In machine learning, we naturally apply an Observation-Oriented principle, in which observational variables preexist and set the stage for constructing relationships. While sufficient for traditional models, the integration of AI with big data exposes the misalignment between the observational models and our actual comprehension. Contrarily, humans shape cognitive entities defined by relationships, enabling us to formulate knowledge across temporal and hyper-dimensional spaces, rather than being confined to observational constructs. From an innovative Relation-Oriented perspective, this study examines the roots of this misalignment within our current modeling paradigm, illuminated by intuitive examples from computer vision and health informatics. We also introduce the relation-defined representation learning methodology as a practical implementation of Relation-Oriented modeling, supported by extensive experimental validation.

翻译：在机器学习中，我们自然遵循面向观察的原则，其中观测变量先于关系存在，并为构建关系奠定基础。虽然这对传统模型而言足够，但人工智能与大数据的融合揭示了观测模型与实际理解之间的错位。相反，人类通过关系定义认知实体，从而能够在时间与超维空间中建构知识，而非受限于观测性构造。本研究从创新的面向关系视角出发，通过计算机视觉与健康信息学中的直观示例，阐明当前建模范式中这一错位的根源。同时，我们引入关系定义表示学习方法论，作为面向关系建模的实践方案，并通过广泛实验验证予以支撑。