DynamiX: Dynamic Resource eXploration for Personalized Ad-Recommendations

Adam Holeman, Sohini Roychowdhury, Mohammad Amin, Feng Wei, Bhaskar Mehta, Sri Reddy

Keywords: self-supervised learning, dynamic segmentation, dwell-time, user-ad engagement

TL;DR: Dynamix is a scalable, self-supervised framework for personalized ad sequence processing that boosts training and inference efficiency with dynamic feature selection and user segmentation, maintaining accuracy while reducing compute costs.

Abstract: For online ad-recommendation systems, processing complete user-ad-engagement histories is both computationally intensive and noise-prone. We introduce `Dynamix', a scalable, personalized sequence exploration framework that optimizes event history processing using maximum relevance principles and self-supervised learning through Event Based Features (EBFs). Dynamix categorizes users-engagements at session and surface-levels by leveraging correlations between dwell-times and ad-conversion events. This enables targeted, event-level feature removal and selective feature boosting for certain user-segments, thereby yielding training and inference efficiency wins without sacrificing engaging ad-prediction accuracy. While, dynamic resource removal increases training and inference throughput by 1.15% and 1.8%, respectively, dynamic feature boosting provides 0.033 NE gains while boosting inference QPS by 4.2\% over baseline models. These results demonstrate that Dynamix achieves significant cost efficiency and performance improvements in online user-sequence based recommendation models. Self-supervised user-segmentation and resource exploration can further boost complex feature selection strategies while optimizing for workflow and compute resources.

Submission Number: 170