提出分层合并方法，提升模型抗扰动能力。
Robustness and Regularization in Hierarchical Re-Basin
- 设计分层模型合并机制，优化融合过程
- 参与合并的模型越多，鲁棒性越强
- 适合关注模型安全与泛化性能的研究者
本文深入研究了 Git Re-Basin 这一新型模型合并方法。提出一种分层合并方案，显著优于标准 MergeMany 算法。实验发现，Re-Basin 能使合并后的模型具备对抗攻击和扰动鲁棒性，且随着参与合并的模型数量增加，该效果愈发明显。然而，实验中观察到的性能下降幅度远大于原始作者报告的结果。
原文摘要 · Abstract (English)
This paper takes a closer look at Git Re-Basin, an interesting new approach to merge trained models. We propose a hierarchical model merging scheme that significantly outperforms the standard MergeMany algorithm. With our new algorithm, we find that Re-Basin induces adversarial and perturbation robustness into the merged models, with the effect becoming stronger the more models participate in the hierarchical merging scheme. However, in our experiments Re-Basin induces a much bigger performance drop than reported by the original authors.
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。