Model Stitching: Looking For Functional Similarity Between Representations

Adriano Hernandez, Rumen Dangovski, Peter Y. Lu, Marin Soljacic

Keywords: Representation Learning, Representation Comparison, Functional, Experimental, Machine Learning, Computer Vision

TL;DR: Explores a representational functional similarity technique and yields perplexing results while encouraging a new paradigm of representational comparisons in the future despite this setback.

Abstract:

Model stitching (Lenc \& Vedaldi 2015) is a compelling methodology to compare
different neural network representations, because it allows us to measure to
what degree they may be interchanged.
We expand on a previous work from Bansal, Nakkiran \& Barak which used model stitching to
compare representations of the same shapes learned by differently seeded
and/or trained neural networks of the same architecture.
Our contribution enables us to compare the representations learned by layers with
different shapes from neural networks with different architectures.
We subsequently reveal unexpected behavior of model stitching. Namely, we find that stitching,
based on convolutions, for small ResNets, can reach
high accuracy if those layers come later in the first (sender) network than in
the second (receiver), even if those layers are far apart.

This leads us to hypothesize that stitches are not in fact learning to match the
representations expected by receiver layers, but instead finding different representations which nonetheless
yield similar results. Thus, we believe that model stitching may not necessarily always be an
accurate measure of similarity.