一句话：提出本地小型 DNN 与远程大模型协同的客户端架构，在保持精度的同时降低远程预测成本。
针对当前最先进 DNN 依赖数十亿参数大模型、只能在第三方服务器上运行并带来高额单次预测费用的问题，本文提出一种面向客户端应用的新型软件架构。该架构同时使用本地小型 DNN 与远程大规模模型：简单输入由本地模型以近乎零边际成本完成预测，困难输入再调用远程大模型，从而兼顾低成本与高精度。在概念验证中，该方法将预测成本最多降低 50%，且未对系统精度造成负面影响。
On complex problems, state of the art prediction accuracy of Deep Neural Networks (DNN) can be achieved using very large-scale models, consisting of billions of parameters. Such models can only be run on dedicated servers, typically provided by a 3th party service, which leads to a substantial monetary cost for every prediction. We propose a new software architecture for client-side applications, where a small local DNN is used alongside a remote large-scale model, aiming to make easy predictions locally at negligible monetary cost, while still leveraging the benefits of a large model for challenging inputs. In a proof of concept we reduce prediction cost by up to 50% without negatively impacting system accuracy.