Neural architectures can leverage relative representations to guarantee, in practice, invariance to latent isometries and rescalings, effectively enabling latent space communication: from zero-shot model stitching to latent space comparison between diverse settings, architectures, and data modalities. Moreover, an optimization-based method is introduced to discover new parallel anchors from a limited number of seeds, allowing for the discovery of unknown semantic correspondences between different domains, alignment of their relative spaces, and achieving competitive results in several tasks.

SPEAKERS:

Luca Moschella (Sapienza University of Rome)
Irene Cannistraci (Sapienza University of Rome)

-------------------------------------------------------------------------------------------------------------------------

The AIT Journal Club is an open-science initiative aiming to create a friendly environment to discuss and speculate about the recent research trends in Artificial Intelligence, Machine Learning, and Computer Science. It is not a formal occasion either! We will have a lightning talk at each meeting to introduce the topic and get the conversation going, leading to having a drink together after the event! It is open to all interested PhDs, students, researchers, (and professors!) who don't mind spending an evening talking about science and making new friends.

-> Website: https://aitrentojc.github.io/

-> Telegram group: https://t.me/smljournalclub

Communicating between latent spaces with limited semantic correspondence