Async Learned User Embeddings for Ads Delivery Optimization

TL;DR

This paper introduces ALURE, an asynchronous method for learning high-quality user embeddings from multimodal activities, improving ad relevance in large-scale recommendation systems.

Contribution

It presents a novel asynchronous learning approach for user embeddings using a Transformer-like model, enhancing ad targeting accuracy.

Findings

Significant offline performance improvements

Enhanced online ad relevance

Effective large-scale user representation learning

Abstract

In recommendation systems, high-quality user embeddings can capture subtle preferences, enable precise similarity calculations, and adapt to changing preferences over time to maintain relevance. The effectiveness of recommendation systems depends on the quality of user embedding. We propose to asynchronously learn high fidelity user embeddings for billions of users each day from sequence based multimodal user activities through a Transformer-like large scale feature learning module. The async learned user representations embeddings (ALURE) are further converted to user similarity graphs through graph learning and then combined with user realtime activities to retrieval highly related ads candidates for the ads delivery system. Our method shows significant gains in both offline and online experiments.