arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.07981cs.LGstat.ML
收藏

机器学习中的差异复制

Differential Replication in Machine Learning

BBVA Data & Analytics(BBVA数据与分析);Universitat de Barcelona(巴塞罗那大学);Universitat Ramon Llull, ESADE(拉蒙·柳利大学ESADE商学院)

Irene Unceta, Jordi Nin, Oriol Pujol

摘要:

当部署在野外时,机器学习模型通常会面临不断变化的数据和需求,这要么是因为生成分布的变化,要么是因为外部约束改变了模型运行的环境。为了在这样的生态系统中生存,机器学习模型需要随着时间的推移不断进化,以适应新的条件。模型适应性的思想已经从不同的角度进行了研究。在本文中,我们提出了一种基于重用已部署的机器学习模型获得的知识并利用它来训练后代的解决方案。这就是机器学习模型差异复制背后的思想。

英文摘要:

When deployed in the wild, machine learning models are usually confronted with data and requirements that constantly vary, either because of changes in the generating distribution or because external constraints change the environment where the model operates. To survive in such an ecosystem, machine learning models need to adapt to new conditions by evolving over time. The idea of model adaptability has been studied from different perspectives. In this paper, we propose a solution based on reusing the knowledge acquired by the already deployed machine learning models and leveraging it to train future generations. This is the idea behind differential replication of machine learning models.

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。

↑