Model reuse with domain knowledge
Xi-Zhu Wu, Zhihua Zhou · Scientia Sinica Informationis · 2017
The life spans of machine learning models are often short and a large number of models are wasted because they can only be applied to a specific task. However, a well-designed, carefully trained model contains learned knowledge from its task, which may be more concise than training data. Furthermore, when we have no access to training data, the trained model is the last remaining source of information. This study introduces a framework to reuse existing models trained in other tasks and help improve the model for the current task, especially when limited data is available for the current task. This framework incorporates high-level domain knowledge to combine existing models and treat them as black boxes, in order for them to be universal for complex models. Experiments on applying the framework to practical problems demonstrate that we can improve the performance on the current task by reusing existing models.