论文标题
WEIP：大规模在线学习的对称融合模型框架
WeiPS: a symmetric fusion model framework for large-scale online learning
论文作者
论文摘要
推荐系统是机器学习的重要商业应用，每天信息流中数十亿个供稿视图。实际上，用户和项目之间的互动通常会随着时间的流逝而改变用户的兴趣，因此许多公司（例如Bondedance，Baidu，Alibaba和Weibo）采用在线学习作为快速捕获用户兴趣的有效方法。但是，数百十亿个模型参数呈现在线学习，面临实时模型部署的挑战。此外，模型稳定性是在线学习的另一个关键点。为此，我们设计并实施了称为WEIP的对称融合在线学习系统框架，该框架集成了模型培训和模型推断。具体而言，WEIPS通过流更新机制来实现第二级模型部署，以满足一致性要求。此外，它使用多级容器耐受性和实时多米诺骨牌降解来达到高可用性要求。
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.
