Difficulties in replication and reproducibility of empirical evidences in machine learning research have become a prominent topic in recent years. Ensuring that machine learning research results are sound and reliable requires reproducibility, which verifies the reliability of research findings using the same code and data. This promotes open and accessible research, robust experimental workflows, and the rapid integration of new findings. Evaluating the degree to which research publications support these different aspects of reproducibility is one goal of the present work. For this we introduce an ontology of reproducibility in machine learning and apply it to methods for graph neural networks. Building on these efforts we turn towards another critical challenge in machine learning, namely the curse of dimensionality, which poses challenges in data collection, representation, and analysis, making it harder to find representative data and impeding the training and inference processes. Using the closely linked concept of geometric intrinsic dimension we investigate to which extend the used machine learning models are influenced by the intrinsic dimension of the data sets they are trained on.

翻译：机器学习研究中经验证据的复现与可重复性困难已成为近年来的突出议题。确保机器学习研究成果的可靠性与有效性离不开可重复性——即通过相同代码与数据验证研究结论的可靠性。这一过程促进了开放可获取的研究环境、稳健的实验工作流以及新成果的快速整合。评估科研出版物对不同层面可重复性的支撑程度，是本研究的目标之一。为此我们引入机器学习领域的可重复性本体体系，并将其应用于图神经网络方法的研究。基于此工作，我们转向机器学习领域的另一关键挑战——维度灾难。该问题在数据收集、表征与分析层面带来困难，使得代表性数据的获取愈发艰难，同时阻碍了训练与推理过程。通过紧密关联的几何本征维度概念，我们探究所使用的机器学习模型受其训练数据集本征维度影响的程度。