arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12970cs.LGcs.DBcs.IR
收藏

基于微服务的框架,用于探索跨建筑知识转移中的数据选择

A microservice-based framework for exploring data selection in cross-building knowledge transfer

LIRIS UMR5205(利昂高等师范学院计算机科学研究所UMR5205);Univ Lyon(里昂大学);CNRS(法国国家科学研究中心);Université Claude Bernard Lyon 1(里昂第一大学(克洛德·贝尔纳));CETHIL UMR5008(热科学与能源研究所UMR5008);INSA-Lyon(里昂国立应用科学学院);Instituto Universitário de Lisboa (ISCTE-IUL)(里斯本大学学院(ISCTE-IUL))

Mouna Labiadh, Christian Obrecht, Catarina Ferreira da Silva, Parisa Ghodous

摘要:

监督式深度学习在各种应用中取得了显著的成功。然而,成功的机器学习应用取决于足够大量数据的可用性。在缺乏来自目标域的数据的情况下,通常需要从多个来源收集代表性的数据汇集。然而,在现有的多源数据上训练的模型可能在看不见的目标域上泛化得很差。这个问题被称为域转移。在本文中,我们探讨了多源训练数据选择的适用性,以解决领域泛化的背景下的领域转移的挑战。我们还提出了一个面向微服务的方法来支持这个解决方案。我们对建筑能耗预测的用例进行了实验研究。实验结果表明,最小建筑描述是能够提高跨建筑泛化性能时,用于选择能源消耗数据。

英文摘要:

Supervised deep learning has achieved remarkable success in various applications. Successful machine learning application however depends on the availability of sufficiently large amount of data. In the absence of data from the target domain, representative data collection from multiple sources is often needed. However, a model trained on existing multi-source data might generalize poorly on the unseen target domain. This problem is referred to as domain shift. In this paper, we explore the suitability of multi-source training data selection to tackle the domain shift challenge in the context of domain generalization. We also propose a microservice-oriented methodology for supporting this solution. We perform our experimental study on the use case of building energy consumption prediction. Experimental results suggest that minimal building description is capable of improving cross-building generalization performances when used to select energy consumption data.

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。

↑