提出三维度框架，全面比较神经网络表示相似性。
The Triangle of Similarity: A Multi-Faceted Framework for Comparing Neural Network Representations
- 融合静态、功能与稀疏性三种相似性视角，全面评估表示
- 架构家族决定表示相似性，剪枝时准确率下降更剧烈
- 剪枝可暴露共享计算核心，适合模型分析与选择
比较神经网络表示对理解与验证科学应用中的模型至关重要。现有方法视角有限。本文提出三角相似性框架，结合三种互补视角：静态表示相似性（CKA/Procrustes）、功能相似性（线性模式连接或预测相似性）以及稀疏性相似性（剪枝下的鲁棒性）。在多种CNN、视觉变换器及视觉-语言模型上，使用ImageNetV2（分布内）与CIFAR-10（分布外）测试集进行分析，初步发现：（1）架构族是表示相似性的主要决定因素，形成明显聚类；（2）剪枝过程中CKA自相似性与任务准确率高度相关，但准确率下降更显著；（3）某些模型对剪枝表现出正则化效应，暴露出共享的计算核心。该框架为评估模型是否收敛于相似内部机制提供了更全面的方法，适用于科学研究中的模型选择与分析。
原文摘要 · Abstract (English)
Comparing neural network representations is essential for understanding and validating models in scientific applications. Existing methods, however, often provide a limited view. We propose the Triangle of Similarity, a framework that combines three complementary perspectives: static representational similarity (CKA/Procrustes), functional similarity (Linear Mode Connectivity or Predictive Similarity), and sparsity similarity (robustness under pruning). Analyzing a range of CNNs, Vision Transformers, and Vision-Language Models using both in-distribution (ImageNetV2) and out-of-distribution (CIFAR-10) testbeds, our initial findings suggest that: (1) architectural family is a primary determinant of representational similarity, forming distinct clusters; (2) CKA self-similarity and task accuracy are strongly correlated during pruning, though accuracy often degrades more sharply; and (3) for some model pairs, pruning appears to regularize representations, exposing a shared computational core. This framework offers a more holistic approach for assessing whether models have converged on similar internal mechanisms, providing a useful tool for model selection and analysis in scientific research.
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。