ContraSim -- A Similarity Measure Based on Contrastive Learning

Adir Rahamim, Yonatan Belinkov

Keywords: Interpretability, similarity measure, analysis, language models, multilingual, image captioning

TL;DR: We develop a new similarity measure based on contrastive learning

Abstract: Recent work has compared neural network representations via similarity-based analyses, shedding light on how different aspects (architecture, training data, etc.) affect models' internal representations. The quality of a similarity measure is typically evaluated by its success in assigning a high score to representations that are expected to be matched. However, existing similarity measures perform mediocrely on standard benchmarks. In this work, we develop a new similarity measure, dubbed ContraSim, based on contrastive learning. In contrast to common closed-form similarity measures, ContraSim learns a parameterized measure by using both similar and dissimilar examples. We perform an extensive experimental evaluation of our method, with both language and vision models, on the standard layer prediction benchmark and two new benchmarks that we develop: the multilingual benchmark and the image--caption benchmark. In all cases, ContraSim achieves much higher accuracy than previous similarity measures, even when presented with challenging examples.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:2303.16992/code)