What Do Neural Networks Learn When Trained With Random Labels?

TL;DR

This paper investigates what deep neural networks learn when trained on random labels, revealing an alignment between network parameters and data that can lead to positive transfer in downstream tasks.

Contribution

It analytically demonstrates parameter-data alignment in networks trained with random labels and shows how this alignment facilitates transfer learning.

Findings

Networks trained on random labels exhibit parameter-data alignment.

Pre-trained networks with random labels transfer positively to downstream tasks.

Alignment effects are observed across various architectures and datasets.

Abstract

We study deep neural networks (DNNs) trained on natural image data with entirely random labels. Despite its popularity in the literature, where it is often used to study memorization, generalization, and other phenomena, little is known about what DNNs learn in this setting. In this paper, we show analytically for convolutional and fully connected networks that an alignment between the principal components of network parameters and data takes place when training with random labels. We study this alignment effect by investigating neural networks pre-trained on randomly labelled image data and subsequently fine-tuned on disjoint datasets with random or real labels. We show how this alignment produces a positive transfer: networks pre-trained with random labels train faster downstream compared to training from scratch even after accounting for simple effects, such as weight scaling. We analyze how competing effects, such as specialization at later layers, may hide the positive transfer. These effects are studied in several network architectures, including VGG16 and ResNet18, on CIFAR10 and ImageNet.