Learning explanations that are hard to vary

Giambattista Parascandolo, Alexander Neitz, ANTONIO ORVIETO, Luigi Gresele, Bernhard Schölkopf

Keywords: invariances, consistency, gradient alignment

Abstract:

In this paper, we investigate the principle that good explanations are hard to vary in the context of deep learning.
We show that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and `patchwork' solutions that sew together different strategies, instead of identifying invariances.
To inspect this, we first formalize a notion of consistency for minima of the loss surface, which measures to what extent a minimum appears only when examples are pooled.
We then propose and experimentally validate a simple alternative algorithm based on a logical AND, that focuses on invariances and prevents memorization in a set of real-world tasks.
Finally, using a synthetic dataset with a clear distinction between invariant and spurious mechanisms, we dissect learning signals and compare this approach to well-established regularizers.

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

Code: [ pytorch/ignite](https://github.com/pytorch/ignite) + [ 2 community implementations](https://paperswithcode.com/paper/?openreview=hb1sDDSLbV)

Community Implementations: [ 4 code implementations](https://www.catalyzex.com/paper/arxiv:2009.00329/code)