Discovering Universal Geometry in Embeddings with ICA
share
This study employs Independent Component Analysis (ICA) to uncover universal properties of embeddings of words or images. Our approach extracts independent semantic components of embeddings, enabling each embedding to be represented as a composition of intrinsic interpretable axes. We demonstrate that embeddings can be expressed as a combination of a few axes and that these semantic axes are consistent across different languages, modalities, and embedding algorithms. This discovery of universal properties in embeddings contributes to model interpretability, potentially facilitating the development of highly interpretable models and the compression of large-scale models.
READ FULL TEXT