem and executing the prediction, and we’ll show you how to put it together yourself with PyTorch Geometric. We’ll show you what the out-of-the-box experience looks like using Kumo’s state-of-the-art GNN platform in production.
Amitabha is a founding engineer at Kumo AI and work on applied machine learning across the breadth of customer problems at Kumo. He holds a PhD from the University of Cambridge, with a postdoctoral stint at EPFL working on graph analytics. Amitabha worked as a research scientist at Intel and then at Google, where he built the first iteration of Google Cloud’s ML-powered DDoS protection for the entire cloud. Subsequently, he led the application of graph neural networks to find and weed out bad actors in the Google Ads Ecosystem.
Machine Learning Engineer
Weihua is a machine learning engineer at Kumo AI, working on productionizing GNNs on enterprise data. Weihua recently received a Ph.D. degree from Stanford, where he developed theory/methods/benchmarks for GNNs. He applied his research to improve diverse real-world applications, including recommender systems, drug/material discovery, and weather forecasting. Weihua led the creation of the Open Graph Benchmark, a widely-used benchmark for machine learning on graphs, and organized KDD Cup and NeurIPS competition around it.