在机器学习中离开以数据为中心的方法的概念模型
A conceptual model for leaving the data-centric approach in machine learning
摘要:
长期以来,机器学习(ML)一直被视为从独立于周围环境的数据中学习关系的抽象问题。这最近受到了挑战,并且已经提出了在机器学习模型中包括外部约束的方法。这些方法通常来自特定的应用领域,例如ML中公平性领域的去偏置算法或物理和工程领域的物理约束。在本文中,我们提出并讨论了一个概念性的高层次模型,统一这些方法在一个共同的语言。我们希望这将促进不同领域之间的交流,以及将外部约束纳入ML模型的不同方法,从而留下纯粹以数据为中心的方法。
英文摘要:
For a long time, machine learning (ML) has been seen as the abstract problem of learning relationships from data independent of the surrounding settings. This has recently been challenged, and methods have been proposed to include external constraints in the machine learning models. These methods usually come from application-specific fields, such as de-biasing algorithms in the field of fairness in ML or physical constraints in the fields of physics and engineering. In this paper, we present and discuss a conceptual high-level model that unifies these approaches in a common language. We hope that this will enable and foster exchange between the different fields and their different methods for including external constraints into ML models, and thus leaving purely data-centric approaches.
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。