HyperZero: A Customized End-to-End Auto-Tuning System for Recommendation with Hourly Feedback

TL;DR

HyperZero is an efficient auto-tuning system designed for recommendation systems, capable of optimizing model weights within days to improve user engagement metrics, addressing the need for rapid deployment in production environments.

Contribution

The paper introduces HyperZero, a novel end-to-end auto-tuning system that significantly reduces tuning time from weeks to days for recommendation system value models.

Findings

HyperZero achieves model tuning within 2-3 days.

It effectively improves recommendation value models in industrial settings.

The framework can be extended to other tuning tasks in recommendation systems.

Abstract

Modern recommendation systems can be broadly divided into two key stages: the ranking stage, where the system predicts various user engagements (e.g., click-through rate, like rate, follow rate, watch time), and the value model stage, which aggregates these predictive scores through a function (e.g., a linear combination defined by a weight vector) to measure the value of each content by a single numerical score. Both stages play roughly equally important roles in real industrial systems; however, how to optimize the model weights for the second stage still lacks systematic study. This paper focuses on optimizing the second stage through auto-tuning technology. Although general auto-tuning systems and solutions - both from established production practices and open-source solutions - can address this problem, they typically require weeks or even months to identify a feasible solution. Such prolonged tuning processes are unacceptable in production environments for recommendation systems, as suboptimal value models can severely degrade user experience. An effective auto-tuning solution is required to identify a viable model within 2-3 days, rather than the extended timelines typically associated with existing approaches. In this paper, we introduce a practical auto-tuning system named HyperZero that addresses these time constraints while effectively solving the unique challenges inherent in modern recommendation systems. Moreover, this framework has the potential to be expanded to broader tuning tasks within recommendation systems.