Bootstrapping Parallel Anchors for Relative Representations

Tiny Paper @ ICLR 2023


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 number of seeds. Our approach can be used to find semantic correspondence between different domains, align their relative spaces, and achieve competitive results in several tasks.

Tiny Papers @ ICLR 2023
Irene Cannistraci
Irene Cannistraci
Ph.D. Student in Computer Science, Sapienza University of Rome
GLADIA Research Group

Visiting Researcher Student, Helmholtz Munich AIDOS Lab

I am a Ph.D. student in Computer Science passionate about Deep Learning.