Generating Samples to Probe Trained Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914208620216320 |
|---|---|
| author | Kıral, Eren Mehmet Aydın, Nurşen Birbil, Ş. İlker |
| author_facet | Kıral, Eren Mehmet Aydın, Nurşen Birbil, Ş. İlker |
| contents | There is a growing need for investigating how machine learning models operate. With this work, we aim to understand trained machine learning models by questioning their data preferences. We propose a mathematical framework that allows us to probe trained models and identify their preferred samples in various scenarios including prediction-risky, parameter-sensitive, or model-contrastive samples. To showcase our framework, we pose these queries to a range of models trained on a range of classification and regression tasks, and receive answers in the form of generated data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06658 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generating Samples to Probe Trained Models Kıral, Eren Mehmet Aydın, Nurşen Birbil, Ş. İlker Machine Learning There is a growing need for investigating how machine learning models operate. With this work, we aim to understand trained machine learning models by questioning their data preferences. We propose a mathematical framework that allows us to probe trained models and identify their preferred samples in various scenarios including prediction-risky, parameter-sensitive, or model-contrastive samples. To showcase our framework, we pose these queries to a range of models trained on a range of classification and regression tasks, and receive answers in the form of generated data. |
| title | Generating Samples to Probe Trained Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.06658 |