paper-with-me

홈 › Papers

Similarity of Neural Network Models: A Survey of Functional and Representational Measures

2023-05-10 · Max Klabunde, Tobias Schumacher, Markus Strohmaier, Florian Lemmerich

Measuring similarity of neural networks to understand and improve their behavior has become an issue of great importance and research interest. In this survey, we provide a comprehensive overview of two complementary perspectives of measuring neural network similarity: (i) representational similarity, which considers how activations of intermediate layers differ, and (ii) functional similarity, which considers how models differ in their outputs. In addition to providing detailed descriptions of existing measures, we summarize and discuss results on the properties of and relationships between these measures, and point to open research problems. We hope our work lays a foundation for more systematic research on the properties and applicability of similarity measures for neural network models.

📄 PDF Abstract BibTeX arXiv:2305.06329

Code (3)

mklabunde/survey_measures 공식 구현
MindSpore-scientific/code-14/tree/main/similarity-of-neural-network mindspore
MindSpore-scientific/code-5/tree/main/similarity-of-neural-network mindspore

Similar Papers 제목 키워드 기반

Evaluating Representational Similarity Measures from the Lens of Functional Correspondence

2024-11-21 · Yiqing Bo, Ansh Soni, Sudhanshu Srivastava, Meenakshi Khosla

Neuroscience and artificial intelligence (AI) both face the challenge of interpreting high-dimensional neural data, where the comparative analysis of such data is crucial for revealing shared mechanisms and differences b…

ReSi: A Comprehensive Benchmark for Representational Similarity Measures

2024-08-01 · Max Klabunde, Tassilo Wald, Tobias Schumacher, Klaus Maier-Hein 외

Measuring the similarity of different representations of neural architectures is a fundamental task and an open research challenge for the machine learning community. This paper presents the first comprehensive benchmark…

Bridging Functional and Representational Similarity via Usable Information

2026-01-29 · Antonio Almudévar, Alfonso Ortega arxiv

We present a unified framework for quantifying the similarity between representations through the lens of \textit{usable} information, offering a rigorous theoretical and empirical synthesis across three key dimensions. …

Comparing and Integrating Different Notions of Representational Correspondence in Neural Systems

2025-09-25 · Jialin Wu, Shreya Saha, Yiqing Bo, Meenakshi Khosla arxiv

The extent to which different biological and artificial neural systems rely on equivalent internal representations to support similar tasks remains a central question in neuroscience and machine learning. Prior work typi…

Integrated representational signatures strengthen specificity in brains and models

2025-10-21 · Jialin Wu, Shreya Saha, Yiqing Bo, Meenakshi Khosla arxiv

The extent to which different neural or artificial neural networks (models) rely on equivalent representations to support similar tasks remains a central question in neuroscience and machine learning. Prior work has typi…