arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.09474cs.IRcs.DScs.LG
收藏

只有最适合你的时候才是最好的:基于动态局部敏感哈希的服务相关模型

It's the Best Only When It Fits You Most: Finding Related Models for Serving Based on Dynamic Locality Sensitive Hashing

Arizona State University(亚利桑那州立大学)

Lixi Zhou, Zijie Wang, Amitabh Das, Jia Zou

摘要:

近年来,深度学习已经成为机器学习和人工智能中最热门的方向。然而,训练数据的准备通常是部署用于生产或研究的深度学习模型的生命周期中的瓶颈。重用模型来推断数据集可以大大节省创建训练数据所需的人力成本。虽然有许多模型共享平台,如TensorFlow Hub,PyTorch Hub,DLHub,但这些系统大多需要模型上传者手动指定每个模型的详细信息,模型下载者筛选关键字搜索结果以选择模型。他们缺乏一个自动的模型搜索工具。本文提出了一种端到端的过程,搜索相关的模型服务的基础上的目标数据集和可用模型的训练数据集的相似性。虽然存在许多相似性度量,我们研究如何有效地应用这些度量,而无需成对比较,并比较这些度量的有效性。我们发现,我们提出的自适应测量,这是基于Jensen-Shannon(JS)的分歧,是一个有效的测量,其计算可以显着加快通过使用局部敏感哈希技术。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑