DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration

ICLR 2026 Conference Submission18990 Authors

Keywords: Rashomon Set, Rashomon Effect, Feature-wise Linear Modulation (FiLM), CMA-ES, Model Multiplicity, Predictive Multiplicity, Neural Network Diversity

Abstract: 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.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 18990