# DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration

arXiv: https://arxiv.org/abs/2601.20627 · HTML: https://mlsanity.com/paper/2601.20627/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 22 of 22)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation](https://mlsanity.com/paper/2001.08735/) (2020)
- [Predictive Multiplicity in Classification](https://mlsanity.com/paper/1909.06677/) (2019)
- [On the Existence of Simpler Machine Learning Models](https://mlsanity.com/paper/1908.01755/) (2019)
- [Exploring the Whole Rashomon Set of Sparse Decision Trees](https://mlsanity.com/paper/2209.08040/) (2022)
- [Rashomon Capacity: A Metric for Predictive Multiplicity in Classification](https://mlsanity.com/paper/2206.01295/) (2022)
- [Predictive Multiplicity in Probabilistic Classification](https://mlsanity.com/paper/2206.01131/) (2022)
- [A Path to Simpler Models Starts With Noise](https://mlsanity.com/paper/2310.19726/) (2023)
- [Exploring and Interacting with the Set of Good Sparse Generalized Additive Models](https://mlsanity.com/paper/2303.16047/) (2023)
- [FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation](https://mlsanity.com/paper/2206.00050/) (2022)
- [Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation](https://mlsanity.com/paper/2402.00728/) (2024)
- [Be Intentional About Fairness!: Fairness, Size, and Multiplicity in the Rashomon Set](https://mlsanity.com/paper/2501.15634/) (2025)
- [An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification](https://mlsanity.com/paper/2311.14859/) (2023)
- [Perceptions of the Fairness Impacts of Multiplicity in Machine Learning](https://mlsanity.com/paper/2409.12332/) (2024)
- [Diagonal Acceleration for Covariance Matrix Adaptation Evolution Strategies](https://mlsanity.com/paper/1905.05885/) (2019)
- [AI-Spectra: A Visual Dashboard for Model Multiplicity to Enhance Informed and Transparent Decision-Making](https://mlsanity.com/paper/2411.10490/) (2024)
- [Allocation Multiplicity: Evaluating the Promises of the Rashomon Set](https://mlsanity.com/paper/2503.16621/) (2025)

## Built on by (most cited first, 1 of 1)

- [Model Stealing Through the Lens of Model Multiplicity](https://mlsanity.com/paper/2606.15493/) (2026)

## Abstract (arXiv)

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.