Bootstrapping Parallel Anchors for Relative Representations

Irene Cannistraci, Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Emanuele Rodolà

Keywords: relative representations, parallel anchors, semantic correspondence, zero-shot, stitching, latent communication

TL;DR: Expand limited semantic correspondences between domains to enable latent communication through relative representations

Abstract: The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot model stitching across a wide range of applications. Nevertheless, relative representations rely on a certain amount of parallel anchors to be given as input, which can be impractical to obtain in certain scenarios. To overcome this limitation, we propose an optimization-based method to discover new parallel anchors from a limited known set (seed). Our approach can be used to find semantic correspondence between different domains, align their relative spaces, and achieve competitive results in several tasks.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2303.00721/code)