Meta Shares Insight into its Evolving AI-Powered Ad Targeting Process

"Generative Ads Recommendation Model (GEM) is Meta's most advanced ads foundation model, built on an LLM-inspired paradigm and trained across thousands of GPUs. It is the largest foundation model for recommendation systems (RecSys) in the industry, trained at the scale of large language models."

"These innovations efficiently boost ad performance, enable effective knowledge sharing across the ad model fleet, and optimize the use of thousands of GPUs for training. GEM has driven a paradigm shift in ads RecSys, transforming ad performance across the funnel - awareness, engagement, and conversion - through joint optimization of both user and advertiser objectives."

"GEM is trained on ad content and user engagement data from both ads and organic interactions. From this data, we derive features that we categorize into two groups: sequence features (such as activity history) and non-sequence features (such as user and ad attributes - e.g., age, location, ad format, and creative representation). Customized attention mechanisms are applied to each group independently, while also enabling cross-feature learning. This design improves accuracy and scales both the depth and breadth of each attention block, delivering 4× the efficiency of our previous generation of models."

GEM is a large-scale ads foundation model trained on ad content and user engagement from both ads and organic interactions. The model extracts sequence features (activity history) and non-sequence features (user and ad attributes such as age, location, ad format, and creative representation). Customized attention mechanisms process each feature group independently while enabling cross-feature learning. The architecture increases accuracy and scales the depth and breadth of attention blocks, achieving roughly four times the efficiency of the previous generation. GEM enables knowledge sharing across the ad model fleet and optimizes GPU utilization to improve awareness, engagement, and conversion.

Read at Social Media Today