Learning Invariant Representations with a Nonparametric Nadaraya-Watson Head

TL;DR

This paper introduces a nonparametric approach using a Nadaraya-Watson head to learn invariant representations across different environments, improving domain generalization in computer vision tasks.

Contribution

It proposes a novel nonparametric method with a Nadaraya-Watson head for learning invariant features, leveraging support set manipulation to encode causal assumptions.

Findings

Effective in three real-world domain generalization tasks

Encodes causal assumptions through support set manipulation

Improves transferability of learned representations

Abstract

Machine learning models will often fail when deployed in an environment with a data distribution that is different than the training distribution. When multiple environments are available during training, many methods exist that learn representations which are invariant across the different distributions, with the hope that these representations will be transportable to unseen domains. In this work, we present a nonparametric strategy for learning invariant representations based on the recently-proposed Nadaraya-Watson (NW) head. The NW head makes a prediction by comparing the learned representations of the query to the elements of a support set that consists of labeled data. We demonstrate that by manipulating the support set, one can encode different causal assumptions. In particular, restricting the support set to a single environment encourages the model to learn invariant features that do not depend on the environment. We present a causally-motivated setup for our modeling and training strategy and validate on three challenging real-world domain generalization tasks in computer vision.