Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911802637418496 |
|---|---|
| author | Hille, Tobias Stubbemann, Maximilian Hanika, Tom |
| author_facet | Hille, Tobias Stubbemann, Maximilian Hanika, Tom |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08438 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research Hille, Tobias Stubbemann, Maximilian Hanika, Tom Machine Learning Artificial Intelligence 68T01 68T07 68T09 51F99 I.2.6 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. |
| title | Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research |
| topic | Machine Learning Artificial Intelligence 68T01 68T07 68T09 51F99 I.2.6 |
| url | https://arxiv.org/abs/2403.08438 |