paper-with-me

홈 › Papers

What Representational Similarity Measures Imply about Decodable Information

2024-11-12 · Sarah E. Harvey, David Lipshutz, Alex H. Williams

Neural responses encode information that is useful for a variety of downstream tasks. A common approach to understand these systems is to build regression models or ``decoders'' that reconstruct features of the stimulus from neural responses. Popular neural network similarity measures like centered kernel alignment (CKA), canonical correlation analysis (CCA), and Procrustes shape distance, do not explicitly leverage this perspective and instead highlight geometric invariances to orthogonal or affine transformations when comparing representations. Here, we show that many of these measures can, in fact, be equivalently motivated from a decoding perspective. Specifically, measures like CKA and CCA quantify the average alignment between optimal linear readouts across a distribution of decoding tasks. We also show that the Procrustes shape distance upper bounds the distance between optimal linear readouts and that the converse holds for representations with low participation ratio. Overall, our work demonstrates a tight link between the geometry of neural representations and the ability to linearly decode information. This perspective suggests new ways of measuring similarity between neural systems and also provides novel, unifying interpretations of existing measures.

📄 PDF Abstract BibTeX arXiv:2411.08197

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Procrustes Procrustes

Similar Papers 제목 키워드 기반

Towards Measuring Representational Similarity of Large Language Models

2023-12-05 · Max Klabunde, Mehdi Ben Amor, Michael Granitzer, Florian Lemmerich

Understanding the similarity of the numerous released large language models (LLMs) has many uses, e.g., simplifying model selection, detecting illegal model reuse, and advancing our understanding of what makes LLMs perfo…

Model Selection

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…

All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality

2021-09-09 · EMNLP 2021 11 · William Timkey, Marten Van Schijndel

Similarity measures are a vital tool for understanding how language models represent and process language. Standard representational similarity measures such as cosine similarity and Euclidean distance have been successf…

All

Towards Meaningful Statements in IR Evaluation. Mapping Evaluation Measures to Interval Scales

2021-01-07 · Marco Ferrante, Nicola Ferro, Norbert Fuhr

Recently, it was shown that most popular IR measures are not interval-scaled, implying that decades of experimental IR research used potentially improper methods, which may have produced questionable results. However, it…

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 per…