SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

Part of Advances in Neural Information Processing Systems 30 (NIPS 2017)

Bibtex Metadata Paper Reviews Supplemental

Authors

Maithra Raghu, Justin Gilmer, Jason Yosinski, Jascha Sohl-Dickstein

Abstract

We propose a new technique, Singular Vector Canonical Correlation Analysis (SVCCA), a tool for quickly comparing two representations in a way that is both invariant to affine transform (allowing comparison between different layers and networks) and fast to compute (allowing more comparisons to be calculated than with previous methods). We deploy this tool to measure the intrinsic dimensionality of layers, showing in some cases needless over-parameterization; to probe learning dynamics throughout training, finding that networks converge to final representations from the bottom up; to show where class-specific information in networks is formed; and to suggest new training regimes that simultaneously save computation and overfit less.