不重训练也不用梯度，用向量进化找多样且高性能的模型
DIVERSE: Disagreement-Inducing Vector Evolution for Rashomon Set Exploration
- 在预训练模型上加调制层，用进化算法搜索不同表现的模型变体
- 在三个数据集上找到多个高精度但预测行为不同的模型
- 适合需要模型多样性与低计算成本的研究者
我们提出 DIVERSE 框架，系统性探索深度神经网络的 Rashomon 集——一组性能与参考模型相当但预测行为不同的模型集合。DIVERSE 在预训练模型上引入特征级线性调制（FiLM）层，并使用协方差矩阵自适应进化策略（CMA-ES）搜索潜在调制空间，生成多样模型变体，无需重新训练或梯度访问。在 MNIST、PneumoniaMNIST 和 CIFAR-10 上，DIVERSE 成功发现多个高性能但功能各异的模型。实验表明，DIVERSE 能以较低计算成本实现具有竞争力的多样性探索，使构建兼具鲁棒性与性能的多样化模型集成为可能。尽管重训练仍是生成 Rashomon 集的基准方法，DIVERSE 在保持相当多样性的同时显著降低计算开销。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。