提出考虑不变性的模型拼接方法，更准确评估深度模型功能相似性。
Grounding Functional Similarity by Invariance-Aware Model Stitching
- 基于前后兼容性约束设计新拼接方法，显式建模模型不变性
- 实验证明传统方法会误判依赖不同信息线索的模型为相似
- 适合研究模型泛化能力或可解释性的研究人员参考
在深度学习中，功能相似性评估用于衡量独立训练的模型学习到的输入-输出关系的相似程度。模型拼接将功能相似性定义为表示的前向兼容性，即两个模型的表示是否能对齐以解决特定任务。然而，近期研究表明，依赖不同信息线索的模型仍可能产生兼容表示，导致其看似相似但实际功能差异显著（Smith et al., 2025）。我们指出，标准模型拼接本质上对拼接模型的不变性特性视而不见，是该问题的根本原因。为此，我们引入前向-后向兼容性要求，提出不变性感知的模型拼接方法。通过分析关键拼接配置，研究了前向与后向兼容性的相互作用，表明该方法提供了更严谨的功能相似性评估框架，并揭示了此前被掩盖的功能差异。
原文摘要 · Abstract (English)
In deep learning, functional similarity evaluation quantifies the extent to which independently trained models learn similar input--output relationships. In model stitching, functional similarity is framed as representation forward compatibility, i.e., whether the representations of two models can be aligned to solve a given task. Recent studies, however, highlight a critical limitation: models relying on different information cues can still produce compatible representations, making them appear misleadingly similar (Smith et al., 2025). We attribute this failure to standard model stitching being inherently blind to the invariance properties of the stitched models. To address this limitation, we introduce the forward--backward compatibility requirement under which we formulate the invariance-aware model stitching. Through analyzing key stitching configurations, we study the interplay between forward and backward compatibility, showing that invariance-aware model stitching provides a more principled approach to functional similarity evaluation while revealing functional discrepancies previously obscured.
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。