WeiPS: a symmetric fusion model framework for large-scale online learning

TL;DR

WeiPS is a symmetric fusion framework designed for large-scale online learning in recommendation systems, enabling real-time updates, model stability, and high availability despite billions of parameters.

Contribution

The paper introduces WeiPS, a novel online learning system framework that integrates training and inference with streaming updates and fault tolerance for large-scale models.

Findings

Supports real-time model updates at billion-parameter scale

Ensures model stability and high availability during online learning

Achieves consistent and fault-tolerant deployment in large-scale systems

Abstract

The recommendation system is an important commercial application of machine learning, where billions of feed views in the information flow every day. In reality, the interaction between user and item usually makes user's interest changing over time, thus many companies (e.g. ByteDance, Baidu, Alibaba, and Weibo) employ online learning as an effective way to quickly capture user interests. However, hundreds of billions of model parameters present online learning with challenges for real-time model deployment. Besides, model stability is another key point for online learning. To this end, we design and implement a symmetric fusion online learning system framework called WeiPS, which integrates model training and model inference. Specifically, WeiPS carries out second level model deployment by streaming update mechanism to satisfy the consistency requirement. Moreover, it uses multi-level fault tolerance and real-time domino degradation to achieve high availability requirement.