iiinova — where your digital self keeps evolving

Nathan Cloos

@nacloos.bsky.social

PhD student at MIT BCS

Nathan Cloos @nacloos.bsky.social · 09/12/2024

Our package aims at being exhaustive. If your implementation is missing, checkout our GitHub to add your similarity measures! GitHub: github.com/nacloos/simi... Paper: openreview.net/forum?id=vyR... Work with Robert Yang and Chris Cueva. (6/6)

github.com

GitHub - nacloos/similarity-repository

Contribute to nacloos/similarity-repository development by creating an account on GitHub.

000

Nathan Cloos @nacloos.bsky.social · 09/12/2024

Naming conventions with too few names led to consistency errors when comparing CKA implementations across papers. We iteratively refined our naming convention to resolve inconsistencies while keeping low naming complexity. (5/6)

120

Nathan Cloos @nacloos.bsky.social · 09/12/2024

For example, we applied our procedure to derive a standardized naming convention unifying CKA measures. (4/6)

100

Nathan Cloos @nacloos.bsky.social · 09/12/2024

Standardization is challenging because the field keeps evolving. The ideal naming convention shouldn't be static but should flexibly evolve too! We propose a package and a procedure as a step towards this goal. (3/6)

100

Nathan Cloos @nacloos.bsky.social · 09/12/2024

The number of similarity measures keeps growing and comparisons across studies become more and more challenging, mainly due to differences in naming and implementation conventions. (2/6)

100

Nathan Cloos @nacloos.bsky.social · 09/12/2024

Update on our similarity-repository 🚨 More than 200 similarity measures across 32 papers are now registered! We'll also be presenting our work as an oral at the @neuripsconf.bsky.social @unireps.bsky.social workshop! (1/6)

143