Equivalence between representational similarity analysis, centered kernel alignment, and canonical correlations analysis

Published: 10 Oct 2024, Last Modified: 18 Oct 2024UniRepsEveryoneRevisionsBibTeXCC BY 4.0
Track: Proceedings Track
Keywords: Centered Kernel Alignment, Representational Geometry, Representational Similarity Analysis, Canonical Correlation Analysis
TL;DR: Representational Similarity Analysis on centered distance matrices is equivalent to Centered Kernel Alignment
Abstract: Centered kernel alignment (CKA) and representational similarity analysis (RSA) of dissimilarity matrices are two popular methods for quantifying similarity in neural representational geometry. Although they follow a conceptually similar approach, typical implementations of CKA and RSA tend to result in numerically different outcomes. Here, I show that these two approaches are largely equivalent once one incorporates a mean-centering step into RSA. This connection is quite simple to derive, but appears to have been thus far overlooked by the community studying neural representational geometry. By unifying these measures, this paper hopes to simplify a complex and fragmented literature on this subject.
Submission Number: 16
Loading