论文标题
模型重复使用，内核平均嵌入式规范降低
Model Reuse with Reduced Kernel Mean Embedding Specification
论文作者
论文摘要
考虑到为各种任务构建的公开可用的机器学习模型池，当用户计划为自己的机器学习应用程序构建模型时，是否有可能在池中的模型上构建，以便可以重复使用这些现有模型而不是从头开始启动？在这里，一个巨大的挑战是如何找到有助于当前应用程序的模型，而无需访问池中模型的原始培训数据。在本文中，我们提出了一个两阶段的框架。在上传阶段，当模型上传到池中时，我们构建了一个减少的内核平均嵌入（RKME）作为模型的规范。然后，在部署阶段，将根据RKME规范的值来衡量当前任务和预训练模型的相关性。理论结果和广泛的实验验证了我们方法的有效性。
Given a publicly available pool of machine learning models constructed for various tasks, when a user plans to build a model for her own machine learning application, is it possible to build upon models in the pool such that the previous efforts on these existing models can be reused rather than starting from scratch? Here, a grand challenge is how to find models that are helpful for the current application, without accessing the raw training data for the models in the pool. In this paper, we present a two-phase framework. In the upload phase, when a model is uploading into the pool, we construct a reduced kernel mean embedding (RKME) as a specification for the model. Then in the deployment phase, the relatedness of the current task and pre-trained models will be measured based on the value of the RKME specification. Theoretical results and extensive experiments validate the effectiveness of our approach.
