"What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909800290320384 |
|---|---|
| author | Babbar, Varun Guo, Zhicheng Rudin, Cynthia |
| author_facet | Babbar, Varun Guo, Zhicheng Rudin, Cynthia |
| contents | The performance of machine learning models relies heavily on the quality of input data, yet real-world applications often face significant data-related challenges. A common issue arises when curating training data or deploying models: two datasets from the same domain may exhibit differing distributions. While many techniques exist for detecting such distribution shifts, there is a lack of comprehensive methods to explain these differences in a human-understandable way beyond opaque quantitative metrics. To bridge this gap, we propose a versatile framework of interpretable methods for comparing datasets. Using a variety of case studies, we demonstrate the effectiveness of our approach across diverse data modalities-including tabular data, text data, images, time-series signals -- in both low and high-dimensional settings. These methods complement existing techniques by providing actionable and interpretable insights to better understand and address distribution shifts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05652 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | "What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts Babbar, Varun Guo, Zhicheng Rudin, Cynthia Machine Learning Artificial Intelligence The performance of machine learning models relies heavily on the quality of input data, yet real-world applications often face significant data-related challenges. A common issue arises when curating training data or deploying models: two datasets from the same domain may exhibit differing distributions. While many techniques exist for detecting such distribution shifts, there is a lack of comprehensive methods to explain these differences in a human-understandable way beyond opaque quantitative metrics. To bridge this gap, we propose a versatile framework of interpretable methods for comparing datasets. Using a variety of case studies, we demonstrate the effectiveness of our approach across diverse data modalities-including tabular data, text data, images, time-series signals -- in both low and high-dimensional settings. These methods complement existing techniques by providing actionable and interpretable insights to better understand and address distribution shifts. |
| title | "What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2403.05652 |