Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.20627 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914286744371200 |
|---|---|
| author | Eerlings, Gilles Zoomers, Brent Liesenborgs, Jori Ruiz, Gustavo Rovelo Luyten, Kris |
| author_facet | Eerlings, Gilles Zoomers, Brent Liesenborgs, Jori Ruiz, Gustavo Rovelo Luyten, Kris |
| contents | We propose DIVERSE, a framework for systematically exploring the Rashomon set of deep neural networks, the collection of models that match a reference model's accuracy while differing in their predictive behavior. DIVERSE augments a pretrained model with Feature-wise Linear Modulation (FiLM) layers and uses Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to search a latent modulation space, generating diverse model variants without retraining or gradient access. Across MNIST, PneumoniaMNIST, and CIFAR-10, DIVERSE uncovers multiple high-performing yet functionally distinct models. Our experiments show that DIVERSE offers a competitive and efficient exploration of the Rashomon set, making it feasible to construct diverse sets that maintain robustness and performance while supporting well-balanced model multiplicity. While retraining remains the baseline to generate Rashomon sets, DIVERSE achieves comparable diversity at reduced computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20627 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration Eerlings, Gilles Zoomers, Brent Liesenborgs, Jori Ruiz, Gustavo Rovelo Luyten, Kris Machine Learning We propose DIVERSE, a framework for systematically exploring the Rashomon set of deep neural networks, the collection of models that match a reference model's accuracy while differing in their predictive behavior. DIVERSE augments a pretrained model with Feature-wise Linear Modulation (FiLM) layers and uses Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to search a latent modulation space, generating diverse model variants without retraining or gradient access. Across MNIST, PneumoniaMNIST, and CIFAR-10, DIVERSE uncovers multiple high-performing yet functionally distinct models. Our experiments show that DIVERSE offers a competitive and efficient exploration of the Rashomon set, making it feasible to construct diverse sets that maintain robustness and performance while supporting well-balanced model multiplicity. While retraining remains the baseline to generate Rashomon sets, DIVERSE achieves comparable diversity at reduced computational cost. |
| title | DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.20627 |