WeiPS: a symmetric fusion model framework for large-scale online learning
This work provides a system framework for large-scale online learning, which is critical for companies like ByteDance, Baidu, Alibaba, and Weibo to quickly capture changing user interests in recommendation systems.
This paper addresses the challenge of real-time model deployment and stability in large-scale online learning systems for recommendation. They developed WeiPS, a symmetric fusion framework that integrates training and inference, achieving second-level model deployment and high availability through fault tolerance and real-time degradation.
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.