论文标题
最好只有在最适合您的情况下才是最好的：根据动态位置敏感的哈希寻找相关的模型
It's the Best Only When It Fits You Most: Finding Related Models for Serving Based on Dynamic Locality Sensitive Hashing
论文作者
论文摘要
最近，深度学习已成为机器学习和人工智能中最受欢迎的方向。但是，培训数据的准备通常是部署深度学习模型进行生产或研究的生命周期中的瓶颈。重复使用推断数据集的模型可以大大节省培训数据创建所需的人为成本。尽管存在许多模型共享平台，例如TensorFlow Hub，Pytorch Hub，DLHUB，但这些系统中的大多数都需要模型上载器来手动指定每个模型和模型下载器的详细信息，以筛选选择模型的关键字搜索结果。他们缺乏自动模型搜索工具。本文提出了一个基于目标数据集的相似性和可用模型的培训数据集的端到端搜索相关模型的端到端过程。尽管存在许多相似性测量值，但我们研究了如何在没有配对比较的情况下有效地应用这些指标并比较这些指标的有效性。我们发现，我们提出的基于Jensen-Shannon（JS）差异的适应性测量是有效的测量，并且通过使用局部敏感的散列技术，可以显着加速其计算。
In recent, deep learning has become the most popular direction in machine learning and artificial intelligence. However, preparation of training data is often a bottleneck in the lifecycle of deploying a deep learning model for production or research. Reusing models for inferencing a dataset can greatly save the human costs required for training data creation. Although there exist a number of model sharing platform such as TensorFlow Hub, PyTorch Hub, DLHub, most of these systems require model uploaders to manually specify the details of each model and model downloaders to screen keyword search results for selecting a model. They are in lack of an automatic model searching tool. This paper proposes an end-to-end process of searching related models for serving based on the similarity of the target dataset and the training datasets of the available models. While there exist many similarity measurements, we study how to efficiently apply these metrics without pair-wise comparison and compare the effectiveness of these metrics. We find that our proposed adaptivity measurement which is based on Jensen-Shannon (JS) divergence, is an effective measurement, and its computation can be significantly accelerated by using the technique of locality sensitive hashing.
